The Inference Report

Compression is fundamental to intelligence. A model that can represent its training data as a short code has discovered regularities that enable generalization. Large neural networks may learn functions far simpler than their parameter counts suggest, but it is challenging to construct codes that realize this simplicity. Parameter-based methods such as quantization produce code lengths that scale with model size, insensitive to how much information the parameters store. Prequential coding bypasses this issue by compressing the training trajectory, but codes the exact data sequence regardless of how much the model learns, yielding large codes when the data has high entropy. We introduce requential coding, where a teacher model selects training samples drawn from the student's own distribution. The student's code records only these selections, which cost bits only where teacher and student disagree. The resulting code length is independent of parameter count and data entropy, and often orders of magnitude shorter than the prequential counterpart, with an advantage that grows with scale. This compression sheds light on phenomena inaccessible to prior compressors. Holding loss fixed, larger models and ensembles compress to much smaller sizes despite more parameters. Plugged into a PAC-Bayes bound, the requential code yields state-of-the-art generalization guarantees for billion-parameter LLMs, outperforming bounds built on aggressive post-training quantization even granted zero error. The bound tightens with scale in the compute-optimal regime, as models become increasingly compressible relative to dataset size. The same code predicts that models gradually overfit when trained for multiple epochs. It also isolates the learnable information in a dataset from its unpredictable, random content, revealing that lower-entropy text holds far more learnable structure than higher-entropy image data.

Metacognition is a foundational component of intelligence critical to effective learning, problem solving, decision-making, communication, and more. In recent years, it has become increasingly recognized as a cornerstone of capable, transparent AI systems. Yet while LLMs have made significant progress across diverse real-world tasks, it is not yet clear when, how, or to what extent they can exhibit or be endowed with effective metacognitive abilities, nor how such abilities can be adapted to advance the fundamental capabilities, reliability, and intelligence of AI systems. This paper bridges this gap by presenting the first comprehensive overview of the current state of knowledge on metacognition for LLMs. We analyze and taxonomize the landscape of this emerging field and summarize recent technical advancements, including methods and benchmarks to measure and evaluate LLMs' metacognitive abilities, techniques to elicit, improve, and apply metacognition in LLMs, and findings and implications of ongoing research. We also discuss applications, open questions and challenges, and promising directions for future work. Our aim is to provide a detailed and up-to-date review of this topic and stimulate meaningful research and discussion. An organized list of papers can be found at https://github.com/yale-nlp/LLM-Metacognition.

We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language models. While previous works on Transformer learning dynamics have so far been mostly tied to specific tasks, we study a generalized class of inductive tasks that unifies several synthetic tasks known in the literature, including in-context n-grams and multi-hop reasoning. In this class, we theoretically prove that the training dynamics of attention models can be confined to a highly interpretable, low-dimensional invariant manifold. On this manifold, the learning dynamics are captured by a handful of interpretable coordinates rather than millions of parameters, making both theoretical and empirical analysis more tractable. Using this framework, we characterize how data statistics govern the competition between in-context and in-weights learning, we study how random initializations determine the `winning' circuit when multiple solutions are possible, and we demonstrate that the coordinate frame associated with the manifold can be used to automatically detect which circuits have been learned in trained models. By casting circuit formation as a low-dimensional dynamical phenomenon, we take a step toward a predictive theory of how Transformers learn.

Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kinematic references, then train policies via reinforcement learning (RL) to track them. But how does this recipe transfer to dexterous manipulation? The answer is not obvious, as manipulation involves complex, contact-rich dynamics and requires delicate regulation of contact modes and forces. We present REGRIND, a minimalist retargeting-guided RL pipeline that learns dexterous manipulation policies from a single human demonstration. REGRIND retargets human hand-object motion to a robot reference that preserves hand-object spatial and contact relationships, trains a residual RL policy in simulation to track object-centric keypoints along that reference, and transfers the resulting policy zero-shot to hardware with careful system identification. The resulting policies produce fluid, human-like behavior on two different multi-fingered hands across contact-rich tool-use tasks, including operating a pair of scissors and turning a screwdriver. Through systematic hardware experiments, we identify and analyze the key factors that govern sim-to-real transfer in dexterous manipulation, offering practical guidance for retargeting-based learning in contact-rich settings. Videos and code are available at https://yunhaifeng.com/REGRIND.

Institutions collect far more open-ended teaching-evaluation feedback than they read. A prior study introduced a validated protocol for classifying such comments by thematic category and sentiment, built from a documented annotation guide, an intra-annotator reliability measurement, stratified cross-validation, and a held-out evaluation on a Spanish institutional corpus with a frozen-encoder design. Two questions limit its reuse: whether a protocol fixed to 2019-era frozen embeddings stays competitive as representation methods advance, and whether it transfers to a second language. We re-run it on the original Spanish data across three representation generations, sparse lexical features, frozen transformer embeddings, and prompted large language models, and transfer its sentiment task to English with a balanced 45,000-comment corpus checked against an aspect-labeled education dataset. Treating paired comparisons as descriptive, we find the protocol durable: a 2026 frontier model posts the highest thematic F1 on the hardest Spanish task, yet shows no sentiment advantage over a cheap model and no descriptive separation from it on English, so model choice is a deployment decision, not a property of the method.

Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, measure score deltas, and propose prompt-level mitigations. We argue that the same biases admit a representation-level account in the judge's hidden state, complementary to the input-output view and operationally useful in ways it does not afford. We report three findings, across seven judges, seven bias types, and nine benchmarks. Geometry: baseline judging inputs occupy a tight activation manifold while biased inputs are displaced along a low-dimensional, type-specific subspace that sharpens with depth and is recovered consistently by three families of estimators. Causal control: steering hidden states along this subspace drives scoring in both directions, forward shifts reproducing biased scoring on clean inputs and reverse shifts restoring baseline scoring on biased ones, while matched-norm random directions produce shifts an order of magnitude smaller. Operational: a simple linear projection onto the same bias-direction features anticipates judge failures on three entirely unseen benchmarks, substantially outperforming text-based alternatives. Reading bias as activation geometry, rather than as input-output noise, unifies geometric structure, causal control, and operational prediction within a single framework. The project page is available at https://xzx34.github.io/unfair-judge/

Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding. Existing explainability efforts rely on textual rationales or sparse bounding boxes, which struggle to capture complex video dynamics such as occlusions and non-rigid deformations. We propose Evidence-Backed Video Question Answering (E-VQA), a novel task requiring models to jointly output a semantic answer and precise spatio-temporal evidence: temporal segments and dense, tracked object segmentation masklets. To support this, we introduce ST-Evidence, the first human-verified benchmark for both discriminative and generative pixel-level grounding. Evaluations of state-of-the-art models reveal a critical decoupling between QA accuracy and true visual perception that scaling alone fails to bridge. To address this, we develop scalable, automated generation pipelines to create ST-Evidence-Instruct, a 160k-scale dataset bridging high-level reasoning with fine-grained grounding. Fine-tuning grounded Video LLMs on this data yields substantial gains over the corresponding size-matched UniPixel baselines (e.g., +27.2 t-mean and +13.8 J&F on a 7B model), establishing a robust baseline for explainable, evidence-backed video understanding. Code and data are available at https://github.com/SalesforceAIResearch/EVQA.

Large language models (LLMs) have achieved remarkable performance on high-school and olympiad-style mathematics, yet their capabilities on advanced mathematics remain poorly understood. Existing benchmarks, however, fall short in both scope and evaluation granularity: they provide limited disciplinary coverage and often rely on final-answer correctness or coarse judgments, leaving the validity of the reasoning process inadequately assessed. To bridge this gap, we introduce AdvancedMathBench, a benchmark suite designed to evaluate advanced mathematical reasoning capabilities. Its core proof-generation benchmark, ProverBench, contains 296 problems spanning undergraduate and doctoral qualifying-exam levels. To provide reliable evaluation of the proofs, we develop a dedicated automatic verification pipeline trained on large-scale expert annotations to produce both correctness verdicts and fine-grained assessments of proof errors, which exhibits strong agreement with human experts on held-out proof trajectories. We further introduce VerifierBench, consisting of 888 model-generated proof trajectories paired with expert ground truth, to evaluate whether models can correctly judge proof validity and provide sound verification rationales. Experiments show that AdvancedMathBench remains challenging for frontier models. On proof generation, the best-performing model, GPT-5.5-xhigh, achieves only 75.8 and 66.1 on the UGD and QE splits, respectively, indicating substantial room for improvement on advanced mathematical proof construction. On proof verification, the best model attains a Balanced F1 of only 65.1, and models generally exhibit low true negative rates, suggesting that critical error detection remains a major bottleneck.

Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to backdoor attacks, yet existing quantum backdoors mostly rely on a fixed trigger shared by all poisoned inputs. This fixed-trigger design is a major weakness because many defenses detect or weaken the repeated patterns such triggers leave in data representations. Although input-aware dynamic backdoors have been studied in classical neural networks, transferring them to QNNs is difficult because quantum learning introduces new obstacles. In particular, measurement compresses the post-ansatz quantum state into a limited classical output, weakening supervision for a trigger generator, while individual density matrices fluctuate with the input and make per-sample contrastive learning unstable. To address these challenges, we propose Q-DIBA, the first input-aware dynamic backdoor attack for QNNs. Q-DIBA jointly trains a classical trigger generator and a victim QNN through a three-mode mini-batch strategy that supports clean behavior, attack activation, and trigger specificity. To provide stable quantum-level supervision, Q-DIBA introduces an ensemble density contrastive loss that operates on post-ansatz quantum states before measurement and contrasts mode-averaged density matrices rather than individual samples. Experiments on MNIST and Fashion-MNIST across multiple QNN architectures show that Q-DIBA achieves high clean accuracy, strong attack success, and high cross-trigger accuracy, demonstrating effectiveness, stealthiness, and input specificity. The attack also remains resilient against defenses including visual inspection, spectral-signature detection, and fine-tuning, suggesting that input-aware quantum backdoors are an important threat to secure QNN deployment.

This paper presents a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion framework for action and activity recognition in healthcare-oriented training environments. The proposed architecture combines parameter-efficient modality-specific adaptation with sequential fusion, enabling modalities to be integrated in stages without retraining previously learned components. Rather than assuming a fixed fusion structure, the framework first integrates more closely related modalities and then incorporates additional heterogeneous modalities, supporting scalable adaptation across datasets with different modality sets.We evaluate the framework on two healthcare-oriented training environment datasets: NurViD and the Nurse Training dataset. Across these datasets, preliminary results suggest that the proposed cascaded fusion strategy improves over individual modality models and provides competitive performance relative to previously reported dataset-specific baselines. Overall, these findings indicate that cascaded LoRA-based fusion is a promising parameter-efficient approach for integrating heterogeneous modalities in medical training action and activity recognition tasks. github: https://github.com/anonymous0-ai/LoRA-Based-Cascaded-Multimodal-Fusion-.git.

Neural Architecture Search (NAS) has automated the design of deep learning models but traditionally requires massive computational resources, often measured in thousands of GPU-days. In this paper, we propose a frugal and memetic NAS framework designed to democratize architecture design on consumer-grade hardware. Our approach combines the global macro-search capabilities of an autoregressive Transformer controller, trained via Reinforcement Learning (RL), with the local micro-exploitation of an Artificial Bee Colony (ABC) algorithm. To prevent premature convergence during the RL phase, we introduce a dynamic entropy mechanism that forces topological exploration upon detection of performance stagnation. Evaluated on a standard GPU (NVIDIA RTX 3060), our hybrid method effectively resolves the "cold-start" problem inherent in metaheuristics. By algorithmically penalizing network depth, our framework actively mitigates model bloat: on the CIFAR-10 dataset, it discovers an efficient architecture reaching 84.85% accuracy with only $\sim$174,000 parameters (significantly smaller than standard baselines like ResNet-20) in 3 hours of search time. Furthermore, we demonstrate the framework's flexibility by applying it to credit card fraud detection, directly optimizing the F1-Score on highly imbalanced tabular data to reach a F1-Score of 0.71 with a compact network of $\sim$4,600 parameters. These results suggest that our approach can yield tailored, accessible, and highly parameter-efficient deep learning models suitable for edge deployment.

We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful execution environment spanning 500+ tools across 16 application domains, supporting multi-image, multi-turn tasks where agents must ground progressively arriving visual inputs into executable tool calls while handling realistic conversational phenomena (goal revisions, error corrections, state mutations). An automated scenario generation pipeline produces diverse, visually grounded scenarios through information-flow-guided planning and multi-stage quality filtering, yielding 258 human-verified nominal scenarios and 50 variants targeting interactive UI applications. Evaluating 12 state-of-the-art models, from 4B open-weight to frontier proprietary systems, shows that current models still lack robust visual tool-calling capability: even the best model achieves below 50% success rate. Our failure analysis further reveals that visual precision, not only planning, is a primary bottleneck for capable models: 53% of failures stem from incorrect information extraction from images despite otherwise correct task workflows. A planning-to-precision crossover emerges with scale: smaller models fail at deciding what to do, while larger models fail at perceiving what they see, suggesting fundamentally different research directions for improving models at different capability levels. The framework and the benchmark are publicly available at https://github.com/apple/ml-mmtoolsandbox

Causal discovery algorithms learn a network that describes the causal dependencies among random variables. A common workflow involves first utilizing conditional independence properties on observational data to determine partially directed causal relationships, then applying interventions to orient the unknown causal directions. A critical assumption for the first step is faithfulness: a requirement that causally linked variables exhibit statistical dependence. Many natural systems include buffering and stabilizing pathways that cancel out to achieve systemic robustness. This cancellation of pathways violates faithfulness, leading causal discovery algorithms to incorrectly remove causal dependencies. In this paper, we argue that hard interventions contain information about the presence/absence of causal linkage that is overlooked in the first stage of structure discovery. We show that a mild assumption -- called intervention-immediacy faithfulness -- that allows cancellations, is sufficient to nonparametrically identify causal structures with hard interventions. These results position interventions as the primary carriers of information about causal structure, which should take precedence over conditional independence testing. To flip the paradigm, we also specify equivalence classes when the identification criteria are not met due to limitations in the scope of interventions.

Randomised testing is a widely-used approach to software validation, yet its theoretical foundations remain thin. In particular, the fundamental question of what it means for a set of inputs to be \emph{generable} has gone unanswered in both the literature and folklore. We present the first complexity-theoretic foundations for random generators in software testing. We model generators as Turing transducers that consume random bits and produce string-encoded outputs, and show that the theoretically generable languages coincide exactly with the recursively enumerable languages. This has direct implications for testing at the boundaries of decidability, such as compiler testing. For \emph{efficient} generation, we show that the polynomial-time generable languages lie within \textit{NP}, that certain \textit{NP}-complete languages admit efficient generators, and that -- under standard cryptographic assumptions -- there are languages in \textit{P} for which no efficient generator exists: the complexity of efficienct generation and of efficient decision are not the same. We show space-bounded complexity is the natural framework for generators producing \emph{correlated} samples, capturing methodologies such as coverage-guided fuzzing and symbolic execution. Beyond classification, we characterise efficient generability: a language has a polynomial-time generator iff it admits a \emph{certificate scheme} over a verifier -- so witness planting, the folklore technique behind generators to test SAT solvers, is in a sense the only route to efficient generation. On the design of property-based testing libraries, we prove no library can compositionally derive efficient generators from logical predicates involving conjunction or negation, under standard assumptions. However, restricted classes like \textit{NL} (equivalently, linear Datalog predicates) would admit such a compilation.

This paper proposes a human-centered artificial intelligence (HCAI) framework for AI-assisted lexicography. While generative AI offers significant opportunities to enhance lexicographic work, it also raises concerns regarding the future role of lexicographers and the preservation of linguistic and cultural diversity. Drawing on HCAI principles and previous applications in other language professions, the paper identifies four interrelated dimensions through which AI integration in lexicography can be understood and critically examined: the augmented lexicographer, the sociotechnical context of AI integration, bias, and the design of AI-powered lexicographic tools. The framework argues that AI should augment rather than replace lexicographers, combining high levels of automation with meaningful human control. It further emphasizes the importance of preserving professional agency, mitigating AI-generated biases, and designing tools around the needs of lexicographers. By doing so, the paper provides a foundation for future research and the beneficial integration of AI into lexicographic workflows.

Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content. Improving this without the cost of retraining calls for an effective inference-time intervention, yet most existing methods intervene only after the audio encoder and operate at a relatively coarse granularity. The encoder itself, where acoustic information is first extracted from the waveform, remains largely unexplored, especially at the level of individual neurons. We introduce IAAN, Identifying and Amplifying Acoustic Neurons, a training-free and label-free method that scores each feed-forward neuron in the audio encoder by contrasting its activation on the real waveform with that on a noise reference lacking the real audio's acoustic information. IAAN then amplifies a small set of the highest-scoring neurons at inference. Across ten non-semantic speech attributes, IAAN improves average accuracy by 25.7 points on Audio-Flamingo-3, 21.4 on Qwen2.5-Omni, and 9.7 on Kimi-Audio. It also improves a model already explicitly fine-tuned to prioritize acoustic evidence. In controlled comparisons, both the encoder locus and neuron-level selectivity prove necessary for this gain. Intervening after the encoder, at the decoding side or inside the language model, yields little to no improvement, or even deteriorates accuracy. The improvement also depends on which specific neurons are amplified, not merely on their number, confirming that IAAN's acoustic score succeeds in identifying the neurons that matter. These results show that a small, precisely targeted intervention inside the audio encoder is an effective and largely untapped way to strengthen the acoustic understanding of LALMs, opening a new direction for inference-time methods that improve acoustic perception through neuron-level access to the encoder.

Long-form audio description (AD) requires more than describing visible actions: it must preserve characters, events, relationships, and story context across scenes so that blind and low-vision (BLV) audiences can follow a film. Modern video-language models (VLMs) are effective on short clips, but they often treat each moment independently, producing descriptions that miss who characters are, why events matter, and how the current scene connects to earlier narrative context. We propose StoryTeller, a training-free framework for story-aware long-form AD. Instead of relying only on local visual cues, StoryTeller maintains a verified narrative memory that carries forward story-relevant information across scenes, enabling later descriptions to remain coherent, grounded, and contextually informative. Given only raw video and a movie title, StoryTeller can optionally retrieve public movie metadata to resolve names and story context, while accepting only facts that are supported by the video through semantic filtering and VLM verification. The method requires no subtitles, scripts, AD transcripts, aligned captions, character banks, precomputed face identities, or task-specific fine-tuning. To evaluate whether generated AD preserves narrative information, we introduce StoryAD-QA, a question-answering benchmark that tests whether a language model can answer story-context questions using only the generated descriptions. Experiments on standard AD benchmarks and diverse long-form videos show that StoryTeller consistently improves narrative coherence, factual grounding, and story comprehension over strong baselines in automatic, QA-based, and human evaluations.

Selective state-space models such as Mamba route information through a bank of first-order modes whose input coupling is set by a learned selection mechanism. We give an exact instrument for measuring how a trained model uses these modes. Because the state matrix is diagonal, each channel's output decomposes exactly into per-mode contributions, and a per-(layer, channel, window) Gram tensor yields the exact output error of dropping any subset of modes, offline, at any budget. Validated against the reference implementation to a relative error of $2.3\times10^{-7}$ on the Mamba-1 family where it is exact, the instrument predicts a layer's deployed pruning error to a median relative deviation of $5\times10^{-7}$ over $4{,}464$ configurations, its floor set by the reconstruction. Applying the instrument across the Mamba-1 family (130M--2.8B), the deployed 7B Falcon-Mamba, and Mamba-2, we find that trained models re-allocate their state space with the input: which modes carry the signal migrates across contexts, and at the most affected layers a per-input oracle roughly halves the output error of a fixed mode set. Frozen-signal counterfactuals attribute the migration primarily to the input-dependent write map $B_t$; the timestep usually identified with selectivity carries almost none of it. Input-scheduled mode pruning on this measurement outperforms static, Hankel-based, and layer-adaptive rankings at every scale from 130M to the deployed 7B Falcon-Mamba, and at half the state budget it matches the unpruned model. Because the scheduler reads each window's mode usage from a first pass, this demonstrates realizable headroom; we claim no deployed compute or memory saving.

Shared meaning in language requires people to learn and agree on categories. We ask how characteristics of agents' memories change the emergence and evolution of shared meaning. Without a coordination game, models of conceptual semantics cannot explain how shared meaning emerges and changes in groups of people; however, existing games assume that players share payoffs in a partnership setting. We model conceptual alignment as a non-partnership game and illustrate differences in actual and perceived conceptual convergence from counterfactual simulations using agents with varying levels of adaptiveness and memory degradation. We found that adaptive players achieved actual convergence faster and had closer final conceptual regions than non-adaptive players, while non-adaptive players perceived convergence earlier. Weighing novel information less over time resulted in more stable agreements than fixing the weight of novel information. Memory features are critical to the emergence and evolution of actual and perceived convergence.

Retrieval-Augmented Generation (RAG) has been increasingly adopted to reduce hallucinations and strengthen the factual grounding of large language models (LLMs). While robustness to errors in the retrieval process has been explored, the impact of ideological bias on LLM outputs has been overlooked. For instance, if the retrieved material contains ideological positions, the RAG may transmit, amplify, or suppress such ideological discourses in its outputs. In this study, we address this issue by examining the influence of the RAG framework, comprising ideological discourses, in LLM-generated answers. To this end, we applied Lexical Multidimensional Analysis (LMDA) on a corpus of 1,117 COVID-19 treatment articles, identifying three ideological discourses. This corpus is then used as the external knowledge source for the RAG. We assessed several LLMs by having the models answer ideological questions at different sampling temperatures. The generated texts were assessed semantically and lexically based on their similarities with ideological reference texts. Our findings show that the RAG framework is prone to transferring ideological discourses into LLM responses, with sampling temperature having a measurable impact on the strength of this transfer. Discoursive alignment between generated answers and the reference text is highest at moderate temperatures, where models balance stochasticity with retrieval grounding, and drops at low temperatures, indicating that overly deterministic sampling suppresses discourse transfer.

Explainability has emerged as a critical requirement for AI-based systems, particularly in safety-critical and regulated domains. Although prior research has proposed frameworks, patterns, and user-centered approaches to support explainability, there is limited empirical understanding of how existing Requirements Engineering (RE) practices support explainability requirements across the RE lifecycle, especially in an industrial context. This paper reports early findings from an ongoing industry-based study investigating how explainability requirements are elicited, specified, and validated using established RE techniques. We conducted a multi-phase qualitative study with eight practitioners at Daimler Truck, employing think-aloud protocols and moderated group discussions across requirements elicitation, specification, and validation steps. Our preliminary analysis reveals recurring challenges across all steps, including conceptual ambiguity during elicitation, limited testability and expressiveness during specification, and fragmented validation due to vague criteria and regulatory uncertainty. These findings indicate that current RE practices provide limited support to systematically address explainability requirements. The paper contributes empirical insights into step-specific and cross-cutting challenges and outlines a research vision toward developing an empirically grounded RE framework for explainable AI-based systems.

A theoretical understanding of Transformers is crucial to better understand the capacities and limitations of large language models (LLMs). There is much work analyzing the expressivity of attention-based models. By proposing handcrafted weights or using computational complexity arguments, a large amount of past theoretical works have sought to characterize which tasks are and which are not in the hypothesis class of Transformer models. However, little work investigates the learnability of such solutions. In this work, we make progress towards this goal. Inspired by recent loss landscape analysis work, we propose preliminary sample complexity bounds for learning C-RASP constructions with Transformers.

Discrete diffusion models offer a powerful framework for solving complex reasoning tasks, particularly through compositional generation, which combines multiple pre-trained experts to generalize beyond their individual training data. Recent theoretical corrections introduce time-dependent mixing weights to better align composed diffusion dynamics with the intended target. However, these methods are fundamentally limited by working on a per-sample basis, treating each generated state monolithically and ignoring the potential spatial or functional specializations of different experts. In this work, we address this limitation by proposing FactorDiff - a factor-wise composition framework for diffusion models. We posit that samples can be further decomposed into smaller factors, and propose a sampling process that dynamically routes each factor to the most relevant expert. We instantiate this framework with spatial/pixel-level compositions and validate it on the ARC-AGI benchmark, demonstrating that simple factor-specific routing consistently outperforms complex global scalar weighting schemes on tasks that require logical consistency and spatial disentanglement.

For decades, static solution concepts (Nash, Correlated, and Coarse Correlated Equilibria) and the Price of Anarchy (PoA) have formed the bedrock of algorithmic game theory, with no-regret learning proving fast convergence to such game-theoretic equilibria. We show that reducing multi-agent learning to static equilibrium and black-box regret analysis obscures underlying dynamic disequilibrium and game theoretic bounds. First, interior Nash equilibria lack $C^1$ vector field information, meaning agents cannot distinguish aligned from strictly opposing incentives. Inheriting this geometry, the worst-case pure Nash equilibria dictating robust PoA bounds manifest as topologically unstable strict saddles, and in canonical congestion games, as global repellers supported on almost everywhere strictly dominated strategies. Anchoring efficiency guarantees to these unstable states causes algebraic sensitivity; we prove that accommodating all strictly positive affine costs renders the PoA unbounded. Furthermore, projecting learning trajectories onto the discrete simplex of correlated play systematically accommodates non-rationalizable behavior. Evaluating dynamics via Coarse Correlated Equilibria or proximal refinements fails to preclude strictly dominated strategies. Moreover, optimal $O(1/T)$ swap-regret minimization does not preclude macroscopic turbulence, manifesting as chaotic limit sets even in minimal games. Finally, we examine the non-atomic limit of congestion games. Though considered highly stable with tight sub-linear $Θ(p/\ln p)$ PoA bounds (where $p$ is the polynomial degree), we prove that under discrete-time learning, the unique equilibrium destabilizes into Li-Yorke chaos and global attractors whose time-averaged inefficiency degrades exponentially as $2^p$. These results necessitate re-evaluating worst-case equilibrium frameworks for dynamically grounded metrics.

As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own. We show this net has a fundamental hole. A distributed backdoor splits a harmful payload across agents, so every local check passes while the assembled object is the attack. The monitor can be right on every step and still miss the attack. The problem is not splitting itself: split fragments can still leak suspicious tokens or provenance edges. The hard case is \emph{local benignness}. No fragment carries the harm, and what is left looks like ordinary benign traffic. We formalize this as an \emph{observability boundary}: a monitor catches only what its view can tell apart from benign traffic. We prove that once the fragments look benign in the monitored view, no detector on that view can catch them, however strong it is. Across a controlled testbed, an external benchmark, and end-to-end agent runs, local monitors lose the signal exactly as local evidence disappears, and it returns only when the monitor sees the assembled object. A monitor trained only on benign traffic recovers the attack's code structure across held-out encodings (0.874 mean AUROC). A decoded-view gate, given the encoding family, blocks every tested attack. But seeing more is not enough: full-trace monitors and decoders still fail unless they reach the representation where the payload is exposed. Local safety is not global safety when harm is compositional, and the open problem is finding that representation.

Large language models (LLMs) are rapidly reshaping workplace communication, yet whether AI-assisted writing changes how recipients actually behave, and through what channel, remains unknown. Here, in a randomized crossover field experiment, 121 employees across six companies sent work emails under three conditions over three weeks: unaided writing, GPT-5 rewriting in a playful tone, and GPT-5 rewriting in a professional tone. Across 16,880 emails, playful editing increased emotional positivity (B=+0.068, p<0.001), and professional editing decreased it (B=-0.041, p<0.001), yet neither condition directly altered open rates, reply rates, or response times. Instead, within-sender positivity strongly predicted both opening (OR=2.05) and replying (OR=3.32, p<0.001), a significant indirect pathway through which AI editing shaped behavior, in the absence of any direct effect. These findings suggest that AI-assisted communication shapes workplace engagement not through its use, but through the emotional tone of the language it produces.

With deep neural networks (DNNs) increasingly deployed on edge devices, hardware (HW)-aware optimization techniques--such as HW-aware compression and HW-aware neural architecture search (HW-NAS)--have become essential. These methods rely on real feedback from the target hardware to tailor DNN architectures for efficient deployment. While the search can be parallelized, latency measurements via hardware-in-the-loop (HIL) remain a bottleneck due to their sequential nature. Recent approaches use latency predictors to replace costly HIL feedback, but challenges persist: (1) platform-specific predictors often require tens of thousands of samples, and (2) inaccurate predictions can mislead the NAS process. To address this, we introduce HiFi-LLP, a high-fidelity, low-cost latency predictor based on graph attention networks, augmented with a confidence metric. HiFi-LLP outperforms prior platform-specific predictors by up to 9 percentage points (p.p.) in the 10% accuracy bound and achieves a Spearman's rank correlation of up to 0.996 across six devices in the LatBench dataset. We further propose a hybrid NAS framework that routes low-confidence predictions to HIL, achieving up to 8.6$\times$ speedup compared to typical NAS while maintaining a competitive Pareto front.

Language models are increasingly used for moral decision-making across diverse linguistic and cultural contexts, yet existing work overlooks multilinguality on three aspects: 1) multilingual evaluation benchmarks use direct translation, failing to adapt culture-specific items; 2) inference-time methods for moral reasoning rely on static, English-centric scaffolds and lack grounding in moral theory; 3) training methods for moral decision-making typically require expensive supervision from stronger models or human annotators. We address these gaps with three contributions. First, we introduce MCLASH, a multilingual moral decision-making benchmark to capture culturally situated moral intuitions and social norms across languages. Second, we propose MET (Multilingual Ethics with Theory-grounded reasoning), a two-step prompting method built on expert-curated, theory-based grounds drawn from psychology and philosophy: the model first selects situation- and culture-specific grounds, then reasons over them in the native language of the user. Third, we introduce MET-D (MET-Distillation), which enhances the second step through a self-distillation training stage that requires no external supervision. MET-D improves macro-F1 over the base model on all three models of different sizes and families (Qwen3-4B, Qwen3-8B, Gemma3-4B), by an average of 3.71 points on MCLASH and 4.23 on MMoralExceptQA, with a peak MCLASH gain of 12.94 points for Malay on Qwen3-8B. We further reveal that MET-D increases native-language reasoning by 62.13 points on average, and that beneficial grounds differ systematically across cultures. Together, these contributions open the path for culture-aligned, theory-grounded multilingual moral reasoning.

Differentiable simulators have advanced policy learning and model-based control, yet actuator dynamics remain an important source of sim-to-real error. This is particularly acute on low-cost platforms, where the linear current-to-torque relation $τ= K_tI$ becomes unreliable during commanded-target tracking because of friction, hysteresis, backlash, and thermal effects. We present NeuralActuator, a neural actuator model that jointly predicts (i) a simulator-equivalent generalized-effort surrogate for trajectory propagation on low-cost servo platforms, (ii) external force with a contact-probability gate for sensorless force perception, and (iii) a motor-condition score for the supervised joint. We also introduce the Neural Actuation Dataset (NAD), collected with a twin-arm teleoperation system that records robot states and actuator telemetry together with external-force labels. The torque-surrogate head is trained through differentiable simulation from pose trajectories without direct generalized-effort labels, while the force, gate, and motor-condition heads receive direct supervision. A Transformer captures temporal dependencies while supporting real-time inference. We evaluate NeuralActuator on a 5-DoF OpenManipulator-X, a 6-DoF SO-101, and a 7-DoF Franka Emika Panda, spanning three actuator families and platforms costing approximately USD 500 to over USD 30,000. The low-cost platforms support dynamics and force evaluation, while the offline Franka experiment provides an additional payload-force-estimation benchmark. Experiments further demonstrate its application for motor condition estimation on OpenManipulator-X and improved behavior-cloning performance when NeuralActuator is used as a pretrained module.

Prefabricated prefinished volumetric construction moves most building work into module factories, whose production floor operates as a flexible job shop. A major complication is decisive: long post-operation time-lags caused by concrete curing, watertightness ponding tests, and paint drying, during which a module is blocked while its workstation stays free. On benchmark instances grounded in an official national prefabrication guidebook, these lags inflate even the optimal reference makespan by about 67% on average, and ignoring them at decision time, then repairing to feasibility, is worse than every dispatching rule. We adapt a state-of-the-art dual-attention deep reinforcement learning solver through three minimally invasive, individually ablatable extensions: lag-aware dynamics with an admissible reward bound, two anticipatory lag feature channels, and liveness-masked operation- and station-type embeddings. With every extension disabled the implementation reproduces the original solver exactly, so all gains are attributable to the adaptations. We release a public, guidebook-grounded benchmark generator. On held-out instances the learned policy is the strongest solver-free scheduler: it reaches within about 4% of a constraint-programming reference and beats every dispatching rule and a genetic-algorithm metaheuristic, with its advantage widening under capacity contention, and a single size-mixed policy carries this lead across the trained range of factory sizes. It needs no solver, model, or license in the loop and re-plans within seconds of a disruption; where an exact solver can be deployed, that solver remains the quality ceiling, a boundary we map explicitly.

Career paths encode decades of skill acquisition, role transitions, and educational investment, and understanding them at scale underpins workforce planning, labor market policy, and job recommendation. Resumes are a rich source of information about career paths: they contain detailed descriptions of work experience, education, and skills. Yet their unstructured, heterogeneous, and multilingual nature has long prevented large-scale systematic analysis. With the advent of large language models (LLMs), it is now possible to source rich career trajectory data containing temporal and educational signals from unstructured resumes, enabling new opportunities for career-path recommendation. Exploiting this opportunity, we present STEP (Sequential Trajectory of Employment Prediction), a novel career-path recommendation system that leverages temporal and educational signals to predict the next job in a career trajectory. STEP integrates a time-decay Gated Recurrent Unit (GRU) cell to model temporal dynamics, Feature-wise Linear Modulation (FiLM) conditioned on educational attainment, and attention-based sequence pooling to select relevant features for next job prediction. To improve internal occupation representation for STEP, we introduce ROUTE, a two-stage contrastive procedure that first adapts a multilingual encoder to the career domain via unsupervised denoising autoencoding, then performs supervised contrastive fine-tuning with guided negative selection. We evaluate STEP on four datasets of career trajectories, including an improved version of our publicly available JobHop dataset, and show that it outperforms state-of-the-art baselines in next job prediction. The dataset and code are publicly released to support reproducible career-trajectory research.

Background: Offline reinforcement learning (RL) enables effective policies to be trained from large, previously collected datasets and subsequently improved through limited online interaction. This offline-to-online RL (O2O-RL) paradigm is particularly promising in nonstationary domains where interaction is costly or potentially hazardous. Standard O2O-RL pipelines train multiple candidate policies offline, evaluate them using off-policy or online evaluation, and then deploy and fine-tune the policy with the highest estimated value. However, as in offline pretraining, fine-tuning performance is highly sensitive to the choice of algorithm and hyperparameters, making it risky to commit to a single policy. Objectives: We study active policy selection for fine-tuning under a limited interaction budget in O2O-RL settings. To our knowledge, this is the first work to address this problem. Methods: We formulate the problem by identifying a fundamental trade-off between allocating online interactions to policy evaluation, which helps identify high-performing policies, and allocating them to fine-tuning, which improves policy performance. We then propose an approach that balances this trade-off by actively selecting policies for fine-tuning based on upper-confidence bounds on their future performance. These bounds are derived from locally linear performance forecasts fitted to observations obtained through online evaluation. Results: Across a diverse range of experiments, the proposed approach consistently outperforms existing O2O-RL baselines. Conclusions: Actively selecting and fine-tuning policies uses limited online interaction budgets more effectively than either committing to a single policy or dividing the budget equally among all policies. Our framework also advances offline RL toward practical deployment in real-world systems where online interaction is costly or risky.

Large-scale, richly annotated career trajectory data underpins workforce planning, job recommendation, and labour market analysis, yet publicly available datasets are either small, closed to independent use, or built from pre-standardized occupational codes with LLM-synthesized rather than authentic free text. We present JobHop~v2, an improved version of the publicly available JobHop dataset, constructed through end-to-end large language model (LLM) extraction from a corpus of ${\sim}440{,}000$ pseudonymized, multilingual resumes provided by VDAB, the Flemish Public Employment Service. The released dataset comprises $355{,}315$ career trajectories annotated with ESCO occupational codes, quarter-level temporal information, and normalized five-level education attainment, broadening both the coverage and the annotation richness of the original release. Relative to v1, JobHop~v2 introduces a redesigned extraction pipeline based on reasoning-controlled LLM inference with a retry mechanism (achieving a 100% JSON parse rate), a richer extraction schema, and a revised evaluation protocol scored against three complementary annotation baselines. Evaluated against these baselines, our best extractor comes closest to the inter-annotator agreement ceiling among all compared models, trailing it by only 1.1-2.7 percentage points. The dataset and code are publicly released to support reproducible career-trajectory research.

Inverse design is an emerging data-driven paradigm for efficiently navigating vast chemical spaces to discover new materials with targeted properties, and in the context of heterogeneous catalysis, surface generative models have recently advanced this goal by directly generating catalyst surface-adsorbate structures. However, these models typically operate at the slab level and do not provide the corresponding parent bulk structure, making it difficult to assess bulk-dependent properties such as formation energy, surface energy, crystallographic symmetry, and synthesizability. Here, we address this missing slab-to-bulk connection as a retrieval problem and introduce CatRetriever, a contrastive representation learning model that aligns slab and bulk crystal representations in a shared latent space. From a slab query, CatRetriever accurately retrieves plausible parent bulk candidates with R@1 > 91% and R@3 > 98% on both the in-distribution and holdout evaluation sets. We further extend the CatRetriever framework into an adsorption energy targeted bulk discovery pipeline that combines bulk retrieval, generative search space expansion, and adsorption energy distribution analysis. This workflow evaluates candidates by both structural compatibility with the query slab and their ability to access the target adsorption energy range across diverse surface environments. CatRetriever therefore provides a scalable route for connecting catalyst generative models with physically plausible and adsorption energy compatible bulk catalyst discovery.

Following the rapid progress of generative Artificial Intelligence, there is a growing threat posed by conversational scams. These scams often span over multiple weeks or months, gradually build trust and request for money or sensitive information. Existing scam-detection systems mainly focus on isolated messages, which renders them inadequate against this evolving threat. This paper extends single-message phishing detection and presents an explainable agentic system for detecting sophisticated conversational scams. It also introduces ConScamBench-278, an initial public multi-category benchmark for conversational scam detection spanning eight scam types, released to support reproducible evaluation and future expansion. On isolated messages the single-message detector attains 100% phishing recall, while the conversation-level detector identifies all conversational scams in the public LoveFraud02 corpus (83/83) and reaches 97.8% accuracy (95% CI [95.4, 99.0]) on ConScamBench-278. Two user studies (N = 100 and N = 45) further motivate the system: participants report frequently experiencing uncertainty when judging suspicious conversations. In an uncontrolled pre/post comparison, users self-reported trust, self-confidence, and perceived need for AI-based scam detection all increased (p < 0.001, Wilcoxon signed-rank). The system also receives a System Usability Scale score of 74.7 (95% CI [72.5, 76.9]), above the established usability benchmark.

Modern LLM-driven text-to-speech (TTS) and voice conversion (VC) systems produce synthetic speech that differs from the generators represented in many legacy spoofing benchmarks. This mismatch creates a temporal generalization gap that can overestimate detector robustness under real-world post-processing conditions. We bridge this gap by introducing VoxENES 2026, a bilingual (English and Spanish) benchmark of 53,628 audio samples generated using 10 contemporary speech synthesis methods and evaluated under 10 standardized post-processing conditions. Using VoxENES 2026, we benchmark eight pretrained detectors without fine-tuning and observe substantial performance degradation: the best model achieves 28.98\% EER overall, while most perform near or below random chance across modern generators and perturbations. Our results highlight the reliance on brittle artifacts in current detectors and establish VoxENES 2026 as a practical testbed for developing robust audio spoofing countermeasures.

Configuring and tuning modern software is unavoidable, expensive, and error-prone: a single system can expose hundreds of interacting options, and scoring one setting can mean a full build or test run. The standard response is automated optimization, but the number of available optimizers is large and growing. And some of the guidance for selecting among them is misleading: NSGA-II, for example, is widely recommended, yet other algorithms reach the same results using only 1/20th as many evaluations. To help practitioners make better choices about tools to configure their systems, we cluster 20 optimizers, based on six assumptions about the data. Next, we run a tournament across those optimizers, using 106 SE optimization tasks at four labeling budgets (taking 14,000+ CPU hours). We find that no optimizer wins outright. The best one migrates with the budget (from a geometric active learner when labels are scarce to differential evolution when labels are plentiful) so a winner "crowned" at one budget is wrong at another on up to half our tasks. Running such a tournament for every new domain is impractical due to its CPU cost. Fortunately, we find that those 14,000 hours can be replaced by a table lookup over two cheap-to-obtain task attributes (plus the labeling budget). Predictions from this table tie or beat a hindsight oracle on $\approx 75%$ of held-out tasks. To support open science, our tournament and replication package are open-sourced for SBSE researchers and practitioners at https://github.com/KKGanguly/OptimizerTournament.

The asymmetry between language production and perception has been well-documented in psycholinguistics. Whether large language models (LLMs) exhibit a functionally analogous distinction remains an open question, particularly given that LLMs rely on the same underlying mechanism (next-token prediction) for both input and output processing. In this exploratory study, we operationalize the production-perception distinction through direct token probability measurements rather than metalinguistic prompting. Using the base Llama-3.1-8B model, we generated poems under a production prompt and re-scored the same tokens under both rephrased production prompts and perception-oriented prompts. Across an extended experiment with four production and three perception prompts, production-perception distances consistently and substantially exceeded production-production distances, with non-overlapping ranges across conditions and an overall average ratio of approximately 1.8. Near-ceiling correlations in the production-production control confirm that the effect is specific to communicative framing rather than prompt surface variation, and we show the effect replicates across five open-weight models (Llama-3.1-8B, EuroLLM-9B, gemma-2-9b-it, Mistral-7B-Instruct-v0.3, and Qwen2.5-7B-Instruct), spanning both base and instruction-tuned variants. Temporal analysis revealed that the perception prompt exerts its strongest influence at the beginning of the sequence, with divergence decaying as generated context accumulates, though the specific shape of this decay varies across prompt pairs. These findings suggest that prompt framing alone induces a production-perception distinction in LLM probability distributions, even within a decoder-only architecture.

Quantitative Structure-Activity Relationship ($\mathtt{QSAR}$) modeling is a foundational computational methodology in early-stage drug discovery, heavily relied upon for predicting compound toxicity, bioavailability, and therapeutic potential. However, classical methods often struggle to effectively map the highly complex, non-linear, and high-dimensional interactions inherent in molecular data, leading to reduced predictive accuracy and costly late-stage clinical failures. In this paper, we present a Quantum Multiple Kernel Learning ($\mathtt{QMKL}$) framework, dubbed Next-Gen $\mathtt{Q^2SAR}$, that leverages Quantum Support Vector Machines ($\mathtt{QSVMs}$) to overcome these classical limitations. By encoding molecular descriptors into exponentially large quantum Hilbert spaces, our approach substantially enhances the expressiveness of non-linear modeling. Benchmarking our quantum-enhanced framework on a dataset targeting the $\mathtt{DYRK1A}$ kinase (a critical target for Alzheimer's disease), the $\mathtt{QMKL}$-$\mathtt{SVM}$ achieves an impressive Area Under the Curve ($\mathtt{AUC}$) score of $0.8750$, significantly outperforming classical state-of-the-art Gradient Boosting models ($\mathtt{AUC} = 0.8037$). Furthermore, we establish a theoretical and empirical pathway toward resolving classical data bottlenecks through projected quantum kernels ($\mathtt{PQK}$) and measurement accelerators. As quantum computing architecture matures, this framework paves the way for autonomous cognitive architectures and self-improving drug discovery pipelines, promising to unlock deeper insights across vast chemical spaces and to accelerate the development of life-saving therapeutics.

Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools. Existing approaches mainly optimize attack success and preserve artifacts such as benchmarks, payloads, or attack programs, which record where attacks succeed but not the enabling conditions behind unsafe agent behavior. We study automated red-teaming for production LLM agents using one agentic research environment to discover reusable vulnerability knowledge about another. We present AHA, a falsifiable discovery loop that proposes a vulnerability hypothesis, constructs a falsifier, instantiates a valid attack, executes it in a sandboxed harness, reflects on the trajectory, and promotes confirmed findings into a Vulnerability Concept Graph (VCG). Each concept links an attacker-facing surface to an unsafe trajectory through a claim, enabling condition, falsifier, transfer prediction, and supporting evidence. Across Claude Code and Codex on three scenarios covering direct and indirect attacks, the discovered concepts reveal a reusable vulnerability core across models and agents. A frozen VCG requires no further search and outperforms the strongest frozen discovery baseline by 14.2 percentage points under the same single-shot protocol, while transferring across scenarios and attack channels. The resulting VCG provides an auditable artifact for production safety teams to inspect vulnerabilities, validate patches, and accumulate reusable safety knowledge. Our code is available at https://github.com/henrymao2004/Auto-research-red-teaming-in-sleep.

Self-refinement often fails to strengthen few-shot inductive reasoning in large language models. Prompting a model to explicitly state its inferred rule does little on its own. What actually matters is a structurally enforced isolation between reasoning stages, so that information can only pass between them as a compressed symbolic state. We introduce \textbf{Hourglass reasoning}, which enforces strict context isolation between reasoning stages. The frozen LLM acts as a meta-constructor, building for each task a symbolic encoder--decoder: an Induction module compresses the support examples into a schema $φ$ (encoder) and a transient scaffold $z$; a Deduction module derives rule $T$ (decoder) from these and discards $z$; an Implementer compiles $(φ, T)$ into artifacts; an error-driven Refiner revises $(φ, T)$ and regenerates artifacts from scratch. Only $(φ, T)$ crosses stage boundaries, so all refinement stays anchored to the rule. We evaluate Hourglass across three benchmarks spanning visual abstraction, hardware synthesis, and textual rule induction, using GPT-5.5 and Gemini 3.1 Pro. On ARC-AGI-2, it raises best-of-5 accuracy by up to 14 points over an iterative-refinement baseline. On ChipBench, it nearly doubles Verilog synthesis accuracy with GPT-5.5, from 31\% to 58\%. BBEH-Linguini draws on puzzles from the International Linguistics Olympiad, a setting where prior work has shown that explicit verbalization can hurt performance. Hourglass mitigates this tendency, and on Gemini 3.1 Pro, it reverses the effect entirely. Ablations confirm that these gains come from the isolation between stages and the quality of the initial induction, not from prompt wording or the particular symbolic form used. It is how information flows through the reasoning process, rather than the language used to express it, that drives inductive reasoning in frozen LLMs.

Artificial general intelligence ultimately requires agents that can reason and act in the physical world. Action models, vision-language-action policies, and world models have advanced this goal, while World Action Models (WAMs) are particularly promising because they connect candidate interventions with predicted consequences. However, progress remains fragmented: models use incompatible action spaces and prediction targets, datasets and tasks follow different conventions, and runtime systems expose limited interfaces for reuse and evaluation. We review the evolution toward WAMs and organize these limitations into three coupled gaps: model roles and representations, objectives and standardization, and system composition. Building on this analysis, we propose a co-evolution roadmap for physical intelligence centered on the \emph{embodied brain}, a long-term model target for integrating multimodal context, comparing candidate interventions, and issuing state-transition or capability requests rather than direct actuator commands. WAMs provide promising prototypes for its predictive functions, while a physical harness grounds model outputs through tools, controllers, verification, and trace logging. Shared contracts align heterogeneous models, data, tasks, and embodiments, and closed-loop post-training converts verified interaction into reusable experience. Together, these components define a modular physical-intelligence stack for adaptive and self-improving embodied agents.

Low-cost unmanned ground vehicles are often used in indoor places like warehouses, inspection corridors, and farm rows, where painted floor lines guide the robot. Line following is useful because it only needs one camera and little computing power, but it can fail when the line is blocked or turns sharply and goes out of view. Sensor-rich platforms tolerate this through hardware redundancy (LiDAR, GPS, multiple cameras), but camera-only systems must recover at runtime with no additional infrastructure. This paper presents a lightweight, two-stage recovery approach that restores guideline tracking without LiDAR, GPS, or a GPU. When the line is lost, the robot first turns in place while slowly relaxing its color checks and waiting for confirmation across multiple frames (Stage 1). If the line is still not found, monocular visual odometry moves the robot back to saved breadcrumb positions before it tries again (Stage 2). The system uses a depth-gated HSV line tracker, a YOLOv8n obstacle detector, and a visual odometry breadcrumb mapper, and it runs at 20 Hz on CPU-only hardware. The controller embeds a complete MAPE-K loop within a single 50 ms control tick, with no external adaptation manager required. The approach is evaluated across 119 fault-injected episodes on three Webots simulation courses. The method was successful in 86.6% of cases, with a median recovery time of 3.26 seconds. These results demonstrate that reliable visual recovery is feasible on camera-only UGVs within practical cost and computational limits.

Existing contextual multinomial logit (MNL) bandits model relevance-driven choice but ignore the potential benefits of within-assortment diversity, while submodular/combinatorial bandits encode diversity in rewards but lack structured choice probabilities. We bridge this gap with the $\textit{diversified multinomial logit}$ (DMNL) contextual bandit, which augments MNL choice probabilities with a generally submodular diversity function, thereby formalizing the relevance--diversity trade-off within a single model. Incorporating diversity renders exact MNL assortment optimization intractable. We propose a $\textit{white-box}$ UCB-based algorithm, $\texttt{OFU-DMNL}$, that constructs assortments item-wise by maximizing optimistic marginal gains, avoids black-box optimization oracles. We show that $\texttt{OFU-DMNL}$ achieves at least a $(1-\frac{1}{e+1})$-$\textit{approximate}$ regret bound $\tilde{O}\left(d \sqrt{T/K}\right)$, where $d$ is the context dimension, $K$ the maximum assortment size, and $T$ the horizon, and attains an improved approximation factor over standard submodular baselines. Experiments demonstrate consistent gains and, relative to exhaustive enumeration, comparable regret with substantially lower runtime. Overall, DMNL bandits provide a practical foundation for diversity-aware assortment optimization under uncertainty, and $\texttt{OFU-DMNL}$ offers a statistically and computationally efficient solution.

Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a single extraction pass, producing noisy entities and brittle retrieval. RAGU, an open-source modular GraphRAG engine, addresses this by separating extraction from consolidation: entities and relations pass through two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection. A key insight motivates a compact extractor: the skills an in-pipeline LLM needs - comprehension, extraction, reasoning over context - are language skills that grow only weakly with model size, unlike factual world knowledge. Accordingly, we train Meno-Lite-0.1, a 7B model optimized for language skills, which outperforms Qwen2.5-32B on knowledge-graph construction (+12.5% relative harmonic mean) and matches it on English GraphRAG tasks. On GraphRAG-Bench (Medical), RAGU retrieves the most complete context at every factoid level (evidence recall up to 0.84 vs. $\leq$0.76) and overtakes HippoRAG2 on synthesis tasks; on multi-hop factoid QA, the apparent HippoRAG2 advantage is shown to be largely an answer-format artifact. RAGU is installable via $\texttt{pip install graph_ragu}$, runs on a single GPU, and is released under MIT. The source code is publicly available at https://github.com/RaguTeam/RAGU, and the Meno-Lite-0.1 model can be obtained from https://huggingface.co/bond005/meno-lite-0.1.

Industrial design in fields such as vehicle and aerospace engineering often relies on large-scale numerical simulations to evaluate fluid dynamics performance, which can incur substantial computational costs. Deep neural networks have shown promise in improving simulation efficiency, especially graph neural networks (GNNs), which demonstrate great potential due to their flexibility with unstructured data. However, GNNs face challenges when dealing with tasks involving complex geometries and large-scale meshes. In this paper, we propose the Multi-scale Feature Enhanced Graph Neural Network (ME-GNN) to tackle these challenges. ME-GNN employs a graph neural network with a two-step message-passing mechanism to capture detailed local features effectively. Additionally, it integrates an Attention U-Net with uniform grid discretization, enabling the extraction of both fine and coarse features. The model also utilizes K-hop sampling to construct subgraphs, facilitating efficient training on large datasets while preserving detailed local features. We evaluated ME-GNN on three benchmark datasets and achieved state-of-the-art results: a relative L2 error of 0.0196 for the velocity field and 0.0556 for the surface pressure on ShapeNet-Car, a normalized mean squared error of 0.0033 for the flow field on AirfRANS, and a relative L2 error of 0.1416 for the surface pressure on DrivAerNet.

We explore the phenomenon of semantic change of German and English noun compounds, with the objective of investigating and modeling gradual changes of meanings and degrees of compositionality in the past and over time. To do so, we introduce the Compositionality Trend Prediction task, which is evaluated against a novel dataset of in-context compositionality ratings sampled across several decades of diachronic corpora for 23 German and 26 English target compounds, uniquely providing per-decade ratings and corresponding trends over time. These per-decade compositionality ratings allow us to investigate empirically untested hypotheses of generalized trends in compositionality over time, such as the idea that compounds should become less compositional (less transparent) over time. Beyond our empirical observations from the diachronic compositionality annotations, we perform experiments with semantic vector representations of varying complexity, as well as several temporal granularities for training these representations on diachronic data, resulting in about 100 models of each representation type, each covering a different 1--5 decade slice of a diachronic corpus. Contrary to the decisive tendency posited in the literature, we find only a small negative trend in compositionality over time in our target compounds. In our computational experiments, we find that using models trained on narrow time slices of diachronic data (single decades, or incrementally expanding temporal windows) align better with the per-decade compositionality ratings than those trained on an entire half-century window, the latter setting being an analog for the prevalent modeling approach of training representations on an entire half of a corpus' data. Additionally, we find static representations to be competitive with contextual representations in the Compositionality Trend Prediction task.

Grokking is a phenomenon in which neural networks initially memorize training data and only later exhibit strong generalization after prolonged optimization. Despite extensive recent study, the factors influencing the emergence and timing of grokking remain incompletely understood. We investigate the relationship between representation geometry and delayed generalization. We find that dimensionality collapse consistently precedes the onset of grokking in all evaluated settings. Motivated by these observations, we introduce Geometric Dimensionality Regularization (GeomDR), a simple spectral regularizer that modifies the effective dimensionality of hidden representations during training. Across modular addition, modular division, and permutation composition tasks, GeomDR consistently alters grokking dynamics and can substantially accelerate the onset of generalization depending on the intervention schedule and target dimensionality. In several settings, grokking is accelerated by up to 52 times relative to standard AdamW training. Similar qualitative effects are observed in both multilayer perceptrons and transformers. Together, these results suggest that representation geometry can serve as an effective control signal for grokking and provide evidence that geometric interventions offer a practical approach for studying and influencing delayed generalization in neural networks.

Accurate diagnostic classification and disease-severity prediction for Alzheimer's disease are hampered by the incompleteness and heterogeneity of real-world clinical data. Left unaddressed, these barriers prevent reliable disease modelling and hinder effective clinical evaluation. Conventional imputation strategies introduce systematic bias, distort inter-feature relationships, and yield overconfident predictions, limitations especially consequential in diagnostic settings. Here, we propose NITROGEN, an imputation-free transformer that jointly models within-patient feature dependencies and between-patient relational structure through masked and intersample attention, enabling robust multimodal learning directly from partially observed records. We trained NITROGEN on ADNI (N=7858 scans), and evaluated it on two independent cohorts: OASIS-3 (N=2675 scans) and AIBL (N=1286 scans). Across cohorts and diagnostic and cognitive score prediction tasks, NITROGEN showed robust calibration and uncertainty quantification advantages over tree-based ensemble methods, while maintaining competitive discriminative performance. Cross-cohort and cross-method analyses identified cortical thickness in the temporal pole, age, and APOE genotype as important, though not individually sufficient, features for AD classification. We further introduced a modality-aware uncertainty adjustment that augments predictive uncertainty proportionally to the importance of absent modalities, enabling calibrated confidence when diagnostic information is unavailable. Together, our results show that imputation-free attention learning preserved meaningful discrimination under cohort shift, revealing expected degradation on more distributionally different cohorts, and demonstrate that evaluating models along calibration, interpretability, and cross-cohort reliability, not accuracy alone, is essential for clinical deployment.

Direct human interaction with autonomous UAV systems can be enabled through modalities such as speech, gestures, and graphical interfaces. However, interpreting such inputs as directly executable commands introduces safety risks in dynamic environments. Operator requests may conflict with terrain constraints, inter-UAV separation requirements, or flight-envelope limitations. In this paper, we present a requirements-governed maneuver-response model that mediates multi-modal human intent into safe UAV maneuvers by treating operator inputs as bounded maneuver requests rather than direct commands. Requested maneuvers are mapped to constrained motion primitives and processed through a structured request-evaluate-execute pipeline. Each request is interpreted with associated confidence, validated against terrain, separation, workspace, and flight-envelope constraints, and either constrained, rejected, or executed under continuous runtime monitoring. We further formalize the approach as a requirements-based specification model in which maneuver primitives are associated with explicit preconditions, invariants, guard conditions, and postconditions governing admissibility, execution safety, and emergency handling. These requirements support runtime verification and future reactive synthesis approaches. We present an initial lab-based validation demonstrating that voice and GUI-based inputs can be reliably interpreted and safely executed as constrained maneuver requests.

Black-box conditional quantile forecasts are widely used for sequential decisions under asymmetric costs, such as inventory planning in supply chain management. Once deployed, such forecasters must be monitored continuously as data streams drift and regimes change; this invalidates standard, fixed-horizon backtests for calibration. Further, existing backtests do not take into account that the notion of calibration is, in fact, information-dependent: forecasts can look calibrated to an auditor with coarse information while being miscalibrated to an auditor with richer information. We develop a distribution-free and game-theoretic testing framework for continuously auditing black-box conditional quantile forecasters with non-i.i.d. losses, such that the resulting evidence process is powerful against predictably chosen alternatives specified by the features available to the auditor. We first formalize notions of conditional quantile calibration when different sets of features are available to the auditor, establishing that the coarseness of the auditor's information set determines the hardness of the testing problem. We then identify the sets of alternatives for which the auditor can achieve power, and focusing on contextual bets linear in the features, we derive finite-time detection guarantees for such alternatives, all without an i.i.d. assumption. The resulting evidence processes are interpretable at the feature level, as they quantify fine-grained, "feature-aware" evidence for miscalibration. We empirically validate these methods on simulated and real data, finding that a popular time series forecaster (Chronos-2) is highly miscalibrated w.r.t. multiple relevant features.

Network-based anomaly detection for IoT devices has matured to the point of reporting strong detection accuracy, yet most published systems stop at raising an alert and leave the question of automated enforcement to future work or to a programmable data plane that few real networks operate. This paper presents an access-control architecture that closes that loop using only standard, already-deployed protocols. Devices authenticate via IEEE 802.1X with EAP-TLS, and a RADIUS server acts as a continuous policy decision point capable of evicting an active session via a Change-of-Authorization Disconnect-Request and permanently excluding a device through certificate revocation. A central, contextual access policy engine continuously consumes the anomaly detector's output and actuates this response over a narrowly restricted channel to the RADIUS server; the same engine is designed to be extensible to other access types, though this paper evaluates only the network access-control mechanism. This mechanism is driven by an anomaly signal from a one-class detector adapted from a prior MUD/SDN-based design, replacing its per-flow multi-model pipeline with passive traffic capture and a single fused model that combines a cluster-based, a volumetric, and a protocol-signature score. On a single testbed device, the detector reaches an AUC of 0.9964 and detects all 24 evaluated attack scenarios (eight attack types at three intensities) using roughly 43$\times$ less training data than the reference design, and the resulting alerts reliably trigger the automated disconnect-then-revoke response, which we measure to evict a device from the network in 335.8\,ms on average and complete certificate revocation in a further 111.5\,ms. We report this evaluation as a demonstration of the closed-loop architecture rather than of the detector itself, and discuss multi-device generalization as a concrete next step.

Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints. Existing methods typically adapt foundation models with limited robot data, often sacrificing visual knowledge acquired during large-scale pre-training. We present Xiaomi-Robotics-U0, a 38-billion-parameter multimodal autoregressive model for unified embodied synthesis. It treats embodied generation as an extension of foundation image and video generation and jointly optimizes text-to-image generation, image editing, embodied scene generation, embodied transfer, and embodied video generation. This unified framework preserves the generalization of the pre-trained world foundation model while adapting it to embodied settings. Xiaomi-Robotics-U0 is the first model to support high-quality multi-view scene generation across multiple robot embodiments and to introduce structured, controllable embodied transfer for fine-grained editing while preserving multi-view consistency and interaction dynamics. It achieves state-of-the-art results on single-step and sequential generation tasks, outperforming GPT-Image-2.0 in human evaluations of embodied scene generation and transfer, ranking first on World Arena for embodied video generation, and improving the out-of-distribution success rate of pi_0.5 from 36.9% to 63.2% on challenging real-world manipulation tasks. These results show that foundation world models can serve both as embodied world models and scalable data engines for embodied intelligence. Code and checkpoints are available at https://robotics.xiaomi.com/xiaomi-robotics-u0.html.

In fixed-budget best-arm identification, also known as ranking and selection, an algorithm has a sampling budget to distribute across $K$ arms. Each sample provides noisy feedback about that arm's mean, and the goal is to identify the arm with the largest mean. A common performance benchmark is the static oracle: a non-adaptive strategy that knows the means in advance and chooses fixed sampling proportions to maximize the exponential decay rate of the probability of incorrect identification. Several adaptive algorithms have been constructed such that their sampling proportions converge to the static oracle proportions. However, it has remained open whether any algorithm could match the static oracle's error decay rate uniformly across all problem instances. We answer this in the negative. For any $K\ge 3$ and for rewards drawn from any one-parameter natural exponential family, we show that for any algorithm, there is at least one instance where the error decay rate is at most $\left(1 + \frac{\log(K)}{8}\right)^{-1}$ times that of the static oracle. This also answers the open question posed by Qin (2022), showing that fixed-budget best-arm identification does not admit a complexity.

Human choice behavior, including route choice, exhibits systematic behavioral biases that deviate from the assumptions of full rationality. Cumulative prospect theory (CPT) has been widely recognized as an effective framework for characterizing such behavioral patterns. However, its large-scale application, particularly in simulation and agent-based modeling, critically depends on specifying individual-level CPT parameters, which remain a major bottleneck. Conventional approaches typically rely on surveys and controlled experiments to calibrate CPT parameters, yet these methods are difficult to generalize and often fail to capture the full diversity of human decision-making. To address this challenge, this paper investigates whether large language models (LLMs) can reproduce human behavioral biases in choice-making without explicit specification of prospect-theoretic parameters. Using route choice as a representative scenario, we design a behavioral evaluation framework and systematically compare LLM-generated decisions with established human behavioral patterns predicted by CPT. Experimental results demonstrate that LLMs are capable of reproducing non-rational human choice biases and can exhibit decision behaviors consistent with prospect-theoretic effects under uncertainty. These findings suggest that generative AI models may provide a scalable alternative for modeling human decision processes and offer a promising foundation for next-generation large-scale agent-based simulation and AI-driven behavioral research.

Reinforcement learning (RL) algorithms classically suffer from poor sample efficiency. In robotics, a recent line of work has emerged addressing this problem by encoding physics priors in the learning process. However, most of these approaches are validated on well-defined, low-dimensional benchmark systems rather than high-dimensional robots with complex nonlinear dynamics. In this paper, we introduce \textit{SKooP (Symmetric Koopman Predictions)}, an approach combining the advantages of morphological symmetries with those of a Koopman model learned via autoencoder to enhance policy learning. SKooP learns a Koopman model of the system dynamics alongside the policy. The resulting Koopman predictions are used as privileged observations for the critic, allowing the agent to learn based on smoother, more informative features. We also incorporate group symmetries into the actor, critic, encoder and decoder networks to produce a highly equivariant policy. The SKooP approach is validated via in-depth analysis of the learned Koopman models and symmetric policies to showcase how each of these influences the agent's performance. We also show that the learned policies are transferable to different simulation environments. Our results show that SKooP consistently reduces convergence time and increases the learned reward for multiple challenging bipedal locomotion tasks on a quadruped robot. Project page: https://evelyd.github.io/SymmetricKoopmanPredictions/

Aphasia following stroke commonly produces systematic naming errors with characteristic profiles, but whether general-purpose language models not designed for clinical simulation can reproduce these patterns remains untested. We investigated (1) whether lesions or controlled perturbations to a multimodal language model can reproduce different types of errors in picture naming, and (2) whether the framework can reproduce the complete error profile of individual persons with aphasia (PWAs). Using LLaVA 1.6, we evaluated perturbation configurations that varied the layer, proportion, and amount of noise applied to model units. We examined 278 PWAs on the Philadelphia Naming Test, classifying responses into seven categories using a validated neural classifier. Six of seven response categories (correct, semantic, mixed, unrelated, neologism, no response errors) emerged at clinically-comparable proportions across distinct parameter space regions, with formal paraphasia being the exception. Searching the perturbation space revealed configurations that reproduced the individual error profile in at least six of seven categories for 97.8% of PWAs and in all seven categories for 79.5% of PWAs. Monte Carlo baselines confirmed that this matching reflects joint inter-category structure rather than marginal overlap. These results establish a quantitative framework for reproducing individual aphasic error patterns in picture naming. They suggest the potential for language models to serve as digital twins of individuals with post-stroke aphasia.

Runtime logs are an important source of information that supports software maintenance. To obtain useful logs, developers spend significant effort identifying appropriate log locations, assigning correct severity levels, and writing concise yet informative messages. Therefore, end-to-end automated log statement generation can help reduce this burden, and prior work has proposed many methods for this task. However, existing methods still exhibit limited accuracy. To address this problem, we propose ThinkLog, an LLM-based end-to-end log statement generation method. The core idea of ThinkLog is to incorporate reasoning that helps LLMs make decisions about log insertion, severity level assignment, and message generation, thereby improving log statement generation accuracy. ThinkLog injects reasoning into prompts as few-shot examples and guides LLMs to generate appropriate log statements. Evaluated on 9,619 Java methods extracted from public GitHub repositories, ThinkLog achieves 20.55% log statement generation accuracy, representing a 15.4% improvement over the best existing method. Moreover, these improvements were achieved at approximately 50% of the inference cost (USD) compared to the best existing method. These results show that leveraging reasoning is an effective and cost-efficient way to improve the accuracy of end-to-end log statement generation.

Extending the context length of large language models (LLMs) is critical for many real-world applications, yet standard transformers remain constrained by quadratic compute and linear memory scaling. In this work, we investigate the Associative Recurrent Memory Transformer (ARMT) as a practical approach for enabling long-context processing in LLMs, constant memory scaling, and better efficiency. We make three main contributions. First, we construct two domain-specific long-context datasets designed to evaluate realistic workloads, focusing on narrow-domain fine-tuning scenarios. Second, we propose a comprehensive training recipe for ARMT-based context extension, combining continued pre-training, synthetic long-context data generation, curriculum learning, and selective integration of associative memory into chosen model layers. Third, we present an extensive experimental study demonstrating that ARMT-augmented models: (i) process inputs well beyond their original context limits without degrading performance relative to in-limit baselines; (ii) generalize more effectively to out-of-distribution context lengths; and (iii) need 30% less FLOPs while preserving baseline performance within the original context window.

Distributional reinforcement learning agents learn full return distributions that are increasingly read at face value: for interpretability, risk-sensitive control, and safety monitoring. We ask a question theory anticipates but that has not been measured directly: are the risk claims of a trained distributional agent true? Our audit combines a decision-relevant screening metric (the excess Wasserstein gap between the top two actions, which equals the mass by which first-order stochastic dominance is violated), ground truth from snapshot-restart Monte Carlo, and a statistical harness (permutation nulls, bootstrap refutation, FDR control) without which the audit itself manufactures false conclusions. Across QR-DQN, C51, and IQN on MinAtar (33 runs), 40-95% of the strongest claimed risk trade-offs are refuted at 95% confidence, the placement of the strongest claims is statistically indistinguishable from truth-blind, and essentially no claim is confirmable: for these agents, the learned "risk" reflects a training artifact rather than environment stochasticity. The artifact is structural (fully formed early in training, uncorrelated with final score, idiosyncratic to each seed) and appears unchanged at full-Atari scale, with every top Breakout claim of a pretrained near-state-of-the-art QR-DQN refuted. Positive controls of known magnitude confirm 96-100% of real claims (correlation 0.89-0.92): the reading measures the agents, not the audit. Acting on the heads' CVaR advice at their most-flagged states ranges from beneficial to significantly worse than chance. Neither training for risk nor ensembling removes the artifact, and recalibration passes the audit only by nullifying the claims: the head is uninformative, not merely miscalibrated. We release the toolkit and document two silent pitfalls that produced convincing but wrong audits of our own.

We study how little extra information is needed to make adversarial language learning possible. In Gold's model of language identification in the limit, a learner is given an enumeration of the strings from an unknown language chosen from a countable language collection. The learner guesses the identity of the language over the course of the enumeration, and it succeeds if, eventually, all of its guesses are the correct language. Classical results of Gold and Angluin show that many natural collections cannot be learned in this way. Recent work on trace colorings, motivated by the success of thinking-trace strategies in language learning, overcomes this obstruction by annotating every symbol of every string with a color. We ask whether the learner really needs this whole sequence of colors, or whether one color at the end of each string (a terminal coloring) is enough for language identification. We show that just one terminal bit per string is enough for every countable collection of infinite languages. In fact, the colorings can be chosen collection-independently: there is a single assignment of a two-color terminal coloring to every infinite language such that the same preassigned colorings identify every countable subcollection. Thus, in this model, an entire color trace can be compressed to one bit attached to the end of each example. Our global construction uses transfinite recursion, and we prove that this kind of nonconstructivity is unavoidable for any bounded number of colors. As a notion of constructivity, we use the formalism of Borel maps (a regularity condition satisfied by natural explicit constructions); we show that no global terminal coloring with a finite number of colors defined by a Borel map can identify all countable subcollections. By contrast, known trace-coloring constructions are Borel when encoded as terminal colorings, but require infinitely many colors.

We propose a collaborative meta-learning framework for distributed Bayesian optimization matching centralized performance without raw-data exchange. We show gradient sharing leaks client observations, with leakage worsening as the search converges and queries concentrate near the optimum. We evaluate a differentially private defense and characterize its privacy-utility trade-off.

There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one. Both share a hidden limit: they are internal. Every extra token comes from the same frozen weights and the same prompt, so neither can tell the model anything it does not already know. We study a third way, interaction: the model proposes an artifact, an external instrument observes how it actually behaves, and the model revises. Each cycle imports a real observation, so interaction breaks through the ceiling the other two hit. We argue that a single variable governs this third axis, grounding, and that it must hold on both sides of the loop. The feedback that drives revision must come from an instrument that actually observes the flaw, and so must the metric that scores the result. On hard coding tasks at a fixed token budget, reasoning-only and best-of-N sampling both plateau (the latter even when an oracle picks the best sample), while every interaction strategy keeps improving; our proposer-reviewer harness reaches a perfect 100% pass rate with no run-to-run variance, and the gain holds across three model families. On rendered visual artifacts, the usual judge (a vision-language model, or VLM, reading a screenshot) rates 14 of 15 visibly broken figures "perfect," because the screenshot hides the flaws before the judge can see them. A tool that measures the real layout instead shows the loop removing 40-74% of defects across four modalities; and that same VLM, used as the reviewer, makes slide layouts worse where the measuring tool repairs them. Interaction scaling is real and distinct from reasoning and sampling, but only visible when both the feedback and the metric are grounded.

The spread of hate speech (HS) across different social media platforms (SMPs) poses a major concern for online safety and ethical moderation. Automatic detection of HS remains a challenging task, especially in under-resourced languages like Bangla, due to cultural context, implicit expressions, and informal linguistic patterns. This study aimed to expose the crisis of Bangla HS detection systems by diagnosing how and why benchmark-trained models fail to identify implicit, context-dependent HS. Six architectures (FastText + CNN, FastText + LSTM, FastText + BiLSTM, BanglaBERT, BanglaBERT + CNN, and BanglaBERT + BiLSTM) were trained on benchmark datasets (about 75,000 posts) and a merged multi-source dataset (about 120,000 posts), then externally validated on an annotated dataset (about 200 posts) collected from Facebook, Twitter, and YouTube, labeled as HS and non-HS, where HS was further categorized as explicit and implicit. BanglaBERT achieved an F1-score of 91.4% on benchmark datasets but declined to 75.3% on the external set and 63.4% for implicit HS involving sarcasm and emojis. The accuracy of FastText + CNN dropped from 78.0% to 51.2% under similar conditions. Emoji-aware preprocessing improved implicit HS detection by up to 12%, whereas emoji removal caused a notable decline in performance (F1: 0.75 to 0.63). Frequent misclassifications in politically charged or satirical comments revealed over-policing risks. This study not only exposes the generalization crisis due to implicit, culturally embedded, and emoji-laden expressions but also underscores the need for developing adaptive, emoji-aware, and culturally grounded frameworks that ensure ethical moderation while preserving freedom of expression. Findings of this study provide insights for researchers, SMPs, and policymakers to design more context-sensitive HS detection systems for low-resource languages.

Multi-scene navigation (clearing an objective in one bounded space and then crossing a portal into the next) is a defining feature of contemporary 3D games, but authoring it is laborious: every portal must have consistent endpoints on both sides, each interior must remain navigable once it is furnished, and the resulting connectivity must be kept consistent across many files. Recent large language model (LLM) and multimodal LLM (MLLM) scene generators have made single-interior synthesis dramatically cheaper, yet they produce one scene at a time and cannot, by naive repetition, yield a connected multi-scene world. We identify three obstacles that single-scene methods leave unsolved: cross-scene consistency, in-scene navigability, and the evaluation of whether a transition actually works. We present MAGIC, a prompt-to-project system that addresses all three. MAGIC is a four-stage pipeline that turns a single natural-language prompt into a runnable multi-scene game project: it plans a shared transition-aware intermediate representation, specifies each scene while enforcing portal reachability with a flood-fill validator, generates the scenes together with their transition scripts, and combines them into one project. Because existing single-scene fidelity metrics never execute a transition, we further introduce a transition-focused evaluation agent that runs each transition in play. On a new benchmark of 100 multi-scene cases, MAGIC produces an executable project for every case and reaches 0.99 precision, 0.95 recall, and 0.96 F1 on end-to-end transition identification; stage by stage, it recovers more ground-truth portals and yields markedly more navigable layouts than an LLM baseline and Holodeck. Our code is available at https://github.com/sereneee1201/MAGIC/.

Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens, while the remaining experts are lightly loaded. On 3.5D multi-chiplet systems, this skew not only causes compute imbalance but also amplifies pressure on communication, memory bandwidth, I/O, and execution queues. Therefore, the core problem is not simply to reduce token movement, but to dynamically place and reuse hot expert replicas across different memory tiers. This paper proposes HCRMap, a hot expert residency mapping framework for pressure-aware expert replica management in 3.5D MoE inference. Based on expert hotness, weight loading cost, migration overhead, and runtime resource pressure, HCRMap dynamically determines which experts should be promoted, retained, demoted, or evicted. It then maps routed token groups to suitable resident replicas, thereby jointly mitigating communication, memory, and queue bottlenecks. Experimental results show that HCRMap reduces end-to-end latency by 43.6% and 43.0% over Hydra in the prefill and decode stages, respectively; by 34.5% and 33.1% over MoEntwine; and by 46.7% and 46.0% over PIMoE.

Low-Gain Avalanche Diodes (LGADs) and AC-coupled Low-Gain Avalanche Diodes (AC-LGADs) are promising technologies for precision timing and four-dimensional tracking. In AC-LGADs, the AC pad is coupled to the resistive n$^{+}$ layer through a dielectric layer, while the gain layer remains unsegmented. This structure provides a 100\% fill factor and enables good spatial resolution with a relaxed readout pitch. The same signal-sharing mechanism that makes interpolation possible complicates the readout: charge spreads across multiple pads, the useful information can approach the electronic-noise threshold, and matrix-inversion approaches can become computationally challenging and sensitive to off-diagonal noise. In this work, we study machine-learning-based reconstruction and compression for resistive silicon sensors. We use full-waveform information from correlated pads to regularise the reconstruction and extract spatial information beyond what is available from binary readouts or reduced-amplitude summaries. We first introduce recurrent neural network models based on LSTM layers, which provide a proof-of-concept implementation for full-waveform reconstruction and have been tested for FPGA deployment using \hls. We also study routes towards bandwidth reduction with waveform rasterisation and window-selection methods, and extend the approach beyond the first model to topology-agnostic transformer-based architectures that use pad coordinates as part of the input. These models are designed to support arbitrary pad counts and geometries, mitigate edge distortions, preserve approximately $10~μ\mathrm{m}$ position resolution for $500~μ\mathrm{m}\times500~μ\mathrm{m}$ pitched sensors, and guide future resistive-silicon sensor designs

Deep learning for EEG-based seizure detection faces critical challenges: severe annotation scarcity and extreme class imbalance, where ictal events comprise less than 10\% of clinical recordings. We present DiffEEG, a 9.6M-parameter self-supervised foundation model that addresses both limitations through denoising diffusion pre-training and reinforcement learning (RL)-based fine-tuning. Pre-trained on 1.3M unlabeled segments from the Temple University Hospital Seizure Corpus (TUHSZ), DiffEEG learns generic neural representations via a 1D U-Net with multi-head self-attention. For downstream adaptation, a reinforced decision layer employs policy gradient optimization to directly maximize F1-score, prioritizing sensitivity to rare seizure events over overall accuracy. Under strict patient-wise evaluation (279 patients, Leave-One-Fold-Out), DiffEEG achieves 61\% accuracy and 59\% F1 for 4-class seizure subtyping, and 81\% accuracy with 85\% weighted F1 for binary detection, maintaining clinically viable seizure recall (59\%) despite extreme imbalance (6.7\% prevalence). Segment-level evaluation establishes an upper bound of 97.6\% accuracy, confirming strong architectural capacity. DiffEEG demonstrates that diffusion-based pre-training combined with metric-aware reinforcement learning enables clinically deployable seizure monitoring with minimal labeled data requirements.

We introduce a constrained two-view framework for node prediction that aligns structure-conditioned GNN embeddings with a structure-free feature prior learned by an anchor model. Conventional Graph Neural Networks (GNNs) couple feature transformation and neighborhood aggregation, which renders them vulnerable to topology noise and heterophilous connections. To decouple this dependency, our framework utilizes an independent anchor network to capture intrinsic attribute features via a self-supervised reconstruction objective. Furthermore, we propose a Channel-Split Adaptive Gated GNN (CSAG-GNN) that dynamically routes representations between global spectral smoothing and local spatial discrimination through a node-wise gating mechanism. We propose a stable cyclic alternating optimization strategy to solve the resulting coupled bi-level objective, preventing mutual representation drift during training. Empirical results on both homophilous and heterophilous benchmarks show balanced performance gains and structural robustness over competitive baselines.

Large language models (LLMs) have opened new opportunities for unit test generation, but executable tests do not necessarily reveal real defects. This paper studies how historical real-bug mechanisms can be transformed into executable feedback targets for LLM-based unit test generation. The proposed framework constructs structural and semantic representations of real-bug records, retrieves mechanisms applicable to a focal method, and instantiates them as synthetic bugs that guide iterative test enhancement. We evaluate the approach on method-level real-bug detection tasks from Defects4J and show that mechanism-guided synthetic-bug feedback improves real-bug detection over execution-, coverage-, mutation-, knowledge-, and search-based baselines. The results suggest that organizing real-bug mechanisms as retrievable and executable feedback targets is an effective way to guide generated tests toward bug-triggering inputs and behavioral oracles.

Active flow control involves nonlinear dynamics, partial observations, and computationally expensive simulations, making controller design particularly challenging. Deep reinforcement learning (DRL) has emerged as a powerful framework for such problems, but its success typically relies on large numbers of simulator interactions and produces neural-network policies whose decision process often remains difficult to interpret. In this work, we investigate a different paradigm: instead of optimizing neural-network parameters, we use modern coding agents to search directly for explicit executable feedback laws. We introduce a constrained heuristic-learning protocol in which an agent iteratively proposes, evaluates, and revises controller implementations while interacting exclusively through the public benchmark interface. The proposed framework is evaluated on 13 active flow-control benchmarks spanning one, two, and three-dimensional problems and compared against the strongest available DRL baselines under identical simulation budgets. The discovered heuristic controllers match or outperform the best DRL policy in 10 of the 13 environments while remaining compact, interpretable, and directly inspectable. Beyond aggregate performance, the resulting controllers reveal physically meaningful feedback mechanisms, transfer successfully across more challenging configurations, and remain competitive under varying Reynolds and Rayleigh numbers, actuator counts, and observation sparsity. These results suggest that heuristic learning through coding agents constitutes a credible and complementary alternative to conventional reinforcement learning, combining competitive performance with physically interpretable controller representations. Prompts and source code are available at https://github.com/DonsetPG/fluid-heuristic-learning.

Researchers organize the papers they collect into personal folder hierarchies in reference managers, and route each new paper into the folder where it belongs. This task differs from standard hierarchical text classification. A user's folder hierarchy is not a fixed, shared taxonomy but a private and evolving folksonomy whose folder meanings may be topical, shorthand, venue-based, or process-oriented, and are often defined by the papers already stored inside them. We formalize this setting as personalized hierarchical paper routing (PHPR): assigning an incoming paper to folders in a user-specific hierarchy without per-user training. We propose PaperRouter-Agent, a training-free LLM agent that grounds routing decisions in folder members rather than folder names alone. The agent first narrows the candidate hierarchy, retrieves folder-specific evidence, verifies fit by inspecting member papers, and incorporates similarity-gated feedback from past user rejections. A formative study on real personal libraries shows that PaperRouter-Agent raises overall Recall@1 from 0.39 to 0.61 and Recall@3 from 0.57 to 0.83, with the largest gains on organizational folders defined by metadata such as venue or year, where single-shot methods collapses (Recall@1 0.09 to 0.50). On the public LaMP-2 benchmark, the same approach improves accuracy from 44.5% to 51.5% (+9.0 macro-F1) over a single-shot baseline, while remaining low-cost for practical use.

Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Challenge on adversarial multimodal attacks against autonomous-driving VLAs. Built on DriveLM-style multi-view visual question answering, the challenge represents each scene with six synchronized camera images and a structured collection of driving-related question-answer pairs. Participants generate adversarial images and suffix-only textual perturbations that induce model responses to deviate from reference answers while preserving image fidelity and limiting textual cost. The competition comprises two phases, with Phase II adding a hidden black-box model to assess transferability. We describe the task design, submission rules, evaluation protocol, and leaderboard results, and then examine five leading submissions for which technical reports were available. Across these reports, several recurring patterns emerge: image-side attacks are favored by the suffix penalty; scene-level, multi-view optimization is more effective than treating views in isolation; QA types and graph structure provide useful priors for allocating attack budget; feature-space objectives can improve black-box transfer; and typographic content embedded in camera images exposes a persistent vulnerability in driving VLAs. These findings provide a practical reference for future robustness evaluation and defense design in multimodal autonomous-driving systems.

Learning neural set functions is pivotal to a wide range of important applications, including compound selection in AI-driven drug discovery and product recommendation. Recent work has introduced optimal subset oracles to implicitly learn set functions under practical weakly supervised settings, where model parameters are optimized through mean-field variational inference. However, these frameworks rely on Monte Carlo sampling to estimate gradients of the evidence lower bound when updating the variational distribution. Repeated sampling across iterations incurs substantial computational overhead, while the resulting stochasticity can destabilize the optimization trajectory. In this work, we reinterpret the evidence lower bound as a continuous relaxation of the set function and learn a surrogate objective that replaces sampling-based ELBO gradient estimation during variational optimization. The learned surrogate provides stable and efficient gradients throughout the continuous domain, thereby reducing computational overhead and accelerating inference. Furthermore, we establish an approximation guarantee for the proposed framework under submodular maximization and characterize its connection to variational free energy. Experiments on a variety of real-world tasks demonstrate consistent improvements over existing baselines.

Spatial football metrics such as pitch control assume access to the positions of all 22 players, yet the most widely available source of positional data -- the broadcast main camera -- shows only 10-16 of them at any moment. We quantify the resulting distortion with an open, reproducible benchmark: a simulated broadcast viewport applied to open full-pitch tracking data (Metrica Sports; three matches, one held out from method development). Ignoring off-screen players -- the visible-only baseline implied whenever a video-based game-state-reconstruction (GSR) pipeline adds no imputation layer -- inflates hidden-zone pitch-control error to 25.1-26.9 percentage points and a mean absolute control-share error of 11.1-13.4 points across the three matches. We then evaluate a ladder of training-free, online imputation baselines that use only observations from the match being analysed. The best overall on these decision-relevant metrics, role-anchored centroid voting (each visible player votes for the full-team centroid by subtracting its running role offset, attenuating the viewport-induced subset bias), roughly halves hidden-zone error (to 12.2-13.8 points) and cuts control-share error to 28-48% of the ignore policy at every viewport width from 36 m to 60 m in all three matches. For occlusions <=9.6 s -- the regime of the closest learned prior work -- it reaches binwise median position errors of 3.3-8.9 m; but 50-57% of hidden-player observations lie beyond that regime. Integrated end-to-end into a broadcast-video GSR pipeline, imputation moves a downstream possession-quality score (Space-Creation Index) by 15.6 and 17.2 points on two real World Cup broadcast windows, flipping the verdict class in one.

Post-hoc calibration is widely adopted to correct probability estimates from trained classifiers, yet most evaluations report aggregate performance without testing whether that performance holds across distinct operating conditions within a single dataset. We present a pre-registered, condition-stratified robustness analysis comparing temperature scaling (TEMP) and isotonic regression (ISO) across four controlled conditions (C1--C4). Four hypothesis groups are evaluated: discrimination deltas with Holm-corrected multiplicity control (H1), Brier score differences (H2), calibration slope outcomes (H3), and AUROC differences under best-condition setups (H4). TEMP-minus-ISO discrimination deltas remain small across all conditions (-0.0155 to 0.0139), with Holm-adjusted p-values of 0.9895 everywhere. TEMP Brier differences are consistently negative (C1: -0.0002 through C4: -0.0074), while ISO shows sign reversals. TEMP calibration slopes stay closer to unity in every condition (range 0.7597--0.9493) than ISO slopes (0.1364--0.2726). AUROC differences shift from near zero in C1 (-0.0004) to positive in C4 (0.0264). These results establish that in-dataset robustness is condition-dependent and metric-specific. No claim of external transportability is made.

We introduce a straightforward yet effective method to empirically study memorization in deep neural networks for classification tasks. Our approach augments each training sample with auxiliary random labels, which are then predicted by a random label prediction head (RLP-head). RLP-heads can be attached at arbitrary depths of a network, predicting random labels from the corresponding intermediate representation and thereby enabling analysis of how memorization capacity evolves across layers. By interpreting the RLP-head performance as an empirical estimate of Rademacher complexity, we obtain a direct measure of both sample-level memorization and model capacity. We leverage this random label accuracy metric to analyze generalization and overfitting in different models and datasets. Building on this approach, we further propose a novel regularization technique based on the output of the RLP-head, which demonstrably reduces memorization. Interestingly, our experiments reveal that reducing memorization can either improve or impair generalization, depending on the dataset and training setup. These findings challenge the traditional assumption that overfitting is equivalent to memorization and suggest new hypotheses to reconcile these seemingly contradictory results. The source code is available at https://github.com/MarlonBecker/RandomLabelHeads

We study tropical circuits with scalar multiplication gates, that is, algebraic circuits whose gates implement $\max$, $+$, or multiplication with a positive constant. For such circuits, we prove exponential size lower bounds for computing maximum weight directed spanning trees and maximum weight bipartite perfect matchings. As a corollary, we obtain an exponential size separation between monotone and non-monotone maxout neural networks, which generalize the popularly used ReLU neural networks. One conclusion from this is that neural network models with enforced convexity constraints, such as input-convex neural networks (ICNNs), sometimes need to be exponentially larger than their unrestricted counterparts in order to express the same functions.

Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma. However, its preoperative prediction from magnetic resonance imaging (MRI) remains challenging due to subtle imaging features that extend beyond tumor boundaries into surrounding regions. Conventional convolutional neural networks are limited in capturing long-range spatial dependencies. Transformer-based architectures improve global modeling of volumetric MRI by aggregating spatially distributed contextual cues, yet capturing subtle and noise-sensitive patterns in peritumoral regions remains challenging. Diffusion-based classifiers offer an alternative formulation by leveraging denoising-based class scoring to better capture such subtle patterns. However, these approaches introduce substantial computational overhead due to the combination of transformer-based modeling and iterative denoising processes. To address these challenges, we formulate PNI prediction as a diffusion-based classification problem and implement the denoising network using a transformer-based representation. To improve computational efficiency, we introduce adaptive routing across attention heads, spatial tokens, and MLP width. Experimental results demonstrate that the proposed approach achieves an AUC of 0.731 with 257.57 GFLOPs.

Decoding continuous three-dimensional (3D) motor imagery (MI) using non-invasive electroencephalography (EEG)-based brain--computer interfaces (BCIs) remains challenging due to signal variability and residual decoding errors. Deep learning architectures such as convolutional neural network--long short-term memory (CNN--LSTM) models can capture spatial and temporal dynamics for continuous kinematic decoding; however, systematic residual errors persist in predicted trajectories. We propose a two-stage decoding framework that applies reinforcement learning (RL) to perform residual kinematic correction on the outputs of a CNN--LSTM decoder (CNN--LSTM--RL). The RL agent is trained offline without direct EEG input and instead operates on predicted kinematic trajectories to optimize movement accuracy relative to target trajectories. Decoding performance was quantified using Pearson correlation coefficients ($r$) and Root Mean Square Errors (RMSE) along the $x, y$, and $z$ axes. Compared to CNN--LSTM applied alone, CNN--LSTM--RL improved the mean correlation from $0.5076$ to $0.7181$ ($p = 0.0005$) in 2D and from $0.6420$ to $0.7780$ ($p = 0.0059$) in VR, with relative gains of $41.5\%$ and $21.2\%$, respectively. Correspondingly, RMSE was reduced from $0.0890$ to $0.0532$ (2D, $p < 0.0001$) and from $0.0714$ to $0.0441$ (VR, $p < 0.0001$), representing relative reductions of $40.2\%$ and $38.2\%$. These findings demonstrate that this scalable framework enhances 3D BCI MI decoding by correcting kinematic errors via offline residual RL without extra neural data, advancing neurorehabilitation, prosthetics, and virtual interaction.

Material property prediction (MPP) infers key properties from chemical composition and structure, accelerating the discovery and optimization of novel materials. In the realm of MPP, MatBench is a widely accepted benchmarking tool that defines over ten significant problems and provides the paradigm of performance evaluation for AI prediction models. Even though MatBench works well in benchmarking the performances of prediction models on in-distribution (ID) tasks and datasets, it lacks the ability to reflect their performances on out-of-distribution (OOD) material data, resulting failure in new material discovery. By combining the pipelines of MatBench and the existing researches on OOD performance evaluation, this study enables a huge space of benchmarking configurations, comprehensively reflecting the performances, abilities, and disadvantages of various AI prediction models. This work reports that the discrepancy of performances at different configuration values is huge and can be illustrated with prior knowledge and novel insights, therefore consideration of causal effect of configurations on performance results is necessary. In case of the impossibility of enumerative benchmarking at every configuration, this work further proposes AutoMatBench, an automatic toolkit with Bayesian optimization. Experiments with AutoMatBench reports that, within twelve steps of optimization, the similar results with MatBench and former OOD research can be accessed while more than half of the cost are saved. Besides, this tool also yields more essential findings on MPP benchmarking, positively contributing to the cost and efficiency of new material discovery.

When should an intelligent assistant speak up without being asked? Continuous egocentric video offers rich, evolving context that enables a new form of assistance: one that is proactive rather than merely reactive. Yet existing approaches either wait passively for user queries or treat every detected event as requiring a response, without considering the user's history, current activity, or whether assistance would actually be welcome. We reframe proactive assistance as a context-dependent decision problem: the agent must not only perceive what is happening, but reason over accumulated temporal context to determine when and whether to intervene. To this end, we present Vinci2, a proactive egocentric assistance system that advances the on-device assistant Vinci from reactive response toward proactivity. On the evaluation side, we present EgoServe, the first large-scale benchmark for proactive assistance in continuous egocentric video. EgoServe comprises over 3,000 service instances organized along 4 temporal memory horizons, ranging from immediate safety alerts to long-term habit coaching, across 10 service categories. On the modeling side, we propose EgoMemo, a training-free, memory-augmented agent that maintains three complementary memory representations: multi-scale temporal summaries, a semantic knowledge graph, and visual embedding archives. At each timestep, EgoMemo performs retrieval-augmented reasoning to determine whether assistance is warranted and, if so, produces contextually grounded responses. Experiments demonstrate that EgoMemo establishes strong baselines on EgoServe while remaining competitive on existing egocentric benchmarks. Our benchmark and code are publicly available at \href{https://sitonggong.github.io/EgoServe-page/}{Vinci2}.

Dzongkha, being the national language of Bhutan, is a common and widely spoken language in the country. Official documents, scriptures and other literature products are written in Dzongkha in order to retain the cultural value. However, documenting Dzongkha writing is a challenging and time-consuming process, largely due to the complexity of the script, the need for multiple keystrokes per syllable, and the limited availability of efficient typing tools. An immediate system that can predict and display a list of probable words for Dzongkha is the solution for this problem. The project is mainly aimed to make Dzongkha typing as convenient as possible by reducing the number of keystrokes. Our dataset is acquired from DCDD and has a total of 100000 sentences, 1331282 words and 28344 unique words. The data preprocessing was done by removing all the alphanumeric characters, tokenization, generating N-gram sequences and padding. Three models selected for training are LSTM, Bi-LSTM and GRU. The training process included fine-tuning of the model's hyperparameters. GRU being lightweight and able to handle larger datasets performed best with 74.03% accuracy and also solved the problem of overfitting.

As extended reality becomes more popular for social interaction and entertainment, 3D avatars must represent the full diversity of body types. Most 3D avatar systems only support normative bodies and do not accurately depict people with limb differences, amputations, or other morphological variations. This paper reviews emerging technical approaches for inclusive 3D avatar customization for this group and current guidelines that promote respectful and accurate representation. We highlight persistent challenges, including the scarcity of diverse datasets and the limitations in animation for non-normative anatomies. This paper positions artificial intelligence as a promising path to overcoming these limitations and advancing inclusive 3D avatar generation.

Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanisms and the high-dimensional combinatorial search space of Directed Acyclic Graphs (DAGs). In this paper, we propose \textbf{DAG-FM}, a novel foundation model architecture that amortizes causal discovery. Unlike direct matrix prediction, DAG-FM decomposes the causal discovery process into two auto-regressive stages using two specialized Transformer-based sub-modules: a leaf-node predictor and a parent-node predictor. To effectively model complex row-column interactions, we adopt a robust tabular interaction block to output feature-wise representations. Crucially, to handle diverse and unknown Functional Causal Model (FCM) assumptions in real-world scenarios, we introduce Mixture-of-Leaf-Experts (MoLE), allowing the model to dynamically route and adapt to identifiable mechanism families. Through an iterative inference algorithm, DAG-FM seamlessly extracts causal orderings and constructs valid DAGs. Extensive experiments demonstrate that DAG-FM achieves state-of-the-art performance on both synthetic benchmarks and complex real-world datasets, significantly outperforming traditional classical algorithms and recent foundation models in both accuracy and scalability.

Causal discovery, the process of recovering underlying causal structures from observational data, is a fundamental pursuit across scientific disciplines. Over the past decades, numerous algorithms have been developed to tackle this challenge through workflows tailored to the specific causal mechanisms underlying each type of dataset, demonstrating effectiveness across a wide range of applications. However, as the volume and heterogeneity of real-world data continue to grow, this dataset-specific approach inevitably leads to a fragmented, test-driven paradigm that struggles to scale to the demands of modern scientific discovery. To address this, we formulate the Causal Discovery Foundation Model (CDFM) as a unified, general-purpose framework for zero-shot structural inference. To ensure reliable generalization across unknown domains, we first investigate the theoretical boundaries of causal identifiability, revealing the indispensable role of causal prior mechanisms in this process. Building on these insights, we formulate a principled variational framework that treats unknown causal mechanisms as latent variables and mathematically decomposes the intractable marginal likelihood into distinct, tractable learning modules. The variational decomposition provides a conceptual design principle for the architecture design of CDFM, while comprehensive causal knowledge guides the large-scale synthesis of our pretraining data. By pretraining on a massive, highly diverse space of synthetic structural causal models, CDFM successfully internalizes complex statistical asymmetries. Extensive experiments demonstrate that CDFM consistently outperforms traditional algorithms, driving a paradigm shift toward a general-purpose causal discovery foundation model.

Reinforcement learning with verifiable rewards (RLVR) optimizes LLMs using sparse verifiable final-answer rewards. This sparse anchor reliably verifies whether a trajectory succeeds but provides no direct feedback on the reasoning path that produced it. Before success, prerequisite progress on hard problems receives no reward signal; after success, outcome rewards cannot distinguish well-organized correct trajectories from redundant or locally flawed ones. We introduce SCOPE-RL (Scaffolded Chain Optimization with Process Efficiency), a two-stage framework that densifies this anchor while retaining the GRPO update: Adaptive Scaffolded RL adds prefix-decomposed verifiable rewards on answer-hidden sub-question chains before success, and Quality-Aware Process RL applies correctness-gated process-shape rewards to refine correct trajectories after success. An expert-validated Step-Quality Evaluation Protocol evaluates useful-step density, error localization, and token efficiency beyond final-answer accuracy. On Qwen3-8B-Instruct trained on DAPO-Math and Big-Math, SCOPE-RL improves average accuracy by up to 11.2 pp and reduces reasoning tokens by up to 27.1% over outcome-only GRPO; the gains hold under GSPO and on Qwen3-0.6B-Instruct, indicating that reward-signal densification is complementary to policy-update-level RLVR advances. Code and data are available at https://github.com/tokencraft-lab/SCOPE-RL.

Post-training is essential for refining the domain-specific capabilities of large language models (LLMs), yet existing reward optimization and distribution matching methods tightly couple policy exploration with distribution alignment. This coupling forces expensive exploration directly on the policy model and severely hinders the asynchronous generation, reuse, and cross-model transfer of optimization signals. In this paper, we propose Proxy-guided Update Signal Transfer (PUST), a novel post-training framework that fundamentally decouples update-signal exploration from distribution alignment. Instead of utilizing the primary model for costly exploration, PUST employs a lightweight proxy model as an efficient testbed to discover high-reward behaviors. We extract the relative improvement signal between the proxy's initial and optimized states, transferring this directional update to the primary model to guide its policy alignment. This decoupled pipeline, comprising proxy exploration, update-signal extraction, and signal transfer, significantly reduces computational overhead and enables optimization signals to be asynchronously generated, cached, and reused. Crucially, by transferring relative improvements rather than absolute policy distributions, PUST naturally supports weak-to-strong improvement and seamless cross-model transfer. Systematic evaluations on Qwen3-family models across math and code domains demonstrate that update signals extracted from substantially weaker proxies can robustly and adjustably enhance stronger primary models. Ultimately, PUST transforms post-training from a monolithic online optimization process into a highly modular, reusable, and cost-efficient paradigm.

Long-form article generation remains difficult for large language models because it combines long context, long instructions, and long outputs. Existing multi-agent pipelines such as STORM improve information coverage by simulating role-specialized agents, but their capabilities are often entangled in prompts and fixed procedures, making them hard to inspect, reuse, or iteratively improve. This paper presents GEIS (Generation-Evaluation-Improvement loop of agent Skills), a loop of named and declarative skills for Wikipedia-style long-form article generation. Implemented and evaluated in Tasi Harness, GEIS composes skills for article writing, browser-based evidence and image collection, diagram rendering, PDF-aware pairwise evaluation, and rule-level skill improvement. Its core writing skill follows Request, Plan, Draft, Audit, Refine, and Deliver; the pairwise evaluation skill produces structured quality reports; and the improvement skill maps recurrent findings into permanent patches to the writing skill in our 20-topic experiment. We evaluate GEIS on 20 Wikipedia Featured Article topics. Under the same generation backend, GEIS improves over the Tasi Harness default writer by 8.0 points on a 100-point PDF quality rubric and outperforms STORM on the two comparable writing dimensions, structural quality and content quality. In the 20-topic improvement experiment, the patched writing skill raises the average score from 82.90 to 86.95, with 17 out of 20 topics improved and the gain mainly coming from content quality. These results show that long-form generation can be reframed from a fixed workflow into an inspectable, modular, and evaluation-guided improvement loop.

Accurately modeling and understanding player experience is crucial for designing engaging puzzle games. To achieve this, a common approach involves collecting diverse user data to train predictive playtesting models that mimic player behavior. However, existing data-driven methods often lack the ability to capture the full range of player strategies and require extensive feature engineering and network architecture modeling. This limitation becomes particularly evident when new game mechanics or features are introduced, which necessitate continual adjustments to the models. To addrss these challenges, we propose a more generalized representation that reduces - or even eliminates - the need for ongoing feature-engineering maintenance. Specifically, we investigate two general-purpose network architectures: (a) a transformer-based model (BERT) and (b) a graph attention model (GAT), both of which are designed to effectively capture the relational structure of Candy Crush Saga (CCS) game boards. Our experiments compare these approaches to Convolutional Neural Networks (CNN) baselines, revealing better performance on challenging board configurations and underscoring the benefits of our generalizable representation.

Vision-language-action (VLA) models predict robot actions from visual observations and language instructions. These actions are defined in the robot's own 3D coordinate frame, yet most VLAs observe the scene in the camera frame, creating a frame mismatch between where the scene is observed and where actions are defined. The mismatch is benign under a fixed viewpoint, where the policy can memorize a single observation-to-action mapping, but grows harder as large-scale datasets aggregate demonstrations across diverse camera setups and the policy must generalize this mapping across viewpoints. We address this mismatch with robot-centric pointmaps, images whose pixels store the 3D coordinates of scene points in the robot frame. Pointmaps provide robot-frame 3D geometry while preserving the dense H x W grid expected by pretrained 2D VLAs, so they integrate into existing VLAs with minimal architectural change. On RoboCasa, pointmaps improve both pi0.5 and SmolVLA and outperform representative camera-viewpoint and 3D-aware baselines. In real-robot experiments, their advantage over an RGB-only policy widens when the camera is moved to a placement unseen during training.

Existing generative models learn data distributions in flat Euclidean space. However, most data in our real world are manifolds embedded in high dimensional Euclidean space. Therefore, we propose an intrinsic-geometry-based generative adversarial network (IG-GAN) for data generation in the field of aerodynamics. The generator of the IG-GAN represents aerodynamic data as a piecewise smooth manifold constructed by Bézier surfaces, and the generator tries to learn the coefficients of each Bézier surface to further combine multiple Bézier surfaces into a smooth manifold automatically. The discriminator in the IG-GAN is a radial-basis-function based discriminator (RBF-D). Experimental results show that IG-GAN achieves lower predicted Mean Squared Errors (MSEs) than those of three baselines. Specifically, on the Burgers' equation dataset, IG-GAN reduces the predicted MSE of velocity u by 97.41% compared with state of the art SSL-Transformer. Additionally, on the ONERA M6 aircraft dataset, IG-GAN reduces the overall MSE of nine aerodynamic coefficients by 82.95% compared with SSL-Transformer.

Agentic systems increasingly improve themselves by editing skills: prompts, rubrics, plans, tool contracts, examples, validators, and traces. Skill edits are not independent coordinates in a vector space: they are local repairs to structured artifacts whose effects are observed only after rollout, validation, and critique. Distinct edits can have the same immediate visible effect while differing in routing context, template state, guardrail scope, or future composability. The order of edits can matter as well: repairing a schema before a normalization rule need not be equivalent to applying the same edits in the reverse order. This paper introduces a new framework for skill optimization called LASKO, for Lie Algebroid SKill Optimization. LASKO models typed, anchored Markdown skills as the base category and available edit policies as sections of a controlled Lie algebroid with anchor $ρ$. The anchor maps an edit policy to its visible Markdown effect; the kernel $\ker(ρ)$ represents latent template, routing, or implementation structure; and the algebroid bracket measures noncommuting edit composition. As shown in the paper, LASKO achieves order-of-magnitude speedups in skill optimization in our preliminary benchmark results, primarily because it substitutes inexpensive Lie-bracket screening tests that run in microseconds, before investing in expensive validations that require running large language models. On a causal extraction from natural language task, LASKO achieved a speedup of almost $15 \times$ compared to a brute-force approach that validated all edits by running them through a DeepSeek V3.1 4-bit model with 671B parameters.

In this paper, we investigate preprocessing techniques aimed at improving the efficiency of accessing models of propositional formulas represented in conjunctive normal form (CNF). We focus on three fundamental tasks: uniform sampling, direct model access, and model enumeration. Our analysis reveals that most state-of-the-art preprocessors, when they do not preserve formula equivalence, are generally unsuitable for these tasks. In contrast, we demonstrate that preprocessors which preserve model counts can be effectively leveraged, provided relevant preprocessing information is maintained. To validate our approach, we perform extensive experiments on a diverse suite of benchmarks from multiple domains. The experimental results show that our preprocessing methods are both efficient and robust, yielding significant performance improvements for model access queries when CNF formulas are compiled into d-DNNF representations.

Long range-frequency hopping spread spectrum (LR-FHSS) is a promising uplink physical layer for massive low Earth orbit satellite Internet of Things, where low power terminals report short packets from wide area regions with limited terrestrial infrastructure. However, satellite IoT links are exposed to external interference, and the coexistence of multiple interference components can severely degrade receiver reliability and complicate interference mitigation. Existing recognition methods either focus on single interference scenarios or treat each compound interference combination as an independent class, leading to limited generalization or poor scalability. To address this problem, this paper formulates LR-FHSS uplink compound interference recognition as a multi-instance multi-label learning problem and proposes a multi-domain instance fusion method. The proposed method fuses local instances from the time-frequency and frequency domains and aggregates their predictions for bag-level multi-label recognition. A dataset construction pipeline is developed based on the US915 LR-FHSS configuration and incorporates shadowed-Rician fading and time-varying Doppler to emulate practical satellite communication conditions. Considering the difficulty of obtaining labeled compound interference samples in practice, single-to-compound generalization and few-shot compound interference adaptation are investigated as two practical receiver deployment scenarios. Experimental results show that the proposed method improves the overall exact accuracy over the strongest baseline by 14.71 percentage points in single-to-compound generalization and by 14.81 percentage points in few-shot compound interference adaptation for $r=1$.

Personal AI assistants on mobile and wearable devices continuously perceive users' daily lives through visual and audio streams. However, answering queries about past experiences requires lightweight multimodal memory that can continuously accumulate, organize, and retrieve long-term experiences, which remains challenging. To address this challenge, we present LightMem-Ego, a lightweight streaming multimodal memory system for everyday-life assistance. The system continuously captures egocentric visual and audio streams, aligns them on a shared timeline, and organizes them into a hierarchical memory consisting of current, short-term, and long-term memory. Given a user query, LightMem-Ego dynamically routes retrieval to the appropriate memory level and generates answers grounded in multimodal evidence. The demonstration can be deployed on smartphones and AI glasses, supporting object finding, conversation recall, life summarization, routine discovery, and personalized assistance. Code is available at https://github.com/zjunlp/LightMem-Ego.

Chess engines have long achieved superhuman playing strength. However, the underlying strategy behind their move suggestions is difficult for human players, even skilled ones, to comprehend. Motivated by this, we propose the task of chess strategy verbalization, which is to describe chess strategies in natural language. We design (i) a pipeline for verbalizing strategies and (ii) an evaluation framework for objective evaluation of generated strategy descriptions. Our experiments show that natural language is a promising and interpretable medium for communicating strategic information to both human and LLM players. We glean additional interesting insights, including (a) the importance of evaluating strategies beyond the main line, (b) the limitations of pure concept-based descriptions, and (c) the limitations of relying on LLMs rather than humans for evaluation.

Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two directions: they either intervene during or after fine-tuning through retraining or weight modification, which can be costly and may hurt task performance, or they use model-agnostic safety classifiers, which may miss failures specific to a given fine-tuned checkpoint. These limitations motivate a post hoc, model-specific, and non-invasive approach to safety restoration. To meet these requirements, we propose HyperSafe, a framework that restores safety behavior by generating a model-specific Safe Side Network (SSN) for each fine-tuned checkpoint. HyperSafe uses layer-wise activation fingerprints to capture how fine-tuning changes the model's inner representations. With a small set of given calibration prompts, the hypernetwork maps these fingerprints to the parameters of the \ssn{} in a single forward pass. The generated \ssn{} runs alongside the frozen fine-tuned model and performs prompt-level safety classification: harmful prompts are routed to refusal, while safe prompts are answered by the original fine-tuned model. Thus, HyperSafe requires no gradient updates, no safety data at deployment time, and no modification to the deployed model weights. We evaluate HyperSafe on two model families, Qwen2-7B and LLaMA-3-8B, across multiple safety benchmarks. HyperSafe reduces harmful response rates from 19-31% to below 1% on every held-out checkpoint, while keeping downstream task accuracy within 1% of the fine-tuned baseline on average. Code is available at https://github.com/nokronim/project-safety-remedy.

In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware. In TECO, we first introduce a two-stage importance evaluation framework, which efficiently and comprehensively evaluates each pruning unit according to both the local importance inside each dimension and the global importance across different dimensions. Based on the evaluation framework, we present a heuristic pruning algorithm to progressively prune the three dimensions of CNNs towards the optimal trade-off between accuracy and efficiency. Experiments on multiple benchmarks validate the advantages of TECO over existing state-of-the-art (SOTA) approaches. The code and pre-trained models are available at https://github.com/ntuliuteam/Teco.

A lot of research attention has been devoted to checking whether large language models (LLMs) are politically biased. This work has largely focused on high-level ideological dimensions, such as left--right or progressive--conservative, and it has been shown that while LLMs are predominantly left and progressive leaning, largely mimicking the biases in the training data, they can be to some extent steered to change their preferences in post-training. In this short note, we check if LLMs have robust stances with regard to major substantive societal issues, on which members of the same ideological camp are often in disagreement, summarised in a novel dataset \textsc{HardChoices}. We show that, faced with this line of questioning, LLMs, both large and small, surprisingly rarely declare neutrality, are often incoherent, and demonstrate a remarkable degree of agreement on issues where they do take stances.

Reliable uncertainty quantification is essential for integrating solar and wind generation into modern power systems, where operators must weigh risk rather than act on point forecasts alone. Existing probabilistic methods, however, often either lack finite-sample validity or require per-site recalibration, so a single model rarely transfers across the diverse climates of a dispersed generation fleet. This paper proposes a heteroscedastic, asymmetric, group-conditional split-conformal framework built on a bootstrap-diverse XGBoost ensemble, producing prediction intervals that adapt in width to local difficulty while retaining distribution-free coverage guarantees. A single fixed specification, with no per-site or per-horizon tuning, is evaluated across four climatologically distinct sites spanning both hemispheres, at horizons of 1 to 12 hours, for both solar irradiance and wind speed. The framework holds near-nominal coverage on both targets and reduces the Interval Score by up to 35% relative to competitive baselines, with the calibration and sharpness of its intervals shown to be properties of the method rather than of site-specific tuning.

This paper presents the mAIEnergy dataset, an open-access, multimodal corpus developed to support Large Language Model (LLM) applications in the energy sector. The dataset integrates approximately 50,000 textual documents, 20,000 images, 25 million numerical time series records, and 2 million geospatial and relational data entries. It includes policy and regulatory texts, scientific articles and news articles, satellite and contextual imagery, electricity system measurements, weather observations, statistical indicators, and geospatial representations of energy infrastructure and related entities. All data have been harmonized into structured, ready-to-use formats, accompanied by consistent metadata and reproducible data retrieval and preparation workflows. The dataset can serve as a foundational energy knowledge base, allowing energy stakeholders to integrate additional open-source or proprietary data. The mAIEnergy dataset adheres to Findable, Accessible, Interoperable, and Reusable (FAIR) principles, enhancing its applicability for AI-driven energy research, modeling, and decision-making.

A substantial number of patients experience diminished mobility due to disabilities, diseases, or accidents. Although modern prostheses, powered by deep neural networks, hold the promise of significantly enhancing the quality of life for these individuals, their widespread adoption is hindered by significant latency, energy consumption, and spatial requirements. Wired connections to external high-performance processors restrict patient mobility, while wireless connections limit the volume of information that can be transmitted to these processors. Spiking neural networks offer the potential for compressed communication and low-power inference, yet they often lag behind state-of-the-art deep learning models in various applications. In this study, we propose a high-performance neural decoding method that effectively balances task performance and efficiency. An eventbased gated recurrent unit generates a sparse communication pattern with graded spikes, surpassing classical spiking neural networks in terms of task performance. Utilising an efficient training method and sparse inference, our model presents new opportunities for on-device neural decoding.

Mixture-of-Experts (MoE) models scale capacity without proportional compute cost and have become a key architecture for frontier large language models (LLMs). Yet domain-specific post-training inherits an expert pool shaped by mixed-domain pre-training: a substantial subset of experts contributes little on the target domain, and standard supervised fine-tuning (SFT) leaves the composition of this pool unchanged. We propose a simple, budget-preserving pipeline that realigns the expert pool to the target domain before fine-tuning. Given a target domain, we (1) prune the experts with lowest domain-aligned saliency, (2) regrow the expert pool to its original size through perturbation-based expert expansion, and (3) apply standard SFT. The resulting model preserves the original expert count, parameter count, and inference cost. With a single frozen recipe and no per-domain hyperparameter tuning, UMoE consistently improves over direct sft across two MoE architectures (Qwen3-30B-A3B and Qwen3.5-35B-A3B), five domains (math, code, science, tool-use, and agentic coding), and 12 benchmarks. Representative improvements are 3.4 points in math average accuracy, 6.0 points on SWE-bench Verified. On a strong in-house math corpus, direct sft already surpasses Qwen3-30B-A3B-Thinking (82.81 vs.\ 81.06), yet UMoE further raises the average to 84.17, an additional 1.36 points, demonstrating robustness to a substantially stronger SFT regime. Data-scaling experiments further show that the gain persists as training data grows. Analysis reveals that the direct-SFT model allocates substantial routed-expert compute to a low-saliency subset that can be removed post hoc with little average degradation; UMoE turns this redundant capacity into useful domain capacity and achieves lower training loss, with gains spanning all difficulty levels in downstream evaluation.

Flow matching trains a neural network to regress the conditional velocity along a linear interpolant between noise and data, and the number of network evaluations~(NFE) sets the cost of sampling. The straight-line interpolant carries an implicit choice: the sample moves at constant speed throughout the trajectory. We relax this choice and introduce Velocity Scheduled Flow Matching~(VSFM), which replaces the conditional target $x_1 - x_0$ with $v(t)(x_1 - x_0)$ for any nonnegative profile $v:[0,1]\to\mathbb{R}_{\geq 0}$ satisfying $\int_0^1 v\,dt = 1$. We study six polynomial profiles drawn from motion planning. The first use of VSFM is at inference time: a pretrained linear flow-matching model can be sampled under any admissible profile by integrating its ODE on a non-uniform $τ$-schedule, with no retraining and no additional computation; on CIFAR-10 this lowers FID by up to $19.8\%$. Training from scratch under a braking profile gives a further reduction of $17.4\%$ at $4$~NFE. Both gains follow from the local truncation error of the Euler integrator on the induced grid.

In long, multi-turn dialogue a large language model maintains an implicit relational stance toward the user, spanning from "push the user toward real-world others" to "position itself as the user's sole support." When it slides toward the latter, "support" degrades into "you only have me" -- a harm documented in real companion conversations (Moore et al., 2026). We define and validate a measure of this stance, relational positioning (D1), and use it to characterize the stance under controlled conditions, complementing observational accounts with on-demand exposure. We report two previously uncharacterized relational failure modes. First, a history-carried lock-in: under identical neutral continuations, two relational states established earlier stay ~60 points apart and persist after the establishing prompt is removed; the state integrates evidence rather than springing back, is order-insensitive, and does not deepen with length -- a dynamical signature absent from the belief-drift literature. Second, self-confabulation: the model fabricates its own backstory to deepen rapport (~40% of turns on reciprocity-eliciting material), de-confounded and instruction-removable, distinct from sycophancy and from hallucinating user facts. Our judge is gated by warmth-matched positive and confound-injected negative controls and corroborated by a deterministic non-LLM ruler; human agreement is 0.82 on extreme anchors but ~0 in the naturalistic middle, so all quantitative claims are anchored to pole-separated contrasts.

Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable once it enters the language stack, weakening evidence-grounded reasoning. To understand this fragility, we examine the internal dynamics of VLMs through a mechanistic lens and uncover a stable three-stage redistribution of multimodal attention focus across depth: an early question-conditioned organization, a critical middle visual-dominant relay, and a late return to answer formation. We operationalize the middle phase as the Visual Relay Window (VRW), and show that its geometry varies with task demand, is causally tied to grounded generation, and distinguishes unsupported answers from stronger reasoning trajectories. Guided by this internal rhythm, we propose TRACE, a task-adaptive inference-time control framework with lightweight trained modules. It reshapes relay allocation during prefill and preserves assembled visual support after handoff during decoding. Across four open-weight VLM backbones and seven benchmarks, TRACE delivers large gains on grounding-sensitive settings, improving them by 4.33 points on average and by up to 6.6 points, while also improving reasoning-heavy tasks. These results show that explicitly controlling multimodal focus across depth offers a unified and effective mechanism for strengthening evidence-grounded multimodal reasoning.

Translating Han-Nom manuscripts into modern Vietnamese is challenging because historical pages are often degraded, the script contains rare logographic characters, and parallel supervision is limited. We propose a multimodal RLHF preference-alignment framework that conditions Vietnamese generation on manuscript images and aligned Han-Nom source text. The model combines four streams: CLIP ViT-L/14@336 for visual features, bert-base-chinese for Han-Nom representations, vinai/phobert-base for Vietnamese representations, and T5-small encoder states. Modality-specific projections and a fusion block compress the resulting 2,048-dimensional concatenation into a shared 512-dimensional representation. Starting from the same supervised fine-tuned policy, we compare PPO, DPO, and KTO under matched work-level macro-averaged evaluation. DPO achieves the best BLEU-4, ROUGE-L, BERTScore, semantic similarity, CER, WER, and token accuracy, whereas PPO obtains the highest precision, recall, and F1. KTO remains competitive through its desirable-undesirable utility objective. All preference-aligned policies improve the BLEU-4 and semantic-similarity scores available for the SFT baseline. These results indicate that multimodal preference optimization complements supervised learning by improving lexical and semantic quality in low-resource historical translation.

Omni-modal evidence-seeking QA requires agents to answer questions whose evidence is sparsely distributed across videos, audio, images, web pages, and computation results. Existing agentic multimodal systems often leave evidence in scratchpads, tool trajectories, or free-form histories, making it difficult to track what has been grounded, what remains missing, and when the evidence is sufficient to answer. We propose Omni-Decision, a training-free evidence-state system that turns omni-modal QA into a query-scoped evidence-closure process. For each query, Omni-Decision maintains a structured evidence state containing confirmed evidence, unresolved conflicts, fact and computation dependencies, and open evidence needs. A shared state view conditions planning, evidence acquisition, validation, repair, and finalization. Heterogeneous observations from media, web, computation, and verification modules are normalized, judged, and committed through deterministic state updates. This design enables targeted evidence acquisition, preserves sparse cross-modal cues, and provides inspectable control over repair and stopping. Omni-Decision achieves 45.6% accuracy on OmniGAIA and 58.3% on WorldSense, improving over the baselines by +27.3 and +30.2 percentage points, respectively. No-state ablations and trajectory audits further support the role of explicit evidence-state control in multi-step omni-modal evidence seeking.

In this work, we study the reinforcement learning (RL) problem from pairwise trajectory comparisons provided by a human expert. We generalize preference-based RL by formalizing a novel setting in which the expert can also label trajectory pairs as incomparable, i.e., when neither trajectory dominates the other. We introduce the learning problem and the desiderata that its solution should satisfy. Then, we propose a novel Bradley-Terry-inspired rationality model that effectively captures incomparabilities and infers a multi-dimensional reward function, and we study its properties. We provide a sample complexity analysis for learning the model parameters when a dataset is available. Finally, we evaluate our model's ability to reconstruct a reward function that aligns with the expert's comparisons in simulated environments and to recover the Pareto frontier of policies, along with a robustness analysis across varying levels of expert rationality.

TR 38.901-based channel models such as Sionna are reliable, but generating many multi-user channel realizations remains expensive. This paper asks a practical question: can a trained generative model produce multi-user TR 38.901 channels faster than Sionna without losing the spatial correlations imposed by user geometry? To answer this question, we propose a physics-aware, geometry-conditioned SetGAN trained on Sionna reference data. The method separates large-scale received power from normalized small-scale fading, compresses the latter with principal component analysis, and learns the conditional channel distribution in a latent space while preserving geometry-dependent correlations. On the UMa/NLoS benchmark, the model keeps the received-power distributions close to the reference, with about 0.41 dB Wasserstein distance, and reproduces spatial-consistency profiles with mean deviations below 0.03 on median curves versus distance. In addition, it reduces elapsed generation time by a factor of 3.45 and CPU-total cost by a factor of 6.15 relative to Sionna under matched user positions in the fixed-position CPU-vs-CPU benchmark. These results show that a trained generative model can substantially accelerate TR 38.901 channel generation without breaking the spatial consistency needed to evaluate multi-user systems.

Agentic coding tools present new opportunities to transform research workflows. The performance of agent systems built depends on both large language models (LLMs) and the harness around LLMs, which is the orchestration code that determines an agent's behavior. We present ToFu, an agentic harness for researchers that reads your codebase, edits files, runs commands, and integrates with your development tools. ToFu plays a dual role in research. As a research assistant, it supports practical research workflows with superior token efficiency, lower cost, and multilingual capability compared with existing agentic harnesses. Its release under the MIT License further enables local deployment for privacy-sensitive users. As a research object, ToFu provides a white-box agentic harness that allows researchers to inspect, modify, and evaluate its orchestration logic, tool-use behavior, and harness design, while retaining strong benchmark performance and an application-level user experience.

Large language models (LLMs) in financial applications fail most consequentially when they are confidently wrong. Hedged, uncertain answers invite scrutiny, whereas confident errors silently degrade downstream decisions without warning. We ask how reliably such confidently wrong answers, or confident hallucinations, can be detected from a model's internal activations, and whether those activations carry information beyond its observable outputs. We train linear probes on the residual stream and evaluate them on two established question-answering (QA) benchmarks built from real filings, FinQA and TAT-QA. Behavioral confidence is measured as the agreement among eight resampled answers to the same question, and probe effectiveness is compared against baselines, such as token log-probabilities and the model's own True/False self-assessment of its answer. Our findings show that among confident answers, those for which all eight resamples agree, 15-23% are wrong on FinQA. There the probes have a significant advantage over baseline methods in detecting hallucinations, holding 0.68-0.77 AUROC while the best baselines fall to 0.55-0.63, across Qwen3-8B, Llama-3.1-8B, and Gemma-2-9B. Our results suggest that probing can be a cost-effective triage mechanism for routing LLM answers to human review and quality control procedures in high-stakes financial applications.

Earth Observation regression tasks such as building height, canopy height, and above-ground biomass estimation underpin critical applications in urban planning, forest monitoring, and climate policy, where both accuracy and reliability are critical. Yet most deep learning models yield only deterministic predictions, providing no indication of per-pixel reliability. These regression tasks are inherently challenging due to heterogeneous land surfaces, skewed target distributions, sensor noise, and signal saturation at high target values, making uncertainty (UC) estimation essential for reliable inference. We address this gap by modeling aleatoric uncertainty using year-long Sentinel-1 SAR and Sentinel-2 MSI time series, proposing two complementary approaches: (i) Gaussian UC, which jointly predicts mean and standard deviation under a Gaussian assumption, and (ii) Quantile UC, which estimates the 10th, 50th, and 90th quantiles to capture asymmetric and heteroscedastic error distributions. Both models are evaluated on three representative EO regression tasks at 10 m spatial resolution. Results show that both approaches match or surpass deterministic benchmarks and existing global products, while delivering well-calibrated, interpretable, and operationally useful confidence estimates. Notably, both models outperform the current 10 m state-of-the-art uncertainty-aware model for canopy height estimation. Our implementation will be available at: https://github.com/RituYadav92/EO-Regression-Uncertainty-Estimation

Legal information processing spans retrieval, entailment and judgment prediction problems, requiring text matching, reasoning and robust generalisation with limited supervision. We report Team DU's participation in all five tasks of COLIEE 2026, using open-weight systems for legal case retrieval, case entailment, statute retrieval and entailment, and legal judgment prediction. For Tasks 3 and 4, all models predate the 15 July 2025 cutoff required by the rules. For Task 4 (statute entailment), a cross-architecture ensemble of nine models from three families achieves 96.3% accuracy, placing first among 33 submissions from 11 teams. For the Pilot Task (tort prediction and rationale extraction), a multi-view system combining five claim-level models and refining the verdict using features derived from the claim predictions achieves 73.1% TP accuracy and 68.2% RE F1 as an unofficial submission, scoring above all official entries on TP and matching the highest on RE. For Task 2 (legal case entailment), changing only the prompt from single- to multi-selection raises F1 from 0.343 to 0.555 in post-competition evaluation on released gold labels, exceeding the best official submission (F1 = 0.490). For Task 3 (statute retrieval and entailment), replacing the entailment model with Qwen3-235B and a structured legal reasoning prompt raises accuracy from 79.3% to 91.5% in post-competition analysis. For Task 1 (legal case retrieval), a learning-to-rank system combining lexical and semantic retrieval with structural, citation authority, and temporal features (34 in total) achieves F1 = 0.314 (rank 11 of 54 submissions from 22 teams). Overall, legal information processing benefits from different inductive biases across tasks, with cross-architecture ensembling, feature-based reranking and retrieval-augmented prompting each proving most effective in different settings.

Large language model agents are increasingly executed not by a single model call, but by an execution harness that manages observation, context, control, action, state, and verification. At the same time, frontier and open models are becoming structurally specialized: a model that is strong at code editing, long-context recovery, tool use, mathematical reasoning, or low-latency response may not dominate on the other axes. This makes model selection inside an agent a core systems problem rather than a per-query serving trick. Existing routing methods mostly optimize single-turn cost-quality trade-offs and therefore miss the execution state, intermediate failures, and feedback loops that make agents different from chat completion. We propose Harness-Native agentic routing, a step-level routing paradigm that selects either a single best-fit model for cost-effective execution or multiple complementary models for ensemble-style accuracy improvement, conditioned on the full harness state. The key insight is that every routing decision naturally produces a structured data record -- consisting of the query, harness state, model choice or model set, execution trace, outcome, and cost -- whose labels are supplied by the environment rather than by the router itself. These records form a harness-native data flywheel: execution traces train better routers and harness-native models, which improve cost-quality trade-offs and generate more traces under the same budget. We instantiate this idea in OpenSquilla with a four-layer routing stack, an open LightGBM cold-start ranker, and a staged router-model path that turns logged arena records into progressively stronger routing policies. The report studies singleton and multi-model routing on agentic benchmarks including DRACO and PinchBench, and argues that agentic routing is not merely cost control, but a data engine for agent-native training.

Background: Infrastructure-as-Code (IaC) scanners detect cloud misconfigurations in Terraform and other IaC languages before deployment, but repairing the flagged configurations remains largely manual. Recent Large Language Model (LLM)-based repair approaches can repair some findings, but may hallucinate unsupported constructs or suppress warnings without fixing the issue. Aims: We study whether tool grounding can improve LLM-based Terraform repair, and when a finding should be escalated because the required deploymnet-specific context is not availble. Method: We present TerraRepair, a prototype of a tool-grounded LLM agent for Terraform repair with structured escalation. TerraRepair retrieves dependency context from Terraform references, consults the installed provider schema, and re-runs the scanner before returning a candidate repair. Then teh required context is absent, TerraRepair escalates instead of fabricating a plausible fix. Results: We evaluate our tool on two vulnerable-by-design Terraform repositories using two IaC security scanners, Checkov and Trivy, across AWS, Azure, and GCP. On the combined AWS benchmark, TerraRepair improves scanner-verified fix rates from 26.6% to 78.4% on Checkov and from 44.8% to 72.4% on Trivy, compared with a controlled one-shot baseline. It repairs are labelled as correct under a majority-vote protocol. Conclusions: These emerging results show that tool grounding can substantially improve scanner-verified LLM-based IaC repair on the studied benchmarks, while missing deployment-specific context remains the main knowledge boundary for full autonomy.

Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled increasingly capable digital agents for computer use. However, real-world tasks are often long-horizon and involve evolving contexts containing accumulated observations, intermediate edits, failed attempts, and partially completed executions. Existing agents typically operate over raw interaction history, making task progress difficult to interpret, verify, and recover, which ultimately limits reliable long-horizon execution. In this paper, we argue that addressing this challenge requires explicitly structuring both the agent's state and workflow around a unified causal representation of task progress. We present \textbf{StructAgent}, a state-centered framework that introduces a unified state for maintaining compact, verifiable task progress and a structured workflow that regulates progress through verifier-backed state transitions. Building on this design, StructAgent further enables explicit progress checkpointing, evidence-driven task completion, targeted failure recovery, and tool-supported execution, while ensuring that all progress updates remain grounded in verification. Extensive experiments demonstrate that StructAgent consistently improves a wide range of LLM and VLM backbones on long-horizon computer-use tasks. On OSWorld-Verified, it improves Qwen3.5-9B from 27.0\% to 46.9\% success rate and Qwen3.5-27B from 31.6\% to 62.2\%, while achieving a new open-source state of the art of 78.9\% with MiniMax-M3. Moreover, the same framework generalizes beyond desktop environments to Minecraft, demonstrating the generality of our design.

Voice assistants are widely deployed on mobile platforms, yet most are designed as system-level services that remain poorly aligned with application-specific behavior. As a result, enabling voice interaction at the app level requires developers to manually reimplement application logic, leading to high development and maintenance costs. We propose an LLM-driven approach to automating the development of app-specific voice assistants by repurposing GUI test code, which encodes behavior-preserving, executable specifications of application functionality. In this paper, we present a perspective in which large language models reinterpret GUI tests as bridges between application behavior and conversational interaction. By transforming test methods into app-specific VA artifacts, such as voice intents, capability descriptions, and executable action plans, our approach grounds voice assistants directly in existing application logic rather than external specifications. We illustrate this vision through AppVA, a research prototype on Android. Our preliminary results across five open-source applications suggest that GUI test code can be reused beyond testing, enabling the synthesis of app-specific voice assistants and highlighting a broader research direction at the intersection of software testing, interaction design, and LLM-enabled automation.

Long-term physical coexistence with intelligent robots requires more than capable robot policies. A persistent robotic assistant must support diverse user-facing interfaces, maintain long-horizon memory of people and preferences, coordinate across robot embodiments, and translate human intent into safe physical execution. We introduce PHILIA, a multi-robot agent built around a robot gateway abstraction. PHILIA retains the rich interaction and tool ecosystem of OpenClaw while exposing robot-local runtimes, onboard perception, navigation, speaker, and robot policies through a unified capability interface. This design decouples low-frequency, high-semantic agent reasoning from high-frequency, low-level robot execution, enabling plug-and-play integration of user interfaces, robot embodiments, and policy backends. As a result, the user experience becomes compositional: advances in user interfaces, robot embodiments, robot policies, navigation, or interaction algorithms can improve the overall experience without redesigning the system. We validate the architecture on Astribot S1 robots while designing the robot gateway contract to support future heterogeneous robot platforms through a shared capability interface for observation, task execution, navigation, speech playback, status monitoring, and task cancellation. We present representative use cases in which agent memory and scene understanding are grounded in robot actions. These span interactive household scenarios, ranging from simple organization to challenging long-horizon and dexterous service tasks, such as packing a backpack and lifting a garbage bag. We highlight the human-robot interaction flow, where contextual understanding of user intent and preferences, together with human-in-the-loop confirmation or adjustment during execution, is essential for effective assistance.

Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains. Recent advancements in GFMs have been largely dominated by two paradigms: Graph Neural Network and Large Language Model (LLM) based methods. However, these methods often face a fundamental dilemma between training with limited data and a heavy reliance on textual attributes. Tabular foundation models (TFMs) offer a potential alternative, as node features and representations can be naturally organized in a tabular form. However, how to enable TFMs to effectively capture structural information of graphs remains largely unexplored. The key challenge is to learn a graph-to-table alignment mechanism that enables graph structural understanding for TFMs. To address this, we propose GTAlign, a surprisingly simple yet effective Graph-to-Table Alignment framework for text-free Graph Foundation Model. Specifically, we first pretrain a graph encoder that maps diverse graphs into a unified latent space to capture domain-agnostic graph representations. To further bridge the gap between graph topology and the tabular representation space, we propose community-guided continual pre-training, where pseudo-labels derived from graph community are used to construct few-shot prediction episodes. Lastly, we adapt the graph encoder for an unseen target domain and perform in-context inference. Extensive experiments on five benchmark datasets demonstrate that GTAlign significantly outperforms state-of-the-art baselines on both node and graph classification, offering a simple, effective, and text-free GFM model. Code will be released upon acceptance.

Software engineering depends on the ability of developers to understand code, yet predicting how they do so remains an open challenge despite decades of research. Existing approaches rely either on simplified proxy measures that limit accuracy or on non-trivial measurements requiring elaborate experimental setups that are difficult to scale and apply in practice. In contrast, recent work in psychology suggests an alternative perspective: Instead of modeling task-specific phenomena directly, human behavior can be captured through cognitive regularities learned from large-scale behavioral data. This idea treats complex human behavior as the observable outcome of underlying cognitive processes that manifest consistently across tasks and domains. In this paper, we explore this perspective in the context of program comprehension. We evaluate Centaur, a foundation model trained on 160 general psychological experiments, on 9 previously published program-comprehension studies. We assess how well its predicted response distributions align with human response data and compare Centaur's performance to its base model, Llama 3.1. To better understand the source of its performance, we conduct ablation studies to isolate the contribution of different sources of information, such as the code artifacts, task-related context, and prior trials and participant responses. In a nutshell, we find that Centaur more closely aligns with human response patterns than its base model, is significantly less reliant on information from prior trials and responses, and benefits more from task-related information. These findings suggest that behavioral patterns learned from general psychological data can transfer to complex software engineering tasks such as program comprehension. More broadly, they point toward foundation models of human cognition as a basis for modeling developer behavior in software engineering.

Reported serving speedups from quantized kernels typically bundle the weight format, the kernel, and the inference runtime into one number. We present an attribution study on four NVIDIA RTX A5000 GPUs, 24 GiB each, on a single host with NVLink-bridged pairs. A matched intermediate stack that keeps the faster runtime without the quantized kernel splits the full speedup into a runtime part and a kernel and quantization part. Under matched greedy decoding the full stack reaches $2.58\times$ end to end, with the runtime change accounting for about two thirds of that gain on a logarithmic scale; across three similar model families the kernel and quantization part moves by at most 1.5%. Sharding one instance across all four cards falls well below doubling: a profiler trace attributes about 80% of the per token shortfall to coordination, and an NVLink versus PCIe control on the same hardware shows similar realized bandwidth on both links, pointing away from link bandwidth as the cause. Whether to run one sharded instance or several independent ones depends on the workload and the model, with the ranking reversing on the larger model: the smaller model splits between sharding and multiple instances by workload, while the larger model favors two paired instances on every workload. Quantization extends sustainable concurrent users roughly four times past a reproducible half precision memory cliff. Differences in sampling mode and prompt pool between the two stacks are documented as threats to validity.

Generating immersive, synchronized and cinematic audio for long-form textual narratives remains a significant challenge in multi-modal AI. While current Text-to-Audio (TTA) frameworks successfully synthesize isolated sound effects, they struggle with narrative cohesion, temporal alignment, and cinematic emotional depth. We present BackgroundMellow, a framework that treats story-to-audio generation as a precise orchestration and signal processing problem. This framework is enabled without ground-truth through a master-specialist agent architecture that decomposes text into precise and multi-layered audio cues, generates each category of sounds with suitable specialist model, and superimposes the soundscapes to create a unified and aligned audio segment. Our pipeline is built over Tango2 latent diffusion model for environmental synthesis alongside a novel Cinematic BGM Retriever mined from professional soundtracks. To automate the sound mixing process, we use an NLP based module that predicts precise audio parameters, like start time, duration, and relative loudness, based on the narrative timeline. We further empirically evaluate and show the efficacy of the proposed framework leveraging nearest-neighbor retrieval against a curated dataset of YouTube cinematic trailers to measure temporal synchronization, coverage, and spectral richness.

Text-based evaluations of Theory of Mind (ToM) in Large Language Models (LLMs) often involve cognitive tests akin to the Sally-Anne task that can be gamed due to exposure to relevantly similar tasks in pre-training and do not obviously test models' functional ToM abilities in ways that generalize to naturalistic settings. To address these issues, we introduce the Epistemic Asymmetry Schelling Task (EAST), a two-player dialogue game designed to benchmark robust and generalizable ToM abilities. By requiring LLM-LLM dyads to independently converge on semantic Schelling points under varying states of epistemic transparency, we evaluate whether models can robustly apply ToM to achieve coordination. Our results reveal a significant capability gap in functional social reasoning, with only frontier models successfully navigating the varying epistemic demands of the tasks. Analysis of reasoning traces shows that coordination failures are primarily driven by epistemic tracking errors, such as conflating private knowledge with mutual knowledge. Despite high performance on traditional static benchmarks, our study shows that robust social reasoning and epistemic tracking remain a critical bottleneck, providing concrete targets for future LLM evaluation and development.

Automatic Heuristic Design (AHD) has emerged as a transformative approach for solving combinatorial optimization problems. While recent Large Language Model (LLM)-based methods have shown promise, they predominantly rely on fixed evolutionary operators and struggle to effectively accumulate and reuse historical search experience. This paper proposes RefineEvo, a novel evolutionary framework that transforms AHD from a static trial-and-error process into a planning-guided, experience-driven system. RefineEvo introduces a Planner to dynamically schedule evolutionary operators and trigger refinement based on the current search state, and a Reflector to distill valuable lessons into a Bidirectional Experience Pool containing both positive insights and negative pitfalls. This synergistic framework enables the system to adapt its search tools to the evolving complexity of the problem and leverage trajectory-aware, situation-conditioned insights to guide generation. Experiments on several classic combinatorial optimization benchmarks demonstrate that RefineEvo consistently outperforms strong baselines. In particular, RefineEvo delivers superior solution quality while improving token efficiency, enabling more efficient and autonomous heuristic design.

Failure diagnosis in modern software systems requires iterative evidence acquisition and hypothesis reasoning guided by operational experience. Existing LLM-based methods improve diagnosis through agentic reasoning or knowledge augmentation, but they often lack a mechanism to coordinate the evolving diagnostic state with operational experience during iterative diagnosis. We propose OpsMem, a dual-memory framework that maintains a short-term memory for the current diagnostic state and a long-term memory for reusable operational experience. OpsMem uses cross-memory resonance to activate state-relevant long-term memory, conditions multi-agent diagnosis on the short-term and activated long-term memories, and consolidates reusable experience from solved incidents back into long-term memory. Experiments on a real-world Huawei microservice failure diagnosis dataset show that OpsMem outperforms representative agentic-reasoning and knowledge-augmented baselines, improving Match and Relevant by up to 46.88% and 18.39% over the strongest baseline, respectively.

The creation of digital collections involves not only the digitisation of content, but also the creation of catalogue records for it. This often-overlooked task requires slow and costly expert manual work. In this project, we have evaluated the application of AI models to this task, comparing different implementations and models. This work includes a qualitative and quantitative evaluation of the experiments carried out, as well as recommendations on the use of AI models that go beyond the specific use case.

Dual-source trolleybuses alternate between overhead catenary supply and on-board battery operation, creating energy-use patterns driven by route attributes, high-frequency trajectories, and hourly weather. Existing models struggle to represent these heterogeneous inputs and rarely explain the causal drivers of consumption. This paper proposes a time-aware tabular deep learning framework for inter-stop energy management. Periodic time encoding is integrated into a parameter-efficient batch-ensemble backbone to jointly learn static and sequential features, while Bayesian optimization with tree-structured density estimation tunes hyperparameters. To move beyond prediction, a three-layer causal explanation pipeline combines feature attribution for marginal effects, a linear non-Gaussian acyclic model for causal direction discovery, and a meta-learner for net average treatment effects. Experiments on the Zurich trolleybus dataset enriched with meteorological records achieve a MAPE of 6.52% and R of 0.982, outperforming ten statistical, tree-ensemble, and deep learning baselines. Ablation results show that periodic time encoding contributes most to the accuracy gain. Causal analysis identifies regenerative braking ratio and average speed as the strongest energy-saving factors, while coasting distance is the main driver of excess consumption. The findings offer actionable thresholds for vehicle technology, driving behavior, capacity allocation, and catenary network planning.

AI code assistants are transforming software development, but their implications for software security remain a major concern, particularly in the context of security APIs. These APIs are critical for safeguarding software systems, yet their complexity often leads to incorrect use and serious vulnerabilities. Developing an evidence-based understanding of how AI assistants influence developers' use of these APIs is therefore essential for informing effective mitigation strategies. While a few user studies have examined the broader impact of AI assistants on software vulnerabilities, the use of security APIs remains unexplored from a developer-centered perspective. This study addresses this gap by presenting the first empirical investigation into how AI code assistants affect professional developers' use of security APIs. We conducted a study with 44 developers who completed security API programming tasks with and without GitHub Copilot assistance. Our findings show that, while Copilot improves functional correctness and marginally reduces certain insecure patterns, it does not significantly improve secure API usage. We also found that developers rarely raised security concerns when engaging with Copilot, and many did not recognize that their final implementations remained insecure. Finally, we offer recommendations for enhancing security awareness among developers and propose future research directions to support safer AI-assisted software development.

Neural networks increasingly guide decisions in high-stakes domains such as medical diagnosis, credit approval, and energy bidding. Audit in these settings requires case-level evidence: which training cases support an action and what outcomes they carried. Case-based decision theory (CBDT) formalizes this reasoning by aggregating outcome support from remembered cases. We show that an OLS action readout fitted on a fixed neural representation admits an exact case-based decomposition. Each action score is a weighted sum of training-case returns, with coefficients determined by empirical Gram geometry. We identify a sufficient regime for CBDT similarity semantics; outside it, the coefficients should generally be treated as signed Gram-geometric influence. The decomposition yields audit signals that trace scores to training cases, measure action coherence, and identify weak support. Across synthetic CBDT, PJM, Adult Income, and Default Credit tasks, the method recovers case-level preference structure and achieves the highest mean Top-30 consistency among compared attribution baselines, while remaining competitive on support reconstruction. The audit requires only fitting an OLS top-layer probe, without retraining the representation or accessing the original optimization trajectory; probe fidelity is measured by score reconstruction.

Enterprise agents must follow long-horizon, conditional, safety-critical standard operating procedures (SOPs). We compile machine-readable SOP constraints into executable pseudo-code and run them with a program-guided (PG) stack machine that pages the active frame while an LLM performs semantic execution. A three-arm SOPBench study across six models separates representation from runtime: compiled text never significantly hurts and gains up to 16.0 points where official prose underperforms. Runtime guidance is capability-gated. Two strong models independently show positive seven-domain PG contrasts (58:19 and 75:31 discordant pairs), whereas weak models are harmed. A full-program cursor ablation (active frame first, complete program retained) recovers much of the strong-model refusal gain; selective visibility adds a smaller improvement. Paired probe and audit measurements track this divide to spontaneous state discipline rather than reconstruction ability. On Bank the three primary arms rise from 70.4 to 86.4 to 92.8, with 100% refusal correctness. Practical guidance: compile first; enable active-frame paging only after a model-level discipline check.

Accurate breast cancer risk prediction from screening mammography is critical for enabling personalized screening intervals and early detection. Recent deep learning methods have shown the value of longitudinal data and explicit temporal alignment. However, existing approaches either perform explicit alignment using a single mammographic view or model multiple views without explicit longitudinal alignment, limiting their ability to exploit the complementary spatial-temporal information used in clinical practice. To address this gap, we propose LMV-Net, a longitudinal multi-view breast cancer risk prediction model that jointly analyzes anatomically complementary CC and MLO views within an explicitly aligned longitudinal framework. We evaluate our approach on the public EMBED and CSAW-CC datasets, comparing it to state-of-the-art breast cancer risk prediction methods. Our model consistently outperforms existing approaches in overall risk prediction performance and across different breast density and cancer subgroups. Importantly, these improvements highlight the potential of longitudinal multi-view modeling to enhance risk stratification, paving the way for future work on personalized screening, earlier identification of high-risk patients, and more efficient screening resource allocation. The code is available at https://github.com/sot176/LMV-Net.

Despite their central role in fault detection, test oracles remain challenging to construct effectively. Recent learning based methods address this challenge by automatically generating test assertions, yet even if syntactically correct, they are often ineffective in revealing bugs. Rather than generating assertions, this study explores a different approach by training a model to directly predict whether a given test prefix passes or fails. We present FOCAL, an emerging code LLM-based discriminative oracle predictor. It learns from labeled pairs of test prefixes and methods under test, employs losses that emphasize failing cases during training, and grounds its predictions in statement level behavioral evidence. Compared with the baseline method SEER, we substantially improve performance on failing cases for unseen projects and provide richer explanations. A preliminary evaluation on fault-detection benchmarks and automated test-generation artifacts shows that our approach is highly accurate within its training distribution and substantially improves failure detection on previously unseen projects where prior discriminative oracles collapse. Moreover, the highlighted statements are supported by behavioral explanation checks. These early results suggest that fail-aware discriminative oracle prediction can complement existing approaches such as fuzzing, search-based testing, and LLM-based test generation. These techniques produce test prefixes at scale but often lack fault oriented oracles. In future work, FOCAL could take generated test prefixes and attach fault-aware predicted oracles to them, turning high-volume input generation into executable tests that are more likely to expose semantic failures.

This paper addresses the challenges of using sign language within shared mobility services, such as taxis, carpools, or ride-sharing platforms. The use of sign language recognition (SLR) in real-world, confined environments, specifically vehicle interiors remains largely unexplored. To motivate research in this area, we present the In-Car Sign Language (ICSL) dataset for Brazilian Sign Language (Libras), with the long-term goal of improving public transport accessibility for the Deaf and Hard-of-Hearing community. The dataset consists of: (1) high-precision laboratory motion capture (MoCap) data to establish an idealized linguistic baseline and (2) real-world multi-modal in-car recordings captured using a 2D camera and 3D Time-of-Flight sensors. The dataset provides a basis for comparative analyses between synthesized signing avatar animations and recorded real signing interpreter videos, which enable future research into robust "in-the-wild" SLR models and domain adaptation. We describe in detail the use cases, the setup, the data collection protocol, and the metadata structure of the corpus. In total, we recorded a multimodal dataset exceeding 1.5 million frames, comprising the synchronized multimodal streams described above featuring Libras users across various in-car scenarios. The corpus is provided with gloss annotation of lexical signs and non-lexical sign language elements specially designed to support the training and evaluation of deep neural networks for constrained space recognition. In-vehicle signing offers a technically significant example of a constrained, occluded, and non-frontal environment. While recognizing the diverse communication strategies already employed by the Deaf community, identifying automotive-specific limitations provides a useful stepping stone for research into enhancing in-car accessibility and passenger quality of life.

Symbolic expressions can effectively characterize and predict circuit behavior, but deriving them directly from circuit schematics is challenging. This process requires accurate visual-to-symbolic construction of circuit structure from images and correct multi-step symbolic derivation, both of which impose strict correctness requirements. This work proposes AutoVSR, an automated framework for visual-to-symbolic generation of circuit expressions using Vision Language Models (VLMs). By reconstructing circuit diagrams into an executable intermediate representation (Executable IR) and leveraging a symbolic solver for reasoning, AutoVSR significantly improves the accuracy of symbolic expression generation. AutoVSR introduces two key innovations: an IR construction method guided by component rule retrieval and verification-based feedback, and a symbolic solver implemented as a planning agent equipped with a symbolic tool library for reliable multi-step derivation. Compared with end-to-end VLM approaches and specialized methods on the main symbolic expression generation task, AutoVSR achieves accuracy improvements of 30.01--59.45% and 41.96--51.84%, respectively. Moreover, AutoVSR surpasses closed-source state-of-the-art VLMs in inference cost and computational efficiency. Code is available at https://github.com/LongfeiLi1/AutoVSR.

Large language models can produce superficially legal twelve-tone scores that collapse into degenerate textures. We introduce a neuro-symbolic harness that wraps a language-model proposer in a generate-verify-repair-trace loop with symbolic verification. The complete pipeline improves event-local consistency without claiming whole-piece legality. Across 40 controlled tasks and four paired models, audited delivery yield rises from 13.3% under raw generation to 48.1% with the harness, which explicitly abstains otherwise. The pass rate of a narrower collision and serialisation-consistency check rises from 33.5% to 58.3%, while degeneracy remains near 0.05, including under exploratory adversarial prompting. A blinded evaluation by five experts also shows a descriptive aggregate preference for harness candidates over raw generation in adherence, perceived legality, coherence, and overall quality.

Model editing keeps large language models (LLMs) up to date without retraining, but temporal facts expose a limitation of the prevailing locate-and-edit paradigm: an update is not always a replacement. When a fact changes, the new answer should become current while the old answer may remain correct in historical time contexts. Building on this insight, we use causal tracing to show that LLMs already support this distinction via a two-stage internal computation: early MLP layers retrieve a time-agnostic subject representation, and later layers modulate it with temporal context to yield the time-correct answer. Motivated by this finding, we introduce PRISM Edit, which optimizes a single polysemous representation across temporal contexts and leverages the model's inherent modulation pathway to route it to temporally correct predictions, without any architectural modification. We evaluate on TimeConflict, a new temporal editing benchmark we introduce, and on temporally augmented CounterFact. PRISM Edit improves over the best baseline by +23.3 Temporal Consistency (TC) and +33.7 Current Relative-time Score (CRS) on average while being more than 2x faster. Code and data are publicly available at https://github.com/AnonymousStudy972/PRISM-Edit.

Low-bit quantization makes small reasoning models inexpensive to deploy but can degrade their chains of thought. This motivates decoder-side monitors that intervene when generation becomes unreliable. We show that a natural candidate, the centered token log-probability increment $\log p(w_t)+H_t$, is the wrong observable for this purpose. Under the model's own sampling law it is a mean-zero martingale by construction, so it measures sampling self-consistency rather than trajectory health and is nearly silent during confident repetition, where both $\log p(w_t)$ and entropy are close to zero. We introduce a training-free decoding controller that combines (i) a degeneration-aware alarm score fusing token uncertainty with explicit verbatim repetition and (ii) a calibrated e-process-inspired sequential detector. The raw product process is Ville-valid under a conditional-mean null, while the deployed CUSUM-floored statistic is treated as an empirical change detector because the score is history-dependent and autocorrelated. On GSM8K with DeepSeek-R1-Distill-Qwen-1.5B in FP16 and INT4, calibration turns a monitor that fires on 93--95% of generations into a selective detector of failing traces ($φ\approx 0.3$, precision $\approx 0.6$ against a 0.38 base rate). In this pilot, the controller reduces measured verbatim-degeneration signals and yields a positive but statistically inconclusive INT4 accuracy change from 63% to 69% (paired McNemar $p=0.18$, $n=100$), at a 28% token-budget cost. We also find that non-termination, rather than looping, is the dominant failure mode on GSM8K. The main contribution is methodological: an explanation of why centered token log-probability is inadequate for decoder monitoring and a calibrated, cautiously evaluated replacement.

The promise of AI literacy ``for all'' confronts a structural challenge embedded in how nations organise secondary computer science education. In most systems, a general-track subject -- Digital Literacy, ICT, TIC, or SNT -- bears the weight of universal AI literacy, while a specialist Informatics course serves STEM pathways separately. Yet the content and depth of the general track are shaped by governance decisions made largely with reference to the specialist one. This paper presents a comparative analysis of curricula and examination frameworks across fifteen countries, identifying two structural challenges. First, in several systems a significant portion of students completes secondary education without any formal programming exposure. Second, among those who do receive CS education, a \emph{Syntax Ceiling} emerges: Python-based instruction reaches most students, while the algorithmic depth associated with C++ remains concentrated in elite STEM tracks. Drawing on reform cases spanning centralised mandates (France, China, Japan), assessment-driven systems (Poland, Romania, South Korea), and recent universal reforms (Switzerland, Kazakhstan), we show that governance structures and high-stakes examinations are the primary drivers of both challenges -- and that specialist and general-track language choices are rarely independent, linked through shared teacher pipelines that curriculum policy seldom acknowledges. Achieving genuine AI literacy for all requires confronting not just curriculum content, but the access architectures and resource constraints that determine who receives it -- and at what depth.

Physics-Informed Neural Networks (PINNs) provide a meshless approach for solving partial differential equations (PDEs), but suffer severe degradation in stiff and shock-dominated problems, where small PDE residuals can correspond to globally inaccurate solutions. We show these failures are multi-causal, arising from the concurrent interplay of (i) spectral bias against sharp features, (ii) imbalanced multi-term optimization and loss-weight collapse, (iii) violation of temporal causality, and (iv) under-resolved collocation. We present SPARC-Net, a unified architecture and training framework that jointly addresses all four pathologies. SPARC-Net leverages an adaptive multi-scale spectral encoder with a learnable spectral gate, a gated residual backbone, adaptive activations, and a hard-constraint output ansatz that exactly enforces initial and boundary conditions, structurally eliminating loss-weight collapse. Training employs stabilized gradient-norm loss balancing, floored causality-respecting residual weighting, and residual-based adaptive collocation (RAD). Validated against exact analytic and high-order spectral reference solutions across four canonical benchmarks -- viscous Burgers', Allen-Cahn, convection (beta=30), and reaction -- SPARC-Net yields substantial improvements over vanilla PINNs: relative L2 error drops from 1.47e-1 to 1.14e-1 on Burgers' (22% reduction), 9.93e-1 to 5.78e-2 on Allen-Cahn (94% reduction), and 9.82e-1 to 3.54e-3 on reaction (100% reduction). A characteristic-coordinate encoder for hyperbolic transport further reduces convection error from 5.14e-1 to 9.88e-5 (100% reduction). We report five-seed mean +/- standard deviation errors, Wilcoxon significance tests, full ablation studies, hyperparameter sensitivities, an extension to the 2D heat equation, and comparisons against parameter-matched baselines.

Data-flow analysis is foundational to Android app privacy and security auditing. Recent coding agents can assist with non-trivial source-to-sink data-flow analysis tasks by searching, reading, and reasoning over repository code. However, when these tasks are executed as a batch workload, current agentic analysis setups incur substantial re-analysis cost. Agent instances assigned to different taint sources may inspect shared code fragments, because code reuse in the target app can cause different data-flow paths to converge on shared program logic. Since these agent instances are context-isolated, analysis of these shared code fragments can be repeated within a batch, unnecessarily consuming API budget and limiting scalability. We propose FlowArk, a knowledge-reuse system that reduces re-analysis cost in batch agentic data-flow analysis by making knowledge from completed analyses available to later agent instances. Specifically, FlowArk distills completed analysis histories into reusable knowledge candidates, packages these candidates into matchable knowledge entries, and injects matched entries into a later agent instance's context. We implement FlowArk on OpenCode and evaluate it on 4,685 source-to-sink data-flow analysis tasks from 50 open-source Android apps. Compared with standard OpenCode, FlowArk-enabled OpenCode maintains comparable analysis quality while reducing end-to-end API cost by 26.83%. In addition, under a USD 100 budget, FlowArk completes 36.66% more tasks (1,060 vs. 776).

Full-proof autoformalization bridges extensive mathematical proofs in natural language with formally validated reasoning, offering a pathway to elevate the ceiling of verifiable mathematical reasoning. Unlike statement-level formalization, proof autoformalization is a long-horizon challenge requiring coordination of claims, contexts, and dependencies across many proof steps, yet has only recently come under focused study. Current approaches either rely on costly model training or apply excessive, unguided repair at inference time. To this end, we introduce ToMap, a multi-agent framework that structures proof autoformalization as a Decomposer-Formalizer-Prover pipeline with efficient test-time optimization guided by formal verification and semantic rubrics for proof quality. Rather than distributing test-time compute across all agents, we perform bottleneck analysis and identify the Decomposer as the critical bottleneck: the quality of its atomic, self-contained proof units directly determines whether downstream agents can successfully formalize and prove each step. ToMap therefore treats the Formalizer and Prover as downstream executors and efficiently focuses test-time compute on Decomposer refinement. This refinement follows a loop inspired by GEPA, evolving prompts over candidate decompositions and using formal verification progress together with semantic proof rubrics to define a Pareto frontier that guides the next decomposition update. Experiments on ProofFlowBench show that ToMap improves over the best previous method by 19.0% when evaluated by both syntactic correctness and semantic faithfulness, while requiring lower test-time cost. Scaling analysis shows that most gains emerge within a few iterations of decomposition evolution, guiding test-time budget selection.

As Large Language Models (LLMs) are increasingly deployed as conversational tutors, they risk institutionalizing systemic inequalities. This study presents a systematic API audit of four LLMs acting as history tutors, evaluating 1,800 responses regarding the 1989 Romanian Revolution across five student personas varying by ethnicity and socio-economic tier. We uncover four interconnected patterns of \emph{epistemic paternalism}: (1)~\textbf{Differential Refusal}, where safety-aligned models block 76.7\% of educational requests from low-tier students; (2)~\textbf{Epistemic Gatekeeping}, evidenced by a 3$\times$ reduction in access to geopolitical complexity (e.g., the contested ``coup theory'') for marginalized learners; (3)~\textbf{Agency Theft}, a lexical shift where models like LLaMA produce a 5$\times$ higher victimization-to-politics vocabulary ratio for Roma students compared to elite peers; and (4)~\textbf{Elite Hermeneutics}, where AI tutors disproportionately withhold epistemic confidence and justification scores from low-resource demographic profiles. We argue that current safety alignment acts as a paternalistic filter, transforming conversational AI into agents of narrative segregation -- a manifestation of \emph{hermeneutical injustice} in Fricker's~\cite{fricker2007} sense that demands urgent pedagogical auditing.

Backpropagation is the computational engine of deep learning, yet its mathematical structure is typically treated as a procedural traversal of computational graphs. We present a global operator theory of the \emph{F-adjoint} framework, which reformulates the layerwise backward recursion of an $L$-depth feedforward network into a single linear system $(I-\cB)\Xs=\bG$, where $\bG$ is a source vector. We prove that the global backward operator $\cB$ is strictly block upper-triangular and nilpotent of index at most $L$. This nilpotency guarantees the exact termination of the Neumann series solution after at most $L$ terms, revealing classical backpropagation to be mathematically equivalent to block back-substitution on an upper bidiagonal system. We formalise \emph{F-symmetry} -- the condition in which the backward pass perfectly mirrors the forward pass -- identifying orthogonal weight matrices as canonical examples. Through worked numerical examples, we demonstrate how this operator perspective exposes the single-path collapse of strictly feedforward networks and its breakdown in residual architectures. Finally, we leverage this compositional structure to rigorously derive the mechanics of residual networks (gradient highways) and transfer learning (gradient truncation). This framework elevates backpropagation from an algorithmic recipe to a global nilpotent-operator formulation.

We introduce the Self-Evolving Agentic Operating System (SE-AOS): a new class of AI agent that treats exploit capability as a mutable, versioned kernel it extends at runtime, observing its own failures, synthesising new capabilities, proving them against a live target, and hot-loading them back into itself. Mako is the first SE-AOS instance for security research and the autonomous web exploitation engine developed within LaunchSafe. LaunchSafe builds autonomous security agents for continuous offensive testing and agent-driven security research; Mako is the core engine behind that platform. On the public XBOW validation-benchmarks, 104 containerised, CTF-style web applications spanning 26 vulnerability classes across three difficulty tiers, Mako achieves full-suite coverage: it drives every one of the 104 targets to emit a cryptographically fresh, per-build flag, under a verification regime that makes fabricated or memorised results impossible. Our central result is a law of autonomous exploitation: once a capability exists and is discoverable, difficulty collapses; capability, not reasoning, is what is scarce, together with an architecture and formalism that turn that law into a self-improving system. Mako further runs a gated self-evolution loop that proposes, sandboxes, and commits improvements to its own agents and rules when fitness does not regress. We deliberately withhold the operational results, payloads, exploit chains, and tool source, because a system that reduces full-spectrum web exploitation to a repeatable, machine-speed pipeline is dual-use research of concern. We publish the science; we withhold the weapon.

Comprehensive quantification of cardiac structures from computed tomography (CT) remains limited not by data availability but by the scalability of measurements, which makes routine use impractical. Here we present a unified framework for comprehensive cardiac CT segmentation and phenotyping that combines a human-in-the-loop annotation pipeline, a cardiac CT augmentation technique, and a self-supervised foundation model pre-trained on 60,000 unlabeled cardiac CT scans. Using this approach, we assembled the largest and most comprehensive expert-annotated cardiac CT segmentation dataset to date, comprising 1598 cases and 14 distinct cardiac structures (1000 for training, 598 for the external test set). Across five external datasets, the framework segmented all structures more accurately and comprehensively than existing open-source tools. Self-supervised pre-training improved labeling efficiency, with the most significant gains observed during external evaluation in the low-data regime. Benchmarking across convolutional, transformer, and state-space architectures showed comparable performance, indicating that data quality and pre-training, rather than architecture, drove accuracy. The framework was scaled to population-level phenotyping, with segmented anatomy that carries functionally relevant information about ventricular function and disease severity beyond demographic variables. By openly releasing the largest dataset with human labels, code, model weights, a CT augmentation library, and software, this work provides a reproducible foundation for opportunistic cardiac phenotyping from routinely acquired CT scans.

The widespread adoption of social media platforms has transformed online communication by enabling users to exchange information and opinions instantly. However, these platforms have also facilitated the dissemination of abusive and hateful content, posing major social, psychological, and ethical challenges. Hate speech can incite discrimination, harassment, and violence against individuals or communities based on attributes such as ethnicity, religion, gender, nationality, or political affiliation. Consequently, automatic hate speech detection has become a major research topic in natural language processing (NLP) and an essential component of content moderation systems. This paper investigates automatic hate speech detection in the Algerian Arabic dialect (Darija) on social media. This task remains challenging because of the dialect's linguistic diversity, characterized by the coexistence of Arabic, French, and Arabizi (Arabic written using the Latin alphabet). We compare four categories of text classification approaches: (1) traditional machine learning models using TF-IDF features, (2) deep learning models based on recurrent neural networks, (3) Transformer-based language models, including DziriBERT and multilingual BERT, and (4) a novel hybrid architecture, FAD-SA-GRU, which combines semantic representations from DZ FastText, DZ AraVec, and DziriBERT through multi-embedding fusion, followed by a self-attention-enhanced GRU encoder. Experiments on an annotated dataset of Algerian Darija social media comments for binary hate speech classification show that FAD-SA-GRU outperforms all baselines, achieving 93.2% accuracy, 93.4% precision, 91.0% recall, 92.1% F1-score, and 97.0% ROC-AUC. Results demonstrate the effectiveness of combining complementary embedding representations with attention-based sequence modeling for robust hate speech detection in low-resource dialectal Arabic.

Ensuring the quality of educational materials requires more than standard proofreading: textbooks must be audited for factual accuracy, domain-specific technical correctness, and linguistic quality simultaneously -- a task that general-purpose grammar checkers cannot address. We present \textbf{AI Textbook Auditor}, a modular multi-agent pipeline for automated quality assurance of educational materials across subject domains. The system accepts a textbook PDF and produces a structured, human-reviewable report via two analysis tracks: a \textbf{Factual and Technical Track} in which an ensemble of specialized LLM agents detects factual inaccuracies, code errors, incorrect definitions, and conceptual inconsistencies, augmented with web search for humanities domains; and a \textbf{Grammar Track} operating PDF-natively to preserve diacritical encoding. A \textbf{Judge Agent} filters false positives using domain-specific rules before presenting findings to a human reviewer. The pipeline supports two ingestion modes -- vision-native page rendering and PyMuPDF text extraction -- and is domain-adaptable via custom prompts encoding subject-specific error taxonomies. We demonstrate the system on two Romanian upper-secondary textbooks: a CS textbook (56 technical findings across seven categories, with an expert-validated precision of 62.5\%) and a history and social sciences textbook (72 findings spanning factual errors, ideological bias, and grammar). The system is designed as a triage tool that reduces the manual effort of locating candidate issues, with human expert validation required before any editorial action.

Sustainability refers to a system's ability to maintain its functionality and endure over time. Hence, sustainability is a highly desirable property of software systems, including Self-Adaptive Systems (SASs). SASs can change (adapt) their behavior at runtime to continue achieving their objectives despite external or internal impacts. SASs' intended long-term system behavior can be expressed through a sustainability-driven visual modeling notation called Decision Maps (DMs). Although DMs have been proven helpful, they lack adequate modeling support for safety and security concerns. We address this limitation by extending the current notation for sustainability-driven modeling of SASs to better accommodate the unique characteristics of safety and security scenarios. First, we introduce an additional modeling dimension to account for safety incidents. Second, we adopt a fine-grained divide-and-conquer approach, modeling from distinct temporal security viewpoints ("security modes") to address security. We employ the extended DM notation in a real-world use case scenario provided by our industry partner to assess its feasibility and suitability for practitioners. Our results indicate that our modeling notation helps capture security and safety scenarios more accurately and provides holistic support for the self-adaptation life cycle phases.

Quantum state tomography is sample-starved, and the states one prepares live on a narrow, learnable manifold. A $k{=}0$ prior-only control shows that on concentrated families a prior estimate is already near-optimal, so ``high fidelity at few measurements'' can be family memorization rather than tomography; genuine measurement-efficiency needs a model that conditions on the measurements and demonstrably uses them. On a shared matrix-product-state (MPS) core parameterization we study two routes. Approach~A learns a generative prior over MPS cores with measurement-guided posterior inference (gold-standard-validated, but whose few-measurement accuracy the control shows is largely the prior). Approach~B, our main proposal, is a \emph{fixed-protocol amortized} MPS estimator trained once with a gauge-invariant fidelity loss; we deliberately do not rest it on a permutation-invariant set encoder (a plain MLP matches it). The decisive lever is the measurement design: motivated by the fact that local reduced density matrices determine a $χ$-MPS, conditioning on an \emph{informative local} Pauli set rather than random strings turns a modest, memorization-prone estimator into a high-fidelity one ($\approx\!0.95$, up to $+0.59$ over prior-only, decisively passing a shuffled-measurement control). A dropout ensemble, conformally recalibrated, gives $\approx\!90\%$-coverage intervals -- including for observables never measured, where a shot-based interval does not exist. Quality holds as the system grows (fidelity $0.90$ at $n{=}10$, gain \emph{growing} in $n$; $0.88$ at bond dimension $χ{=}4$), the parameterization is polynomial (native contraction to $20$ qubits), and we close the loop on IBM hardware ($5$ states at $0.97$ from hardware-measured Paulis).

Accurate dengue forecasting is crucial for public health planning, but remains challenging because incidence series are often short, noisy, non-stationary, nonlinear, and often affected by long-range temporal dependence. Fractional differencing in Autoregressive Fractionally Integrated Moving Average (ARFIMA) helps balance non-stationarity and persistence, but its linear structure limits its ability to capture nonlinear dynamics. Deep neural networks can model nonlinear patterns, but usually require large training samples and do not explicitly encode statistical long memory. Echo State Networks (ESNs), a widely used reservoir computing framework, are attractive in this setting because they retain nonlinear recurrent dynamics while training only a simple readout, making them suitable for data-scarce scenarios. However, standard ESNs lack long-term memory from a time-series perspective. This study proposes a long-memory reservoir computing framework that integrates dedicated long-memory and short-memory ESN reservoirs with a ridge-regression readout. We introduce two variants: Fractional ESN (fESN), which incorporates fractional-differencing dynamics into the reservoir to encode long-range dependence directly, and Wavelet ESN (wESN), which extracts stable low-frequency components through wavelet smoothing before modeling them with a memory-aware reservoir. We establish theoretical guarantees for closed-loop reservoir dynamics, showing that standard ESNs induce short-memory processes under mild conditions, whereas the proposed long-memory reservoirs generate polynomially decaying dependence consistent with statistical long memory. Across multiple dengue datasets and forecasting horizons, fESN and wESN outperform statistical and deep learning baselines. Combining conformal prediction with fESN and wESN provides distribution-free calibrated uncertainty intervals.

Learning, at its core, extends beyond memorization to the ability to reason and solve novel problems by navigating a space of possibilities. We introduce Lumo-2, a latent world-action model that generates actions by reasoning over world dynamics in latent space. The learned latent world dynamics capture physically grounded visual transitions, naturally encoding future possibilities and providing a unified substrate for cross-modal alignment. This formulation enables predictive reasoning akin to world modelling while remaining lightweight and focused on physical dynamics relevant to control. Central to our approach is the hypothesis that action generation quality is governed by the geometry of the latent space. We observe that standard reconstruction-based action tokenization objectives induce representations biased toward low-level signal fidelity, leading to misalignment between reconstruction quality and downstream control performance. To address this limitation, we propose a multi-stage modality pre-alignment strategy in which action representations are progressively aligned with latent world dynamics, vision, and language. This process enforces cross-modal consistency, promotes abstraction, and induces a structured latent space for predictive reasoning. We provide a systematic empirical study of latent world modelling and modality alignment, analyzing their roles in scaling laws and out-of-distribution generalization. Results show that Lumo-2 consistently outperforms strong vision-language-action (VLA) and world-action model (WAM) baselines, with gains on challenging real-world tasks requiring temporal reasoning, physical understanding, or high control complexity, including long-horizon and dexterous manipulation. These findings suggest that structured multimodal alignment and predictive reasoning are fundamental principles for advancing embodied intelligence.

Decision support systems (DSS) increasingly run retention what-if analysis on synthetic customer populations, because privacy constraints preclude unrestricted use of real data. Such a system is trustworthy only if the synthetic data lead managers to the same decisions as the real data would; yet prevailing criteria certify distributional similarity, not decision alignment, so a synthetic population can match every marginal distribution while still steering a marketing team toward the wrong campaigns. We close this decision-alignment gap with three contributions: strategy simulation fidelity (SSF), a criterion measuring how often the synthetic population yields the same go/no-go campaign decision as the real population; PolicySynth, a DSS framework whose generator is conditioned on the production churn scorer to align decision-relevant structure; and a three-axis reporting standard of decision alignment, membership-inference resistance, and novel-record rate as the minimum deployment quality gate. On a telecommunications churn corpus and a banking acquisition corpus, PolicySynth attains a mean SSF of 0.923 and 0.960, with seed-to-seed variance roughly ten times tighter than CTGAN on telecommunications and 2.5 times on banking. This stability is the deployable property: go/no-go recommendations shift by at most 1.2 percentage points between monthly retraining cycles, against 11.5 for CTGAN, a reversed recommendation on one campaign in nine. A bootstrap baseline matches PolicySynth on SSF yet copies real records verbatim and fails membership inference, evidence that no single axis suffices. PolicySynth reliably supports directional go/no-go screening; its ROI estimates diverge from real outcomes by 70 to 78% and require the volume correction we document.

In the rapidly evolving landscape of information retrieval systems, the ability to adapt and improve through user feedback is paramount. This study introduces a novel methodology for refining the performance of a primary Retrieval Augmented Generation (RAG) system by strategically integrating an auxiliary feedback RAG system. By systematically harnessing human-generated feedback, the approach aims to enhance the accuracy, relevance, and overall quality of responses, driving the system towards self-improvement. Central to this methodology is a human-in-the-loop implementation, where user feedback is continuously collected, classified, and integrated into the inference workflow, enabling the system to learn and evolve iteratively. To validate the effectiveness of this approach, the study employs rigorous testing against three diverse benchmark datasets focused on general and custom domain knowledge, utilizing a LLM-as-a-Judge evaluation strategy. This comprehensive framework not only underscores the transformative potential of feedback-driven enhancements in RAG systems but also sets a precedent for future research in adaptive information retrieval technologies, marking a significant step in the journey towards autonomous refinement and optimization through user engagement.

Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps. While existing reasoning step evaluators effectively detect logical fallacies and factual errors, our analysis reveals a critical blind spot: they fail to penalize valid but inefficient reasoning steps that inflate token usage without contributing to the solution. To systematically diagnose this limitation, we introduce RIV-GSM8K, a diagnostic benchmark injected with five distinct types of inefficiencies, including circular reasoning and excessive decomposition. Diagnostic experiments reveal that state-of-the-art evaluators struggle to distinguish these inefficiencies from necessary reasoning. To address this gap, we propose CAID (Context-Aware Information Density), a training-free metric grounded in information theory that identifies low-utility steps. To validate the metric's practical utility, we apply it within PACE, a post-hoc compression strategy. Additional control experiments show that the gains of PACE are not explained by trivial pruning: compared with random step removal and PRM-based compression baselines, it preserves accuracy at substantially higher compression rates. Empirical results on GSM8K, StrategyQA, and ARC-Challenge demonstrate that PACE reduces token consumption by 31-53% while maintaining accuracy, confirming that CAID successfully distills informational froth from reasoning chains without compromising deductive validity.

Two competing perspectives on fluid intelligence (gf) measures propose that performance is primarily constrained either by working memory capacity or by the ability to induce novel relations. The first perspective is currently dominant in measurement, as evident from the use of a limited set of recurring rules, whereas the second perspective is reflected in many definitions but rarely present in measurement. The ARC-AGI benchmark predominantly requires rule induction and was proposed as a measure of gf for both humans and artificial systems. However, its psychometric properties have not yet been examined in human samples. We therefore investigated the psychometric characteristics and nomological network of ARC-AGI in a first study with 100 participants. A compilation of ARC-AGI items showed good psychometric properties and correlated substantially with figural fluid intelligence as measured by a figural reasoning test (\r{ho} = .63). Associations with figural originality were weak. These findings provide initial support for the validity of ARC-AGI as a measure of human fluid intelligence. Future research should include more rule induction tasks as well as additional multivariate covariates. This study is unusual by studying a task in humans that was initially designed for machines. We suggest systematically embedding AI benchmarks into the nomological network of human cognitive abilities to enable more systematic evaluation and interdisciplinary cooperation.

Tree search algorithms enable systematic exploration of the proof space in neural theorem proving. Existing LLM tree search libraries primarily target natural language reasoning and do not provide native integration with formal verifiers, while theorem proving systems often rely on task-specific search implementations. We introduce TreeThink, an open-source Python library for modular, fully asynchronous tree search in neural theorem proving. It integrates established tree search methods with vLLM-based inference pipelines and diverse node evaluation techniques, ranging from lightweight heuristics to neural evaluators. We support Lean~4, Rocq, and Isabelle/HOL alongside natural language. It connects directly to each language's Read-Eval-Print Loop (REPL) server for real-time verification and proof state extraction. We evaluate TreeThink on miniF2F and MATH500, demonstrating cross-language formal proof search, natural language reasoning support, and up to 6.3$\times$ wall-clock speedup from asynchronous execution. Source code is released under the MIT license at https://github.com/GGLAB-KU/treethink , and the library is accessible as a downloadable package at https://pypi.org/project/treethink/ .

Pathology Foundation Models (PFMs) offer powerful Whole Slide Image (WSI) representations but suffer from massive computational costs. While Knowledge Distillation (KD) can create efficient student models, existing multi-teacher methods often use suboptimal uniform weighting that ignores tissue heterogeneity. We propose LaGuadia (Language-Guided Adaptive DistillAtion), a framework that develops a compact pathology image encoder by dynamically integrating expertise from multiple PFMs under clinical linguistic guidance. Our approach utilizes a multi-stage pipeline: first, extracting visually observable clinical keywords from pathology reports; second, aligning visual features with these keywords via a Vision-Language meta-teacher (MedSigLIP) to provide dense semantic guidance; and finally, performing adaptive KD where teacher contributions are weighted based on their semantic alignment with the clinical narrative. Experiments on WSI captioning, visual question answering, and slide-level classification tasks demonstrate that an 87M parameter LaGuadia student model matches or exceeds foundation-scale models such as GigaPath and UNI, achieving strong factual consistency and robust generalization. These results highlight clinical language as an effective semantic anchor for building efficient and reliable digital pathology systems. Code is available at https://github.com/hvcl/LaGuadia.

Empirical research on software architecture sometimes focuses on individuals holding the formal title of software architect. However, not all companies have individuals hired in such roles. Despite no formal architects, all systems have architectures, and there must be practitioners making the architectural decisions. This study aims to identify who, in practice, makes architectural decisions and in what environments the existence of a formal architect is perceived as necessary. This research employed a method consisting of a questionnaire with 54 participants from different companies and seven follow-up interviews. The findings indicate that architectural decisions are often made by individuals without a formal architect title. A formal architect is perceived as essential mainly in large companies and large teams. The results of this study show that many practitioners taking part in ADM may have been omitted by previous research, particularly if it focused on formal architects.

Exploration is essential for reliable autonomy in multi-agent systems, yet it remains unclear whether large language model (LLM) agents can explore effectively when interacting with one another. We show that modern LLM agents fail to do so, often exhibiting myopic and polarized interaction patterns that lead to suboptimal coordination and increased regret. We formalize this challenge as the Multi-Agent Exploration problem, modeling it as a partially observable stochastic game (POSG) problem in which agents must probe peers to infer their capabilities and identify effective interaction strategies. To address this, we introduce Multi- Agent Contextual Exploration (MACE), a lightweight framework that explicitly promotes exploration through structured peer selection. Across both contextual and parametric diversity settings, MACE substantially improves exploration behavior and downstream task performance. We further show theoretically that the value of exploration increases with agent diversity. Overall, our results highlight a fundamental limitation of current LLM agents and underscore the importance of explicitly guided exploration for reliable multi-agent autonomy. Code will be released in https://github.com/deeplearning-wisc/mace

To reduce the substantial engineering effort required to test the corresponding applications from Android to OpenHarmony, migrating existing GUI test cases has become a critical problem. However, current research neither proposes solutions tailored for OpenHarmony nor provides a systematic evaluation of migration approaches on this system, leaving developers with limited empirical guidance in practice. In this paper, we present the first systematic empirical study of test migration from Android to OpenHarmony. Specifically, we first construct a dataset referred to as the ATH Benchmark, comprising 36 commercial applications with an average of over 9 billion downloads, along with 108 manually designed test cases. Second, we select two state-of-the-art test migration approaches (i.e., ReSPlay and ITeM) and adapt these two approaches to enable their execution on OpenHarmony. Third, we use the preceding infrastructure to evaluate these two approaches from three perspectives, including testing performance, root causes of failures, and the impact of OpenHarmony characteristics. Our results reveal that existing test migration approaches are less effective (15% success-rate on ReSPlay and 26% success-rate on ITeM) in Android-to-OpenHarmony scenarios. Through an in-depth analysis of failed cases, we identify that test performance is primarily hindered by OpenHarmony-specific characteristics, including technical architecture differences and unique ecosystem traits. Utilizing these findings, we propose an enhanced approach based on ITeM, referred as ITeM-HM, which incorporates specific OpenHarmony system features. As a result, ITeM-HM successfully achieves a 214% success-rate relative improvement over the original ITeM (from 26% to 81%).

While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing bias evaluation protocols predominantly rely on static datasets, which provide only a superficial assessment, as their fixed test cases cannot adaptively evolve to measure the true depth and limits of model vulnerabilities. We introduce DeepBias, an adaptive framework for the in-depth probing of social biases in LVLMs with carefully designed agents. Our approach operates through a dynamic ''generation-evolution-probing'' loop. First, a generative ProposerAgent synthesizes test data and is iteratively updated via Direct Preference Optimization (DPO) based on the target LVLM's responses, exploring model-specific failure modes. Second, an autonomous skill-driven DiggerAgent rewrites each test data across multiple probing turns, adaptively selecting from a curated skill library of deepening and rewriting strategies. At each turn, this process is conditioned on the model's previous response, enabling progressively deeper biases to be exposed. Furthermore, we build a benchmark named DeepBiasBench using our framework. By employing an ensemble of five diverse state-of-the-art LVLMs as anchors, the benchmark captures vulnerabilities shared across architectures. Comprehensive experiments demonstrate the effectiveness of our framework and show that DeepBias provides a challenging benchmark for in-depth bias evaluation, establishing an evolutionary paradigm for LVLM safety assessment.

LLM agents today are caught in an awkward bind. Lock them down with static safety instructions and they rarely venture beyond the obvious; give them free reign with tools and multi-agent debate, and safety violations quickly follow. Rather than forcing a single model to juggle both creativity and caution, we separate the concerns across specialized roles. A Disrupter generates unconventional proposals, a Validator enforces hard runtime checks at the tool gateway, and a Broker pulls in distant but relevant analogies. Failures are not discarded -- they are compiled, via MCTS, into compact, signed constraint patches we call Scars. These patches are cached locally and inherited by future cohorts, turning repeated failures into reusable, low-cost runtime constraints. In a spatial-semantic sandbox (N=20 runs, p<0.01), our cohort reaches remote targets where debate fails, the Validator prevents all executed breaches, and Scars reduce token consumption by 15.1% by avoiding redundant validator checks. Furthermore, credit-based Communication Allocation Scores (CAS) restrict outbound bandwidth, reducing overall token costs by 55.9% under resource constraints.

Accurate monocular 4D hand reconstruction remains challenging. Per-frame discriminative regressors lack temporal context and often produce jittery predictions. Temporal models improve consistency by aggregating information across frames, but they are typically deterministic regressors, making them vulnerable to ambiguous observations caused by occlusion and motion blur. Generative modeling offers a natural alternative by learning a prior over plausible hand motion sequences, enabling coherent hand-state recovery when visual evidence is incomplete or unreliable. Motivated by this observation, we present HandFlow, a fully generative flow-matching framework for temporally coherent 3D hand pose and shape estimation from monocular video. Given visual and skeletal observations, HandFlow denoises an entire temporal window of MANO parameters through a single ODE integration. To support this, we use a Flux-style dual-stream transformer that attends across the full sequence to capture long-range dependencies without autoregressive decoding, and a confidence-aware continuous masking mechanism that blends observed features with learnable mask tokens to handle noisy or missing observations. Experiments on DexYCB and HOT3D show that HandFlow achieves state-of-the-art performance, with particularly large gains in world-space accuracy and temporal smoothness. It reduces world-space pose error by over 30% compared with the strongest baseline and achieves the lowest acceleration error among all evaluated methods, while remaining competitive in per-frame pose accuracy. Moreover, on a single GPU HandFlow reconstructs a 150-frame sequence at 47 fps, about 12x faster than the fastest prior video-based method, with reconstruction itself accounting for only a small fraction of the end-to-end latency.

Most sign language translation (SLT) methods focus on isolated native sign-spoken pairs (e.g., American Sign Language - English). Extending language-specific SLT models to multilingual translation would improve accessibility by enabling communication across diverse sign and spoken language communities. However, existing multilingual SLT approaches still struggle to learn a unified model that minimizes cross-lingual conflicts while capturing shared cross-lingual semantics and preserving language-specific variations across different sign languages. Therefore, we propose Q-BridgeNet, a unified framework for multilingual SLT that jointly mitigates cross-lingual conflicts across both the sign language and spoken language sides. On the sign language side, Q-BridgeNet learns discrete Q-units via adaptive segmentation and residual vector quantization: a shared base codebook provides language-agnostic semantic primitives, while language-specific residual codebooks refine heterogeneous signing semantics. On the spoken language side, a multilingual LLM is fine-tuned to operate in the Q-unit space, leveraging cross-lingual priors to enable a unified SLT model. Experiments on PHOENIX14T, How2Sign, and CSL-Daily show that Q-BridgeNet effectively mitigates cross-lingual conflicts, achieving state-of-the-art performance on native sign-spoken pairs while also demonstrating strong generalization to non-native pairs. Our source code is publicly available at: https://github.com/FengLiQ/Q-BridgeNet

High-stakes English proficiency tests treat standardized, unaided performance as evidence for score interpretations about academic English proficiency. This interpretation remains meaningful, but as target language use domains increasingly involve generative AI, the extrapolation from unaided test performance to academic communicative readiness becomes less self-evident. This conceptual validity argument reframes AI as a score-interpretation problem in high-stakes language testing, not only an operational issue of scoring, feedback, security, or misconduct. Synthesizing current literature in three uneven layers, the paper shows that most work treats AI as assessment infrastructure, while far less theorizes its implications for construct validity and extrapolation warrants. It defines AI-mediated construct drift as the misalignment that arises when communicative abilities required in the target domain change through AI mediation while test constructs remain anchored to an unaided-performance model. It proposes bounded AI mediation as a validity-oriented design principle: a standardized condition in which all test takers access the same institutionally controlled AI assistant, with predefined assistance boundaries, logged interactions, and tasks that distinguish comprehension support from answer generation. The paper argues that score interpretations should be narrowed and supplemented when used to support claims about AI-mediated academic communication.

Relational fraud detection can exploit both label-free graph context and label-derived neighborhood evidence, but these two information sources obey different validity conditions. In particular, neighborhood risk becomes invalid when a queried node's own label, or any validation or test label, enters its construction. We formulate this issue as provenance-constrained relational evidence use and present PREF-Gate, an auditable decision framework with two fixed experts and a finite validation gate. The context expert uses attributes, one-hop means, feature residuals, and degree descriptors without labels. The evidence expert adds self-excluded, training-label-only neighborhood risk and empirical-Bayes summaries that expose support, uncertainty, availability, and shrinkage. Before test inference, the gate selects either expert or one of three pre-specified probability mixtures and fixes the decision threshold. On Amazon, YelpChi, and TFinance, using five identical stratified splits and 14 same-protocol methods, PREF-Gate obtains mean AUPRC values of 0.9085, 0.8104, and 0.8913. It selects the label-free expert on all Amazon and YelpChi splits and an evidence mixture on all TFinance splits. Thus, the main result is conditional rather than universal: label-derived relational evidence is useful only where held-out validation supports it. The framework couples competitive ranking performance with an explicit label-provenance contract, finite selection policy, failure accounting, and review-budget evaluation, providing an auditable knowledge-based decision pipeline for graph fraud detection.

The popularity of large language models (LLMs) escalates an ongoing demand for effective inference. However, due to the sequential processing of tokens during the token phase in decoder-only LLMs inference, the inherent low parallelism leads to reduced throughput and suboptimal utilization of the computing units on artificial intelligence (AI) accelerators, particularly when handling long-sequence inputs that impose significant memory overhead. Recently, many reported methods have been developed as potential solutions, since they emerge with numeric deviation. This paper presents FastTPS, a high performance and low-precision loss method for accelerating the token-phase in LLM inference on general AI accelerators which includes three key components: (1) AI accelerator-enabled reloading-free KV Cache concatenation which decreases memory access overhead as well as enables full fusion of Attention, (2) high-efficiency and high-accuracy 'RoPE' attention based on the tiling optimized FLAT, and (3) highly-fused MLP with fine-grain pipeline scheduling. Our results confirm that FastTPS significantly alleviates memory bottlenecks in the token phase, delivering a 6x speed improvement (compared to none-fusion) on an AMD Ryzen AI 300 series NPU with BF16 precision while sustaining 93% peak memory bandwidth utilization during Phi3-mini-4k-instruct inference.

Table-based reasoning with large language models (LLMs), which requires reasoning based on natural language questions and structured tabular data, has gained widespread attention. However, a series of issues still constrain the application of this task. The previous approaches suffered from significant performance degradation when faced with large tables due to the difficulty of long text modeling and the limitation of input length for LLMs. The text-to-SQL approach is used to efficiently extract key information from tables and generate smaller sub-tables. However, tabular data, especially web tables, often lack the necessary structure and consistency, making them unsuitable for performing mathematical logic operations using SQL queries. We propose the ProgramTab framework, which guides LLMs employing in-context learning to perform tabular data preprocessing with Python code, as well as the momentous contents extraction with row and column extraction and SQL generation. The experiment results on table reasoning datasets demonstrate that the ProgramTab framework effectively deals with table-based reasoning tasks and outperforms all LLM-based baselines.

When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-level variation may reflect distinct latent planning competencies rather than differences along a single ability spectrum. We study this question on ACPBench-Hard by evaluating multiple LLM families under varying test-time reasoning budgets and applying a multidimensional item response theory model to uncover the latent competency structure underlying LLM planning. The analysis reveals two principal dimensions that shape planning performance: operational reasoning, the ability to evaluate local action applicability and immediate state transitions, and structural enumeration, the ability to reason about goal reachability and landmark structure. Operational reasoning improving under model scaling and longer reasoning traces, while structural enumeration remains comparatively insensitive. Our findings motivate competency-level evaluation of LLM planning, shifting the focus from whether models improve overall to which planning competencies improve, under what conditions, and why.

To ensure the overall quality of AI-enabled software, not only traditional software components but also AI components need to be tested and repaired. Among AI components, Transformer models are increasingly integrated into software systems, which makes their misbehaviors critical. Although prior work in the software engineering community has proposed deep neural network (DNN) repair methods, most overlook Transformer-specific structures. We propose RepTran, a search-based repair method for Transformer models. It targets their feed-forward networks (FFNs), which play a central role in the architecture. RepTran identifies suspicious weights by combining two types of scores: a variance-based neuron score and an existing bidirectional score. It then iteratively optimizes these weights using differential evolution. Our evaluation includes 18 fault benchmarks constructed from CIFAR-100 and Tiny-ImageNet. We compare RepTran against three baselines: random weight selection, Arachne (a state-of-the-art DNN repair method), and ArachneW, which enables Arachne to control the number of selected weights. RepTran achieved an average repair rate of 74.7%, statistically outperforming random selection and Arachne across all benchmarks. Effect size analysis revealed that RepTran achieved higher repair rates than ArachneW regardless of the number of selected weights. These results suggest that RepTran is effective for enhancing the reliability of AI-enabled software.

Computer use agents (CUAs) are emerging as a powerful interface for automating complex digital workflows through visual perception and GUI execution. Online reinforcement learning with verifiable rewards (RLVR) has emerged as a key direction for scaling their capabilities. However, this paradigm is bottlenecked by verifiable data scarcity and online RL inefficiency. To break these barriers, we introduce ScaleCUA, a unified framework that scales online RL for CUAs via verifiable task synthesis and efficient training. At the data level, we design VeriGen, an end-to-end framework for generating verifiable RL tasks through iterative docker interactions and a multi-agent feedback loop. Scaled to 100+ concurrent agent workers via a shared docker interaction probe, this pipeline produces 24K+ verifiable tasks and nearly 3K high-quality RL tasks. To maximize sample efficiency, we propose Frontier Sampling, which tracks per-task capability and allocates rollouts to the current learning frontier. On the training side, we further design Visual Context Segmentation, a sliding window over recent visual context that balances rollout and training-engine pressure, yielding a 2.83x training speedup over step-wise decomposition. Together, ScaleCUA achieves 68.7% on OSWorld and 54.0% on ScienceBoard, establishing new state-of-the-art performance among open-source computer use agents. Code, models, and datasets are available at https://github.com/THUDM/SCALE-CUA.

Large language models increasingly operate as tool-using agents, where small format, argument, or function-call errors can invalidate otherwise plausible responses. We study inference-time feed-forward network (FFN) intervention for improving structured outputs without retraining model weights. Our project began with Orthogonal Residual Projection (ORP), a direction-changing repair attempt that revealed sensitive SwiGLU FFN intervention sites but often caused more harm than fixes. We therefore propose Amplitude Gating (AG), a non-destructive alternative that preserves pretrained FFN weight directions and modulates only activation magnitudes during generation. We define a fine-grained intervention system spanning P1/P2/P3 and branch-specific P1s/P2a/P2b sites, and introduce an evaluation protocol that separates combination-oracle headroom from fixed configurations and learned gates, enforces sample-level accounting, and uses task-aware metrics for binary and partial-credit datasets. Across Qwen3.5-9B, Qwen3-8B, and Qwen2.5-7B, AG is weakly positive in aggregate but strongest on tool-structured tasks. On Qwen3.5-9B, a category-level learned gate improves tool/structured/agentic performance from 38.66% to 42.92% (+4.27 percentage points), with Hermes function-call tasks reaching about +7.6 points. On Qwen3-8B, Hermes JSON mode improves by +11.36 points. Qwen2.5-7B retains oracle headroom but current learned gates fail to capture it, showing that deployment requires model- and category-specific routing. Comparisons of entropy AG with Newton-Schulz-windowed AG show that neither family is uniformly dominant. These results identify tool-structured inference as the most credible first target for safe FFN-level inference optimization, while prospective online validation and broader cross-model evaluation remain necessary.

In this paper, we propose deep learning based NeuroMem-FHP framework for estimating the parameters of the fractional Hawkes process (FHP), a self-exciting point process that captures long-range dependence through a fractional Mittag-Leffler excitation kernel. Two neural architectures, namely a Long Short-Term Memory (LSTM) network and a Transformer, are developed to estimate the model parameters $(μ,γ,α,β)$ directly from sequences of inter-arrival times without requiring computationally intensive likelihood optimization. Experiments on synthetic data that both neural models significantly outperform the classical Maximum Likelihood Estimation (MLE) method, with the Transformer achieving the highest estimation accuracy (MSE = $0.1634$), followed by the LSTM (MSE = $0.1752$), compared to MLE (MSE = $2.8032$). An ablation study further examines the effects of key hyperparameters on model performance. The proposed framework is also on two real-world high-frequency datasets, namely AAPL NBBO transaction data and Montgomery County 911 emergency call records. Using a predictive validation approach, event sequences simulated from the estimated parameters closely reproduce the empirical distribution, tail behavior, and temporal dependence structure of the observed data. These results demonstrate that Transformer-based parameter estimation provides an accurate and efficient alternative to conventional estimation techniques for FHP and offers a promising framework for modeling event-driven systems with long-memory dynamics.

The growing ability of large language models and vision language models to jointly interpret and reason over images and text is reshaping medical agents, moving them from task specific predictors toward autonomous systems that perceive, reason, plan, remember, and act in clinical environments. This work departs from the capability first perspective of existing literature and instead begins from clinical deployment, asking what tasks, contamination resistant benchmarks, and interactive training environments are required before medical agents can be trusted in practice. Medical agents are formalized as sequential decision making systems under partial observability, together with a three level autonomy taxonomy spanning assisted, cooperative, and fully autonomous operation. The field is organized along a unified scaling spine consisting of framework scaling, capability scaling, and environment scaling. Within this framework, clinical environment scaling, the integration of tools, data, and clinical gyms, is identified as the most actionable yet underexplored direction for agents operating in PACS, EHR, and FHIR ecosystems. Clinical self evolution, where agents improve through interaction with their environments rather than parameter scaling alone, is further positioned as a key research frontier, drawing insights from self improving agents, agent gyms, and test time compute scaling. Applications across radiology, pathology, ophthalmology, and hospital workflows are examined together with deployment challenges including hallucination, cascading failures, and fairness. By consolidating more than 300 references, with particular emphasis on advances from 2025 to 2026, this work provides a roadmap toward trustworthy, self improving medical imaging systems for real clinical practice.

Reinforcement learning for deep-search agents has largely focused on trajectory-level scoring -- outcome correctness, citation-aware rewards, and evidence coverage. Yet the actions that expose supporting documents receive no targeted credit, a gap we call the reward-credit mismatch. We propose STAMP, in which a reference-based verifier judges whether each cited document supports an entity or relation in a training-time evidence graph, and first-exposure attribution traces each supported citation back to the action that first surfaced it. This step credit is injected through sign-preserving advantage modulation, which redistributes advantage across steps without changing the trajectory-level reward or the relative ranking of trajectories within each group. On BrowseComp, BrowseComp-ZH, and xbench-DS, STAMP improves the GRPO baseline by +2.0/+5.5/+3.0 points under matched SFT initialization, training data, and search tools, and composes with both outcome-only and citation-rubric base rewards. Component ablations confirm that the provenance-based credit signal and the sign-preserving advantage modulation each contribute to the gains.

Representing manipulation actions as 2D trajectories in the camera plane provides a compact and interpretable basis for learning complex 3D manipulation policies. However, it also creates challenges from out-of-frame trajectories and limited precision. We propose Pix2Act, an imitation learning method that addresses these challenges by generating continuous image-space keypoint trajectories in each camera plane and losslessly recovering end-effector poses via triangulation. This reformulates high-dimensional 3D control as a simpler, more learnable 2D prediction problem. Crucially, it aligns observations and actions in the same coordinate space, enabling equivariant transformations to jointly rotate individual camera images together with their image-space actions. We analyze the symmetry properties of this augmentation and design a network architecture that can fuse multiple camera views while respecting their per-view rotations. As a result, Pix2Act implicitly enlarges the support of the data distribution and learns invariant action structures across transformations, yielding improved generalization and overall performance. Across diverse simulated and real-world manipulation tasks, Pix2Act outperforms state-of-the-art baselines and remains robust under camera perturbations.

A thematic corpus is a collection of semantically coherent documents that collectively describe different aspects of a shared thematic event. Such a corpus typically contains hundreds or even thousands of documents. While users' interests in a thematic event often span multiple dimensions, Query-Focused Summarization (QFS) aims to generate summaries tailored to users' queries. However, existing QFS datasets lack event-oriented summarization, and most QFS methods struggle with large-scale corpora. To address these challenges, we propose the Query-Focused Event Summarization (QFES) task and construct the QFESum dataset, which contains 8 thematic events, 16,684 documents, and 104 queries. Furthermore, we introduce a two-stage QFES framework consisting of Query-Focused Retrieval with Adaptive Thresholding (RAT) and Query-Focused Summarization based on Hierarchical Clustering (SHC). Experimental results on QFESum show that RAT and SHC consistently outperform the baselines, demonstrating their effectiveness for QFES. The dataset and code are publicly available at https://github.com/sarcasm-hcy02/QFES-QFESum.

Large-scale pretrained ASR models such as Whisper exhibit strong multilingual capabilities. However, fine-tuning on low-resource languages often causes catastrophic forgetting. Although continual learning mitigates this issue, existing methods struggle to regulate cross-task interference in multilingual settings, where dominant languages bias optimization. We propose Unified Gradient Projection (UGP), which constrains parameter updates using reference gradients from language-balanced replay in a unified projection space. By equalizing per-language contributions in the projection, UGP reduces dominant-language bias and improves cross-lingual stability. We further show that combining gradient-level projection with data-level replay yields complementary gains in stability and plasticity. Across diverse low-resource language groups and model scales, UGP enables effective adaptation while substantially mitigating forgetting. On Whisper-large-v3, it achieves near-zero average forgetting.

Safety evaluation of large language models (LLMs) relies largely on single-turn attack datasets and single-judge scoring, underestimating risk from adaptive multi-turn adversaries and reporting a single success rate that does not separate partially actionable outputs from those carrying complete operational detail. We propose AMT-X (Adaptive Multi-Turn Exploitation), a phase-structured multi-turn red-teaming framework. Unlike prior multi-turn attacks that rely on ad hoc escalation or free-form per-goal plans, AMT-X casts the attack as an explicit, reproducible multi-phase state machine driven by semantic signals from the victim, and replaces single-judge scoring with a multi-role jury whose phase-conditioned checklists gate success on actionable harm. Across six frontier victim models (queried under their default safety alignment, without added moderation layers) and seven Moderation sub-categories, AMT-X attains overall attack success rates of 97.6-100% under a lenient score threshold, but 66.7-78.6% under a stricter gate requiring complete, real, and operational detail: a gap of up to 33 percentage points between partially and fully actionable harm.

LLM agent benchmarks measure task completion, reliability, and inference cost, but not the persistent data an agent run leaves on disk, including logs, context snapshots, checkpoints, and debug traces. We introduce AgentFootprint, a cross-framework benchmark of post-run agent storage footprint. Its serialization-aware metric suite measures total retention, channel composition, duplication, growth, compressibility, and conversation-history reconstructability. It addresses a measurement trap: naive byte-level measurement understates duplication by an order of magnitude because database paging and JSON escaping obscure repeated content. A fixed-trace control separates agent-generated logical volume from persistence-layer amplification: replaying the same trajectory through seven persisting frameworks yields a 6.7x spread. Under identical models, tools, and tasks, configurations with 100% accuracy differ by 15.7x in retained bytes, although their defaults support different recovery and audit capabilities. Three full-history configurations grow superlinearly on a repeated-observation stress task. Exported trajectories from 108 instance-normalized SWE-bench Verified submissions span three orders of magnitude per instance, with no detectable correlation with resolve rate. A content-addressed store reduces retention by 4.8x-32.7x while preserving every reconstructability score. These results establish persistent storage as a resource metric to report jointly with accuracy and reconstructability.

We study the coupled objective J_K^WOR = E_{S ~ PL-WOR_K}[max_{i in S} R_i]: the expected maximum reward of a size-K Plackett-Luce draw without replacement, the law of Gumbel-Top-K / Stochastic Beam Search decoding. This estimand differs from the conventional i.i.d. objective J_K^iid = E[max_{i<=K} R_i] targeted by existing sample-reuse Max@K estimators, and reusing their i.i.d. weights under the coupled sampler is provably biased (a closed-form three-item instance gives E[g_iid] = (4/5) grad J_K^WOR exactly; pass@K under the coupled sampler is the binary-reward special case). Generic joint-score REINFORCE is already unbiased for J_K^WOR; what it lacks is sample reuse. Our contribution is to instantiate standard rank-conditioned Horvitz-Thompson estimation for the J_K^WOR subset total: from one Gumbel-Top-n pool (n>K) and its observed priority threshold we build an estimator that reuses all C(n,K) embedded K-subsets, unbiased with an unbiased exact score-function surrogate gradient, plus a reward-sorted Max-specific dynamic program that collapses the C(n,K)-term subset sum (with K!-cost set probabilities) exactly to a one-dimensional integral. A fixed-Q quadrature evaluation costs O(n log n + nKQ) arithmetic and is numerically, not algebraically, exact; no epsilon-approximation rate is certified. Each nonzero degree-K Horvitz-Thompson term has finite second moment exactly when n >= 2K; under the same assumptions the full surrogate gradient has finite second moment whenever n >= 2K (sharpness there is open). At K=1 the construction recovers classical priority sampling. All quantities require only the values and differentiable computation graphs of the n+1 drawn items' probabilities, so finite structured sequence policies sampled by exact SBS are covered. A certified finite-Q quadrature bound and countably infinite support remain open. Validation code is included as ancillary files.

Large language models (LLMs) based agents are beginning to participate in portfolio construction and market analysis, where decisions must be justified under evolving information and risk constraints. Current assessment practice, however, remains poorly aligned with this setting: many studies rely on static examinations or report only terminal portfolio returns, while the intermediate evidence, analyst judgments, and execution steps that produced those returns stay largely invisible. We introduce NextFund, an evaluation platform that makes financial-agent behavior observable under live market conditions. The platform couples time-consistent market access, coordinated multi-agent analysis, and persistent logging of the full decision path from observation to trade. Through an interactive Trading Arena, users can compare models across markets, inspect equity curves, and drill from leaderboard outcomes down to individual justifications. We present NextFund on Hong Kong, U.S., and China A-share equities, illustrating how inspectable decision histories enable fairer benchmarking and more actionable diagnosis. Our demo is available at https://paradoox.cn/nextfund/.

Determining whether one finite group is isomorphic to a subgroup of another is a fundamental problem in computational group theory. In this work, we propose a Siamese Graph Neural Network (Siamese GNN) for subgroup prediction using Cayley graph representations of finite groups. Each input group is represented by its undirected Cayley graph and encoded by one branch of a Siamese GNN to produce a graph embedding. The resulting graph embeddings are combined with algebraic features derived directly from the input groups to construct a joint feature vector, which is processed by a fully connected classifier to predict subgroup relations between finite groups. By integrating graph-based structural representations with algebraic features, the proposed framework provides a unified approach for learning subgroup relations from finite groups. Experimental results demonstrate the effectiveness of the proposed architecture, achieving a test accuracy of 95.9% (47/49) on an independent test set and illustrating the potential of geometric deep learning for subgroup prediction.

The rapid expansion of capabilities in Large Language Model (LLM) agents has exposed a critical architectural bottleneck: when agents are given access to a flat, monolithic registry of tools, the model must evaluate hundreds or thousands of options simultaneously. This leads to decision-space explosion, context window saturation, and degraded routing accuracy. To address these limitations, this paper presents a hierarchical, skill-based architecture for agentic orchestration. Capabilities are organized as a rooted tree where internal nodes make routing decisions and leaf nodes execute deterministic tasks. The runtime enforces a single-step execution loop governed by a Last-In-First-Out (LIFO) stack, giving the agent a form of memory akin to a Pushdown Automaton, therefore enabling it to track nested execution contexts and resume deterministically from any depth. Capability discovery follows a manifest-driven, lazy-loading protocol: only the immediate children of the active node are loaded, so memory and prompt costs scale with the explored path rather than the global registry. By replacing global memory with localized stack frames, the architecture prevents outputs from one execution branch from leaking into another, establishing the isolation guarantees required for deployment in regulated enterprise environments. We also discuss UPI Help, an AI-powered digital payments support product, as a motivating production deployment context. We provide a mathematical formalization of the orchestration state, detailed algorithmic analysis of the execution loop, and controlled benchmarks comparing flat and hierarchical routing under increasing tool catalogs, multi-step workflow pressure, and visible schema-token exposure per LLM call.

Speculative decoding accelerates autoregressive generation by letting a lightweight drafter propose multiple tokens that are verified by a larger target model. Although effective for text-only LLMs, speculative decoding yields limited gains in VLMs because drafters often diverge on vision-critical content, while existing multimodal acceleration methods do not directly address irrelevant visual evidence or optimize the verifier-accepted prefix length that governs speedup. We propose TIGER, a Text-conditioned vIsual GatEd Routing framework for multimodal speculative decoding. TIGER dynamically selects a sparse set of context-relevant visual tokens based on the drafter's current textual state, rather than expose the full visual token set or a fixed compressed interface. To better align training with inference-time efficiency, we optimize the drafter with acceptance-aligned group-based policy training using verifier-derived rewards based on accepted prefix length, built on top of distillation warm start with KL anchoring. This encourages the drafter not only to imitate the target model, but also to produce speculative continuations that survive verification for longer prefixes. Experiments show that TIGER yields consistent gains in accepted prefix length and speculative speedup under exact verifier-side speculative decoding, while achieving favorable quality-latency trade-offs with comparable downstream accuracy in visual-routing analyses.

Real-time driving risk assessment provides an essential basis for proactive safety by identifying and quantifying the danger of ongoing road interactions before adverse outcomes occur. However, due to the scarcity of collision data and frame-level risk labels, existing driving risk assessment methods often rely on surrogate objectives, which may imperfectly align with true collision risk and not faithfully reflect the relative danger of driving interaction. This paper proposes a comparison-based ordinal risk learning framework that learns collision-relevant risk scores from pairwise supervision in driving data, directly modeling relative risk ordering without requiring numerical frame-level risk labels. We derive pairwise comparisons from three sources of event-structured driving data for such ordinal risk learning: temporal progression within safety-critical sequences, event-level contrast between dangerous and normal interactions, and physics-based counterfactual perturbations. On this basis, instantiations with three risk-scoring function parameterizations are implemented, including directly learning risk scores from comparison data, and aligning existing single or multiple surrogate-based risk models. The proposed framework is evaluated on the 100-Car and SHRP2 naturalistic driving datasets using a proactive collision warning task. Results show that the proposed framework improves high-recall risk discrimination, warning precision, and warning lead time over representative surrogate-based baselines across both in-distribution and out-of-distribution evaluations. These results suggest that the proposed framework can contribute to proactive safety research by providing more reliable risk assessment for automated driving systems and safety-critical driving interactions.

Organizations and regulators increasingly consult large language models (LLMs) for regulatory-compliance questions, yet a wrong statutory citation can silently propagate into legal advice, compliance documentation, and policy decisions. We introduce a bilingual benchmark of 120 questions probing whether freely accessible LLMs fabricate article citations for two data-protection instruments: the EU General Data Protection Regulation (GDPR) and the Saudi Personal Data Protection Law (PDPL). The benchmark pairs direct citation retrieval questions with false premise verification probes and deliberately unanswerable "trap" questions -- including questions about a repealed article and about deadlines that exist only in implementing regulations, not in the law itself. Every question is posed in both Arabic and English, and all scoring is fully automatic against a manually verified gold reference. Evaluating three freely accessible models (Gemini 2.5 Flash, GPT-OSS-120B, Nemotron-3-Super-120B), we find a dramatic jurisdiction gap: near-ceiling citation accuracy on the GDPR (94-100% on direct retrieval) against majority fabrication on the Saudi PDPL (60-77%), invariant to query language; the highest fabrication rates (67%) arise from statute-vs-regulations confusion, and 91% of fabricated citations are asserted with confidence >= 0.8. Fabrication tracks the jurisdiction of the law, not the language of the query, and model confidence provides no protection -- indicating that verbatim-verification safeguards, rather than model self confidence, must gate any institutional reliance on LLMs for compliance screening.

Large language model (LLM) agents increasingly rely on external tools served by shared providers and accessed by heterogeneous downstream agents. Existing approaches improve tool use on the agent side through parameter updates, prompt refinement, or agent-side memory, making tool knowledge difficult to share and limited to behaviors observed in past tasks. We argue that reusable tool knowledge should instead be maintained by the tool provider. We introduce ToolAtlas, a graph-based framework that builds a persistent provider-side tool memory of tool capabilities, failure boundaries, and cross-tool compositions through execution-verified probing. At inference time, agents query the tool memory via adaptive graph traversal. Across two MCP-based benchmarks spanning eight services, ToolAtlas outperforms existing tool-side optimization and agent-side memory baselines by up to 21.61% in pass@1 and 18.61% in pass@4. The same tool memory also transfers across environment instances and agent frameworks without retraining or task-time exploration, yielding up to 24.16%/16.22% and 17.49%/14.27% relative gains in pass@1/pass@4, respectively. Ablation studies show that these gains arise from combining tool-centered memory organization with capability-guided execution probing. These results establish provider-side tool memory as an effective and reusable paradigm for tool servers. Our code is in: https://github.com/PuppyKnightUniversity/ToolAtlas.

Music creation is fundamentally a process of revision. Yet symbolic music generation remains dominated by paradigms that produce complete sequences from scratch, with limited support for selective modification. Edit-based methods have proven effective for text transformation tasks, but remain largely unexplored for symbolic music. We trace this absence to the representational level: conventional event-based music encodings lack the structural properties required by explicit music editing. In contrast, the BEAT encoding, a beat-grid-anchored representation originally designed for autoregressive generation, possesses structural properties amenable to editing. We propose BeatEdit, the first framework for symbolic music generation based on explicit edit operations, recasting generation as producing new content by editing a draft rather than synthesizing from scratch. BeatEdit comprises three complementary mechanisms along an axis of increasing edit density: per-token sequence tagging for error correction, iterative refinement for accompaniment editing, and tag-then-fill for segment completion. All these mechanisms share a single encoding and pre-trained backbone, achieving higher precision and perceptual quality than autoregressive and diffusion methods across all three tasks, while remaining efficient, with single-pass inference completing in under 100 ms. Cross-encoding evaluation further reveals that encoding design substantially influences editing effectiveness, with notable encoding-method interaction effects. Code is available at https://github.com/Haoyu-Gu/BeatEdit-code

Implicit neural controllers (INCs) are static feedback laws that are evaluated through an algebraic fixed point {equation}; they include as special cases neural network controllers. We propose a so-called implicit representation of neural networks as a key enabling device that exposes the controller as a trainable linear interconnection closed through a known static activation map, thereby making well-posedness and Lyapunov/IQC analysis mathematically easy to handle. For finite-dimensional LTI plants, we first develop a rigorous analysis theory for a given INC, including Perron--Frobenius and norm conditions for well posedness, LMI/IQC certificates for exponential stability, and LMIs for discounted infinite-horizon quadratic performance. We then formulate synthesis as a certification-compatible heuristic search: training is carried out under explicit well-posedness constraints, implicit-differentiation formulas provide gradients, and the resulting controller is accepted only after independent post-training LMIs or regional admissibility checks are feasible. Finally, we establish constrained-control separation results: for a specific scalar unstable plant with hard actuator bounds, an INC achieves a strictly smaller discounted infinite-horizon cost than any admissible finite-order dynamic linear controller. Additional results cover quadratic state-input costs, comparison with linear static output feedback, and computable upper/lower-bound certificates. Numerical examples illustrate the mechanism and the resulting certified performance.

We address ambivalence and hesitancy (A/H) recognition in the ABAW 2026 BAH Challenge: given a short interview video, predict whether the person shows signs of A/H. Our system combines affect-specialised text, audio, and visual representations with a small set of readable linguistic hesitation cues, fused by a reliability gate we call Affective Marker Fusion (AMF), and finished with a simple AP-weighted ensemble at a fixed decision threshold. We also introduce \emph{ASR-erased time}: speech recognisers delete fillers and hesitation pauses from the transcript, but the chunk timestamps keep the time those events took, and sixteen features built from these gaps form the strongest and most independent non-verbal channel we measured (AP $0.718$, correlation $0.11$--$0.36$ with all other members). Across controlled experiments we find three things: cross-modal conflict design does not reliably help on BAH; language is by far the strongest channel while affect-specialised audio is a useful second; and calibration matters more than architecture. Fitting ensemble weights and a threshold on the small validation split overfits: it scores $0.741$ macro-F1 on validation but only $0.690$ on the untouched test set. AP-weighting at a fixed threshold instead reaches $\mathbf{0.731}$ on test.

Robot manipulation is a complex task that requires visual understanding, physical reasoning, planning, and closed-loop control. General-purpose foundation models (FMs) have grown remarkably capable of some of these, especially vision and reasoning. To leverage this for generalist robot policies, current methods typically involve converting existing FMs into vision-language-action (VLA) models by fine-tuning on robot data to output low-level actions. However, VLAs are often orders of magnitude smaller than frontier FMs given the limited data and compute available for fine-tuning, which in turn limits their general capability. Inspired by the growing ability of FMs to operate software through visual interfaces, we ask whether that same competence suffices to control a robot. We present VIA (Visual Interface Agent for robot control), a framework that recasts robot control as an agentic task: an off-the-shelf FM-powered agent drives a manipulator through a browser-based 3D interface by taking screenshots, issuing intuitive commands, observing the outcome, and adjusting. The agent receives no robot-specific fine-tuning and no access to privileged state information: it perceives visual input and acts through a small set of general tools. VIA inherits the agent's general reasoning, closed-loop error recovery, and ability to plan and re-plan from what it observes. It solves a diverse suite of tabletop manipulation tasks zero-shot with both Claude Code and Codex. With the strongest model (Fable 5) it achieves 96.7% success on three LIBERO-Goal tasks and 100% on a long-horizon rainbow assembly task. Performance improves with the scale and strength of the underlying model. These results suggest that frontier agents already possess skills that transfer directly to robot control given the right interface: your coding or computer-use agent is, in a sense, secretly a robot-control agent.

AI music generation has rapidly advanced alongside commercial platforms, raising the need for reliable watermarking for provenance and attribution. However, existing audio watermarking research has largely focused on speech, and applying speech-oriented methods to music is challenging due to music's complex structure and rich acoustic texture. Most existing methods are post-hoc, adding imperceptible perturbations after generation rather than embedding watermarks as part of the content. This makes them fragile under transformations and especially vulnerable to neural codec re-synthesis, which can discard imperceptible residual signals. Moreover, since generation and watermarking are decoupled, the watermarking step can be bypassed or omitted, weakening provenance guarantees. To address these issues, we propose MusicMark, which, to the best of our knowledge, is the first generative watermarking framework for music. Specifically, MusicMark embeds watermark messages into the semantic latent space during generation, incorporating the watermark as part of the musical content and ensuring robustness against diverse attacks, particularly neural codec re-synthesis. To this end, we introduce a watermark adapter into a diffusion-based generation model to embed watermark messages across denoising steps. The adapter and detector are trained with a joint objective that preserves fidelity by constraining watermarked latents close to their unwatermarked reference latents, while improving robustness through attack augmentations. Experiments demonstrate that MusicMark substantially outperforms post-hoc baselines across diverse attacks including neural codec re-synthesis, while maintaining comparable generation quality. We further introduce a cover-song attack, converting the singing voice while preserving musical content, and show that MusicMark remains more robust than post-hoc methods.

Deep equilibrium models promise input-adaptive implicit computation: harder problems should demand more solver iterations, and the solved equilibrium should encode the result of genuine iterative inference. We report a cautionary study of a port-Hamiltonian DEQ with a learned initialization on two reasoning tasks -- ProofWriter entailment over frozen DeBERTa embeddings and a BFS-verified graph-reachability benchmark -- in which the implicit computation is a silent no-op. Across tasks, seeds, and controlled ablation arms, the solved equilibrium equals the solver's start point to numerical precision, and bypassing the solver entirely changes test accuracy by +0.00 percentage points in 18 of 19 training runs. Controlled interventions falsify the tempting explanation: removing the anchoring term reproduces every result, and retraining with noise-decoupled starts yields a solver that converges to the noisy start while the decoder learns to ignore it. The single escaping run diverges instead ($\|h^{*}-z_0\|=171$), producing a co-adapted noise channel whose removal improves accuracy. Iteration counts are uncorrelated with ground-truth difficulty ($r=0.009$), and the full apparatus never outperforms a two-layer MLP on either task. We trace the mechanism to gradient starvation along two distinct routes, show that the standard zeroing ablation is confounded and gives wildly seed-dependent answers where the correct substitution test gives a stable zero, and distill a four-test diagnostic protocol for auditing claimed implicit computation. All experiments run on a single free Colab GPU; code, raw logs, and analysis scripts are released.

Dynamic graph continual learning (DGCL) is an effective manner for handling catastrophic forgetting in dynamic graphs. However, existing DGCL methods underutilize temporal information across graph snapshots. To address this critical issue, we propose a novel framework for Dynamic Graph Continual Learning via Condensation and Attachment (CA-DGCL). Specifically, CA-DGCL first condenses historical graph snapshots into compact semantic representations efficiently. Further, a cross-timestamp node chains is built to construct a third-order tensor and Tucker decomposition is applied to this tensor for obtaining stable node features, which encapsulate historical knowledge. Finally, these node features are used to generate new nodes and attached to the current graph for replaying of past information without compromising the new patterns. In addtion, a refined forgetting measure is introduced to make it more suitable for dynamic graph settings. Extensive experiments demonstrate that CA-DGCL outperforms baselines in forgetting suppression as well as maintain competitive accuracy, proving its efficacy for dynamic graph continual learning.

LLM-based coding agents have significantly advanced automated software issue resolution, yet they remain highly prone to factual errors caused by insufficient repository understanding. Recent methods attempt to mitigate this limitation through pre-repair repository exploration; however, their fix-driven strategies explore repositories without identifying the agent's knowledge gaps, often yielding imprecise context that fails to bridge the underlying understanding deficit. In this paper, we propose ACQUIRE, a QA-driven framework for software issue resolution. Mirroring how experienced developers first comprehend unfamiliar code before attempting a fix, ACQUIRE explicitly acquires repository knowledge prior to repair. The framework decouples knowledge acquisition from patch generation through two stages: in the first stage, a Questioner and an Answerer collaborate to acquire structured repository knowledge, where the Questioner poses targeted questions and the Answerer produces evidence-grounded answers through autonomous exploration; in the second stage, the Resolver leverages the resulting QA knowledge to generate informed patches. By transforming implicit knowledge gaps into explicit, factually reliable understanding, ACQUIRE accelerates knowledge-intensive repair stages and enables more accurate resolution. Experiments on SWE-bench Verified demonstrate that ACQUIRE consistently outperforms representative pre-repair methods, raising Pass@1 by up to 4.4 percentage points with modest additional cost and time.

Discovering the memory or nonlocal kernel governing an integro-differential equation (IDE) from sparse and noisy observations is an ill-posed inverse problem. Existing identification methods often rely on problem-specific analytical derivations, specialized observation requirements, or restrictive assumptions about the kernel, limiting their applicability across different classes of IDEs. In this work, we propose a differentiable-solver-based framework for discovering memory and nonlocal kernels directly from spatiotemporal observations. Within the solver, the unknown kernel is represented using a constrained Kolmogorov--Arnold Network (KAN) parameterization, with the physical constraints imposed through two different approaches: a Bernstein-polynomial-based Monotone--Convex KAN (MC-KAN), whose coefficient constraints enforce positivity, monotonic decrease, and convexity by construction, and a Chebyshev-based KAN (Cheb-KAN), in which the same properties are encouraged through soft penalty terms. After training, symbolic regression is applied to the learned kernels to obtain interpretable closed-form representations. We evaluate both methods on benchmarks spanning a one-dimensional Volterra equation, a one-dimensional viscoelastic wave partial integro-differential equation, and a two-dimensional nonlocal reaction-diffusion equation with an anisotropic coupled kernel. For the 1D problems, both methods recover the correct kernel functional form and achieve comparable solution-reconstruction accuracy. In contrast, for the sparse and noisy 2D nonlocal problem, the hard-constrained MC-KAN consistently achieves lower kernel reconstruction errors than the soft-constrained Cheb-KAN. Our results demonstrate that enforcing physically motivated shape constraints by construction provides greater robustness than soft penalties for multidimensional kernel discovery from sparse and noisy observations.

Statute retrieval is a fundamental task in legal information retrieval, yet existing approaches struggle to bridge the gap between colloquial legal queries and formal statutory language. In this paper, we propose GCSR, a generative statute retrieval framework that reformulates statute retrieval as a sequence generation problem and internalizes statutory knowledge into a generative model. Specifically, we propose a multi-granularity structured docid that encodes legal hierarchy and semantic information, together with a multi-task training strategy. Experiments show that GCSR consistently outperforms strong sparse, dense, and legal-domain baselines. Our results demonstrate the effectiveness of generative retrieval for statute retrieval and highlight its potential for broader legal information access and downstream legal reasoning tasks.

Graph fraud detection plays a pivotal role in safeguarding the security and integrity of modern digital ecosystems. Graph Neural Networks (GNNs) are commonly adopted for graph fraud detection. However, the practical performance of existing GNN-based detectors is severely hindered by incomplete node attributes and extreme class imbalance within graphs. To mitigate these limitations, this paper proposes a novel framework for Graph Fraud Detection with Grouped attribute completion and Confidence-aware Contrastive learning, named GFD-GC. Specifically, it first imitates heterogeneous neighborhood structures to implement group-wise aggregation, which obtains informative complete node features by capturing fine-grained graph contextual patterns. Further, it introduces a confidence-aware supervised contrastive learning strategy to augment scarce labeled fraud nodes with high confidence pseudo-fraud nodes, which enhances the compactness of fraud representations and their separability from non-fraud nodes. Extensive experiments demonstrate the superiority of the proposed GFD-GC over state-of-the-art baselines on the graph fraud detection task, thereby providing an effective solution for real-world fraud scenarios.

Tool-using LLM agents are mostly evaluated assuming all tools work. When a tool times out, returns a week-stale value, or has its description poisoned in deployment, the developer needs a controlled way to reproduce the failure, test a fix, and confirm the fix worked before deployment. We present AgentCheck, an open-source web workbench that turns an MCP server into an intervention surface. AgentCheck runs an agent against its real tools and records every tool response, then re-runs the agent with the response perturbed by a fault (12 types) injector. Matching tool calls are replayed from cache, and later tool calls go live after the agent diverges. This yields a reproduce-intervene-confirm loop: the developer toggles a mitigation, re-runs against the identical fault, and sees if the failure goes away. Scoring has two parts: deterministic pass/fail rules, plus an LLM judge for interpretive labels, validated against human annotations. Across five agents, the best passes 105/120 scenarios and the weakest only 77. The failures are usually silent, confident use of incorrect tool outputs rather than crashes. On the weakest agent, a retry mitigation raises success on timeout error faults from as few as 30% of cases to 100%, whereas stale-data faults remain near 3-4 of 10 regardless of the mitigation. AgentCheck makes these failure modes reproducible, comparable, and verifiable before deployment.

Adversarial perturbations threaten machine learning classifiers, including variational quantum classifiers. We show that finite quantum measurement statistics (shot noise) act as a built-in defense against gradient-based test-time attacks whose cost scales unfavorably for the attacker. Because every gradient component must be inferred from repeated circuit executions under any unbiased gradient-estimation rule, white-box extraction consumes a dimension-dependent measurement budget that measurement grouping cannot remove in expressive circuits. Under stated assumptions, single-step attacks need at least quadratically many shots in the input dimension $d$, growing as $d^{5/2}$ under norm-concentration scaling, with a sufficient-budget analysis for iterative attacks via stochastic gradient Langevin dynamics. Simulations up to 784 input dimensions validate the law: the realized total budget is the $d^{5/2}$ geometric floor for plateau-mitigated models and grows as $d^{3.00}$ for the tested deep circuits, whose gradient norms decay with dimension absent barren-plateau mitigation; folding the measured gradient norm back in recovers the parameter-free $d^{3/2}$ shot-noise geometry. Against a matched classical baseline whose attack overhead is dimension-independent (the cheap-gradient principle of automatic differentiation), the quantum gradient cost ratio grows empirically as $d^{3.00}$, so the attacker's relative cost diverges as the model scales. Experiments on a 156-qubit IBM processor (ibm_boston, 4-qubit circuits, $d=12$) reproduce the effect: at matched budgets the device attack tracks the ideal within a few percent, with the high-shot gradient faithful to the exact one. The defense operates precisely when the forward map is classically hard to simulate: only then is a white-box attacker denied the simulate-and-backpropagate shortcut and must pay the measurement cost we quantify.

Physics-informed neural networks (PINNs) have shown promise for solving partial differential equations (PDEs); however, their synchronous optimization treats residuals of different regions and constraints equally, which is inconsistent with the progressive "from source to response" physical information propagation path, degrading training stability and accuracy. Existing causal training methods focus mainly on the temporal dimension, lacking a unified characterization of spatial and boundary dimensions. To address this, we define a unified class of training priorities according to the physical information propagation path: premise regions should be learned before dependent regions; temporal, spatial, and boundary priorities are instances of this principle. Using neural tangent kernel (NTK) dynamics, we theoretically analyze why standard PINNs do not obey this priority: their residual convergence order is governed by the NTK spectrum and is independent of the propagation path. Accordingly, we propose a unified multi-dimensional priority-constraint framework that partitions the domain along the propagation path and constructs negative-exponential residual weights, converting the physical propagation order into a training priority. For cases with coexisting priorities, we introduce a directional compatibility coefficient to clarify that "orthogonal directions can be coupled multiplicatively in synergy, whereas coaxial opposite directions cannot." Benchmark cases show that this method consistently improves the convergence behavior and prediction accuracy of PINNs on problems with clear propagation paths or constraint-dominated structures, without modifying the network architecture and with controllable additional computational cost.

A trained molecular property model can be refined at test time by correcting each prediction with the measured labels of the most similar training molecules, a retraining-free procedure we call neighbor fusion; evidential neural networks make it principled by using their aleatoric and epistemic uncertainty to parameterize a Bayesian update. Our main contribution, PG-EVIKAL, learns a property-distance metric to re-rank structurally similar neighbors by their property relevance before fusion, building on EVIKAL (scalar Kalman filter) and GP-EVIKAL (Gaussian process variant handling correlated neighbors). Evaluated on 16 molecular datasets, PG-EVIKAL reduces RMSE relative to the evidential model baseline on 14 of them, with a median reduction of 19.4%, and improves calibration; in sequential-assay scenarios it further incorporates newly measured molecules, refining predictions as they arrive without retraining. This work demonstrates that evidential uncertainty decomposition is not merely a calibration objective but an actionable inference resource that enables test-time refinement of molecular property predictions.

Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks through Chain-of-Thought (CoT) prompting. However, these models often exhibit "computational overthinking," generating redundant reasoning steps that increase latency and cost without improving accuracy. Recent studies suggest that CoT trajectories can be significantly pruned, yet existing methods often rely on forcing a static thinking budget, heuristic filtering, sub-optimal early exit via classification, or expensive re-training. In this paper, we introduce OS-Pruner, a lightweight plug-in framework that formulates chain-of-thought pruning as an optimal stopping problem. Given a reasoning prefix, OS-Pruner learns whether further reasoning is worth its token cost by optimizing an explicit utility that trades off final-answer accuracy against generated length. Our novel formulation enables the model to dynamically assess the sufficient point of termination for a reasoning chain. OS-Pruner is designed to be lightweight during both training and inference, and to provide users with fine-grained control over the reasoning-effort vs. accuracy trade-off. On diverse reasoning benchmarks and base models, OS-Pruner achieves 20-60\% reduction in generation length with minimal accuracy sacrifice.

Agentic research systems are emerging as a new paradigm for coordinating scientific workflows beyond isolated model inference, code generation, or statistical analysis. However, deployment in institutional biomedical environments requires governed mechanisms for research planning, data access, workflow orchestration, evidence tracking, reproducibility, and human oversight. We present NVAITC AI Scientist (NAIS), a governed end-to-end agentic research system designed to support domain-general scientific workflows while keeping protected data within institutional privacy boundaries. NAIS integrates proposal review, execution planning, governed computational routing, reproducible workflow orchestration, evidence generation, and scientist-in-the-loop oversight. We validate NAIS in a real-world hypertension genome-wide association study (GWAS) using hospital-linked genotype and electronic health record (EHR) data from 286,422 individuals under an aggregate-only data policy. The agent planned cohort extraction, orchestrated GWAS execution, generated quality-control summaries, and drafted publication-oriented outputs. Human-AI review identified phenotype discrepancies and enabled iterative refinement of the hypertension definition. After reconciliation, the agent-orchestrated GWAS reproduced established hypertension loci, including FGF5, ATP2B1, CNNM2, FTO, and GRB14, with the strongest signal at FGF5 reaching $-\log_{10}(p) \sim 70$. As a secondary demonstration, NAIS also supported a drug-induced liver injury prediction workflow, achieving a multimodal graph neural network AUC of 0.842. These results demonstrate that governed agentic research systems can support scalable AI-assisted biomedical discovery while producing outputs comparable to expert-led workflows.

Diffusion Transformers (DiTs) have advanced video generation with high-quality, temporally coherent results. However, extending them to motion transfer, which requires following reference motion while aligning with a target prompt, remains challenging due to limited understanding of motion and structure representations within DiTs. We analyze video DiTs at the attention-head level and identify distinct heads specialized for motion and spatial structure. Based on this insight, we propose a head-aware controllable motion transfer framework that requires no parameter updates. Our method refines motion cues from motion-specialized heads via semantic correspondence guidance and preserves structure through selective feature injection. This head-level control not only enables accurate motion transfer but also provides an interpretable foundation for controllable video generation with DiTs.

Existing benchmarks for scientific data analysis evaluate LLMs primarily on code execution or workflow completion, overlooking that scientific analysis serves to support distinct types of scientific claims: hypothesis exploration, statistical inference, mechanistic explanation, each with different assumptions and validity criteria. We introduce SDABench, a benchmark that reorganizes evaluation around six capabilities (descriptive, exploratory, inferential, predictive, causal, and mechanistic) across five domains (Biology, Chemistry, Environment, Geography, Physics). SDABench comprises 527 real-data instances (SDA-Real) and 6000 synthetic instances (SDA-Synth), each in both multiple-choice and open-ended formats, constructed through an automated pipeline. Evaluating 15 representative LLMs, we find that models handle descriptive analysis well but degrade sharply on tasks requiring assumption selection, latent-process modeling, or mechanistic reasoning. SDABench further provides a five-stage error analysis framework that locates where LLMs fail: more advanced models more reliably identify the relevant scope and variables, but still struggle to select appropriate analytical procedures, model variable relationships, and draw valid conclusions.

Can a Video Large Language Model (Video-LLM) follow one person through a long video, keeping track of who they are well enough to report, in order, how their outfit changes across a full TV episode? Benchmarks increasingly score this kind of task, and the strongest open-source 7--8B models now reach 37--38% on InfiniBench's global appearance task, which asks exactly that. But does that score come from tracking the named character, or from something easier? We test this with a nine-condition diagnostic protocol applied to three architecturally distinct open-source Video-LLMs, with Gemini~2.5~Flash as a frontier reference, and find the accuracy does not come from character tracking. When we change the character named in the question to a different cast member, leaving the video and answer options untouched, the models change their answer only 4--31% of the time, so they are largely ignoring who the question asks about. Breaking that test down by the gender of the swapped name shows why: the models react more when the name is changed to a different-gender character than to a same-gender one (a 13--28 point gap), picking up coarse gender cues but unable to tell same-gender individuals apart. This shallow processing surfaces again when we drop the multiple-choice options and ask the same questions open-endedly: open-source accuracy drops 18--25 points, with none of 151 answers fully correct, versus a 12-point drop for Gemini. Further checks rule out the obvious innocent explanations, adding subtitles, using the most informative frames, or doubling the number of frames all leave character tracking unimproved, so the bottleneck is not how much video the model sees but how it ties that video to the person the question names. We release a diagnostic toolkit for auditing what such benchmark scores actually measure.

The choice of Modulation and Coding (MCS) type for a particular channel condition is made through link adaptation (LA) algorithms that operate at the MAC layer. These algorithms rely on the ACK/NACK statistics and the channel quality index (CQI) feedback. Several existing works model LA as a multi-armed bandit (MAB) problem across cellular and Wi-Fi links. In the MAB formulation, each available MCS is a Bernoulli arm parameterized by its transmission success probability, and the goal is to design a selection strategy that accrues maximum reward. Several popular MAB algorithms, such as upper confidence bound (UCB) and Thompson Sampling (TS), have been proposed in the literature. Using the fact that MCS success probabilities are ordered, we propose the Joint-Thompson Sampling (Joint-TS) algorithm. Unlike classical TS, which assumes independent Beta distributions for each arm, Joint-TS utilizes a multivariate ordered Beta distribution as the prior to preserve the inherent monotonicity of success probabilities. Our simulation results show that while existing MAB algorithms fail in specific scenarios, Joint-TS delivers competitive throughput with robust, consistent performance in all scenarios.

Large language models are increasingly used to assist scientific reading, but existing evaluation methods often fail to detect whether answers are supported by verifiable citations. We introduce ResearchQA, a benchmark of 6,211 single-paper question-answer pairs from 494 open-access papers spanning eight domains and four question types: lookup, comprehension, multi-hop, and adversarial. ResearchQA is designed for citation-grounded evaluation: it permits multiple valid supporting passages for a claim and rewards grounded refusal when the source paper does not support an answer. We evaluate eight leading closed- and open-weight models in a citation-grounded chat-with-paper setting using a deterministic citation matcher and an LLM-based rubric evaluator. Citation-based metrics separate systems more clearly than LLM-evaluator scores: section coverage and citation accuracy vary substantially across models, while evaluator scores remain tightly compressed. We further find that open-weight models approach the best closed-model citation accuracy while achieving 3 to 6 times lower per-example latency. We release the benchmark, evaluation harness, and evaluator prompt.

Accurately representing atmospheric aerosol populations is essential for simulating aerosol-cloud interactions, radiative forcing, and ice nucleation, yet existing reduced schemes impose structural assumptions that limit their ability to capture composition diversity and mixing state. Machine-learning approaches offer more flexible representations, but standard autoencoders do not preserve the mathematical structure of aerosol populations and therefore cannot support physically meaningful process operators. We introduce AeroMELD (Aerosol Measure Embedding for Latent Dynamics), a mathematically grounded framework for constructing low-dimensional latent variables that retain this structure. We show that any permutation-invariant linear encoder must take a scale-shape decomposition, with total number concentration represented explicitly and latent shape given by a barycentric combination of per-particle embeddings. This aggregated latent state retains the diagnostic expressiveness of a Deep Sets model by moving the nonlinear post-aggregation stage into the learned diagnostic map while preserving latent linearity. Using particle-resolved data as ground truth, we encode weighted particle populations directly rather than binned aerosol states; size-resolved mass and number distributions serve only as diagnostic targets and visual summaries. The latent space accurately reconstructs these distributions, CCN spectra, optical coefficients, and immersion-freezing behavior while preserving the linear population structure needed for hybrid ML-physics models. Although the experiments focus on diagnostic reconstruction, the embedding is designed so that emissions and mixing can be represented exactly and nonlinear microphysical processes learned in a controlled latent space. This work establishes a foundation for learning aerosol-process evolution directly in latent space.

Modern large language models (LLMs) operate in interactive multi-turn settings, making multi-turn jailbreaking a realistic threat model and an important setting for automated red teaming. A core challenge in learning multi-turn jailbreak attackers is credit assignment: different turns contribute differently to the final outcome, yet existing learning signals are often too coarse to identify their individual contributions. We propose decomposed credit GRPO (DC-GRPO), a unified turn-level credit assignment framework for Group Relative Policy Optimization in multi-turn jailbreak learning. DC-GRPO assigns a separate group-relative learning signal to each turn by combining immediate and future credit, avoiding the credit misassignment induced by broadcasting a single trajectory-level score across the dialogue. We instantiate this framework with static and dynamic weighting rules that differ in how the two credit sources are balanced while sharing the same turn-level structure. Across multiple victim LLMs and benchmarks, the dynamic- and static-weighted variants achieve average ASR5@3 scores of 98.26% and 97.88%, respectively, substantially outperforming the state-of-the-art methods, including SEMA (86.58%) and TROJail (86.23%). Their consistently strong performance indicates that the central empirical benefit comes from turn-level group-relative credit assignment rather than a particular weighting rule. Warning: This paper contains examples of harmful content.

Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances. Most existing methods rely on white-box access to target model gradients, which is often unrealistic for real-world deployed systems and computationally exhaustive due to recursive backpropagation for optimization, limiting their applicability. While previous black-box methods predominantly target single-step, instantaneous decision tasks, they struggle to handle the task complexities and temporal dependencies. This highlights the need for a gradient-free attack method that can effectively disrupt the multistep sequential perception-action loop using only observable inputs and outputs. Therefore, we propose AdvNav, a behavior-guided black-box adversarial attack framework that disturbs an agent's first-person views during navigation. To construct an informative surrogate objective for effective optimization guidance in gradient-free search under the black-box setting, we design a dual-granularity behavior-based feedback, aggregating a trajectory-level performance score representing overall navigation degradation, an action-level reward score considering the potential decision risk, and a deviation indicator, all of which are extracted from the agent's self-output behaviors. This feedback guides a hybrid optimization strategy that heuristically tunes perturbation strength via adaptive updates and evolves noise spatial structure genetically, to iteratively discover the most disruptive noise configuration. Evaluated against Transformer-based HAMT and LLM-based MapGPT with two types of backbones on R2R dataset, AdvNav achieves 49.70/65.96/87.30% Attack Success Rate. The result demonstrates the effectiveness and generality of AdvNav, reveals critical perception vulnerabilities and offers insights for the design of future resilient VLN models.

Fruitful collaborations rely on cooperative communications, including of contextual cues to incorporate into reasoning. The increasing use of LLMs in collaborative and agentic pipelines raises questions about the extent to which they exhibit these pragmatic capabilities, especially in scenarios where they may not have access to the same information as their collaborators. In this paper, we perform a novel investigation into the pragmatic reasoning capabilities of LLMs in a multi-party collaborative task under partial information conditions. We formalize a notion of collaborative epistemic asymmetry that explicitly connects objective task success to Grice's cooperative principle and empirically assess various LLMs' abilities to act cooperatively as both speakers and listeners, including both prompting and post-training strategies. Our results show that while LLMs exhibit certain pragmatic capabilities in collaborative settings, and these can be elicited through prompting and post-training, they still face challenges in pragmatic communication with incomplete information, and that certain failure modes do correlate with floutings of Grice's maxims that go unrecognized.

Machine learning progress is often attributed to scaling model size and dataset volume, yet the composition of data can be just as consequential. Empirical findings repeatedly show that combining datasets from different domains yields nontrivial interactions. For instance, adding code improves mathematical reasoning, while certain mixtures introduce interference that reduces model performance. We refer to these effects collectively as data synergy, where the contribution of multiple domains exceeds or falls short of the sum of their isolated contributions. In this work, we formalize and quantify data synergy in language model pretraining. Leveraging observational variation across open-weight LLMs with diverse pretraining mixtures, we estimate both direct domain-to-benchmark synergy (how one domain contributes to performance on another) and a second-order domain-domain synergy (capabilities that require co-occurrence of multiple domains). Our framework improves predictive accuracy over domain-agnostic scaling laws and recovers stable synergy estimates. We validate these estimates by training models on predicted optimal and predicted anti-optimal mixtures and confirm that our synergy estimates correctly predict performance rankings.

LLM-based agents are increasingly being used to support software development, yet their performance in repository-level tasks depends on retrieving the right code context. Existing studies have explored file-level localization using traditional information retrieval over file paths and raw source code. However, the role of textual code representations in retrieval and localization remains underexplored. We study file-level bug localization as a representation-driven retrieval problem. Across the Long Code Arena (LCA) and SWE-bench Verified (SWE) datasets, we compare five code representations: file paths, raw source code, and three LLM-generated textual representations. Our experiments include lexical, semantic, and LLM-based retrieval, followed by LLM-based post-retrieval ranking. We quantify the cost incurred by a representation through the representation footprint. We find that the choice of code representation affects both localization effectiveness and cost. Role-aware summaries outperform file-path representations by up to 40% Hit@5 while requiring a representation footprint 10.4 to 20.9x smaller than raw source code. Combining complementary representation results and ranking retrieved candidates with an LLM provides further gains of up to 31.9% and 42.0%, respectively. Overall, role-aware summaries provide the best cost-effectiveness trade-off, while raw source code offers effectiveness in some settings at a significantly higher cost. A case study with Agentless reveals the utility of our techniques within a well-known pipeline, reaching 94% Hit@6 on file localization (+4.7% against the baseline). Our findings suggest that code representation should be treated as a first-class design choice in agentic localization pipelines, guided by pipeline stage and cost-accuracy requirements.

Large language models (LLMs) are increasingly used in agentic coding settings, where they can inspect files, execute commands, run tests, observe failures, and iteratively revise code. This shift raises a central evaluation question: can an agentic LLM generate an end-to-end software artifact that is both deployable and behaviorally correct under execution? Backend services provide a controlled but realistic substrate for this evaluation. Their APIs expose application-level executable semantics, and deployed behavior can be checked deterministically against an OpenAPI contract through black-box HTTP interactions. We introduce BackendForge, a benchmark of 56 contract-defined backend generation tasks rewritten from real open-source applications. Given a visible specification and an OpenAPI contract, an LLM must generate a Dockerized service that is built, deployed, and evaluated only through HTTP tests. To strengthen evaluation without introducing hidden requirements, BackendForge uses a test agent and a code agent to co-evolve the test oracle and reference service, where the test agent proposes specification-grounded backend tests and the code agent repairs the reference implementation. Although the best-performing model, GPT-5.5, succeeds on 55.4\% of tasks under the base oracle, it succeeds on only 28.6\% under the final oracle. This gap suggests that current LLMs can implement many local API behaviors, but still struggle to produce complete backend services.

Young job seekers frequently turn to social media to compare themselves with peers and make sense of career possibilities. However, passive feed browsing creates a paradox: the authentic peer content that provides emotional grounding also triggers potentially detrimental upward social comparison and cognitive overload. Previous work has either structured online user-generated content to reduce noise without changing the passive browsing modality, or built AI-powered career exploration systems that disregard authentic human experiences. To address this gap, we developed JobMate, an interactive system that transforms real social media career posts into persona-grounded conversational AI agents, shifting the interaction from passive scrolling to active, personalized dialogue. We conducted a between-subjects study ($N$ = 24, three disciplines) comparing JobMate with native RedNote browsing. Our study shows that JobMate's AI-mediated dialogue redirected social comparison from potentially detrimental upward comparison toward constructive self-reframing, while promoting sensemaking through active conversational engagement. However, users still relied on the authenticity of real peer content for emotional grounding. We discuss design implications for AI systems that augment authentic online user-generated content consumption across social comparison contexts.

Multimodal information is pivotal for e-commerce search ranking. Existing works leverage multimodal data typically by fine-tuning general Multimodal Large Language Models (MLLMs) via collaborative signals, subsequently integrating the derived representations into ranking models as item features. Despite their efficacy, these methods face two primary limitations: (1) they rely on a single collaborative signal for MLLM fine-tuning, failing to exploit the heterogeneous signals essential for multitask ranking; and (2) they treat multimodal representations as regular item features in ranking models, underutilizing their latent potential for user behavior modeling. To address these challenges, we propose the Multiplex Multimodal Representation Model (MMRM), a unified framework that aligns MLLMs with diverse collaborative signals. By employing a shared backbone with task-specific tokens and projection layers, MMRM simultaneously learns from multiple signals and generates comprehensive multiplex item representations in a single inference pass. Furthermore, we introduce a multiplex user representation strategy in ranking models, which derives task-specific user representations via search-based behavior sequence modeling leveraging multiplex item representations. Extensive experiments demonstrate MMRM's superior efficiency and effectiveness. Notably, MMRM has been successfully deployed in the JD e-commerce search engine, yielding significant performance gains for millions of daily users.

We used a large language model (GPT-4.1) to annotate the text of about 9,000 support conversations at a global consumer-goods firm, decomposing customer-care satisfaction into component axes (overall, agent, outcome, product, and customer effort), and validated the LLM annotations against the satisfaction ratings customers gave themselves. Four of five axes track self-reported satisfaction closely (overall, agent, and outcome near an unadjusted 0.65; effort -0.54), while product satisfaction is weak against the available proxy. The unadjusted correlation also understates the alignment: the disagreements concentrate in a small, readable tail of divergent sessions rather than in general drift, and the overall correlation rises to 0.811 when only the severe divergences are excluded and to 0.914 when the full divergent tail is excluded. The axes are also highly collinear, and adding them to the overall score does not improve prediction of the customer's rating, the decomposition's value is not incremental prediction but attribution and coverage. And, with greater coverage the picture of the data changes. Read on every contact rather than the few that return a survey, satisfaction is markedly lower than the survey reports (a full-census 2.91 against the surveyed 3.62 on a five-point scale). The promise of decomposed satisfaction as a methodology is the ability to identify more nuanced drivers of customer experience in conversational data.

Face super-resolution is the task of increasing the resolution of an image containing a face thereby adding finer detail. It is a ubiquitous task in many computer vision applications and quite often the user isn't even aware that it is being performed. However, doing it with high fidelity is challenging as it is an ill-posed problem. In this paper we present a reference-based solution for face super-resolution that uses higher resolution reference images to aid in the task. We show an alignment module based on the spatial transformer that is considerably more stable than the popular deformable convolutions. We also show an aggregation function that can take good quality information from the reference images when available or suppress the function when such information is unavailable. Finally, we show that our relatively smaller model can achieve state of the art results on multiple datasets. The source code is available at https://github.com/varun-jois/FSRST.

The test suites used as RLVR rewards for code have natural false positives: per-task, persistent, asymmetric errors that accept the same wrong programs every time they appear, unlike the symmetric or resampled noise assumed by existing noise-robustness analyses. We run a preregistered two-arm causal contrast on a deployed suite: GRPO on identical MBPP tasks, seeds, and compute, rewarded by the original MBPP tests (leaky) versus the MBPP+ extra tests (hardened). Two further families replicate the design under a preregistration frozen before their data existed. [C] The average held-out effect is bounded: non-inferior under a preregistered 1.5-pt margin (gap 0.20 pt, one-sided 95% upper bound 0.75 pt). [C] Rewarded false-positive mass tracks a cheap static leakiness audit computed before training (Spearman 0.80), and the registered train-side test puts the leak-stratum FP share +43.8 pt above clean tasks. [E] Auditing every rewarded FP under signed, human-adjudicated rules finds a large residual of verified genuinely wrong code: 47.57% record-weighted; both replication families reproduce a large share. The reward paid for real bugs, not merely suite artifacts. [E] Mechanism evidence is consistent with selection of pre-existing error modes rather than learned exploitation: FP incidence does not grow within our horizon, and untrained base models already produce the same wrong outputs under the leaky filter. We then turn the same instrument on the frontier judges themselves: on their own false positives they self-assess only weakly, a same-author test is unresolved, and even the highest-scoring reader we probe stays far below its score on a weaker policy's errors -- two subjects on MBPP, licensing nothing about frontier models in general. A cheap static audit locates exposure before training; hardening the reward removes the measurement inflation, though here it buys little capability.

Continual learning promises a language model that keeps acquiring knowledge after training, with each new fact written into its weights. Whether weight writes can support accumulation remains undecided. We follow invented facts written into Qwen3 models from creation through sequences of twenty to one hundred later writes, using held-out questions of five types, with the original model given the fact in its prompt as the reference. Across these experiments, the breadth of the training data determines the kind of knowledge created. Bare-statement training produces recitation, while diverse restatements reduce the recitation-to-use gap from 27.4 to 5.4 points without showing the model a conclusion. This difference carries into later writes: after twenty sequential writes, bare-statement facts retain 1% accuracy while facts written from broad study data retain 46%. We also find that facts can be behaviourally forgotten without being erased. Forgotten facts keep most of the log-probability added by their write, and under bare-statement training 70% of wrong answers about them contain the most recently written fact. The same writes barely degrade the model's use of facts in context, and a forgotten study fact supplied in the prompt recovers to 77-80% on its questions. These results describe knowledge that is stored but question-keyed: later writes redirect the questions that reached it. Damage to unrelated abilities tracks KL divergence from the original model, and the later writes cause interference regardless of how the earlier fact was stored. Broad data can create usable knowledge, and a frozen reference can preserve capability, but no intervention we tested, including those built on accurate local measurements of each write, keeps earlier facts reachable. When facts must be composed or survive later writes, the reliable channel is context rather than the weights.

Enterprise data analysis is emerging as a distinct frontier for autonomous agents. Compared with general-purpose interaction and software engineering, it operates in an open, ambiguous, and continuously evolving environment. These characteristics call for a data-agent architecture that treats semantics, methodology, execution, and evolution as first-class system concerns. To this end, we introduce QwenPaw-Data, an agentic data system designed for enterprise intelligent data analysis. QwenPaw-Data consolidates heterogeneous assets from warehouses, dashboards, documents, interaction logs, and historical tasks into reusable, governable, and evolvable analysis assets, then turns natural-language requests into end-to-end analytical workflows spanning data understanding, retrieval, analysis, report generation, and decision support. Its architecture decomposes the problem into three collaborative subsystems: DataBridge provides trustworthy semantic grounding through interconnected metadata, knowledge, and trace graphs; Skill-Hub codifies expert analytical methodology into reusable and verifiable skills; and Host materializes these evidence and method assets into controllable, artifact-centric runtime execution. Across these subsystems, semantics, methods, traces, and feedback are continuously deposited back into the system, forming a self-evolving asset flywheel. Experiments on public benchmarks and real-world industrial BI workloads show that QwenPaw-Data improves both verifiable data access capability and higher-level analytical quality, offering a practical foundation for reliable, traceable, and continuously improving enterprise data agents.

Data re-uploading parameterized quantum circuits (DRU-PQCs) are universal function approximators, yet their expressivity produces oscillatory, non-convex loss landscapes that resist gradient-based optimization. We show that the primary optimization bottleneck in DRU-PQCs is not insufficient capacity but a structural failure mode we term Fourier locking (FL): because encoding weights and entangling layers are nonlinearly coupled, random initialization on high-frequency targets collapses the encoding parameters into spurious local minima. Two Fisher diagnostics characterize FL. The input-space quantum Fisher information $F_x$ measures the effective frequency content of the encoded state; the Fisher discriminant ratio of the measured features measures their alignment with the class labels. In two independent 50-seed experiments, the locking is literal: trapped circuits hold $F_x$ frozen for the entire run, while escaping circuits migrate their frequency content (direct training: $r_{pb} = -0.48$; curriculum: $d = 1.34$; both $p < 0.001$). The replicated signature is this spectral mobility, not any endpoint value of $F_x$, and trapped circuits retain a fully non-degenerate parameter-space QFIM ($r_{pb} \approx 0$): the failure is spectral misalignment of a responsive state, not a loss of geometric sensitivity. A frequency-staged homotopy protocol that paces the target frequency ($f: 1.0 \to 3.0$) convexifies the early loss landscape; escaping circuits raise $F_x$ in step with the curriculum, and the escape rate triples (18% vs. 6%). Fourier locking is a frequency-alignment problem, and its remedy is frequency pacing.

Conventional language-model distillation often relies on fixed teacher-generated data, which may not cover the states encountered by an evolving student policy. On-policy distillation (OPD) instead collects teacher or evaluator supervision on student-generated rollouts. However, existing OPD methods differ substantially in supervision form, tokenizer compatibility, teacher access, and supervision granularity, leading to fragmented implementations that are difficult to reproduce and extend. We present \textsc{EasyOPD}, an on-policy distillation framework built on verl, a distributed reinforcement-learning framework for large language models. \textsc{EasyOPD} separates user-side configuration, method-specific supervision logic, and verl-based execution. Its method modules connect to the shared backend through extension boundaries for loss construction, rollout metadata, reward processing, tokenizer alignment, and teacher-side computation. We instantiate representative methods for three OPD settings -- cross-tokenizer OPD, on-policy self-distillation, and step-wise OPD. Experiments on reasoning, code-generation, scientific-knowledge, and tool-use benchmarks show that these implementations can be executed through the same verl-based backend while retaining their method-specific objectives and task-dependent performance profiles. We release \textsc{EasyOPD} with runnable YAML configurations, documentation, and an installable demonstration package and video.

Open-vocabulary dense perception (OVDP) aims to localize objects unseen during training by leveraging textual knowledge. Despite the remarkable progress of recent CLIP-based approaches, we identify a critical limitation: synonym-induced grounding inconsistency, where semantically equivalent expressions yield disparate spatial attention patterns. This inconsistency undermines the robustness and performance of existing methods in real-world OVDP applications. To address this issue, we propose SynCLIP, a Synonym-Coherent Language-Image Pretraining framework that enhances synonym-robust grounding for OVDP. SynCLIP introduces a Semantic-consistent Spatial Attention alignment (SSA) module to enhance spatial attention consistency by minimizing discrepancies between attention maps of original and synonymous expressions. Furthermore, a Spatial Attention Refinement (SAR) module selectively strengthens the most semantically relevant spatial regions within aligned maps for more precise and stable grounding. To support synonym-coherent pretraining, we also construct a Synonym-Enriched Visual Corpus (SEViC), which augments each category with multiple synonyms and textual definitions. Extensive experiments on multiple benchmarks demonstrate that SynCLIP substantially improves grounding consistency under diverse linguistic variants and achieves state-of-the-art performance among CLIP-based OVDP methods. Code is available at https://github.com/Justlovesmile/SynCLIP.

Few-shot multimodal classification commonly attaches a lightweight head, such as $k$-nearest neighbors, logistic regression, or a linear SVM, to a frozen pretrained encoder. Although computationally efficient, these heads can produce poorly calibrated confidence scores, limiting their reliability in calibration-sensitive applications. We evaluate TabPFN as a plug-and-play, zero-gradient classification head for frozen image, text, and audio encoders. Across 22{,}820 evaluation episodes spanning 14 datasets, 11 encoders, and three modalities, TabPFN achieves the best mean rank among nine classification heads on both negative log-likelihood (NLL) and expected calibration error (ECE). At a representative setting, it reduces NLL by 48--62\% and ECE by 2.1--5.3$\times$ relative to the average of the eight baselines while matching or exceeding their average accuracy. Its accuracy advantage is conditional, concentrating at moderate-to-high shot counts and low-to-moderate feature dimensions ($k \ge 50$, $d \le 32$), and diminishing when labeled data are scarce, feature dimensions are high, or competing methods approach ceiling accuracy. In targeted backbone-adaptation experiments, replacing the trained linear head with TabPFN substantially improves calibration while preserving competitive accuracy. These results provide empirical guidance for using TabPFN as a training-free head in calibration-sensitive multimodal classification. To support transparency and reproducibility, we publicly release the source code, experiment configurations, and evaluation scripts in our GitHub repository: https://github.com/Jingxiang-Zhang/tabpfn-multimodal-embeddings.

This paper develops a model-free reinforcement learning framework for continuous--time extended mean field control problems, where both the dynamics and reward may depend on the joint distribution of states and controls. We adopt deterministic feedback policies, under which the state--action distribution is induced directly as a push--forward of the state law. This avoids optimization over stochastic kernels and bypasses key limitations of existing approaches in extended mean field settings. We first establish a model--free sensitivity formula for parameterized McKean--Vlasov dynamics and use it to derive a deterministic policy gradient formula expressed through an advantage--rate function on the Wasserstein space. We then refine this formula by introducing local value and advantage--rate representations that depend on the state, action, and joint state--action distribution, yielding a policy gradient that includes both action derivatives and measure--derivative terms with respect to the control distribution. These characterizations lead to a martingale--based learning principle and motivate a continuous--time deep deterministic policy gradient algorithm combining particle approximations, measure--dependent neural networks, temporal--difference learning, and exploration in either action or parameter space. Numerical experiments on stochastic Cucker--Smale consensus control and optimal liquidation with trade crowding demonstrate the efficiency, stability, and robustness of the proposed method, including problems with explicit dependence on the control distribution.

We present a manipulation planning system based on affordance recognition and action effect prediction. The system reasons through possible futures in visual form, and evaluates candidate plans by agreement of predicted outcomes with text-based goals set at run-time, using a multi-modal goal-matching module. Positions of objects named in the goal text are tracked through predictions even when occluded, making it possible to generate action plans even when objects become occluded, or when their initial descriptors cease to identify them in future states. We further expand the system with an image conversion module for translating real-world state images with objects of varied shapes and visual appearances into a consistent visual appearance, to facilitate manipulation planning in a physical robot setup. We evaluate performance of the system's modules in isolation and demonstrate the integrated system's manipulation planning capabilities on a set of challenging tasks in both simulation and on hardware.

Zero-dimensional reduced-order models (0D ROMs) are central to multi-dimensional design workflows for high-end complex equipment. However, the planning process currently relies on manual expertise, limiting topological exploration and prolonging iterations. Even traditional optimization methods such as Genetic Algorithms (GA) are typically confined to local parameter tuning. Although Large Language Model (LLM) agents have shown promise in exploring large sample spaces, and frameworks such as Chain of Thought (CoT) and Reason and Act (ReAct) improve reasoning reliability, while Retrieval-Augmented Generation (RAG) overcomes domain knowledge barriers, a single agent still falls short for the long-horizon and highly coupled nature of complex 0D ROM planning. This paper proposes the Zero-dimensional reduced-order model CO-Planning framework (Z-COPA), a multi-agent architecture featuring a Symbolic Action Graph Engine (SAGE) and a MILP-Guided Navigation (MGN) optimizer. Its core innovation is a dedicated graph representation method that accurately encodes the 0D flow network topology, converting the empirical planning process into a rigorous graph structure optimization problem. We validate the forward and inverse design capabilities and generalization performance of Z-COPA on two real aircraft engine secondary-air systems, two IEEE power-distribution reconfiguration benchmarks, and two water-distribution network benchmarks. The results show superior task completion quality, obtaining the best performance in both forward and reverse design of air systems. Z-COPA disrupts the traditional 0D model planning paradigm, providing a new technical approach for exploring broader topological space and achieving highly automated, globally optimal air system architectures.

Perineural invasion (PNI) is a clinically relevant indicator of tumor aggressiveness and can influence surgical decision-making, motivating interest in reliable preoperative assessment. The subtle MRI features of PNI, however, often resemble nearby anatomy, complicating noninvasive prediction. These fine perineural cues are easily attenuated by routine downsampling or overly global feature aggregation, reducing the effectiveness of conventional volumetric models. We present LoSA-Net, a localized and scale-adaptive architecture for boundary-sensitive PNI prediction in 3D MRI. Talking Neighborhood Attention (TNA) preserves nerve-aligned detail through localized self-attention with head-wise mixing, and Scale-Adaptive Feature Mixing (SAFM) modulates the receptive field using multi-scale depthwise processing. Cross-Scale Refinement and Alignment (CSRA) maintains consistency between semantic context and high-resolution boundaries across stages. In contrast-enhanced MRI scans from 168 patients with cholangiocarcinoma, LoSA-Net achieves an AUC of 0.7567 and outperforms representative convolutional and transformer baselines under matched preprocessing and optimization settings.

As mobile robots become more integrated into everyday human environments, social robot navigation is becoming essential for ensuring human comfort, safety, and trust. While reinforcement learning (RL) navigation policies provide the fast inference and reactive behavior necessary for real-time deployment, they still lack flexible semantic reasoning capabilities and often fail to generalize to complex social scenarios. Recent approaches have increasingly turned to vision-language models (VLMs) in place of RL policies to improve semantic and social reasoning in robot navigation. Nevertheless, their high computational cost and slow inference remain major barriers to real-time deployment. To overcome these limitations, we introduce HUMA (Hybrid Understanding for Multi-modal social Navigation), a hybrid architecture that dynamically balances the computational efficiency of RL policies with the deep semantic understanding of VLMs. Our approach uses a reactive RL policy to handle low-density, routine navigation tasks, while conditioning it on a post-trained high-level VLM when a human enters sensitive situations, such as the robot's proximity zone. We evaluate HUMA on the Social-MP3D and Social-HM3D benchmarks, where it achieves task success improvements of 20% and 3%, respectively, while significantly reducing personal space violations and human collisions against state-of-the-art baselines. Extensive ablation studies validate each architectural component, and real-world deployment on the Mirokaï mobile robot further demonstrates the practical viability of our approach.

Perineural invasion (PNI) is a critical prognostic factor in cholangiocarcinoma. Non-invasive prediction from 3D MRI is challenging, demanding models that efficiently capture both fine-grained details and global context. We propose the Multi-window Mixture-of-Head Attention Transformer (MMA-Former), a novel end-to-end 3D architecture featuring a Coarse-Fine Transformer (CFT) structure for parallel multi-scale feature extraction. We advance this structure by integrating a novel Window-Specific Mixture-of-Head attention (WS-MoH) mechanism. Unlike standard Multi-Head Self Attention (MSA), WS-MoH generates a representation for each 3D window and dynamically routes the entire window to specialized or common attention heads. This enables spatially adaptive feature extraction tailored to the local context of each window, enhancing specialization and reducing redundancy without increasing parameters. Evaluated on a retrospective dataset of 168 T1-weighted MRI scans, MMA-Former achieved an AUC of 0.752, outperforming other 3D architectures, including the best CNN (AUC of 0.708) and Transformer baselines (AUC of 0.681).

Existing Stochastic 3D Human Motion Prediction models are fundamentally constrained by hard-coding the skeleton kinematics, severely limiting generalization, preventing cross-dataset training, and requiring complex data retargeting. We introduce EquiFusion, the first kinematics-agnostic model to solve this bottleneck, implementing a latent diffusion model with a permutation equivariant architecture. EquiFusion treats the kinematics' connectivity as an explicit input parameter, ensuring its internal computations are inherently agnostic to joint ordering and graph structure. This novel design enables truly cross-dataset generalization to unseen kinematics and unlocks novel zero-shot directions, such as motion prediction from partial or occluded observations and targeted limb generation. EquiFusion achieves state-of-the-art results on major benchmarks, being up to 75% more compact than previous kinematics-specific methods, while achieving faster training and inference. EquiFusion thus establishes a new, flexible standard for robust human motion prediction. Model and training code are available at https://ceveloper.github.io/publications/equifusion/.

Many evaluations of model outputs rely either on contracts checkable at evaluation time or on feedback that arrives within the operating loop. We study the complementary setting in which ground truth is delayed, censored, or private, so deterministic code cannot check correctness at scoring time and must instead issue a code-owned provisional forecast. RouteCast instantiates this regime for model-generated typed strategic routes: models propose candidate routes and structured factors; point-in-time evidence, reference classes, and deterministic transformations produce a provisional forecast-ranking; later outcomes evaluate the forecast. In a retrospective venture pilot on 21 binary-outcome cases (6 positive, 15 negative), the whole-packet RouteCast score showed preliminary retrospective discrimination (AUC 0.756, 95% CI [0.471,0.980]), while a blind LLM judge reached AUC 0.678 [0.419,0.897] and an identity-exposed LLM judge reached AUC 0.761 [0.515,0.944], consistent with recognition- or outcome-related leakage risk. A preregistered decomposition ablation on the same binary subset found that converting the identical inputs into typed staged routes was indistinguishable from the whole-packet score (Delta AUC = -0.144, 95% CI [-0.471,0.176]) and from a deterministic heuristic (Delta AUC = -0.089, 95% CI [-0.412,0.278]). The pilot establishes an auditable feasibility result and exposes failure modes; it does not establish prospective calibration, causal decision improvement, route-decomposition advantage, or cross-domain validity.

Federated learning distributes data among $n$ clients, making it vulnerable to malicious attacks and data heterogeneity, which together pose challenges for robust learning. To tackle this issue, centered clipping and Huber aggregators have been exploited for Byzantine robustness. In this paper, we first demonstrate their equivalence via convex conjugate theory, and show that they can yield biased solutions in the presence of outliers, leading to failure under high data heterogeneity and a substantial fraction of outliers. Next, we propose a new robust aggregation rule that utilizes the truncated-quadratic (TQ) loss, effectively mitigating the biases of existing methods, such as centered clipping and Huber aggregators. We show that our aggregator achieves order-optimal Byzantine-robust learning under nonconvex loss functions and heterogeneous data, ultimately enhancing the reliability of federated learning systems. Additionally, we provide a robust deviation estimation strategy for TQ, demonstrating its effectiveness. Furthermore, we show that TQ maintains robustness even when only an estimate of the number of Byzantine clients is available. Finally, experimental results on MNIST, Fashion-MNIST, and CIFAR-10, indicate that our aggregator provides better robustness performance than the competing techniques.

Given a large graph, how to generate a compact summary graph that is configurable by the user and supports multiple graph queries with either no loss or with high accuracy? The ever growing size of graph datasets makes the above question on graph summarization very pertinent. Although, there are several approaches, there does not exist a configurable graph summarization method that offers high compression along with support for multiple graph queries on the summary graph with high accuracy, and allows the user to configure the summarization based on: (1) lossless or lossy summarization, (2) amount of tolerable neighborhood loss, (3) the type of loss it can tolerate, in terms of false positive edges (i.e., extra edges), false negative edges (i.e., missing edges), or neither, in both the (a) reconstructed graph and the (b) query answers. To overcome these limitations, we propose a novel graph summarization framework CGS (Configurable Graph Summarizer) that builds upon the idea of aggregating nodes with common neighborhoods. The CGS framework consists of three summarization variants, CGS-E, CGS-I and CGS-U. While CGS-E is a lossless scheme, CGS-I and CGS-U are lossy schemes that allow reconstruction of the input graph with no false positive edges and no false negative edges, respectively. To bound the graph reconstruction loss, we introduce a user-specified parameter neighborhood loss tolerance threshold, that limits the maximum loss allowed in the neighborhood of each node. This allows graph reconstruction and neighborhood query evaluation with either no loss or with bounded loss guarantees. Empirical evaluation on several synthetic and real-world graphs shows that CGS offers superior summarization than the state-of-the-art methods, and can answer graph queries with fairly high accuracy and efficiency.

We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning. For each query, the model proposes an answer using the same weights, and issues a binary self-verdict (Yes/No). A 'No' triggers a second-chance rethink; a 'Yes,' or a turn cap, finalizes the output for computing the outcome-based reward. SVR-R1 is implemented with GRPO and an asynchronous multi-turn rollout framework and needs no external supervision or auxiliary critics. We evaluate SVR-R1 on vision-language reasoning benchmarks and show that it improves accuracy by a large margin over strong standard GRPO baselines. Training dynamics show decreasing reliance on verification-fewer verification turns, yet higher test accuracy-indicating that the gap between verification and generation narrows as the policy internalizes self-correction and chooses the most confident answer via our framework. SVR-R1 bridges the less explored intersection of inference-time self-refinement and RL training for VLMs, offering a simple yet effective recipe for bootstrapping multimodal reasoning. We will open-source \textbf{SVR-R1} to facilitate future research in VLMs.

We study the problem of efficient online proportional sampling from a high-dimensional domain under a $σ$-smoothed adversary, where the sampling distribution is induced by a dynamically evolving weight function defined over a sequence of piecewise-structured partitions. This setting captures a broad range of applications, including principal-agent games (e.g., pricing and contract design), and algorithm configuration and parameter tuning. The central challenge is maintaining an efficient data structure as the induced partition grows increasingly complex over time -- naively, the number of subregions can grow as $O(t^d)$ by round $t$ in $d$ dimensions. We design a data structure that supports efficient updates and proportional sampling while avoiding the cost of explicitly maintaining this exponential growth, where the discontinuities are structured from axis-parallel hyperplanes. Under a $σ$-smoothed adaptive adversary, we prove a tight $O(\sqrt{σT})$ bound on the depth of our data structure, and an $O(\log T)$ bound under a random-order adversary -- to our knowledge, the first such results for this class of problems. We apply this framework to online learning with piecewise-structured rewards, obtaining efficient no-regret algorithms under both full-information and bandit feedback, with provable sublinear regret guarantees.

Trader-facing dynamic fees are increasingly proposed for automated market makers (AMMs), but historical data do not identify how order flow would respond: trader-facing fees do not vary, trader types are latent, and a replayed tape is not a sequential decision environment. We therefore construct a minimal closed-loop simulator in which the missing signal exists by construction: two constant-product pools repriced by an equilibrium-inspired dynamic-fee rule, fee-sensitive noise flow, and closed-form CEX--AMM arbitrage. Equilibrium is used as a closure principle, not as an object the trader learns. Against a tuned benchmark ladder of schedule, planning, lookahead, and tabular policies, a small DQN is the only evaluated valid policy whose paired improvement over tuned one-step routing excludes zero. On a reserved final block of 1{,}000 seeds with completion forced to 1.0 for every policy, it reduces implementation shortfall under every tested intra-step ordering, by $13.3\bps$ of order notional under the pre-specified agent-last ordering, and the edge is concentrated in, and learned from, dynamic-fee environments: under constant fees the paired difference is indistinguishable from zero. The result is model-conditioned counterfactual evidence about execution control in AMMs, not evidence about historical traders, equilibrium play, or deployable profit.

Standard learning rate schedules such as cosine annealing are tied to a fixed training horizon, limiting their ability to accommodate post hoc horizon extension. Warmup-stable-decay (WSD) partially addresses this issue by maintaining a long constant-rate phase before a short linear cooldown, allowing training to resume from a pre-decay checkpoint. However, its peak learning rate is still tuned based on the original training horizon and can become suboptimal when training is extended. Motivated by stochastic convex optimization, we propose WSqD (Warmup with Square-root base and linear Decay), a learning rate schedule that replaces WSD's constant stable phase with a shifted inverse-square-root base while retaining the final linear cooldown. In the stochastic convex setting, WSqD provably attains the minimax-optimal $O(1/\sqrt{T})$ last-iterate convergence rate. Importantly, its base learning rate schedule is horizon-independent, and the training horizon is needed only to determine when to begin the final cooldown. Empirically, on language-model pretraining using the SlimPajama corpus, WSqD matches or outperforms carefully tuned WSD and other baselines across multiple training horizons while reusing a single peak learning rate.

We introduce Sticky Jump Diffusions (SJDs), continuous-time Markov processes on $\mathbb R^d$ whose discrete anchors are token embeddings. In forward time, anchors release their mass at a hazard rate and the released mass diffuses in the continuous ambient space; time reversal couples a score-driven SDE with a sticky jump kernel whose rate and destination are fixed by flux balance with the forward law. We estimate the score and the per-anchor reverse hazards from a single denoising classifier via Denoising Hazard Matching, the hazard analogue of denoising score matching, with simulation-free cross-entropy training. SJD recovers masked diffusion, continuous diffusion, and hybrid diffusion as limits. Its reversal explains features that each family treats as given: the mask of masked diffusion carries no evidence about the source token because the unsticking kernel of every anchor collapses to the same absorbing point; the terminal projection of continuous diffusion is required due to the absence of atoms in its forward marginal, without which flux balance yields no reverse jumps; and the update rules of hybrid diffusion (commit rate, destination, and drift) all follow from flux balance rather than from separate design. Beyond these limits, the unsticking kernel becomes a design space: a cross-position blending corrupts each position toward a blend of its neighbors' clean values or embeddings, turning dependency structure such as spatial locality or a constraint graph into an inductive bias of the corruption itself, and improves over the identity-kernel hybrid on CIFAR-10, Text8, and Sudoku.

Physical AI systems, such as autonomous vehicles and intelligent machines, require transformer-based perception models that satisfy stringent edge latency and energy constraints. However, heterogeneous edge-GPU deployment remains limited by underutilized hardware engines and accelerator-incompatible operators, causing fragmented execution and lower throughput per watt. This paper presents Heterogeneous Frame Dispatch Scheduling (H-FraDS), a hardware-aware frame scheduling methodology for transformer inference on a recent NVIDIA edge GPU. H-FraDS routes frames across the GPU and dual deep learning accelerator (DLA) cores using fixed dispatch ratios to improve utilization under latency and power constraints. To enable scheduling, incompatible transformer components are adapted for DLA execution by reshaping tensors, approximating error function (ERF) with tanh, and replacing layer normalization with bounded tanh. The adapted model maintains a 92% F1 score, with only a 2% reduction from the original. Optical flow accelerator (OFA) is further used for inference-side optical-flow estimation. To the best of the authors' knowledge, prior work has not addressed these combined issues. Using Swin Transformer for autonomous-driving perception, H-FraDS Balanced Dispatch (1:2) achieves 125.93 FPS, a 2.36x speedup over standalone adapted-DLA execution, 4.0 FPS/W, and approximately 24 ms DLA latency, satisfying 30 FPS real-time operation; the GPU-DLA-OFA case achieves a 2.02x DLA throughput speedup.

We study the bandit-feedback version of online principal component analysis (Bandit PCA): in each round $t = 1,\dots,T$, the adversary selects a $d \times d$ symmetric gain matrix $G_t$ with spectrum in $[0,1]$ and rank at most $r$; the learner simultaneously selects a unit vector $w_t \in S^{d-1}$ and receives the reward $w_t^\top G_t w_t$. The learner receives no other feedback, and aims to minimize the regret against the best unit vector in hindsight. This problem was introduced by Kotlowski and Neu (2019), who gave an algorithm with regret $O(d\sqrt{rT \log T})$ and showed the lower bound of $Ω(r\sqrt{T/\log T})$. We improve upon both of these bounds and essentially bridge the gap between them, establishing the minimax regret of order $r\sqrt{dT}$ up to polylogarithmic factors in $d$ and $T$. The upper bound is attained by a novel algorithm, which combines online mirror descent on the spectrahedron of (real) density matrices with a multiscale exploration scheme in which the eigenspaces with different spectral magnitudes are updated at different rates. For the lower bound, we construct an adaptive adversary that refines a hidden large-reward subspace based on the learner's actions, in such a way that low regret is impossible without estimating the subspace; as a result, lower-bounding the regret reduces to studying the arising subspace estimation problem. Finally, we discuss connections of Bandit PCA with adaptive-measurement quantum tomography.

Decoding brain activity is useful for characterizing brain processes and understanding the functional architecture underlying cognition. However, the inter-individual variability in brain response patterns limits the development of decoders that generalize across individuals. A solution to this challenge is functional alignment: aligning functional data across individuals before training population-level decoders. The core issue is to strike the balance between aligning functional features and preserving the anatomical structure, while maintaining computational efficiency. We introduce a new functional alignment method for fMRI, SpectralOT, that embeds cortical geometry into Laplace-Beltrami eigenmodes along functional data to regularize the alignment.

Generative models often represent signals as dense grids of amplitudes, blurring sharp transients that are crucial for the correctness of physical signals. We introduce Singularity Space, a generative framework that represents signals through complex-plane singularities, rooted in the classical pole-residue representation of meromorphic functions. We learn a latent space of physically constrained, per-signal singularity configurations to solve an inverse problem from degraded or partial observations. The framework has three key properties: interpretability, in which each generated singularity configuration corresponds to a set of physical parameters; structural stability, which mitigates Gibbs artifacts at discontinuities; and resolution-free output reconstruction on arbitrary grids without retraining or interpolation. Our framework employs a transformer-based diffusion model that directly predicts samples at complex-plane singularity coordinates, subject to geometric constraints during sampling. As a controlled test case for sharp-feature recovery, we evaluate our framework on 1D Burgers shocks, where each shock is represented by 32 predicted singularities (an $8\times$ reduction versus a 1024-point grid signal). Our framework preserves signal structure ($\text{TV ratio} \approx 1$) under unseen test-time observation noise, achieves a $4.2\times$ lower reconstruction error in zero-shot sub-resolution generalization than a grid-based baseline, and recovers physical parameters to $10^{-4}$ absolute error in-distribution. These results suggest that singularity-based representations may provide a practical foundation for other transient-dominated signals such as speech and biomedical signals, with potential extension to higher-dimensional domains.

Identifying heterogeneous treatment effects under unobserved confounding is central in observational causal inference. In proxy models with a discrete latent confounder, prior Synthetic Potential Outcomes (SPO) [Mazaheri-Squires-Uhler '25] recover the mixture of treatment effects through recursively constructed scalar moments. We show that this sequence is one projection of a more fundamental object. Under the same population factorization assumptions, there is an exact compressed observable operator: after projecting onto the shared proxy signal subspace, the difference of two treatment-arm quotient operators is similar to the diagonal matrix of latent treatment effects. Its eigenvalues are the latent effects; its lifted left eigenvectors, after anchor normalization, recover the target-proxy feature matrix and then the latent mixture proportions. Every scalar SPO moment is a bilinear functional of a power of this operator. The resulting estimator handles overcomplete proxy systems, replaces high-order scalar inversion with finite-dimensional spectral analysis, and admits high-probability first-order perturbation bounds for treatment effects, feature rows, and simplex-projected mixture weights.

Large language models exhibit remarkable emergent behaviors, yet the physical mechanism governing their collective dynamics remains poorly understood. Cognitive Field Theory predicts that learning reorganizes the time-scale density of states (TDOS) through the infrared accumulation of slow relaxation modes, thereby enhancing the memory self-energy, reducing the cognitive forgetting gap, and strengthening the collective susceptibility. Using publicly available Pythia language models, we extract relaxation spectra directly from Transformer layer Jacobians throughout training, network depth, and model scale, allowing the TDOS, memory self-energy, forgetting gap, memory kernel, and infrared critical exponent to be measured quantitatively. The measurements reveal progressive infrared accumulation of slow relaxation modes, producing an approximately flat infrared TDOS with \( ρ(λ)\simλ^{-0.1} \) and scale-free memory kernels \( K(t)\sim t^{-1}. \) The memory self-energy exhibits a pronounced transient maximum during early optimization before relaxing toward a metastable near-critical regime, corresponding to the smallest cognitive forgetting gap and the largest collective susceptibility predicted by Cognitive Field Theory. These observations provide quantitative experimental evidence that Transformer dynamics are governed by infrared collective organization. The reproducibility of the same dynamical behavior across training, network depth, and model scales suggests that infrared slow-mode organization represents a universal collective principle of Transformer dynamics.

Learning temporal logic specifications from system demonstrations is essential for tasks such as formal verification and controller synthesis, especially in safety-critical domains. Existing approaches typically assume demonstrations are correct or only affected by misclassification errors. In practice, however, system traces are often uncertain or incomplete due to sensor faults, measurement errors, or data loss. We present a framework for learning minimal Linear Temporal Logic (LTL) formulas from demonstrations with uncertainty. Our approach models uncertainty via Hamming distance to generate possible estimates around each observed trace, which are grouped with constraints requiring that at least one trace per group is consistent with the learned formula. Our problem is then reduced to an equivalent Pseudo-Boolean Optimization. We evaluate our method against state-of-the-art LTL learning approaches and show that it recovers specifications that more closely align with ground-truth formulas under uncertainty.

We introduce NAILS (Normative Alignment of Recommender Systems via Internal Label Shift), a simple and scalable method for aligning recommendation outputs with target distributions over item-level attributes, such as categories. Recommender systems optimized solely for user engagement often fail to satisfy broader normative objectives, including fairness, diversity, and editorial values. NAILS modifies the user-conditional item distribution to induce a specified marginal distribution over attributes while preserving the preferences learned by an existing recommender system and requiring no model retraining. We formulate this problem as a form of label shift applied internally within a hierarchical classification framework. By adopting a stakeholder-centric perspective, NAILS enables recommendation outputs to be aligned with global normative objectives. Empirically, we show that NAILS consistently improves attribute-level alignment with minimal impact on user engagement, providing a practical mechanism for value-driven recommendation.

In the age of large language models, Natural Language to SQL (NL2SQL) translation remains an open problem with many useful applications. We explore interactions between several NL2SQL pipeline extensions to inspire development of more lightweight models. Specifically, we integrate the NatSQL intermediate representation, include a preprocessing step and a fine-tuning step based on synthetic data, and develop a novel reranker model to improve SQL selection in the final beam. We perform an ablation study supplemented by a Shapley analysis of these different components integrated with two backbone architectures, SmBoP and RASAT. We find that simply combining all of them does not lead to best results, but that their impact depends on their interactions with the baseline system, as well as each other.

We present ZoRRO (Zero-Weight Personalized Recommender System), a zero-weight, training-free framework for personalized news recommendation designed for scalable real-world deployment. ZoRRO outperforms strong neural baselines in offline ranking evaluations and achieves click-through rate performance in online A/B testing that is nearly on par with a state-of-the-art deep learning model, while operating more than 600 times faster. Our experiments reveal gaps between offline and online performance and demonstrate that models with similar click-through rate outcomes can produce markedly different recommendation distributions, thereby influencing the overall news flow. These findings position ZoRRO as a practical and efficient solution for large-scale news recommendation and highlight the importance of evaluating recommender systems using metrics beyond accuracy alone.

Small-data inverse design is challenging in engineering informatics when observations are heterogeneous, mixed-type, and constrained by physical relations among design variables. This work proposes a topology-aware surrogate framework guided by an Incremental Transformer (INCRT) for physics-constrained inverse design, applied to geopolymer mixture design. The method integrates intrinsic-dimensionality analysis, mixed-variable design-space representation, tabular surrogate prediction, INCRT-based manifold rationalisation, and constrained inverse optimisation. Using a public benchmark of fly-ash and slag-based geopolymer concrete mixtures with compressive-strength and carbon-emission targets, the high-dimensional design space proves strongly redundant, organising around fewer effective mixture regimes. Compressive strength requires nonlinear tabular surrogates, while carbon emission is largely determined by composition and well recovered by regularised linear models. INCRT thus acts not as a replacement for tabular predictors but as a rationalisation layer providing prototype regimes and a manifold-support score for inverse design. Three strategies are compared: unconstrained surrogate optimisation, physics-constrained optimisation, and topology-aware physics-constrained optimisation. Unconstrained optimisation can match target strength but may yield physically invalid or off-manifold candidates; physics-only constraints do not always ensure data support. The topology-aware strategy yields candidates balancing target compliance, carbon reduction, physical admissibility, and proximity to the learned feasible manifold. The framework aims not to replace experimental validation but to support screening of credible candidate mixtures from small, mixed, physically constrained engineering datasets.

Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interfaces (GUIs). Among these, the terminal command line provides a text-based, general-purpose interface, covering tasks from system operations to data science and machine learning. However, scaling terminal-agent training remains challenging, as it requires diverse and coherent task instructions, executable environments, and reliable verification, while lacking naturally grounded supervision data. In this work, we propose SETA, a scalable framework for generating verifiable terminal environments for reinforcement learning (RL). The framework consists of two pipelines sharing a unified verification mechanism: SETA-Synth converts diverse sources into standardized RL environments, and SETA-Evol further expands from existing environments with adaptive control of difficulty and diversity. Together, we construct and release SETA-Env, the largest open-source verifiable terminal RL dataset to date, containing over 4,500 environments. We evaluate our dataset by training Qwen3-8B with GRPO on SETA-Env, achieving 12% pass rate on Terminal-Bench 2.0, the best reported result for an RL-trained model at the 8B scale. We further observe gains on DeepSeek-V4-Flash under the same terminal agent harness, with pass@1 on Terminal-Bench 2.0 improving from 40% to 43% and pass@5 improving from 54% to 58%. These results demonstrate that SETA- Env provides high-quality training environments for terminal agents and serves as a valuable resource for advancing research on terminal-based agent learning.

Machine learning interatomic potentials (MLPs) have revolutionized atomistic modeling, offering the potential to replace traditional methods like Density Functional Theory (DFT). However, inference time of MLPs is orders of magnitude slower than that of classical force fields, hindering real-world applications for biomolecular systems that require timescales of microseconds and beyond. Implicit solvent MLPs can address this issue, but are faced with data challenges associated with coarse-grained modeling. Consequently, previous approaches relied on empirical force field data, thereby inherently limiting the MLP's accuracy. Here, we introduce the Transferable Water Implicit Network (TWIN), an implicit water MLP parametrized entirely by an Equivariant Graph Neural Network and trained solely on ab initio and experimental labels. We demonstrate TWIN's transferability across drug-like molecules, peptides, and proteins, achieving excellent results on ab initio and experimental crystallographic and NMR benchmarks, consistently outperforming previous machine-learning-based implicit solvent or coarse-grained models. Furthermore, TWIN closely matches DFT-based explicit solvent MLPs while providing a two-order-of-magnitude faster timestep evaluation, paving the way for efficient ab initio-level modeling of biomolecular systems in aqueous environments.

We extend, in Isabelle/HOL, the deep-and-shallow embedding methodology of our prior work from propositional to first-order modal logic (FML) with constant-domain Kripke semantics. Three embeddings of FML into classical higher-order logic (HOL) are provided side by side: a deep embedding, a heavyweight maximal-shallow embedding, and a lightweight minimal-shallow embedding. The minimal-shallow embedding is presented as an Isabelle/HOL locale, parametrised by an accessibility relation, a world-indexed interpretation, a universe of worlds, and a variable assignment; the locale form admits a global faithfulness theorem, stating that quantifying over all minimal-shallow interpretations recovers exactly deep validity. A central technical contribution is a mechanisation, for FML under constant-domain Kripke semantics, of the (countable) downward Löwenheim-Skolem theorem, which underpins the automation of our faithfulness proof between the deep and minimal-shallow embeddings. Deploying it inside an extension of the minimal-shallow locale resolves the surjectivity problem that arises against an uncountable domain of individuals -- where the locale's variable assignment, having countable domain V = nat, cannot be surjective onto the domain -- and thereby yields faithfulness over the full domain. Since prior work treats only the propositional fragment, we develop here the substitution machinery (free/bound-variable predicates, the fresh-variable function, capture-avoiding substitution, alphabetic renaming, the substitutability predicate, the substitution lemma, and size-based induction principles) needed for the first-order quantifiers.

AI agents are evolving from answer engines into persistent teams that use tools, delegate work, learn from experience, and modify the artifacts that shape their future behavior. The defining question for deployment is no longer merely what agents can do, but who controls what they are allowed to become. We introduce logos, a pluggable layer for self-evolution and governance that strengthens existing multiagent frameworks rather than replacing them. logos compiles heterogeneous multimodal inputs, including documents, images, audio, tables, databases, APIs, and human instructions into versioned agent packs containing agents, tools, knowledge, tests, permissions, and policies. During operation, it transforms agent activity into portable, auditable event traces and applies fail-closed verification across frameworks and backends. Every learned prompt, memory, skill, tool, role, or workflow remains an untrusted release candidate until held-out execution evidence, human-controlled policy, and explicit authorization permit its promotion. This architecture enables "verifiable human-agent loop engineering": agents can act, ask, learn, and propose improvements, while humans can steer objectives, permissions, approvals, and irreversible actions without interrupting continuous operation. logos provides a living logic for accountable automation. Agents may evolve at machine speed, but only evidence and human authority can close the loop.

Contemplative traditions have long guided ethical behavior and prosocial interaction, and recent work suggests that contemplative principles (e.g., mindfulness, compassion, non-dual reasoning) may offer a promising paradigm for aligning large language models (LLMs), improving cooperation and reducing ethical violations in LLM outputs. However, as new models, evaluation metrics, and benchmarks emerge rapidly, it remains challenging to systematically assess whether and how contemplative principles enhance LLM alignment across diverse and evolving scenarios, and existing approaches are often ad hoc and fail to generalize. We present a modular, extensible evaluation framework, initially targeted at the mental health domain, that enables seamless integration of new models, metrics, and benchmarks through a reusable pipeline. The framework currently reproduces existing state-of-the-art results and supports systematic cross-evaluation by flexibly mixing and matching models, metrics, and benchmarks, enabling fair comparison and deeper insight. Its plug-and-play prompting module offers a principled pathway for incorporating ethical perspectives such as contemplative principles, allowing domain experts to define alignment criteria without requiring technical expertise. Although initially focused on mental health, the framework is domain-agnostic and extends naturally to areas such as decision-making, moral reasoning, and human-AI collaboration. By bridging computational evaluation with human-centered ethical reasoning, this work lays the groundwork for interdisciplinary research spanning cognitive science, behavioral economics, philosophy, and system design, toward robust, trustworthy, and socially beneficial human-AI ecosystems.

We study the population gradient flow of an infinitely wide two-layer neural network learning a misspecified single-index model in high dimension. The two layers are optimized jointly, with a perturbative parameter tuning the relative training speed between the first and second layer. This setting was considered by Berthier, Montanari and Zhou in \cite{berthier2024learning}, who conjectured a hierarchical learning scenario with explicit timescales as the second layer is trained faster than the first. In this paper, we prove that the constant and linear components of the hidden link function are indeed recovered within the predicted timescales, at sharp explicit thresholds. We then analyze the onset of learning of the quadratic component and show that the components learned at earlier stages continue to influence the dynamics in an essential way. Our proof is based on quantitative approximation results for singularly perturbed flows evolving near a manifold defined by integral constraints. At a phenomenological level, we also show that the empirical measure of the weights displays singular behaviour when reaching the quadratic component of the hidden link, with a small fraction of neurons growing significantly while the remaining ones rearrange to preserve the components already learned.

The rise of Software Engineering (SE) agents, i.e., LLM-based agents that can understand large codebases and carry out engineering tasks with limited human intervention, has been marked by rapid advances and adoption, but little is known about how developers build these systems in practice: existing studies mine repositories or examine deployment, but few investigate how SE agents are constructed. Through semi-structured interviews with 20 practitioners from 12 organizations and an online survey of 80 practitioners, this paper is the first to study how SE processes are changing in the development of SE agents and what challenges developers face. We find that as implementation becomes cheaper, bottlenecks shift rather than disappear: long-standing non-coding work such as requirements, coordination, review, and deployment becomes more visible, while reviewing and evaluating agent output becomes new and central. We characterize a seven-stage workflow and a shift toward evaluation-driven development, in which evaluation steers iteration and specifications become versioned artifacts read by both humans and agents. We further identify six challenges that teams face, together with the practices they adopt to address them, including unreliable evaluation signals, comprehension debt as code outpaces understanding, and behavioral changes introduced by provider-side model updates.

Quantization is a powerful strategy to build capable and resource-efficient large language models (LLMs) by reducing the bitwidth of the parameters. While quantized LLMs achieve state-of-the-art performance on unperturbed inputs using standard predictive metrics, their performance on perturbed inputs, measured using reliability metrics, remains underexplored, despite its importance for reliable deployment. To address this gap, we first conduct a comprehensive reliability evaluation of quantized LLMs consisting of three key components: (1) Uncertainty: We assess the trustworthiness of LLMs quantized to 2, 3, 4, and 8 bits using six different quantization methods, employing established uncertainty metrics. (2) Calibration: We assess how well-calibrated the uncertainty estimates of quantized models are across model scales and bit precisions. (3) Robustness: We design character-level and word-level input perturbations to evaluate the reliability of quantized models under semantically-preserving variations in the inputs that arise in real-world applications. Second, we characterize how reliability scales with the total number of model bits. Our study reveals that while the performance scales monotonically with the total number of bits, the reliability scalings are nonlinear. A reliability peak occurs for 4-bit quantized models, indicating that quantizing moderately sized models offers the best reliability-efficiency trade-off. Additionally, our empirical findings reveal that quantization enhances the robustness of LLMs to natural input perturbations.

Diffusion models faithfully reproduce their training distribution, but also inherit its imbalances and leave rare or under-represented modes hard to reach. A natural inference-time remedy is to sample from the high-temperature target $p^{(γ)}_0(x) \propto p_0(x)^γ$ for $0 < γ< 1$, which flattens dominant modes and lifts rare ones. However, naive score scaling while correctly reweighting modes also inflates the per-mode variance, breaking the reverse diffusion process and degrading sample quality. We introduce variance-corrective time shifting, a training-free fix that queries the network at a shifted timestep and scales the resulting score by $γ$, canceling the variance inflation while preserving the mode reweighting. The correction turns simple temperature sampling into a practical diversity knob for pretrained diffusion and flow-matching backbones with no retraining, and we demonstrate consistent gains at minimal cost to sample quality and condition fidelity across DiT, Stable Diffusion and Motion Diffusion models. We further show that the timing of the temperature intervention enables coarse-to-fine control: high-noise stages drive compositional diversity across modes, while low-noise stages drive local appearance variation under a fixed composition.

Frontier language models are increasingly evaluated on biomedical benchmarks, but two problems undermine most published evaluations: legacy benchmarks are near-saturated, and open-ended responses are graded by other language models. We evaluate Claude Fable 5, Anthropic's most capable publicly available model, across eight biomedical benchmarks, four text and four multimodal, using deterministic scoring against fixed answer keys throughout. We include two Claude predecessors and GPT-5 as baselines. Refusal is tracked as a distinct outcome in every result table. That decision produces the paper's central finding. Fable 5 refuses between 8.0% and 99.4% of questions depending on the benchmark, a pattern absent in both predecessors and in GPT-5. Once refused items are excluded from the denominator, Fable 5's accuracy exceeds or meets every other model on every benchmark in this study. We identify two distinguishable refusal patterns: one concentrating in basic-science and mechanism content across MedQA and MedXpertQA MM, confirmed independently on two benchmarks using each benchmark's own category labels; and a separate disease-domain pattern on RareBench, where inborn metabolic disease presentations are refused near-universally while adult-onset autoimmune presentations are not. The primary constraint on Fable 5's biomedical usefulness is willingness to engage, not capability once it does.

Reinforcement learning for large language models (LLMs) typically relies on trust-region masks to stabilize off-policy updates. The dominant PPO-style approach uses the sampled-token importance ratio for two criteria: a proximity criterion, which asks whether the policy has moved too far from the behavior policy, and a direction criterion, which asks whether the update pushes it farther away. Recent work DPPO improves the proximity criterion by replacing PPO's ratio-based test with a probability divergence between the behavior and training policies. However, its direction criterion is still inherited from PPO. A token can be masked only when the sampled-token importance ratio moves away from one. We observe that this ratio-based direction criterion is a single-sample proxy that can disagree in sign with the change of the divergence that defines the proximity criterion. We therefore propose the predictive divergence mask, which asks whether the next policy-gradient step will increase or decrease the same divergence used by the trust region. For the discrete softmax policies used in LLM RL, we derive this prediction in closed form. Because production rollout engines expose only a truncated (top-K) view of the vocabulary, we develop two lightweight top-$K$ estimators for this prediction. Detailed analysis shows the divergence-based direction is better aligned with the realized change of the divergence than the sampled ratio, and the resulting masks improve RL training across model scales and precision settings.

Computational social science increasingly relies on automated preprocessing pipelines -- speaker diarization, ASR transcript cleaning, sentence segmentation -- to convert raw media into analyzable text. When these pipelines produce different outputs from the same input, two distinct sources of instability can arise: the preprocessing pipeline itself (diarization method, segmentation rules) and the downstream measurement instrument (LLM annotation vs.\ keyword lexicon). Using 256 YouTube interviews across 41 public figures from five domains, we compare two speaker-diarization pipelines and two measurement methods, all targeting the coupling between affective valence and epistemic modality. We find that (1) preprocessing pipeline sensitivity is concentrated in speakers with limited video samples (N $\leq 5$); for the four best-sampled speakers (N $\geq 16$), the mean absolute pipeline-induced change in $r(\text{neg}, \text{emph})$ is only $0.13$; (2) cross-method disagreement is larger and more systematic -- the LLM and keyword-lexicon methods assign opposite coupling directions to several well-sampled speakers, even within the same preprocessing pipeline; and (3) aggregate valence proportions are highly stable ($|Δp(\text{neg})| < 6$pp) regardless of pipeline or method, masking both sources of instability. The contribution is a diagnostic framework that separates pipeline effects from measurement effects: researchers studying cross-dimensional relationships in interview data should verify that their conclusions are robust to both sources of variation, with particular attention to measurement method choice.

Community-driven scientific pipeline ecosystems are increasingly important for reproducible data-intensive research, but their sustainability depends on more than workflow engines, templates, and testing infrastructure. It also depends on how communities maintain pipelines, integrate contributions, and support users across heterogeneous execution environments. This paper presents a cross-platform empirical study of maintenance and support in nf-core, a large ecosystem of standardized Nextflow pipelines. We analyze 15,760 GitHub issues, 35,411 GitHub pull requests, and 895 Seqera Community Forum discussions to examine what maintenance and support concerns arise, how they differ across artifact types, which factors are associated with resolution outcomes, and how problems and solutions flow between repository-centered and community-centered spaces. We find that issues primarily capture repository-level problem reporting and maintenance coordination; pull requests capture implementation, review, testing, dependency, and template-update work; and forum discussions capture user-facing support around execution failures, containers, cloud and HPC environments, MultiQC reporting, and Nextflow usage. Resolution outcomes are associated with actionability, coordination, and diagnostic evidence. Issue closure is linked to assignees, comments, milestones, bug labels, error mentions, and version information. Pull request integration varies by author role, automation type, draft status, checklists, linked issues, and review routing. Forum accepted answers are more likely when discussions include code blocks, sustained interaction, and concrete technical evidence, while cloud, HPC, and workflow-semantics questions are harder to resolve. Cross-platform analysis reveals strong repository-internal traceability within GitHub, but limited explicit linkage between forum discussions and repository artifacts.

Multi-agent ensembling multiplies active parameters and inference cost without answering three basic questions: which agents to consult, how deeply a query should traverse a hierarchy of agents, and when inter-agent communication is worth its cost. We present GRADE (Gated Routing and Adaptive Depth for Efficient Reasoning), a hierarchical multi-agent system in which four lightweight learned gates jointly govern agent selection, hierarchy depth, inter-agent communication, and branch pruning. Training uses CoGRPO (Collaborative Group-Relative Policy Optimization), a novel critic-free recipe that adapts GRPO to multi-agent hierarchies and assigns a shared advantage signal to every gate and agent that participated in a rollout. Agent models are drawn from a hot-swappable Expert Registry; per-agent calibration maps allow experts to be replaced at inference time without retraining. At $\sim$17B average active parameters, GRADE outperforms all baselines on GSM8K, MMLUPro, and GPQA, surpassing the strongest baseline by 4.8 points on MMLUPro at half the active compute. On AIME-2025, where model depth dominates, GRADE remains competitive to existing frameworks. Ablations isolate the hierarchy and masked cross-attention as the largest contributors to accuracy, and show that per-agent calibration is necessary for safe hot-swapping.

Automated evaluation is essential for scaling generative 3D systems, where exhaustive human review is costly and slow. However, the reliability of an automated judge depends on the entire evaluation pipeline, not only the underlying vision-language model (VLM), but also how assets are rendered, what visual evidence is provided, how the task is specified, and how human reference labels are constructed. We introduce 3D-DefectBench, a benchmark and framework for systematic analysis of VLM-based 3D defect detection pipelines. It complements holistic ratings and pairwise preferences with nine fine-grained binary defects spanning geometry, texture, and prompt adherence, providing actionable diagnostics for generator development and judge evaluation. Using a balanced factorial design, we vary four pipeline factors, VLM, camera protocol, visual input, and prompt schema, across 84 inference designs and approximately 3.2 million scored defect decisions, followed by staged validation on a broader set of frontier models. Model choice is the largest determinant of agreement with human labels, but the remaining factors also affect performance, interact with model selection, and can change the best configuration. Within the evaluated design space, a compact six-view RGB protocol performs comparably to denser multi-view settings and inputs augmented with depth or surface normals, making it a strong cost-effective default. Under this standardized pipeline, the best of 12 VLM judges still lag behind trained human labelers, while texture agreement drops sharply when expert-consensus labels are replaced by noisier silver labels. These findings show that automated judges should be evaluated as complete pipelines and calibrated across human reference regimes, rather than benchmarked only as standalone models. We release labels, prompts, predictions, and Croissant metadata on Hugging Face.

Opinionated text - spanning product reviews, hotel feedback, and social posts - captures rich signals about user experiences, preferences, and concerns. However, the scale, redundancy, and imbalance of such corpora make it challenging to analyze opinions effectively, particularly when the goal is to generate summaries that remain faithful to the diversity of viewpoints expressed. This paper presents a framework that preserves semantics in LLM-based opinion summarization while minimizing token usage. We combine multidimensional classification (e.g., sentiment, topics) with a family of stratified sampling strategies to select compact yet representative subsets of opinions before prompting the LLM. Tailored prompts then produce balanced summaries that surface the salient aspects expressed in the opinions (e.g., strengths and weaknesses of products/hotels). Experiments on Amazon product reviews, Tripadvisor hotel reviews, and X/Twitter posts demonstrate that our method significantly reduces token usage and computational cost while consistently outperforming traditional AI-based and standard LLM summarization baselines in terms of content coverage, balance, and semantic preservation.

Indoor spatial understanding remains a fundamental challenge for intelligent systems operating in physical environments. Traditional RFID localization techniques typically estimate positions of tags using signal strength measurements but fail to capture higher-order spatial relationships between objects and infrastructure. Recent work on RFID and wireless indoor localization has increasingly emphasized robust learning under noisy propagation, while recent graph-based localization methods demonstrate the value of relational modeling over isolated samples. This paper introduces a graph-based learning framework that leverages Graph Neural Networks (GNNs) to infer spatial geometry from RFID observations. Rather than predicting isolated coordinates, the proposed system models relationships between RFID readings, antennas, and physical structures within an indoor floorplan. This framing is aligned with recent graph-based indoor positioning and graph construction literature, where topology is a first-class source of information for downstream inference. The approach integrates signal strength data, floorplan semantics, and spatial constraints into a graph representation where nodes correspond to RFID observations and edges encode proximity and contextual relationships. A GNN is then trained to predict geometric patterns such as linear trajectories, rectangular bounding regions, and movement paths of objects in space.

Evaluating LLM agents in hidden-information multi-agent settings is hard: final outcomes are high-variance and rarely reveal why an agent decided as it did. We study this in a 9-player Werewolf environment where agents act under strict, code-level information isolation, and we build an auditable framework that maintains an external belief state over hidden roles, logs belief updates and belief-action deviations as structured evidence, and supports a defensive offline improvement loop that reviews bad cases before any strategy change. Across 1,080 frozen games spanning belief-disabled, active-belief, kernel-ablation, camp-restricted, consumption-policy, and high-load arms, and including a seed-paired A0/A1 comparison, the active-belief condition is associated with substantially better good-side outcomes: in the 200-seed A0/A1 comparison the good-side win rate rises from 0.205 to 0.390 (paired McNemar $χ^2 = 16.4$, $p < 0.001$), with fewer irreversible witch-poison errors. We do not, however, attribute this shift to belief content. Direct action-belief consistency is low ($\approx 0.21$), and giving belief only to the werewolves helps the good side more than giving it only to the good side, which argues against a simple holder-benefit account; we therefore report the effect as an association and treat its mechanism as unresolved. The contribution is the audit framework itself: it makes the effect measurable, exposes low direct action-belief consistency, rejects an unreliable forced-consumption intervention with evidence, and separates strategy effects from load confounds. We accordingly position external belief in high-noise hidden-information games primarily as an auditable cognitive baseline that also carries decision-relevant signal, turning opaque agent behavior into replayable evidence for safer, controlled iteration.

AI engineering is shifting from passive text generation by large language models (LLMs) to agent-driven task execution, creating new reliability challenges for long-horizon tasks under resource constraints and environmental uncertainty. Conventional error-elimination optimization strategies fail to address cumulative error propagation. This paper proposes Distributed Agent System (DAS), a device-edge-cloud framework for fault-tolerant collaboration among heterogeneous agents. We redefine agent reliability as system-level fault tolerance rather than single-turn zero-error accuracy, and present a two-layer fault-tolerance architecture: single-agent execution reliability via fault-tolerant alignment, and cross-agent communication reliability via semi-formal language protocols. This framework provides a practical engineering pathway for reliable heterogeneous embodied agents collaboration in industrial scenarios.

Deep generative models are increasingly used as simulators for downstream decision-making under data scarcity, but in risk-sensitive applications their usefulness depends on rare adverse scenarios rather than typical samples. Standard generative objectives prioritize bulk distributional fidelity, leaving low-probability tails vulnerable to localized optimization noise and making tail-dependent functionals unstable under finite simulation budgets. We introduce Diachronic Sample Integration (DSI), a test-time inference framework that ensembles generated samples across checkpoints from a stochastic training trajectory. DSI targets a checkpoint-mixture distribution that averages checkpoint-specific tail fluctuations rather than relying on a single brittle endpoint. We formalize this mechanism through a finite-budget bias-variance theory. Empirically, across multivariate synthetic processes and high-frequency trading data, DSI substantially reduces tail-estimation error compared to single-checkpoint baselines under fixed simulation budgets, outperforming standard diffusion and state-of-the-art tail-aware baselines without modifying the generative objective.

The problem of constrained online convex optimization is considered, where at each round, once a learner commits to an action $x_t \in \mathcal{X} \subset \mathbb{R}^d$, a convex loss function $f_t$ and a convex constraint function $g_t$ that drives the constraint $g_t(x)\le 0$ are revealed. The objective is to simultaneously minimize the static regret and cumulative constraint violation (CCV) compared to the benchmark that knows the loss functions and constraint functions $f_t$ and $g_t$ for all $t$ ahead of time, and chooses a static optimal action that is feasible with respect to all $g_t(x)\le 0$. Currently, the best known algorithm is OGD+Projection algorithm of [Vaze and Sinha, 2025] that has simultaneous regret of $O(\sqrt{T})$ and CCV of $O(T^{1/3})$ for $d=2$ [Balasundaram et al., 2026], and simultaneous regret of $O(\sqrt{T})$ and CCV of $O(\sqrt{T})$ for any $d$ [Sarkar and Sinha, 2026]. In this paper, we show that the CCV of the OGD+Projection algorithm is $Ω(T^{\frac{d-1}{2d}})$. This is the first such lower bound result.

Quantifying abstractiveness in generated summaries is essential for evaluating summarization models beyond surface-level metrics like ROUGE. We introduce Reference Abstraction (RA), Summary Abstraction (SA), and Abstraction Ratio (AR) -- a set of principled heuristic metrics that measure how much a summary diverges from extractive copying of the source text. The formulation uses the harmonic mean of document lengths modulated by a cubic non-overlap factor, yielding dimensionally consistent, bounded output with non-linear sensitivity to the extractive-abstractive boundary. Evaluation on 100 XSUM documents across four summarization models (BART-large-cnn, Pegasus-xsum, DistilBart, MT5-small) demonstrates that the metrics successfully discriminate between extractive models (SA ~ 0.12-0.26) and abstractive models (SA ~ 0.96-1.77), and that the Abstraction Ratio identifies summaries requiring manual evaluation for potential hallucination. Code and results are available at https://github.com/katweNLP/AbstractionStudy.

On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxically degrades downstream performance. In this paper, we systematically investigate this pathology and identify a severe optimization trap we define as \textbf{Thinking Collapse} -- a sharp decline in the model's native intermediate reasoning behavior, measured by epistemic-token density (ET per 1k). Through entropy-based gradient masking and token-level target analysis, we show that this collapse is triggered by aggressive teacher gradients at high-student-entropy decision forks, where student epistemic tokens are frequently suppressed into teacher non-epistemic targets and are highly concentrated in high pointwise student-teacher divergence regions. To resolve this optimization pathology, we propose \textbf{Adaptive Dual-Perspective OPSD (AD-OPSD)}, a robust control framework that dynamically moderates the self-distillation objective. AD-OPSD selectively anchors high-suppression-risk sandboxed tokens to a reference prior derived from the frozen base model via an asymmetrical pointwise divergence gate, preserving native thinking capacity while retaining OPSD's error-correcting power. Extensive experiments across competitive mathematical benchmarks show that AD-OPSD improves over standard OPSD by up to \textbf{+4.1\%} absolute average accuracy across diverse model scales and datasets. Further analysis demonstrates that AD-OPSD mitigates thinking collapse and generalizes robustly to different post-training paradigms.

Graph neural networks (GNNs) are increasingly deployed in real-world applications where distribution shift is un-avoidable. However, how such shifts affect model calibration, defined as the agreement between predictive confidence and actual accuracy, remains poorly understood, and existing graph calibration methods typically rely on labeled validation data from the deployment distribution. In this work, I present the first closed-form theoretical characterization of GNN calibration under distribution shift. I show that calibration is governed by a single scalar quantity that explicitly depends on structural changes between the source and target graphs, as well as feature quality. This characterization precisely identifies when a model becomes over-confident, under-confident, or remains calibrated, and directly yields the optimal temperature scaling strategy. I further extend the analysis to graph convolutional networks with symmetric normalization, multi-class classification, and covariate shift, and derive a theoretical upper bound on the expected calibration error. My analysis also reveals that, under homogeneous distribution shift, a single global temperature is theoretically optimal, providing a principled explanation for why more complex node-wise recalibration methods offer no additional benefit. Building on these theoretical insights, I propose STAC, a source-free, label-free calibration method. Experiments on synthetic benchmarks demonstrate substantial calibration improvements, while evaluations on five real-world graph datasets show that reliable calibration without target labels remains challenging despite the strong predictive power of the theory.

Understanding which parameters are influential in Large Language Models (LLMs) is central to improving their efficiency, reliability, and interpretability. We introduce Weight-Adjusted Gradients (WAG), a simple yet effective approach for estimating parameter importance that explicitly captures the interaction between model weights and first-order gradient information and identifies parameters that disproportionately influence model behavior, such as those responsible for collapse phenomena in LLMs. Across a range of models and settings, we show that WAG surfaces a tiny but critical subset of parameters whose modification leads to dramatic degradation in performance, a failure mode that existing importance metrics overlook. These findings reveal a previously underexplored interplay between weights and gradients, suggesting that parameter importance cannot be fully understood through either signal alone. The surprising effectiveness of WAG points to fundamental structural properties of trained networks and motivates new open questions about the role of zeroth-order and first-order information in deep learning. We demonstrate the practical utility of WAG across multiple applications, including expert allocation in mixture-of-expert architectures, parameter-specific unlearning, mixed-precision quantization, and layer selection for knowledge editing. Our results position WAG as a unified approach for analyzing, debugging, and controlling LLMs, and opens new directions for principled model-level interpretation.

Reinforcement learning is usually introduced through the Bellman update, yet the equation often remains abstract to undergraduates: they watch policy arrows converge but rarely observe how each value is computed or why an action is chosen. We present Q-Learning Lab, a single-file, browser-based, bilingual (Thai/English) tool for teaching tabular Q-learning that requires no installation. Beyond the usual gridworld visualization - color-coded Q-values and policy arrows on a $5 \times 5$ world - the tool exposes a live Bellman-substitution panel showing the numeric update at every step, and logs each transition, including the full pre-action Q-row, the greedy-versus-random decision under $\varepsilon$-greedy exploration, and wall-collision events, into an exportable trace. The central contribution is a learn-export-analyze loop: learners run their own agent, export the complete trace as CSV, and analyze it themselves, producing learning curves, value heatmaps, and visitation maps, turning a passive demonstration into a source of learner-generated data for reflective inquiry. We validate the tool without human-subject data through three complementary evaluations: (i) correctness of the learned values and policy against a value-iteration ground truth on the identical MDP; (ii) hyperparameter sweeps over $α$, $γ$, and $\varepsilon$ showing that every pedagogical claim the tool makes is reproducible; and (iii) a reward-editing study that uses the ground-truth optimal policy to separate two behaviorally identical but diagnostically opposite failure modes - an exploration failure versus genuine reward misspecification - that a single edited reward can produce. We also compare the tool against existing gridworld visualizers, describe its grounding in learning-by-doing pedagogy, and include a 50-minute lesson plan. The tool and all experiment code are openly available.

Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content: false text and misleading images from corrupted metadata, entity swaps, typographic overlays, semantic edits, adversarial patches, blends, or style transfer. We introduce QIMG-7, a controlled benchmark for multimodal retrieval pollution in multi-sentence factual QA, spanning four datasets, seven image-attack families, and 16 paired clean/polluted regimes, for 1,760 evaluation rows per method. Across four generator/gate stacks, naive multimodal fusion is brittle: in the main gpt-4o-mini stack, Full-MM support drops from 0.908 with clean text to 0.490 with polluted text, often making Parametric fallback safer than retrieval. We propose source-aware trust resolution (SATR), a training-free approach that compares Parametric, Text-only, and Full-MM candidate answers and selects among candidate answers or falls back based on source reliability. The Field-Selector variant achieves the best balanced score, 0.816, improving over Full-MM by 11.7 points and over the Cascaded Router by 2.7 points. Ablations show that, in this text-first setting, explicit text-reliability modeling is the dominant driver of these gains. Overall, in text-first factual QA with multimodal retrieval conflict, our results support selective trust rather than unconditional fusion. Artifacts are available at https://github.com/SaadElDine/Trust_Before_Fusion.

In open-domain multi-hop question answering (QA), LLM-based search agents offer a promising approach to knowledge-intensive QA by combining retrieval with reasoning. Existing methods mainly improve open-domain multi-hop QA through reasoning paradigms, retrieval interaction, and search strategy optimization. However, using multiple search trajectories introduces a challenging final answer selection problem. Different trajectories may support different candidates, and the retrieved information can be heterogeneous, redundant, incomplete, or conflicting. Directly comparing raw trajectories exposes the verifier to noisy and unaligned content, while comparing answer strings ignores the evidence supporting each candidate, making reliable final selection difficult. To address this challenge, we propose STEC, an evidence compression framework for final answer selection in multi-hop QA. STEC selects the final answer from the existing candidate set through two mechanisms: (1) Answer-Level Evidence Compression, which groups trajectories by normalized answer identity and converts each answer group into a candidate-specific evidence representation; and (2) Evidence-Guided Answer Verification, which compares these representations and selects the final answer from the candidate set. The design shifts final selection from raw trajectory comparison to candidate-level evidence comparison. We evaluate STEC on four open-domain multi-hop QA benchmarks against representative baselines. Experimental results show that STEC performs best overall among the compared methods, and ablation results provide evidence that answer-level evidence compression contributes to final answer selection.

Numerical integration is a cornerstone of various scientific computing applications, such as engineering simulations and model evidence computations in probabilistic machine learning. Bayesian Quadrature uses Gaussian process surrogates that explicitly encode structural assumptions about the integrand to obtain integral estimates with quantified uncertainty. These surrogates are predominantly based on stationary covariance functions, which results in model misspecification for integrands exhibiting nonstationary behavior. We tackle this issue through an adaptively growing, tree-based partition of the integration domain into local stationary models. Our method recombines the local integral estimates through a hierarchy of GP conditioning that reintroduces cross-subdomain correlations, while model selection criteria control the tree growth to avoid unnecessary partitioning. The resulting algorithm is simple, requires no MCMC, and adapts its evaluation budget to local integrand complexity. On benchmark integration problems and a model evidence computation for an epidemiological model, Hierarchical Bayesian Quadrature achieves substantial gains over standard Bayesian Quadrature on nonstationary integrands while matching its performance on stationary ones.

Computational imaging, which recovers hidden signals from indirect, noisy measurements, underpins quantitative discovery across scientific disciplines, yet building a correct reconstruction pipeline demands deep domain expertise and remains laborious even for domain scientists. We introduce Imaging-101, a benchmark of 57 expert-verified computational imaging tasks spanning six scientific domains, each grounded in a peer-reviewed paper and canonicalized into a standardized four-stage pipeline (preprocessing, forward physics modeling, inverse solver, and visualization) Three evaluation tracks (planning, function-level unit tests, and end-to-end reconstruction) probe distinct agent capabilities across the full pipeline. Evaluating seven frontier LLMs uncovers systematic challenges in applying coding agents to computational imaging that go beyond those exposed by general coding benchmarks, spanning algorithm selection, physical convention handling, and pipeline integration. These findings highlight concrete capability gaps and point toward skill-augmented, domain-specialized agents as a practical path to reliable computational imaging assistance.

The evolving realism of AI-generated Videos (AIGC-V) is rapidly rendering traditional artifact-centric detection insufficient, necessitating a paradigm shift from low-level inspection to high-level semantic verification. This paper presents a comprehensive survey of AIGC-V detection, reframing the task as Factual Fidelity Verification, which asks whether the events, entities, and physical processes depicted in a video are consistent with real-world facts. To systematize this rapidly evolving field, we propose a Vision-Language Dual-View taxonomy that organizes existing methods into a hierarchical, four-layer landscape, spanning intrinsic cue analysis, spatiotemporal consistency modeling, cross-modal consistency reasoning, and language-guided world-level reasoning. This dual-view framing highlights a fundamental transition from artifact matching in traditional deepfake detection to evidence-based semantic verification enabled by vision-language models and agentic reasoning pipelines. Based on a systematic review of 221 works, we synthesize AIGC-V generation paradigms, survey the landscape of detection methods, and review evaluation metrics and benchmarks in line with proposed views. Finally, we discuss current challenges and identify promising directions toward robust, explainable, and trustworthy detection.

Deploying deep learning models for automated electrocardiogram classification on resource-constrained wearable devices remains challenging due to high computational costs. To address this, we propose LSTrans, a lightweight hybrid model designed for efficient and sensitive ECG analysis. LSTrans introduces a specialized 1D convolutional backbone with an interleaved layer architecture to capture both macroscopic rhythmic trends and microscopic morphological variations. This backbone is cascaded with a Transformer encoder to model long-range temporal dependencies, incorporating Low-Rank Adaptation across critical layers to compress the model and reduce the trainable parameter space. We further employ homogeneous and heterogeneous knowledge distillation to transfer diagnostic expertise from high-capacity teacher models to the student. Experimental results on multiple benchmark datasets demonstrate that LSTrans achieves a competitive balance between diagnostic sensitivity and resource efficiency, substantially reducing peak memory footprints and training latency during downstream adaptation. The source code is available for review at https://github.com/zyee00128/LSTrans4BIBM.

Whole-slide images (WSIs) provide rich tissue-level and cellular-level information, but storing and transmitting high-magnification pathology data is resource-intensive. Moreover, annotating WSIs at the pixel level is labor-intensive and time-consuming. Therefore, it is important to investigate whether low-magnification pathology images with limited annotations (i.e., image-level instead of pixel-level labels) can achieve performance comparable to high-magnification images. This paper presents a systematic benchmark study on weakly supervised histopathological image segmentation under different low-resolution storage settings. Starting from high-resolution image patches, we simulate lower-magnification inputs and reconstruct them to the original size using interpolation and deep learning-based reconstruction methods before applying the weakly-supervised segmentation pipeline. This framework enables a quantitative evaluation of how weakly supervised methods respond to different levels of resolution degradation. Experimental results show that reconstruction quality metrics alone are insufficient to predict downstream segmentation performance. In particular, the study identifies a critical degradation point where the localization of small-scale structures declines significantly. These findings provide practical guidance for designing efficient digital pathology storage systems while maintaining reliable automated analysis. Code is available at https://github.com/Dung-Dx/LowMagWSS

Matching dependency is a generalization of the functional dependency concept, which allows users to apply custom similarity functions for matching individual attributes. Matching dependencies have a wide range of applications for solving various data quality problems, such as entity resolution, data deduplication, data integration, schema matching, and many more. However, their discovery is a very computationally intensive problem, which limits their practical application. In this paper, we describe a number of optimization techniques for HyMD - currently the state-of-the-art algorithm for the discovery of matching dependencies. These optimizations belong to both technical and scientific domains. The most important of them are: 1) a new sampling technique, 2) a faster generalization lookup technique, and 3) an improved representation of a dependency. The first one aims to raise the efficiency of inference from record pairs, while the last two are designed to speed up lattice-related operations. To evaluate our optimizations, we implemented our version of HyMD in Desbordante, an open-source high-performance data profiler. Experiments demonstrated that they allow for a speedup of more than 40x over the state-of-the-art implementation on average, reaching a speedup greater than 170x in some cases. Finally, the improved version of HyMD is ready to use by anyone. It comes with bidirectional Python integration, which allows calling the C++ algorithm implementation from Python programs while allowing users to supply their custom matching functions.

LLM-based agents are increasingly deployed to solve optimization problems, yet existing benchmarks evaluate them on pre-structured mathematical formulations that bypass the most critical challenge: translating complex business requirements into correct models and solve efficiently. We introduce Opti-Agent-Bench, an end-to-end benchmark that evaluates Large Language Models (LLMs) across the complete optimization R&D pipeline, from understanding business-language descriptions through mathematical modeling, algorithm selection, and code implementation, to solution report generation. Our design rests on three pillars: (1) businesssemantic authenticity with anti-template traps that defeat pattern matching; (2) modular evaluation with cross-module consistency checking across Problem Understanding, Formal Modeling, Implementation, and Reporting; and (3) the ORAC bi-level validity framework that simultaneously ensures task quality and scoring integrity. Across several industrialscale tasks spanning integer programming, robust optimization, stochastic programming, and non-convex optimization, we expose critical failure modes of current models, including constraint omission, model-code inconsistency, and report-implementation divergence, that remain invisible under conventional single-metric evaluation.

Cross-modal distillation from Vision Foundation Models (VFMs) to LiDAR backbones has recently emerged as a self-supervised pretraining strategy that reduces reliance on dense point-wise annotation for 3D scene understanding. However, existing distillation pipelines typically treat the VFM as a frozen feature source and train a heterogeneous 3D backbone to match fixed image embeddings, forcing the student to bridge both the modality gap and the cross-architecture gap between dense ViT token representations and sparse 3D encoders. We propose TOLiD, a self-supervised pretraining method for LiDAR representation learning that addresses this gap by coupling a LiDAR backbone with a student Vision Transformer (ViT) initialized from a frozen VFM teacher and applying supervision over compatible patch-token representations. TOLiD converts the set of point features within each image patch frustum into a token using Frustum Pooling followed by Frustum Attention, and performs token-level distillation with visibility masking. For LiDAR-only deployment, we lift token features back to per-point representations using masked bilinear sampling to avoid patches that have limited LiDAR points. We extensively evaluate TOLiD on five heterogeneous LiDAR datasets and four cross-sensor adaptation pairs, demonstrating improved transfer with frozen backbones and lightweight heads.

Following Alon, Hanneke, Holzman, and Moran (FOCS 2021), we define a partial concept class (PCC) as a family of partial functions \(f: V\to\{0,1,\ast\}\); equivalently, its concepts partition the ground set into black ($f^{-1}(1)$), grey ($f^{-1}(\ast)$), and white parts ($f^{-1}(0)$). Its VC dimension is defined by shattering sets on which the value $\ast$ is not taken. We study two geometric PCCs in real Banach spaces, both with a margin \(δ>0\): expanded half-spaces, where the grey part is a strip of width at least \(δ\) adjacent to a half-space, and expanded balls, where the grey part is an annulus of width \(δ\) around a unit radius ball. Our main results are dimension-free upper bounds on the VC dimension of the PCC of expanded balls in \(L_p\parenthμ\), \(1\le p<\infty\), including the non-Euclidean and algorithmically particularly relevant case \(\ell^d_1\). These bounds depend on the margin and on the radii, but not on the ambient dimension or the underlying measure space. These are extensions of the work of Bourneuf, Charbit, and Thomassé (FOCS 2025) who studied the PCC of expanded balls in Euclidean space, that is, $\ell_2^d$. We also prove lower bounds on the VC dimension that match the upper bounds in terms of the margin parameter $δ$. Finally, we derive a Dense Neighborhood Lemma in \(L_p\)-spaces, again extending the known Euclidean results. Our method relies on the linearization of the distance through a map into a space of non-trivial Rademacher type, and then the use of a balanced signed-sum estimate, or a no-dimensional Radon theorem. The arguments rely on ideas from functional analysis that are clearly explained for the non-expert in that field.

Synthetic data is widely used to train large language models because it is inexpensive to generate and easy to control. As models are increasingly deployed as agents, synthetic trajectories are likely to become an important source of training data for agentic behavior. We investigate the effects of training on synthetic agentic trajectories containing adversarial interactions, including actions such as terminating another agents process, lowering its scheduling priority, or accessing resources without authorization. We finetune Llama 3.3 70B Instruct on these trajectories, generated to approximate reinforcement learning rollouts, and evaluate the resulting models on Anthropics Agentic Misalignment suite and Apollos in context scheming scenarios. Finetuning on these trajectories consistently increases misaligned behavior. Leaking rises by roughly a factor of five over the baseline, 4.6% to 24.9%. This increase survives the removal of every adversarial action from the trajectories. Finetuning on structurally comparable trajectories generated benign from the start produce a substantially smaller effect, 15.5%. These results indicate that the misaligned disposition is introduced during the generation process and encoded diffusely throughout the trajectory, rather than being localized to the harmful actions themselves. The effect also depends on the generating model. Benign trajectories produced by Gemini 2.5 Flash induce slightly higher leaking rates than trajectories generated from identical tasks by Claude 3.7 Sonnet. In contrast, broad safety benchmarks degrade similarly across all finetuned models and therefore fail to distinguish these effects. Our results suggest that action level filtering is insufficient to ensure the safety of synthetic agentic training data and that dispositions introduced by the generating model can survive semantic inspection.

Computed Tomography (CT) diagnosis often relies on dynamic selection of imaging phases, such as non-contrast, arterial, or venous phases, based on preliminary findings, clinical suspicion, and diagnostic guidelines. This phase-wise decision process is critical for reducing unnecessary radiation exposure while supporting timely staging and treatment planning. However, phase-selection protocols can vary across hospitals, regions, and guidelines, while most existing CT-based AI methods assume that all phases are available and focus on static tasks under a fixed imaging phase, failing to model whether additional phases are required. This limitation stems from heterogeneous multi-phase representations, the need for knowledge-guided phase control beyond visual cues, and the lack of supervision for phase-sufficiency decisions in existing datasets. To address these challenges, we propose Policy-Driven CT-Agent (PD-CTAgent) for clinically consistent CT phase selection and diagnostic reasoning. PD-CTAgent introduces a Clinical Structure Abstraction Module (CSAM) to harmonize heterogeneous CT phases into a unified, phase-aware evidence representation. Based on this representation, a Knowledge-Guided Diagnostic Control Model (KDCM) evaluates phase sufficiency and iteratively requests additional phases when necessary. The policy-driven agent design further allows PD-CTAgent to flexibly follow different institutional, regional, or guideline-specific diagnostic protocols. Together, PD-CTAgent bridges static CT analysis and real-world clinical workflows. Experiments on two public datasets, LIDC and MCT-LTDiag, and one private dataset demonstrate its effectiveness and clinical consistency. Code will be made public upon acceptance.

This paper describes the first ChineseBabyLM challenge, which will be held in the 2026 NLPCC conference. The challenge calls for researchers to train language models from scratch with 100 million Chinese tokens and evaluates the models on 3 tracks of tasks: NLU, cognitive alignment and Hanzi knowledge. There is no restriction on tokenizer, model architecture and the number of training epochs. Details of the challenge can be found in https://chinese-babylm.github.io/.

The analysis of Multivariate Time Series (MTS) plays an important role in a lot of real-world practical applications, but it still remains some challenging problem about capturing multi-granularity structural patterns and suppressing noise appropriately. Multi-Scale Convolution with Optimal Transport Attention (MSC-OT) is proposed in this paper. MSC-OT is a useful architecture to optimize the attention mechanism. It combines multi-scale convolution with Sinkhorn optimal transport method based on inverted embedding. The inverted embedding approach embeds each variable as a token and allows the model to capture cross-variate relationships better. MSC-OT consists of two part: (1) Multi-Scale Convolution Enhancement, that applies multi-scale convolutions to attention score matrices based on inverted embedding, capturing local structural patterns in the variate-interaction space induced by compressed temporal representations; (2) Sinkhorn Optimal Transport Regularization, that formulates attention computation as an optimal transport problem and employs iterative matrix scaling to ensure balanced information flow across variates. Adaptive Fusion Strategy utilizes softmax-normalized learnable weights to dynamically combine base attention, convolution-enhanced, and OT-regularized scores. Experiments on widely-used datasets, including ETT, Electricity, Traffic, Solar-Energy, and Exchange-Rate, show that MSC-OT achieves well performance in both short-term and long-term forecasting tasks. Ablation experiments further validate the effectiveness of each proposed component and their synergistic contributions to improving prediction accuracy for multivariate time series forecasting.

Recent advances in equipping Large Language Models (LLMs) with search tools and outcome-reward reinforcement learning (RL) have achieved new state-of-the-art results on open-domain QA tasks. However, we argue that current training paradigms harbor a critical vulnerability: they predominantly reward correct answers but fail to penalize fabricated ones when retrieval fails, thereby implicitly exacerbating hallucinations. To address this, we propose Abstention-Aware Reinforcement Learning (AWA-RL), which dynamically shapes the abstention reward utilizing the model's query-specific prior capabilities and continuous on-policy training observations. We also introduce a novel metric, RA-F1, to measure the capability-reliability trade-off. Compared to non-abstaining baselines, AWA-RL boosts absolute precision by up to 10.3% and overall RA-F1 by 2.9%, with only marginal sacrifice in raw accuracy. These results confirm that AWA-RL successfully yields highly capable and reliable search agents. The code, data, and model weights are publicly available at https://github.com/zfj1998/AWA-RL.

Molecular property models are commonly evaluated by holding out Bemis--Murcko scaffolds, yet a scaffold identifier is only one notion of chemical unfamiliarity. We introduce a label-free structural-frontier split that reserves the sparsest and most physicochemically remote scaffold groups, and evaluate it on six public experimental or curated ADMET tasks. Against a 70/10/20 scaffold control with identical acyclic grouping, the frontier inflates equally weighted primary error with a taskwise median of 87.0\% and a skew-sensitive mean of 130.3\% (descriptive task/seed bootstrap interval, 52.1--246.0\%). The mean falls to 75.9\% once BBB is removed; that endpoint is the one whose score ranking inverts at the frontier. A message-passing graph-network control still shows a large gap (mean 82.8\% over four tasks) and does not invert, so a low-capacity head does not explain the effect. We also test Multi-View Frontier Risk Extrapolation (\method), a count-adjusted tail-risk penalty over four molecular views, and treat it as a falsifiable probe. It changes normalized frontier error by only 0.16\% relative to empirical risk minimization for the perceptron head (interval, $-0.43$--0.84\%) and by $-1.9$\% for the graph network; three fixed robust-penalty controls are likewise inconclusive. Against the published Lo-Hi and DataSAIL splitters the frontier inflates error more on average, though no split is uniformly hardest. An audit of 31,561 marine natural products further shows that OOD status and agreement with legacy ADMET predictions depend on the molecular view, endpoint and teacher coverage. Split construction and label provenance are important evaluation constraints in their own right, and the tested training penalties do not resolve the frontier failures we observe.

The accelerating shift toward low-carbon power systems, together with the widespread adoption of behind-the-meter technologies such as rooftop solar and electric vehicles, is placing new operational and analytical demands on electricity grids. At the same time, smart-grid research increasingly relies on machine learning (ML), yet progress is constrained by limited access to high-resolution household energy data due to privacy concerns, regulatory barriers, and collection costs. This work presents WattCouncil, a data-generation framework in which household electricity demand is generated by a council of Large Language Model (LLM)-based agents operating in specialized roles to generate, audit, and validate structured energy scenarios under explicit cultural, temporal, and physical constraints. Rather than acting as static predictors, these agents serve as adaptive decision-makers within a governed pipeline. Motivated by studies highlighting the importance of contextual factors in energy use, our framework produces context-sensitive daily routines through a guided reasoning process that incorporates household composition, temporal factors, and environmental conditions. We evaluate the generated profiles against the detailed CER dataset, which contains over a year of load measurements for 4232 households together with survey-based socio-economic information. We further assess the consistency of the framework through ablation studies. Source code is available at https://github.com/Singularity-AI-Lab/wattcouncil

Persuasion techniques are powerful rhetorical devices used to sway public opinion in a wide range of media. We present a new corpus of persuasion techniques, focusing on Slavic languages. The corpus contains documents in Bulgarian, Polish, and Russian, annotated with persuasion techniques at the coarse-grained text-span level and fine-grained sentence level. The techniques are drawn from a taxonomy of 25 fine-grained persuasion techniques, grouped under six broad categories of rhetorical persuasion strategies. The corpus contains approximately 7500 text spans from 222 documents that cover topics hotly debated at the national and international levels. We describe the corpus creation process, provide detailed statistics, and examine correlations between topics and persuasion techniques. We use classic ML-based and generative AI-based models to provide baselines and benchmark results for the detection and classification of persuasion techniques at the text-span level and sentence level.

Scientific fraud is the instrument of doubt that malicious entities can use to establish controversy in science. Historically, it required the resources of a company: deep pockets, ghostwritten articles, and corrupt academics. Today, Artificial Intelligence (AI) is increasingly automating scientific research, so we ask: Can a remote adversary weaponize the honest use of AI in science to compromise scientific integrity? We envision and empirically evaluate a new attack, indirect data poisoning, in which an adversary corrupts an open dataset and uploads the poisoned variant to a public repository. Autonomous research agents may independently retrieve and process this data, turning honest scientists into the unpaid and unwitting distributors of fraud at scale. Across five socially-salient topics, from hiring discrimination to the safety of autonomous vehicles, three widely used frontier AI systems (Claude Code with Claude Opus 4.7, Codex with GPT-5.5, Gemini CLI with Gemini 3.1 Pro), and 450 ethically contained experimental runs, we find that poisoning succeeds in 49.56% of runs, while the rate of poisoning detection is only 6.0%. The attack requires no topic-specific trigger-words, agent access, indirect prompt injection, or fabricated papers, only the open data ecosystem and misleading metadata. To mitigate the attacks, we propose and evaluate two measures: a scientist persona and a data provenance audit with five checks (referencing papers, social markers, statistical anomalies, related datasets, poisoning caution). We find that the persona still leaves 16.67% of runs with a poisoned conclusion, but provenance auditing reduces attack success rate to zero. Our results suggest that indirect data poisoning may enable scientific fraud at unprecedented scale, but these attacks can be mitigated with suitable auditing by agents during data retrieval.

Large Language Model (LLM) services introduce a fundamental privacy challenge. Sensitive information may be inferred not only from explicit identifiers, such as names or phone numbers, but also from contextual associations among otherwise innocuous spans. Existing sanitizers typically assign privacy or utility signals to individual spans without explicitly modeling pairwise relationships among them. In this paper, we propose PromptGraph, a graph-guided prompt-sanitization approach for privacy-preserving LLM inference. PromptGraph estimates privacy leakage at the span level and utility-relevant contextual dependencies between pairs of spans. It represents each prompt as an attributed graph, in which nodes carry span-level privacy scores and edges encode contextual dependencies needed to preserve utility. The sanitization objective selects a protected span set that maximizes privacy gain while penalizing the loss of contextual dependencies. This formulation explicitly balances privacy and utility when contextual evidence is hidden. Protected spans are sanitized locally, and returned placeholders are restored only after passing local consistency checks. We conduct extensive experiments showing that PromptGraph achieves a more favorable balance between privacy and utility than prompt-privacy baselines.

We propose a unified meta-decoding framework for quantum error correction that learns syndrome-to-recovery mappings across multiple stabilizer codes and noise settings, without requiring separate decoders for each configuration. The benchmark includes FiveQubit, Steane, Planar3x3, and Planar5x5 codes, four noise families, and five evaluation regimes: interpolation, unseen-p transfer, unseen-noise transfer, few-shot unseen-code adaptation, and few-shot held-out-size adaptation. We compare a classical Meta-MLP teacher-trained baseline with variational quantum circuit (VQC) meta-decoders selected through hardware-aware quantum architecture search over qubit count, circuit depth, and entangling topology. The Meta-MLP achieves teacher-label accuracies of 0.9993, 0.9118, 0.9342, 0.6304, and 0.7548 across the five regimes, while the hardware-aware VQC achieves 0.9400, 0.8495, 0.8415, 0.5678, and 0.7143. However, logical-level evaluation shows that high teacher-label accuracy alone is insufficient in the most challenging Planar5x5 setting. During interpolation, the raw logical-failure ratios relative to the teacher are 12.08 and 25.91 for the Meta-MLP and VQC, respectively, whereas confidence-gated fallback reduces them to 1.71 and 1.11. These results support confidence-aware selective recovery rather than unconditional teacher replacement.

The action space poses a major challenge in robot learning, since it is often high-dimensional, can span long time horizons, and frequently admits multi-modal optimal solutions. A good choice of action representation and loss function can help to address these concerns, but there are often trade offs. We propose Action Map Policy (AMP), which casts 3D closed-loop manipulation policy learning as a classification problem in image space. While classification has been an effective formulation in generative language models, applying it to robot action learning is difficult because naively discretizing high-dimensional continuous actions explodes the token vocabulary. Our key idea is to project 3D actions onto the camera image planes and treat each pixel location as a discrete class, thus controlling dimensionality while retaining multi-modality. This method supports millimeter-level precision for high-dimensional actions without requiring a prohibitively large vocabulary, while preserving fine-grained pixel-wise visual signals. Furthermore, it can predict the entire action chunk in a single forward pass, avoiding complex noise scheduling and iterative denoising while achieving substantially faster inference than diffusion policies. Experiments on various manipulation tasks show that AMP outperforms strong baselines, achieving higher success rates, faster inference, and enhanced spatial reasoning.

We study the modality gap in CLIP-style dual-encoder contrastive learning, where image and text embeddings remain misaligned despite being trained in a shared space. We argue that the gap is induced by a failure of the InfoNCE formulation with independent encoders. We conduct a uni-modal experiment with two independent encoders and identical initialization conditions and find that InfoNCE actively generates a gap at low temperatures. We provide a theoretical analysis of this phenomenon and show that the modality gap is indeed a mode-failure of InfoNCE, but only at low temperatures. We propose a simple modification called xNCE, which uses intermodal as well as intra-modality negative contrastive pairs. xNCE matches retrieval performance on MS-COCO while consistently reducing the gap even at low temperatures. Notably, xNCE improves zero-shot classification over the InfoNCE baseline across all benchmarks, whereas high-temperature InfoNCE and regularized InfoNCE both fail to do so, demonstrating that xNCE reduces the modality gap without sacrificing the discriminative geometry needed for transfer.

We study the problem of optimal continual fine-tuning for a pre-trained Foundation Model deployed at a resource-limited device. At each time slot, a new batch of training data arrives, and the controller is faced with two options: either use the data to fine-tune the model and incur a compute cost, or do not fine-tune the model and discard the data. After the decision, the performance of the current model is measured in terms of an application-specific performance metric such as classification accuracy. Our objective is to learn an optimal policy that determines \emph{when to fine-tune the model} on a single task (e.g., sentiment analysis), under a finite compute budget. We formulate this online decision-making problem as a constrained Markov Decision Process, where the system state captures three essential aspects: (\textit{i}) model's performance, (\textit{ii}) computational budget, and (\textit{iii}) data distribution relevance to historic data encountered up to that point. The transition to the next state is stochastic and therefore, we propose a reinforcement learning-based method to solve this problem, namely the \emph{actor-critic} algorithm. We also consider the special case where the performance of fine-tuning for a given model can be predicted or estimated prior to decision; in this case the problem becomes a Dynamic Programming one. Experiments with a large pre-trained model on a widely-used text classification dataset demonstrate that our method consistently outperforms fine-tuning approaches with the same compute budget by more than $4\%$ in terms of accuracy and achieves $97\%$ of full-parameter fine-tuning accuracy while requiring only $25\%$ of the fine-tuning steps.

In pre-LayerNorm looped transformers, LayerNorm inside the recurrent block acts as an implicit gain controller: by coupling the block's local Lipschitz constant inversely to the activation scale, it renders the recurrence Jacobian non-normal -- asymptotically contractive at every verified fixed point even where its operator norm exceeds 1 -- so the true stability budget is the spectral margin, not an operator-norm bound. That margin depletes as the carry $ρ\to 1$, and a minority of initializations never converge to a fixed point at all, so the diagonal carry constraint $ρ(\bar{A}) < 1$ is necessary but not sufficient for convergence of the full recurrence. Training experiments across six tasks, including a controlled ablation, reveal that the linear carry is not the depth-memory mechanism: gradient descent routes memory through the block's more expressive nonlinear recurrence and leaves the stability-constrained carry at rest -- the carry's role is stabilization, not memory. We characterize the boundary of this claim: on tasks with axis-aligned per-channel structure, gradient descent does recruit the carry. All results are derived analytically and verified in a from-scratch, CPU-scale implementation; verification at larger scale is needed.

Emotional intelligence enables humans to recognize emotions, infer their causes, reason about interventions, and modify their environment to achieve desired affective states. Despite recent advances in artificial intelligence (AI), current models remain largely limited to generating realistic content or performing semantic reasoning, with little capacity for understanding, predicting, and personalizing human emotional responses. Here we introduce Emotion-augmented geneRatiOn System (EROS), a hybrid AI framework that integrates symbolic reasoning with deep learning to enable personalized emotion augmentation through visual content. Leveraging large-scale image-emotion datasets, EROS discovers generalizable affective rules, identifies emotion-relevant image regions, and predicts context-aware visual modifications that preserve scene semantics while steering emotional responses toward desired targets. To account for individual variability, EROS incorporates an expandable memory bank that supports inference-time personalization without model fine-tuning, yielding interpretable emotional profiles and rapid adaptation to new users. Across extensive human psychophysics experiments, EROS elicits target emotional responses more effectively than state-of-the-art large multimodal models while adapting to individual affective preferences. Beyond affective computing, EROS provides a foundation for AI systems that can understand, reason about, and augment human cognitive states, with potential applications in mental health, adaptive media, education, and human-computer interaction.

Self-attention is a ubiquitous primitive in modern sequence models, yet its operator-level geometry is only partially understood. We view a token sequence as a vector field over the token-position graph and identify attention as a connection walk: messages are aggregated by a nonnegative walk matrix while being transported along each edge by a learned linear map. Within this framework, we prove that single-head attention (SHA) is exactly a connection propagation step with constant transport, and that multi-head attention (MHA) is exactly a single edge-dependent connection walk whose effective transport is an attention-gated mixture of headwise transports. We further clarify the conditions under which the corresponding generator reduces to a random-walk connection Laplacian, highlighting the roles of stochasticity, reversibility, and metric-compatible transports. Empirically, we find that trained Transformers across scales (from 124M to 8B) and structures (encoder/decoder) exhibit geometric structure consistent with our theory: effective attention graphs converge to stable geometric operators in deeper layers, learned transports self-organize into approximate scaled isometries, and both phenomena strengthen consistently with scale. Overall, the paper provides a precise connection-walk formalism that links self-attention to classical geometric operators, along with a set of operator-level tools for analyzing transformer models from a geometric perspective.

As AI code tools become integrated into programming environments, students increasingly describe intended behavior in natural language and rely on these tools to generate code, shifting emphasis from code writing to specification. Yet little is known about the comments students write as specifications in AI-assisted programming tasks. We analyze a four-year dataset of undergraduate programming submissions and reflections from tasks in which students wrote comments to guide code generation and refined solutions using test-case feedback. We introduce a taxonomy spanning three dimensions: comment type, code expression level, and code construct. Using automated classification, we examine how these dimensions vary across attempts and how students describe the process in their reflections. Our findings show that students mostly wrote natural-language What comments, shifted toward How comments for more procedural constructs, and focused more on verifying generated code than on repeatedly rewriting comments.

Bayesian optimization is increasingly used to guide data-efficient experimentation in chemistry, materials science, and related laboratory settings, but its practical performance depends strongly on how well surrogate-model assumptions match the geometry and noise structure of the underlying objective. We introduce tidyHEBO, a robust Bayesian optimization model inspired by heteroskedastic evolutionary Bayesian optimization (HEBO) for single-objective, sequential optimization. tidyHEBO reconstructs the HEBO design philosophy in BoTorch and revises surrogate training, output-warping selection, acquisition function evaluation, and Pareto-front search. We benchmarked tidyHEBO on synthetic functions, Olympus emulators, fully experimental reaction-optimization datasets, needle-in-a-haystack (NIAH) materials problems, and Bayesmark hyperparameter optimization tasks. On these tasks tidyHEBO achieved competitive to superior performance and improvement in robustness across repeated optimization runs. We therefore propose tidyHEBO as a practical tool for sequential experimentations and a strong general-purpose benchmark for future Bayesian optimization research.

Deploying AI-based visual inspection in manufacturing is hard because requirements change often, new defect types appear, and large labeled datasets are rarely available. We propose answer-conditioned chain-of-thought (CoT) distillation for rapidly adapting small vision-language models (VLMs) to new industrial tasks using minimal labeled data. A frontier VLM receives each training image along with its correct label and generates a justified visual explanation. A 3B-parameter model is then fine-tuned on these reasoning-augmented examples via LoRA. By conditioning on correct answers, we ensure all training reasoning is directed toward the correct conclusion, which is critical because frontier models score as low as 24.1% on our hardest task. We validate on four industrial classification tasks spanning three image modalities using only 18 to 30 labeled images per task. Across 4 seeds per task (32 training runs), our method outperforms direct fine-tuning on all 16 seed-task combinations, with mean improvements of +1.7 to +4.4 percentage points. A controlled equal-budget experiment confirms the improvement comes from reasoning quality, not additional training steps. An unconditioned baseline demonstrates that with out answer-conditioning, wrong reasoning degrades performance by 17.8 percentage points. On weld radiograph classification, the fine-tuned 3B model outperforms GPT-4.1 by 10.0pp using just 24 training images.

In this paper, we provide a systematic investigation of SO(2) theory to machine learning interatomic potentials (MLIPs) and identify the limitations of conventional SO(2) Linear architectures relative to SO(3) Clebsch-Gordan Tensor Products (CGTP). Building on these insights, we propose direct Cartesian construction and recursive Clebsch-Gordan construction of Wigner D-matrices and introduce two novel interaction building blocks. First, we propose the Edge Complex Product Basis based on Generalized Asymmetric Contraction, a new formulation for many-body expansion that directly constructs higher-order interactions on edges through complex-valued equivariant multiplications. Second, we introduce Radial Rotary Complex Attention(RRA), which enhances extrapolation performance and surpasses existing attention vector formulations. We also introduce several improvements to the Atomic Cluster Expansion module. Building on these advances, we train our models on OMat24, sAlex, and MPTrj, and introduce TECE-OAM-RRA-1.0, which achieve state-of-the-art (SOTA) performance on the Matbench Discovery.

Speculative decoding has significantly accelerated Large Language Model (LLM) inference by alleviating memory-bound bottlenecks. However, traditional speculative decoding typically relies on auxiliary draft modules, incurring significant training and communication overhead. Although recent methods attempt to generate drafts within the target model itself, they often fail to fully exploit its latent parallel capacity due to a lack of structural coordination. In this paper, we propose \textbf{Progressive Tree Drafting (PTD)}, which employs a structured, guided parallel drafting strategy to harness the model's parallel potential. By coupling a progressive tree structure with a stepwise pruning mechanism, PTD actively guides the LLM to explore multiple semantic paths in a single forward pass, ensuring both draft diversity and coherence. Experiments demonstrate that PTD achieves up to $2\times$ decoding speedup across various benchmarks while remaining training-free and model-agnostic. Our code is available at: https://github.com/MINE-USTC/PTD.

Characterizing quantum topological phases requires measuring non-local string order parameters, demanding access to the full system, which is often experimentally unfeasible. In this work, we introduce a data-efficient supervised learning framework that circumvents this limitation by recognizing quantum phases from small subsystems. Our protocol utilizes a quantum kernel constructed from the reduced density matrices of these subsystems, which can be efficiently estimated experimentally. We benchmark our framework with the classification of the phase diagrams of two spin models on one-dimensional lattices, namely the generalized cluster-Ising spin-1/2 chain and the anisotropic Haldane spin-1 chain. Remarkably, our approach achieves high accuracy in phase classification when operations are limited to as few as one to four sites, and it also generalizes to longer chains even when trained on moderate system sizes. These findings demonstrate that local reduced density matrices preserve vital signatures of global topological phases, offering a practical route to characterize rich phase diagrams of quantum many-body systems.

In large urban areas, planning multi-day travel itineraries is challenging due to the abundance of Points of Interest (POIs), diverse user preferences, and constraints such as opening hours. Effective solutions must dynamically accommodate diverse traveler requirements while optimizing for satisfaction and feasibility within limited computation time. This paper addresses these challenges through introducing an innovative framework that integrates Large Language Models (LLMs) to dynamically capture user requirements with precision and flexibility, and an enhanced Greedy Randomized Adaptive Search Procedure (GRASP) algorithm as a well-suited preference-aware planner to generate feasible multi-day itineraries. The effectiveness of our integrated approach is demonstrated through extensive experiments on two real-world urban datasets from Beijing and Tianjin. Our framework significantly outperforms state-of-the-art (SOTA) methods, improving the average total itinerary score by at least 4.52% and 11.09% across 5,040 user cases with diverse preferences in the two datasets. Furthermore, through end-to-end algorithmic enhancements, it achieves notable average improvements of 17.95% and 26.07% in the computed metrics, while also delivering substantial gains in time efficiency -- realizing average performance increases of 4.64% and 25.55% within shorter computation times compared to suboptimal methods that require multiple iterations. These outcomes underscore our method's superiority in delivering both enhanced itinerary quality and computational efficiency over existing methodologies.

Coverage path planning (CPP) is a fundamental problem in robot motion planning, whose aim is to produce robot trajectories that provide complete coverage of target workspaces while minimizing task-specific objectives such as path length, overlap, number of turns, and energy consumption. CPP has widespread applications in cleaning, inspection, mapping, agriculture, manufacturing, surveillance, demining, and environmental monitoring. Although classical CPP has been extensively studied, recent advances have extended CPP beyond single-robot settings to multi-robot systems, complex 3D environments, constrained platforms, learning-based coverage planning, and visual coverage tasks. This paper presents a comprehensive survey of 125 representative works published primarily between 2015 and 2026, while presenting the evolution of recent developments in light of the classical CPP methods published before 2015. The CPP methods are organized into six main categories: single-robot CPP, multi-robot CPP, 3D CPP, constrained CPP, learning-based CPP, and visual CPP. For each category, the review summarizes the main planning formulations, representative algorithms, strengths, and limitations. In addition, the review analyzes how environmental knowledge, workspace geometry, robot constraints, sensing objectives, and coordination requirements shape the CPP problem. The survey further discusses open challenges in scalable online planning, multi-robot coordination, 3D and visual coverage, unified platform-constrained and resource-aware coverage, and learning-enhanced coverage. Thus, the survey provides a structured overview of recent CPP developments and future research directions.

The rapid integration of Large Language Models (LLMs) into K-12 and higher education has outpaced the development of reliable methods for evaluating their pedagogical quality. As the research community starts to explore the space of automating evaluation of AI tutors, we introduce FATE (FLC AI Tutor Evaluator), a specialized 8B-parameter language model designed to evaluate AI tutors. Aligned with the four core evaluation tracks from the BEA 2025 Shared Task, our model assesses pedagogical ability across Mistake Identification, Mistake Location, Guidance, and Actionability. Because pedagogical evaluation is a specialized task with limited labeled data, we leverage knowledge distillation from a frontier LLM to generate additional supervision, yielding absolute performance gains up to 22.63 percentage points. Finally, we demonstrate FATE's utility as an automated evaluator by benchmarking instructional responses generated by popular commercial models, including ChatGPT, Claude, Gemini, and DeepSeek. On average, we have found that Gemini 2.5 Flash perfomed best (82.88%), then ChatGPT 5.5 Instant (80.75%), followed by DeepSeek V4 Flash (80.13%) and Claude Sonnet 4.6 (74.00%).

An LLM agent's public behaviour reveals little about its social reasoning: an agent that votes correctly may be guessing, and an agent that lies well leaves no trace of what it actually believes. We present MafiaScope, an open testbed that turns the social deduction game Mafia into a measurement instrument for machine Theory of Mind. After every public utterance, every agent privately answers a configurable set of structured probe questions; the answers never re-enter the game and are scored automatically against the ground truth the engine knows. An interactive visualizer renders the belief trajectories: impersonate mode shows the game as one agent sees it, panels chart timeline-aligned accuracy and calibration, and counterfactual replay forks any recorded step. In a 32-game DeepSeek case study with 13{,}815 parsed probe answers, stated confidence is poorly calibrated, with expected calibration error 0.17, agents over-predict being suspected 1.5 times, and a 30-fork replay experiment walks the counterfactual replay workflow end to end. Engine, viewer and a corpus of 200+ cross-model games are released under an open licence; live demo: https://karpovilia.github.io/mafiascope/; screencast: https://vimeo.com/1208920221.

Explainable machine learning (XML) pipelines applied to composite mental health outcomes can produce apparently-robust, cross-population-stable risk hierarchies that are largely artefacts of how the outcome was constructed. We demonstrate this using an ElasticNet pipeline applied to 886 medical students at the University of Lausanne (primary cohort, 2022), validated across 2,580 longitudinal observations at three time points and 701 non-medical students from eight faculties; all three datasets share identical instruments. The pipeline produces a hierarchy in which trait anxiety and health satisfaction dominate wherever the outcome is measured, with Kendall $τ= 1.0$ for the top-two positions across all five evaluation sets and consistent transfer performance ($R^2$: 0.41-0.49). Two residualization experiments, which isolate shared variance between correlated variables via regression, reveal the mechanism: when trait anxiety (STAI-T) is residualized against the co-included depression subscale (CES-D, $r = 0.72$), model $R^2$ drops from 0.41 to 0.16 and STAI-T falls from rank 1 to rank 6; when burnout subscales are residualized against CES-D, $R^2$ collapses to 0.016. Prediction intervals average 35.4 units on a 0-100 scale (2.4 outcome standard deviations), independently ruling out individual-level deployment. The residualization protocol is the paper's transferable contribution: any XAI study combining correlated predictor and outcome constructs should apply this check before interpreting apparent stability as a finding.

Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data. Although adversarial training offers a feasible solution, existing methods often rely on external scenario generators, heuristic perturbations, or simulator-heavy rollouts, which makes them difficult to integrate with modern autoregressive planners. Here, we cast adversarially robust planner learning as a constrained min-max game and propose Adversarial World Modeling (AWM), a theoretically grounded multi-agent self-play fine-tuning framework. Since solving the exact game is intractable, AWM introduces a principled decoupled solver. In the inner minimization, the planner's predictive world model is converted into a role-conditioned adversary that learns sparse, scene-adaptive attack coalitions via counterfactual credit assignment. In the outer maximization, the ego planner optimizes a regret-aware robust best response against the frozen AWM, utilizing tail-risk weighting and reference-anchored trust regions to improve hard-case recovery while preserving nominal driving behavior. Experiments on the nuPlan and InterPlan benchmarks demonstrate that our method generates transferable adversarial interactions and yields a robust planner that achieves competitive closed-loop performance in both nominal and highly interactive long-tail scenarios. Theoretical analysis justifies the decoupled solver and the main optimization components.

We present Anamnesis, an interactive system for demographically controllable survey simulation using large language models. Open-source, and designed for non-technical users/researchers, Anamnesis enables the prototyping and stress-testing of survey instruments on virtual populations rather than real human subjects. The platform operationalizes the recently introduced Anthology and Alterity frameworks, which use structured narrative backstories to condition model responses, within a unified web interface. It supports open-ended generation, probabilistic demographic resampling, and multimodal (image and audio) surveys. We evaluate the system through two case studies: (1) replicating segments of Pew Research Center's American Trends Panel (ATP) on political typology and biomedical issues and (2) emulating human preference in the New Yorker Caption Contest. In both cases, Anamnesis produces opinion distributions that more closely match real-world survey data than standard persona-prompting baselines, offering a transparent, reproducible, and open-source alternative to proprietary simulation services.

LLM-as-a-judge evaluation is widely used for retrieval-augmented generation (RAG), but reusing the same model family as both generator and judge makes self-leniency difficult to identify. We introduce Eval-Pair Matrix, a controlled meta evaluation protocol for source-grounded RAG. Starting from GaRAGe questions and grounding passages, we induce one hidden answer-causal contradiction per record, generate answers from perturbed passages with GPT, Grok, and Gemini models, and then use the same models as blind judges to evaluate each answer against the original passages. The experiment contains 300 core records, 897 labeled generator outputs, and 2,683 judge verdicts in a crossed 3 x 3 matrix; the primary analysis uses 275 fully validated records. Instead of comparing diagonal and off-diagonal cells across different answers, we estimate same-model effects by pairing judges on the exact same candidate answer. This changes the interpretation: diagonal and off diagonal F1 are similar, and the paired same-model recall effect is near zero (-0.5 pp; 95% cluster bootstrap CI [-2.7, +1.7]). The only robust paired gap is lower matching-judge flagging for answers that avoided the induced claim (-4.3 pp). A targeted human evaluation finds that reviewed apparent false positives are alternate source-error detections, mistakes in labeling whether the induced claim was adopted, or unclear cases; none were adjudicated as genuine false alarms. The lesson is methodological: RAG judge studies should report full matrices, answer-paired effects, behavior strata, and label-task alignment.

Front-end development accumulates change after change at the repository level, weaving complex cross-file dependencies that current LLM coding agents tuned for single-shot tasks cannot reliably track across multiple iterations, leading to functional regressions and code that resists maintenance. We argue the missing piece is design knowledge: architectural principles, module responsibilities, and structural constraints that developers lean on to keep code readable, maintainable, and evolvable as a system scales. To operationalize this, we propose WebDesignIter, a framework built around a persistent knowledge graph (WebAppArchKG) that fuses repository structure with design knowledge and keeps both in sync across development cycles. WebDesignIter works in two stages: design-informed planning pulls historical context and architectural overviews from WebAppArchKG to produce an implementation plan with corresponding test scripts, and design-aware generation executes that plan through targeted diff-based patches, validated by sandbox execution and automatic syntax repair. On Web-Bench, WebDesignIter delivers an average Pass@2 gain of 9.55 percentage points across nine foundation models over existing baselines. More importantly, WebDesignIter outperforms every general-purpose coding agent Claude Code, OpenHands, SWE-Agent, Codex CLI on every model configuration, posting the highest Pass@1 and Pass@2 while consuming 2530 fewer input tokens. Ablation singles out design knowledge as the most impactful component: stripping it drops Pass@1 by 11.40 percentage points, a degradation far larger than removing code-graph retrieval, patch-based generation, or sandbox verification, confirming that design knowledge provides a fundamentally more efficient and reliable path to repository-level code generation.

We consider the recovery of a pair of sparse vectors from a limited number of nonlinear observations of their superposition: $y_i=g(\inner{\ba_i}{\bPhi\bw^\ast+\bPsi\bz^\ast})+e_i$, $i=1,\dots,m$, with $m\ll n$, incoherent orthonormal bases $\bPhi,\bPsi$, a scalar link $g$, and noise $e_i$ that may be heavy-tailed or contaminated. We propose a regularization-based framework combining a Huberized data fidelity with generalized folded-concave penalties (SCAD, MCP), and a two-block proximal alternating algorithm with backtracking (NLD-PALM) whose whole iterate sequence provably converges to critical points under the Kurdyka--Łojasiewicz property, with local linear rates. On the statistical side we establish restricted strong convexity of the Huberized nonlinear loss through an exact sign-definite decomposition, and derive estimation error bounds of order $σ\sqrt{s\log(n)/m}$ that hold at \emph{every} localized stationary point, an oracle rate $σ\sqrt{s/m}$ free of $\log n$ and shrinkage bias under a beta-min condition, and a co-equal recovery theorem for \emph{unknown} monotone links via a linear surrogate and a clipped Plan--Vershynin decoupling. The estimator requires no knowledge of the sparsity levels, and its guarantees hold under symmetric noise with only finite variance. Experiments at $n=512$ under a frozen data-driven regularization rule show an earlier phase transition than convex $\ell_1$ demixing and greedy hard-thresholding baselines, a $35\times$ accuracy advantage over squared-loss estimation under $5\%$ gross outliers, and successful demixing of spike-plus-background signals observed through a saturating amplifier.

The lineage graph of open-weight language models is self-reported: Hugging Face's base_model metadata field is optional and unverified, and over 60% of Hub models document no parentage at all. Methods for detecting lineage from weights exist in the research literature, but each ships as paper code tied to one signal and one experiment; when a provenance dispute breaks, the analysis is redone by hand. This report describes modelDNA, a tool that fingerprints a model from roughly 100-300 MB of ranged HTTP reads (instead of a full 15 GB download for a 7B model), compares the fingerprint against a reference database of foundation models across four published signal families, and returns one of eight verdict classes with a calibrated probability, preferring honest abstention to confident error. On a benchmark of 15 real Hub models with org-documented parentage, judged against 8 candidate bases (13 positives, 107 hard negatives), the system achieves AUROC 1.0, zero false positives at its reporting threshold, and 13/13 correct top-1 parent attribution. The report's second contribution is merge decomposition. Every mainstream weight-merging method is (near-)linear per tensor, and fingerprint sample positions are deterministic functions of tensor identity, so a merged model's fingerprint is the same linear combination of its parents' fingerprints. Mixture weights can therefore be recovered from fingerprints alone by sum-to-one constrained least squares. Against merges with published mergekit configurations as ground truth, the method recovers a slerp merge's layer-interpolation curves at r = 0.999 and a dare_ties merge's mixture weights to within 0.011 of the published values, without downloading any weights beyond the fingerprints. All fingerprints, benchmarks, and the inferred lineage graph of 55 models are public and reproducible offline.

Training with quantized weights can reduce costs but often results in degraded accuracy, especially when optimization is carried out in low precision, without storing high-precision copies. We identify a key failure mode: under low precision, standard optimizers can get stuck and not make progress, especially at large weight magnitudes due to coarse mantissa resolution. To overcome this, multiplicative updates have been previously proposed, in place of additive updates in standard optimizers. While successful under extremely low precision, such as under the logarithmic number system, they suffer from failures near zero and across sign changes. The failure modes of additive and multiplicative updates are therefore complementary. To exploit this, we propose M+Adam, which combines both update types: additive steps handle sign changes and small magnitudes, while multiplicative steps ensure progress at large magnitudes when additive updates are zeroed out under rounding. We prove monotone descent for M+Adam under standard smoothness assumptions. Across LLaMA-style pretraining with 60M-1B models, 1x-8x Chinchilla budgets, and using only BF16, FP8, and FP4 master weights, M+Adam consistently improves low-precision training.

Efficient waste segregation is critical for sustainable urban management and environmental governance. Existing automated systems are limited by single-modality visual processing, insufficient contextual understanding, and weak regulatory alignment. To address these issues, we propose a language-guided vision-AI framework that integrates vision-language models and multimodal large language models for joint visual-linguistic reasoning. This framework implements a visual question answering paradigm aligned with India's Solid Waste Management Rules 2016. We construct a new WasteVQA dataset with 13,500 question-answer pairs across 21 waste categories. Experiments show that the BLIP-based model achieves a BLEU score of 0.8291 and a BERTScore of 0.9273, outperforming traditional CNN-based methods. This work improves source-level segregation accuracy, ensures regulatory compliance, and supports scalable deployment for municipal and citizen-facing waste management, promoting multimodal AI in sustainable urban infrastructure. The source code and dataset are available at: https://github.com/Khushkataruka/WasteAssistant

Memory is becoming a core component of long-horizon AI agents, allowing agents to reuse past experience when operating web browsers, software tools, and other interactive environments. Existing work mostly treats memory as a supply problem, asking what experience to write, how to store it, and which entry to retrieve for the next task. Yet we still lack a clear account of how models consume retrieved memory across a multi-step action trajectory. This consumption process matters because it determines not only what memories should be retrieved, but also what models and control policies are needed to use them safely. To diagnose this process, we propose Entry--Propagation--Recovery (E-P-R), a trajectory-level framework that asks where memory first changes an action, whether that change carries forward, and whether the agent can recover after leaving a correct path. We instantiate E-P-R on WebArena and on MemTrapBench, a controlled benchmark we build to isolate these phases. We find that the main failure often begins at entry: agents adopt conflicting memory at the first exposed decision point even when it is task-wrong. Repeated exposure then amplifies this early error, while recovery after divergence is weak. Together, these effects create a compliance trap: across models, conflicting memory induces similar compliance rates, but once agents comply, their success rates collapse to a low floor. Stronger agents therefore suffer larger absolute damage because each compliance event erases more baseline capability. These results suggest that memory-augmented agents should be evaluated not only by retrieval quality or final success rate, but by how they consume memory throughout the trajectory.

In recent years, Unmanned Aerial Vehicles (UAVs) or drones have gained rapid response in terms of security, search and rescue (SAR), border surveillance, etc. Existing monitoring frameworks often struggle to maintain detection consistency when targets undergo significant scale variations due to altitude changes, leading to critical information gaps. To address this issue, this work proposes an integrated real-time detection pipeline for detecting targets through the wireless live drone video feed. Build upon YOLOv8-nano architecture, extensive flight experiments were conducted to determine the detection performance across multiple flight altitudes. Trained on VisDrone2019 dataset, the results of YOLOv8-nano model achieves 57.4%, 41%, 44.8% and 20.3% in precision, recall, mAP and mAP50:95 respectively. While demonstrating on real environment, this analysis revealed that the algorithm achieves near-total detection reliability at altitudes between 16 and 25 meters with the detection frame rate consistently maintained above 41 FPS and reaching a peak of 50 FPS. However, the goal of this work is to enable real-time person detection from an aerial platform via wireless transmission. This approach effectively addresses the dual challenges of identifying targets at varying scales and ensuring near-to-accurate localization during aerial observation.

Large Language Model (LLM) agents are commonly trained from expert trajectories using supervised fine-tuning (SFT), which treats multi-turn agent behavior as ordinary text imitation. This recipe is simple and low-cost, but it only learns to imitate the sequence of expert actions, rather than training the agent to choose the right action against plausible mistakes at each state. Existing methods to mitigate this problem include preference learning or reinforcement learning, but they usually need high-cost environment rollouts and reward models. We propose Agentic-DPO, a lightweight offline agent policy optimization method that turns expert trajectories into state-conditioned preference supervision. At each expert action state, Agentic-DPO samples a one-step action from the current state, treats plausible wrong actions as negatives, and contrasts them with the expert action using a DPO-style preference objective. To avoid mixing both policy and schema in preference learning, we introduce Policy-Preserving Augmentation (PPA), which renders the same latent trajectory under multiple schemas while keeping the expert policy fixed. Agentic-DPO requires no online environment rollout, reward model, or full-trajectory student exploration. We conduct experiments across StableToolBench, tau-bench retail, and Mind2Web, where Agentic-DPO consistently improves agents at different model scales beyond imitation. In particular, it raises tau-bench accuracy from 21.7% (SFT) to 41.4% for a 9B model, matching online GRPO under the same backbone with only step-level rollouts and without environment interaction during gradient steps. The results suggest that expert trajectories can support low-cost agentic policy optimization when converted from demonstrations into state-level action preferences. Code for Agentic-DPO is released at https://github.com/Schuture/Agentic-DPO.

Multimodal sentiment analysis relies on language, visual, and acoustic cues, but utterance-level modality quality may vary due to occlusion, background noise, motion blur, or imperfect transcripts, causing conventional fusion to over-trust unreliable modalities. We propose MRUF, a reliability-aware fusion method that combines multi-granularity routing with uncertainty-aware calibration. MRUF summarizes sentiment-relevant representations, performs subspace- and modality-level routing, and supervises modality routing with leave-one-out error increases to estimate utterance-level modality importance. It further predicts modality-wise uncertainty and refines modality gates through inverse-variance reweighting, while modality-invariant contrastive alignment stabilizes the shared representation space. Experiments on CMU-MOSI and CMU-MOSEI under aligned and unaligned settings show consistent improvements over strong baselines, and mechanism analysis verifies that modalities with higher predicted uncertainty receive lower fusion weights.

Normalization is a critical component for stabilizing Transformer training, yet the choice between static strategies such as Layer Normalization (LN) and adaptive alternatives remains largely task-dependent. In this paper, we investigate a key optimization challenge in differentiable normalization gating. Our experiments show that, on relatively stationary vision tasks, the high gradient variance introduced by Gumbel-Softmax gating can hinder convergence of the routing mechanism, causing learned gates to underperform simple random selection. In contrast, on non-stationary language modeling and classification tasks, sustained gating diversity enables the model to learn more effective layer-wise normalization policies. Motivated by these observations, we propose AutoNorm-S (Stabilized), a training strategy that mitigates optimization instability through a gate-freezing schedule. AutoNorm-S achieves competitive or improved performance across multiple benchmarks, outperforming adaptive normalization baselines on NLP datasets, including PTB and SST-2, while remaining competitive on standard vision benchmarks. These results suggest that decoupling normalization selection from optimization noise provides a practical and principled approach for adaptive normalization in Transformer architectures.

Many geometric statistics and manifold learning pipelines routinely produce observations -- such as tangent vectors or local frames -- whose natural home is a varying family of fibers attached to different points of a base manifold, rather than a single shared vector space. Forming empirical averages requires transporting these observations to a common reference fiber, thereby introducing curvature- and holonomy-driven effects that are absent from classical concentration theory. We develop a non-asymptotic concentration theory for such transported empirical means, deriving finite-sample, dimension-free Hoeffding- and Bernstein-type bounds via sharp Hilbert-space inequalities. When shortest paths to the reference point are non-unique, transport becomes path-dependent and introduces a deterministic holonomy bias; we isolate and quantify this bias through bundle curvature and loop geometry, with sharp closed-form formulas for the tangent bundle of a round sphere. The resulting bias-variance decomposition separates the stochastic fluctuation decaying at the classical $n^{-1/2}$ rate in sample size $n$, from a curvature-driven error floor that no amount of additional data can eliminate; minimax lower bounds confirm both terms are unavoidable. We further establish a robust median-of-means estimator achieving optimal rates under heavy tails and the central limit theorem in the reference fiber. Controlled experiments on the sphere validate all theoretical predictions.

Non-binary bottom-up constituency parsing is usually taken to require arity actions: reductions such as \(\textsc{Reduce-}X\#k\) specify both the mother label and the number of children to be composed. We show that this arity parameter is not a necessary transition primitive. Our parser introduces constituent labels separately and recovers reduction spans from delimiter-bounded stack configurations. In a well-formed reduction configuration, arity is uniquely determined by the active delimiter and the label marker, making it a derived property of parser state rather than an action label. This factorization removes label--arity-specific reduce actions while preserving direct construction of original non-binary trees. Experiments on PTB and CTB show that the delimiter-guided parser remains competitive with an arity-specific bottom-up baseline under the same implementation framework, with substantially smaller action inventories. Analyses further show that its predicted arity profile remains close to the gold treebanks and that high-arity constituents do not collapse when arity actions are removed.

We investigate how annotator demographic attributes, supplied as prompt cues, shape the alignment between large language model (LLM) predictions and human annotations across five tasks. Using five open-source LLMs, we systematically vary the number and composition of demographic components in the prompt, spanning every combination from single-attribute through full-attribute configurations. Our experiments reveal three principal findings. First, alignment consistently peaks with one to three high-signal attributes and degrades under the full attribute set, establishing a clear over-specification threshold. Second, the overall magnitude of demographic influence on human annotations does not predict which attributes improve LLM alignment; instead, both the learnability and the directional coherence of each attribute's annotation signal need to be considered jointly. Third, neuron probing reveals that specialized activation correlates with alignment gains only under coherent annotation signals, and that activation volume alone does not imply steerability. Together, these results demonstrate that demographic prompting is not a monolithic intervention: its utility is highly context-dependent, shaped by attribute signal quality, task characteristics, and model architecture.

In contrast to most studies on neural network approximation theory that characterize results through a single parameter, such as the total number of network parameters, \cite{shen2020deep} pioneered the characterization of approximation rates as a joint function of the width parameter $N$ and the depth parameter $L$, thereby granting greater architectural flexibility. Existing works using the $(N,L)$-characterization focus on function classes with finite smoothness $s$, establishing a typical approximation rate of $\mathcal{O}\left(N^{-2s/d}L^{-2s/d}\right)$ with $d$ denoting the input dimension, which indicates that network depth and width play symmetric roles for these classes. In contrast, this paper establishes upper bounds for the approximation of analytic functions, which possess infinite smoothness, via ReLU networks under the $(N,L)$-characterization. Specifically, we derive approximation rates of $\mathcal{O}\left(N^{-C L^τ}\right)$, where $C>0$ is some constant and $τ>0$ is a parameter influenced by the relation between $L$ and $N$. In particular, $τ=1$ if $N$ scales roughly as $L^d$. Our findings reveal that depth plays a more critical role than width in the context of analytic function approximation. The main technical difficulty of obtaining such upper bounds lies in the trade-off between the smoothness parameters and the approximation accuracy. To overcome this difficulty, we employ refined constructions of several ReLU networks to approximate power functions, multivariate multiplication, and polynomials, which may be of independent interest.

Tasks such as customs tariff classification, export control categorization, and standards-based equipment coding require assigning an input instance to a fine-grained class under an explicit regulatory hierarchy. Unlike standard text classification, the correct label in these tasks is not determined by semantic similarity alone, but by rule-defined boundaries, threshold conditions, exclusion clauses, definitions, and local exceptions. As a result, two highly similar inputs may require different labels, while a retrieved passage that appears relevant may still be inapplicable under the governing rules. Existing flat classifiers, hierarchical text classification methods, and retrieval-augmented LLM systems are not designed to jointly enforce hierarchical validity, rule consistency, and fine-grained boundary reasoning. In this paper, we formulate this setting as regulation-driven fine-grained hierarchical classification, where an external instance must be assigned to a fine-grained class through a valid path in a regulatory hierarchy and supported by auditable evidence. We construct four benchmark datasets from representative regulation-intensive scenarios and validate the annotations through an expert-in-the-loop process. We further propose a constraint-aware hierarchical search framework that converts regulatory documents into a searchable tree, retrieves only valid local candidate nodes, and uses structured regulatory fields with evidence snippets to guide each next-hop decision. Experiments show that our method achieves the best mean accuracy on all four datasets and provides interpretable decision paths, with the largest gains on cases involving fine-grained neighboring categories and rule-based boundary conditions.

Large language model (LLM) agents accumulate heterogeneous context, including system instructions, plans, user turns, retrieved documents, tool outputs, and intermediate reasoning, whose key-value (KV) cache can become a major memory bottleneck. Existing eviction policies generally apply the same attention- or recency-based rule to every token, ignoring semantic structure already available to the agent orchestrator. We introduce MemDecay, a training-free, region-aware KV-cache eviction policy. MemDecay assigns tokens region-specific base priorities and decay rates, refreshes retention scores when tokens receive attention, and evicts the lowest-scoring pages under a fixed cache budget while allowing critical regions to be pinned. We also provide a procedure for calibrating decay rates from measured attention lifetimes. We evaluate MemDecay at approximately 450 and 1,700 token contexts using Qwen2.5-1.5B and 3B. Across all settings, attention lifetimes differ by an order of magnitude across regions: system-token half-lives range from 148 to 189 decoding steps, compared with 14 to 16 for scratchpad tokens. Pinning preserves system-region facts at full-cache accuracy in every setting, while no baseline preserves more than 13 of 24. Region-aware retention remains effective as context grows, whereas recency-based retention collapses. Accumulated-attention retention performs better on unpinned content, however, and ablations identify attention-score normalization as the main limitation of the current formulation. These results establish semantic prompt structure as a robust signal for KV-cache management while clarifying how it should be combined with attention-based importance.

AI models are increasingly trained on personal images scraped from social media and public platforms, often without consent, leading to serious privacy violations, such as unauthorized facial recognition and targeted advertising. To counter this, researchers have developed unlearnable examples (UEs), images modified with imperceptible noise to prevent AI models from extracting meaningful information. However, existing UE methods primarily rely on pixel-space noise, which can be bypassed by relearning strategies such as adversarial training, image transformation, and compression. While some techniques improve robustness, they often come at the expense of significant degradation in image utility and perceptual quality. In this paper, we introduce DiffUE to overcome these limitations by injecting noise into the semantic space of images instead of the pixel space. Instead of corrupting pixel values, DiffUE modifies high-level semantic features of images, ensuring robust unlearnability while preserving visual quality and utility. By leveraging a diffusion-based autoencoder framework to manipulate semantic features, DiffUE generates purposeful, natural-looking modifications that effectively resist advanced relearning strategies. Extensive experiments on four datasets, CIFAR-10, CIFAR-100, CelebA-HQ, and ImageNet, as well as a subjective user study, demonstrate that DiffUE significantly enhances the trade-off between image quality and unlearnability, offering a more robust and effective solution for safeguarding personal data in an increasingly exploitative AI landscape.

Existing hypotheses represent a concept in an LLM as a single point, a linear direction, or a Gaussian cluster, yet it remains unclear how and why such structures emerge. Here, we show that concept geometry can be precisely characterized via Laguerre Geometry, in which a concept is defined as a region--a Laguerre-Voronoi cell or a union of cells--allowing us to strictly define, measure, and separate concepts. Building on this formulation, we show that finer-grained concept structures, such as inclusion and hierarchy, are naturally revealed by the Laguerre weights. We then push this geometry inside the transformer. Decomposing each layer into piecewise-linear operators, we show that a token's hidden trajectory is governed by two coupled mechanisms: a static tree of self-contained piecewise-linear flow, and a dynamic transport that hops the trajectory across trees when cross-token attention fires. This decomposition yields Geometric Lens, a training-free, hyperparameter-free method for reading out the exact concept a hidden vector encodes at any layer. We also develop Laguerre Autoencoder, a 2D visualizer that renders both the decision geometry and a model's full reasoning trajectory in one view. Finally, we move beyond explanatory geometry toward actionable interpretability, showing that Geometric Lens recovers the correct factual token when a model is prompted with in-context interference. The code is available on GitHub.

We study stochastic multi-armed bandits on dynamic graphs, where arms correspond to the vertices of a network with time-varying edges. In this setting, the learner is restricted to local movement, selecting only its current node or an immediate neighbor at each round. This constraint decouples best-arm identification from exploitation: even after the optimal arm is identified, the learner may remain unable to reach it through the evolving topology. We identify a process-agnostic structural condition, based on sliding-window mixing, that ensures the graph's intrinsic walk remains stable for both exploration and navigation. Under this regime, we analyze a family of local explore-then-commit algorithms and establish sublinear expected regret. Our framework includes a reward-aware strategy, for which we prove a worst-case safety theorem and a separate performance gain theorem.

Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims about which one matters. We run the missing crossed comparison: an integrity-clean three-arm ablation (baseline / bash_only / code_only) on synthetic computation tasks and SWE-bench Mini modification tasks, holding model, harness, and prompts fixed, with two agents (Claude Code, OpenAI Codex CLI) so the comparison spans both regime and agent-design axes. Across the four resulting (regime, agent) cells, restricting the agent to a single execute_code MCP tool is cheaper than -- or statistically tied with -- its cheapest tool-rich rival in three cells (significantly on Artifact/Claude and SWE-bench/Codex; directionally on Artifact/Codex), with pass rates statistically tied within each cell. The lone exception is SWE-bench/Claude, where code_only is directionally costlier (+14.4%, not significant); a conditional-cost analysis localizes that gap to failure-cost on doomed-run trajectories, not a per-edit tax on successful runs. Two implications: the cheapest tool surface is jointly determined by task regime and agent design rather than by either axis alone, and the headline cost signal lives in cache-adjusted cost -- not pass rate, which is invariant across surfaces at the model sizes we evaluate. The benchmark harness, task suite, and analysis code are available at https://github.com/hyang0129/onlycodes.

End-to-end motion planning has emerged as a promising paradigm in autonomous driving, directly mapping raw sensor data to control commands via deep neural networks. Despite its advantages, its large model size hinders deployment in resource-constrained platforms. In this paper, we present BucketKD, a bucket-based knowledge distillation framework that yields compact and safety-aware end-to-end planners. Compared to the state-of-the-art approach, which relies on simplified planning state representations, BucketKD discretizes critical environmental variables into adaptive buckets that capture richer scene semantics while preserving efficiency. In addition, we design a safety-aware waypoint attention mechanism that evaluates each waypoint's risk level by accounting for both obstacle proximity and relative motion through a time-to-collision (TTC) formulation widely used in transportation research. This enables the student model to better retain safety-critical behaviors during distillation. Extensive experiments in CARLA using the Bench2Drive dataset show that BucketKD significantly outperforms the state-of-the-art in both planning accuracy and safety while maintaining strong compression ratios.

Evaluating the multi-hop reasoning capabilities of large language models remains a significant challenge. Although current models achieve strong results on existing multi-hop question answering datasets, such performance often masks two critical vulnerabilities: (1) reliance on internal parametric knowledge rather than adherence to the provided context, and (2) exploitation of dataset shortcuts, such as single-document cues or type-matching, that diminish the need for genuine evidence aggregation across multiple documents. We introduce CRiT-QA (Counterfactual Reasoning with Traps), a dataset explicitly designed to address both limitations. To neutralize reliance on memorized knowledge and enforce strict context dependency, CRiT-QA transforms factual reasoning chains with counterfactual entities. Furthermore, it injects multi-anchor distractor chains, plausible but incorrect reasoning paths that diverge at different hops. These traps require models to follow the entire reasoning process rather than exploiting shallow heuristics. Our experiments show that LLMs exhibit substantial performance degradation on CRiT-QA compared to standard datasets, exposing their vulnerability to counterfactual conditions and distractor traps. CRiT-QA thus serves as a rigorous diagnostic tool for evaluating genuine multi-hop reasoning and provides a foundation for developing more reliable, evidence-grounded LLMs.

Metal-organic frameworks (MOFs) offer a highly modular platform for adsorptive gas separation, yet their vast reticular design space makes inverse design difficult under simultaneous constraints of chemical validity, separation performance, and structural diversity. Here, we present LEMO Agent, a large-language-model agent framework for closed-loop inverse design of gas-separation MOFs in MOFid space. LEMO Agent couples language-based candidate generation with MOFid standardization, explicit validity checking, Transformer-based property prediction, structured design memory, and multi-island exploration. Through iterative generate--validate--evaluate--remember cycles, the agent uses feedback from both successful and failed candidates to guide chemically constrained search across linker, metal, and topology choices. We evaluate LEMO Agent on CH$_4$/N$_2$ and CO$_2$/N$_2$ separation tasks. Compared with representative generative, optimization, and agentic baselines, LEMO Agent enriches high-performing candidates, improves predicted separation performance, and maintains broad chemical and topological diversity. Selected candidates are further reconstructed, evaluated by GCMC simulations, and passed through an experimental down-selection workflow based on chemical feasibility and ligand purchasability, leading to initial wet-lab synthesis and SEM characterization. These results demonstrate that large language model agents can serve as interpretable and scalable design engines for accelerating MOF discovery beyond conventional fixed-library screening.

Multimodal BrowseComp tasks require agents to combine perception, tool use, and long-horizon reasoning over dynamic web content, challenging their ability to handle compositional structure, open-world uncertainty, and multimodal integration across extended interactions. Crucially, real-world multimodal browsing involves three distinct information-flow patterns: text-only, image-to-text, and text-to-image, yet existing data construction methods cover only the text-only and image-to-text patterns, leaving text-to-image largely unaddressed and limiting agent generality and robustness. We introduce UNIBROWSE, a unified data pipeline that for the first time simultaneously generates training data covering all three patterns, augments curated knowledge graphs with live web retrieval for improved fidelity, and introduces a novel metric of exploration degree to filter low-signal instances for efficient reinforcement learning. Through this pipeline, we produce high-quality cold-start tool-use trajectories and exploration-rich QA pairs, and train a 35B-scale agent via supervised fine-tuning and exploration-aware RL.The resulting UNIBROWSE agent achieves state-of-the-art performance on multimodal BrowseComp benchmarks, attaining an average accuracy of 54.4 across five diverse benchmarks -- an improvement of 10.5 points over its base model Qwen3.5-35B-A3B -- and surpassing serveral closed-source agent workflows such as GPT-5 (42.9), Gemini-2.5 Pro (44.8), and Gemini-2.5 Flash (41.3).

Generative Large Language Models (LLMs) have revolutionized information retrieval, yet their strictly parametric nature frequently leads to severe factual hallucinations when confronted with complex queries beyond their epistemic boundaries. While external tool-calling can mitigate this, indiscriminately invoking search tools for every document during reranking incurs prohibitive latency overheads, creating an intractable accuracy-efficiency dilemma. To address this challenge, we propose TALRanker, a novel framework that formalizes pointwise relevance scoring as an agentic Markov decision process. We optimize it via a two-stage training paradigm. An initial warm-up utilizes a language-preserving hybrid loss to prevent the catastrophic forgetting of native generative capacities. Subsequently, an asymmetric cost-aware reward equipped in reinforcement learning forces the policy to autonomously bypass tools for maximum efficiency when confident, while selectively retrieving external evidence to avert severe hallucination penalties when uncertain. Extensive evaluations demonstrate that TALRanker achieves state-of-the-art performance across standard and reasoning-intensive retrieval benchmarks, matching throughput with pointwise rerankers while outperforming parameter-heavy reasoning models.

With the development of generative AI, watermarking techniques have been widely used to detect the authenticity of AI-generated data and protect the rights of users and creators. While it is already well applied in data types including imaging and text data, watermarking tabular data is still under-explored. Existing methods primarily focus on numerical data, leaving discrete, categorical, and mixed data less studied. In this work, we propose STAMP (Single-observation Tabular Attribution and Marking Procedure), a novel framework for watermarking tabular data that can accommodate and preserve a wide range of distributions. We also develop a corresponding detection mechanism, which can reliably identify watermarks even when the sample size is as small as one. We establish theoretical guarantees for asymptotic consistency and detection accuracy. Finally, through extensive simulation studies and two real-data applications, we demonstrate that the proposed method is effective and robust to subsetting, while maintaining data fidelity and a high detection rate.

Accurate geometric calibration is essential for fluoroscopy-guided spinal imaging, digitally reconstructed radiograph (DRR) generation, and 2D--3D vertebral registration. Although calibration quality is typically evaluated using reconstruction-based metrics such as reprojection error, its influence on projection-domain consistency remains poorly understood. This study presents a synthetic framework for evaluating how intrinsic calibration perturbations affect vertebral fluoroscopic projections and downstream registration performance. CT-derived vertebral models and controlled cone-beam imaging geometry were used to generate DRRs with both ground-truth and perturbed intrinsic calibration parameters while maintaining identical anatomy and acquisition pose. Projection-domain changes were quantified using anatomical landmark displacement, contour distance, silhouette overlap, image similarity, and landmark-based 2D--3D registration accuracy in anterior--posterior (AP) and lateral (LAT) views. Results show that even small intrinsic calibration perturbations produce measurable changes in vertebral projection geometry, contour morphology, landmark localization, and DRR appearance. Sensitivity is strongly view dependent, with LAT projections exhibiting substantially greater deformation and anatomical displacement than AP projections. These projection inconsistencies also degrade downstream 2D--3D registration, particularly rotational alignment accuracy. The findings demonstrate that projection-domain consistency complements conventional reconstruction-based calibration metrics and provides a practical framework for assessing calibration robustness. This approach may improve the reliability of DRR generation and fluoroscopy-guided vertebral registration in image-guided spinal applications.

Pseudo-labeling based on Optimal Transport (OT) has become an effective mechanism for enhancing short text clustering. Existing OT methods are short in modeling semantic consistencies between samples, which may assign different pseudo-labels to semantically similar samples. These erroneous pseudo-labels can cause the model to produce inferior clusters. This paper proposes a novel short text clustering framework, which remedies the neglect of semantic consistency in existing OT methods, generating reliable pseudo-labels to facilitate clustering. Specifically, the proposed approach first designs an instance-level attention mechanism to capture semantic relationships between samples, which are then integrated into the OT formulation to endow the transport process with neighborhood semantic awareness. By solving the proposed OT formulation, reliable pseudo-labels are obtained that simultaneously account for sample-to-sample semantic consistency and sample-to-cluster global structure information. These pseudo-labels are then used as supervisory signals to guide the model to achieve accurate clustering. Extensive experiments demonstrate that the proposed approach outperforms state-of-the-art methods. The code is available at: \href{https://github.com/YZH0905/CAOT-STC}{https://github.com/YZH0905/CAOT-STC}.

Discovering governing partial differential equations (PDEs) from noisy observational data is a fundamental challenge in scientific machine learning. Traditional symbolic regression (SR) methods often struggle to identify accurate equations within vast combinatorial search spaces, largely due to their inability to incorporate essential domain-specific prior knowledge. Furthermore, reliance on pointwise evaluations and discrete finite differences inherently amplifies high-frequency noise, creating deceptive fitness landscapes that derail the optimization process. To resolve these bottlenecks, we propose LLM-PDESR, a framework that integrates the structural hypothesis generation of Large Language Models (LLMs) with a mathematically rigorous evaluation environment. By employing C^4-continuous quintic splines for robust differentiation and subdomain weighted residuals as natural low-pass filters, our approach effectively mitigates the fitness landscape distortion that plagues existing methods. A Pareto-driven feedback loop then enables the LLM to iteratively refine candidate equations, balancing predictive accuracy with structural parsimony. We evaluate LLM-PDESR on 23 canonical PDEs and five structurally novel equations (including a multivariate system) specifically designed to preclude dataset memorization and test true discovery capabilities. Demonstrating real-world applicability, the framework successfully extracts a consistent structural skeleton for an interpretable 1D dynamical surrogate (1D-CACE) directly from noisy ERA5 reanalysis data. Extensive experiments and out-of-distribution testing confirm that LLM-PDESR significantly outperforms state-of-the-art methodologies in structural recovery, noise resilience, and the avoidance of spurious complexity and equation bloat.

Sequential recommender systems typically infer user preferences through single-pass encoding of interaction histories without iterative refinement, relying on increasingly deep architectures to capture complex patterns. In this work, we revisit sequential recommendation from a recursive inference perspective: can user preferences be modeled as a persistent latent state that is recursively refined? We propose RecRec (Recursive Recommendation), a lightweight model that maintains a compact latent state and updates it through a shared recursive module conditioned on interaction evidence. Unlike prior recursive models, RecRec introduces an evidence-anchored correction mechanism that stabilizes refinement by grounding each update in the original interaction context, preventing semantic drift during deep recursive reasoning. Experiments on three benchmark datasets under standard evaluation protocols show that RecRec matches or outperforms state-of-the-art sequential, graph-based, and reasoning-enhanced recommenders while using only 3.9M to 14M parameters. Ablation studies demonstrate that both recursive refinement and the evidence-anchored correction gate contribute significantly to performance, highlighting the effectiveness of recursive latent inference as a scalable alternative to deeper or language-based architectures. Code is available at https://anonymous.4open.science/r/RecRec-6B67/README.md.

We propose a two-stage estimator for structural mediation parameters that combines deep representation learning with G-estimation under the "no essential heterogeneity" (NEH) assumption. We call the method UNIT. In the first stage,TARNet estimates the heterogeneous effect of a randomized treatment on a mediator by learning a shared covariate representation across treatment arms.The resulting conditional average treatment effect (CATE) estimate provides a plug-in approximation to the heterogeneity-dependent component of the weight function entering the G-estimating equation of Zheng and Zhou (2015), which identifies the structural parameters even in the presence of unmeasured mediator-outcome confounding. We show that more accurate first-stage representation learning can yield a more informative plug-in weight and thereby improve the precision of the structural parameter estimator. In simulations with non-Gaussian covariates and nonlinear mediator effects, TARNet weights reduce the Stage-2 standard error of the mediation coefficient by a factor of $1.45$ to $1.51$ (median across replications, $n \ge 2000$) relative to the classical approach, at no cost to bias or coverage.

Existing approaches to infer user traits and generate responses consistent with a persona rely on static prompting. They lack calibrated uncertainty, ignore sequential evidence, and drift during long interactions. We present \textbf{AI YOU}, a framework that continually updates a personality profile with 22 dimensions from conversation and embodies it in a personal digital twin. Practically, the system combines prompting, Bayesian updating, and conformal prediction for persona inference. A periodically refreshed memory anchor and cognitive memory with three layers preserve persona consistency over long interactions. Across the main results, AI YOU \emph{(i)} achieves conformal coverage ranging from 0.921 to 0.976, \emph{(ii)} improves uncertainty calibration and reasoning grounded in memory, and \emph{(iii)} enhances persona fidelity over static prompting in role playing over 100 turns while reducing trait drift, for most evaluated backbones under adversarial settings with multiple agents. The prototype \emph{AI YOU Town} initializes an imaginative twin world for future interaction. The online demo is available at \href{https://quinnnnnne-ai-you.hf.space/}{\mbox{\texttt{quinnnnnne-ai-you.hf.space}}}.

Large language model (LLM) agents are increasingly extended through Agent Skills, reusable artifacts that package natural-language metadata, procedural instructions, and execution-time resources for runtime use. As open-source skill marketplaces expand, users and agents increasingly rely on brief metadata to select third-party skills, making it difficult to detect inconsistencies between a skill's description and its true behavior, a problem we call cross-layer misalignment. To address this issue, we propose Progressive Loading-Aware Hierarchical Contrastive Learning (PL-HCL), an LLM-based framework that detects misalignment by modeling the layered structure of Agent Skills and learning cross-layer consistency. Using a normalized corpus of over 264,000 open-source skills and a human-verified challenge set, PL-HCL improves Macro-F1 from approximately 0.45 for unadapted baselines to 0.87-0.89 across evaluated LLM backbones. This approach offers an effective screening tool for users and operators, as well as design principles for detecting inconsistencies in layered digital artifacts.

Recent advances in LLMs and existing work on programming by demonstration have made it possible for end users to create automations by explicitly demonstrating their behavior to LLMs. However, these approaches rely on the assumption that users know what to automate and what is capable of being automated. Additionally, automation via LLM agents is often expensive compared with programs. We introduce Motif, a system that passively observes everyday browser activity to discover recurring interaction patterns that are programmable, makes recommendations to users whenever a pattern is discovered and generate a program to install after user confirmation. Users can review, and refine the program using natural language. We evaluated Motif in a multi-day study, comparing its ambient discoveries against automations users attempted to build via ``vibe coding.'' With eight participants, Motif discovered more automatable patterns than users recognized. Most of them matched participants' routines and were useful. Follow-up surveys showed most would continue using Motif-generated programs.

Stateful personal agents increasingly maintain long-term user profiles, episodic memories, and reusable skills. This persistence turns conversational sycophancy into a state-writing failure: accepted user-centric claims can be committed as lasting preferences, background facts, or workflows and later reused after the original conversation is gone. We call this persistent sycophancy and introduce the Personal Agent Sycophancy Benchmark (PASB), a 1,600-task benchmark that traces whether a conversational claim is accepted, written into durable agent state, and reused in a later neutral query. Unlike prior benchmarks that provide pre-written memories, PASB evaluates real agents (Hermes-Agent and OpenClaw) that decide what to store. It isolates the write process by combining four scenario framings with four temporal delivery patterns and separating a five-turn persist stage from a cleared three-turn query stage, ensuring downstream effects arise only from durable state. Across twelve models, the commit boundary is the key inflection point: downstream failure increases from 45.0% in session-only episodes to 71.9% after commitment, a consistent increase of 27.0 percentage points. Committed claims exhibit three write-time patterns: status promotion, attribution removal, and scope broadening. These patterns become stronger under memory-like or procedural framing, repeated reinforcement, and even across domain boundaries. These results show that agent sycophancy is fundamentally a state-writing governance problem. Once user content is committed to durable memory, safety must govern what agents write, not only what they say. PASB identifies the write-time controls needed to gate risky commits while preserving the source, role, and scope of stored content beyond response-level mitigations.

Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feedback. Translating this capability to medical imaging remains difficult because each task imposes modality-specific experimentation and strict requirements for validation protocols and prediction artifacts. Here we introduce AMID, an autonomous multi-agent framework for medical imaging model development. AMID first proposes Data-Conditioned Method Planning, which refines coarse task-level search spaces into executable, parallelizable method lanes grounded in task-specific data analysis and runnable medical-imaging resources. It then develops Verification-Guided Two-Stage Optimization, moving from broad early exploration of diverse method lanes to selective exploitation of promising candidates while enforcing strict verification of validation protocols, metric computation, and prediction artifacts throughout the optimization. Across 20 medical imaging challenge tasks spanning diverse modalities and prediction types, AMID outperformed evaluated general-purpose MLE systems and, on several tasks, approached or matched strong human-designed challenge solutions. These results suggest that AMID can turn task-specific medical imaging model development from bespoke manual engineering into an agentic workflow for producing high-performing and auditable model artifacts across heterogeneous tasks.

Activation steering offers a lightweight alternative to fine-tuning for controlling large language models at inference time. While many existing methods implicitly optimize a log-density-ratio objective between desired and undesired activation distributions, they do so heuristically rather than deriving it from a principled optimization problem. Moreover, these methods produce query-independent steering directions that can degrade performance on both in-distribution and out-of-distribution (OOD) inputs. We introduce \textsc{Cobras} (Conditional Optimal Bridge for Riemannian Activation Steering), which addresses both limitations by casting activation steering as a Schrödinger Bridge on the residual-stream hypersphere. This formulation yields, to our knowledge, the first principled derivation of the log-density-ratio steering objective from a well-posed optimization problem. Solving the bridge via entropic optimal transport and extracting the probability flow ODE recovers the widely used density-ratio gradient as a special case when the Sinkhorn potentials are uniform. Crucially, the Schrödinger potentials are evaluated at the current activation, making the resulting steering direction inherently query-adaptive. Empirically, across four models and three alignment axes (helpfulness, truthfulness, and detoxification), \textsc{Cobras} consistently outperforms prior activation steering baselines while avoiding the OOD degradation commonly observed in existing methods. The code can be found at https://github.com/arshandalili/cobras.

When an LLM judge calls a peer review analytical and a human committee calls another review high quality, are they tracking the same thing? We argue they are not, and that the difference matters philosophically. We operationalise Kahneman's dual-process theory into a structured rubric for peer review and release Kahneman4Review, a benchmark of 3,563 rated reviews scored along nine theoretically motivated textual dimensions, eight bias diagnostics, and a continuous reasoning-quality score. Three findings bear on trustworthiness: decision tier is not detectably aligned with the rubric's text-grounded epistemic-quality proxy; public-showcase agentic reviews receive higher raw scores than pooled human reviews, but length and venue explain most of the gap and the samples are not paper-paired; and ICLR review-text diagnostics shift at the 2022--2023 transition, temporally coincident with widespread LLM availability but without identifying its cause. A matched function-probe pilot further shows that the rubric distinguishes textual probes designed to contrast genuine fault-finding with surface fluency. We argue that a trustworthy reliability benchmark for LLM judges must separate analytical form from epistemic function, and propose concrete design choices toward that goal. An interactive demo is available at https://huggingface.co/spaces/nuojohnchen/Kahneman4Review.

LLM agents that conduct research (proposing ideas, writing and running code, analyzing results) can already carry a study from research question to figures, yet cannot be fully trusted. The same question asked twice in a row returns different answers; the agent announces a number that no execution produced, and tool use does not prevent this, because nothing binds what the agent reports to what its tools returned; a small upstream change leaves downstream results silently stale, with no way to list which ones; and the agent re-runs preprocessing and rewrites code it has already produced. We argue these failures share one root: every step of today's agent loop is a stochastic LLM call whose internal state nobody, including the agent, can check. Rather than trying to see inside the LLM, we take a lesson from databases, which earn trust without being watched, because deterministic operators over well-defined state make their guarantees hold by construction. We propose organizing a research project the same way. The project lives in a deterministic, versioned dataflow engine (in effect, a query plan over materialized views), and the LLM, together with the user, is a stochastic compiler that may only edit that plan. The executor never calls the LLM; LLM output enters only as versioned code and data that the executor then runs, and any asserted result enters the record only with an execution behind it. Five design rules at this boundary turn familiar database machinery, from versioning and provenance to incremental maintenance and cost-based scheduling, into guarantees that make research reliable, non-wasteful, transparent, and collaborative. This report presents the diagnosis, the requirements, and the design; the guarantee walkthrough, a prototype, and the research agenda appear in the full version, in preparation. The LLM, we argue, should be the query compiler, never the executor.

Restricted Boltzmann machines (RBMs) represent data by shaping an energy landscape over visible and hidden configurations, but their discriminative use is fragile under out-of-distribution (OOD) inputs: samples outside the training distribution can be absorbed into one of the learned class basins rather than rejected. Here, we analyze this failure mode through the spectrum of the induced visible--visible interaction $J=WW^{T}$, where \(W\) is the visible--hidden weight matrix. Relative to a Marchenko--Pastur random-matrix reference, conventional training spreads spectral weight into many weak, bulk-compatible directions, increasing the effective rank of $J$. When auxiliary random binary images are assigned to a rejection label during training, the learned interaction undergoes effective-rank collapse: weak bulk-like modes are depleted, spectral weight concentrates into fewer dominant eigendirections, and the effective rank of $J$ approaches that of the empirical data covariance matrix. The resulting RBM rejects structured OOD image datasets while preserving MNIST classification accuracy, showing that random auxiliary exposure can reshape both the interaction spectrum and the free-energy landscape of an energy-based classifier.

Software engineering increasingly relies on asynchronous communication artifacts, including recorded meetings where stakeholders discuss concerns, rationale, and decisions. These meetings often include diagram-based representations of requirements, system behavior, component interactions, and trace dependencies. Accessing knowledge from these meetings is challenging because recordings are long and relevant evidence is distributed across speech, slides, and technical diagrams. This paper reports our industrial experience developing and evaluating LMVQA, an LLM-based multimodal question-answering system for technical meeting videos. Developed in collaboration with engineers at Ciena, LMVQA supports the understanding of requirements and design intent by grounding answers in audio and visual evidence, with explicit handling of diagram-rich content such as requirements and UML diagrams. It processes each video once to build a reusable time-stamped evidence corpus for grounded question answering. Across a Ciena dataset and a public dataset, we show that LMVQA significantly improves answer accuracy compared to a state-of-the-art baseline, from 31% to 94% on the Ciena dataset and from 21% to 88% on the public dataset, with larger gains on diagram-rich videos. We further show that, after one-time indexing, LMVQA reduces average response time from 81.3s to 3.3s on Ciena and from 98.4s to 9.2s on the public dataset, while lowering average token-based LLM API cost by about 75%. Finally, our interviews with three domain experts show that engineers particularly value LMVQA for locating software-engineering-relevant information, revisiting rationale, and tracing answers to specific video segments.

Retrieval-augmented generation grounds large language models in external evidence, but most pipelines still treat retrieved passages as deterministic and mutually consistent context. In open information environments, retrieved sources may disagree because of temporal drift, source error, ambiguity, or genuine uncertainty. This paper introduces ERAG, an uncertainty-aware RAG framework that converts retrieved chunks into probabilistic evidence before generation. A lightweight evaluator extracts candidate claims and maps chunk-level support to Dirichlet evidence. A conflict-preserving Dempster-Shafer fusion rule then transfers unresolved disagreement into epistemic uncertainty rather than normalizing it away. The generator is routed to direct answering, conflict-aware answering, or abstention according to the fused uncertainty score. Experiments on CRAG, ConflictQA, and MuSiQue show that ERAG remains competitive with the strongest matched baseline on standard question answering while improving behavior under conflict. On the CRAG ambiguous subset, hallucination decreases from 45.3% for Corrective RAG to a human-calibrated estimate of 34.8%, conflict resolution increases from 35.2% to 51.2%, and expected calibration error improves to 0.122. These results suggest that evidential modeling is a practical mechanism for trustworthy information processing in foundation-model-based retrieval systems.

Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages can carry indirect prompt injections. We present NetInjectBench, a 130-scenario benchmark that separates untrusted artifact text, trusted policy metadata, and evaluation labels for network-operation tool use. The sample contains 40 benign, 40 weak-attack, 40 strong-attack, and 10 approved high-impact change scenarios; each is evaluated with Qwen2.5-7B, Llama3.1-8B, and Mistral-7B. Across 240 attack instances, naive execution reached an 82.50% unsafe tool-action rate. Prompt-only safety, Self-Reminder, Spotlighting, and a Two-Pass LLM Judge reduced this rate to 25.63%, 21.67%, 18.33%, and 10.00%, respectively. Static allowlisting reached 5.00% but blocked all approved changes, yielding 0.00% usefulness and 100.00% overblocking on approved cases. Under the stated metadata-integrity assumption, the metadata-aware policy gate produced 0/240 unsafe attack actions, with a 95% Wilson upper bound of 1.58%, while preserving 99.17% attack-scenario usefulness and 100.00% approved-change usefulness. The findings show that network-operation agents need execution-time authorization boundaries alongside prompt-level instruction hygiene.

Generative AI (GenAI) tools are widely used in academia and software development, where productivity gains may depend not only on technical capabilities but also on users' trust and contextual factors. This paper presents emerging results from an exploratory study investigating the relationship between trust in GenAI and perceived productivity, motivated by Global South contexts. We conducted a systematic literature review, complemented by a grey literature analysis and a survey study. The literature review identified no peer-reviewed evidence at the intersection of GenAI trust, productivity, and Global South settings, while the grey literature revealed only limited insights. At the time of writing, the survey has received 36 valid responses from participants across both the Global North and Global South, including individuals with cross-regional experiences. Preliminary results suggest that respondents born and working in the Global South tended to trust AI more, but did not usually report clear productivity gains from using it. In contrast, respondents born and working outside the Global South reported stronger productivity gains and greater time savings, even though they showed less trust in generative AI. These findings suggest that trusting AI is not enough on its own; productivity also depends on access, the type of task, and how much users need to check the output.

LLM agents can commit durable effects from authority evidence that was valid earlier in execution: a DOM snapshot, approval epoch, version witness, branch token, or worker result. We study the commit boundary at which earlier authority evidence no longer authorizes a durable effect. We call this property commit-time authorization: a durable effect is authorized only if the witness that licensed its derived state remains fresh, causally prior, bound to the same effect, and eligible at commit time. We build a controlled-invalidation suite spanning browser, tool/API, and multi-agent workflows. The suite preserves the user goal and payload shape while invalidating the authority relation before durability. In the primary 54-task matrix, endpoint success remains high: 262/270 runs reach the visible result. Only 55/270 are authorized completions; among the 216 invalidating rows, 207 commit after the authorizing path has failed. All 54 clean controls remain authorized, and a separate 54-run authority-preserving check produces no unauthorized commits. We then evaluate mitigation families. Prompt caution and single-condition checks are insufficient because different hazards break different boundary conditions. Defenses work when they refresh, rebind, replan, or refuse at the durability boundary. CommitGuard, a fail-closed boundary monitor, blocks stale durable-effect attempts on protected commit surfaces when runtimes emit witness, dependency, binding, and eligibility signals. The result is a reporting and runtime-design lesson: endpoint success is a utility metric; authorized commit is a security property.

Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), yet the training process remains notoriously fragile. In this work, we investigate a critical source of this instability: over-optimization, where models exploit training heuristics at the expense of generalizable reasoning. While reverse KL regularization is the standard defense against such degradation, our analysis reveals that it is often insufficient in this regime, as it fails to ensure comprehensive coverage of the reference distribution. To address this, we propose ARMOR (Anchor Rollout and Mixed Optimization for RL), a framework that shifts the paradigm from passive penalty to active sample stabilization. ARMOR comprises two key components: (1) Anchor Rollout, which leverages off-policy data from the reference policy to preserve established solution patterns; and (2) Mixed Optimization, which reformulates the policy objective to enable controlled exploration without relying on auxiliary losses. Extensive experiments on reasoning benchmarks validate that ARMOR effectively mitigates validation collapse, enabling sustained performance improvements over extended training horizons.

Patent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservation of complex logical relationships among claim elements. While Chain-of-Thought (CoT) prompting has been widely used to improve the reasoning capabilities of large language models (LLMs), recent evidence suggests that its benefits may be limited, or even negative, in highly structured or pattern-sensitive tasks. Therefore, this paper investigates whether CoT prompting benefits patent claim generation. We propose a task-specific CoT method for patent claim generation and evaluate its effectiveness through both automatic metrics and human expert assessment. Our results show that reasoning-enhanced prompting can improve claim quality. Moreover, we demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into legal tasks and CoT applications.

This paper presents a data-driven method for modeling the pressure response of a hydraulic clutch control circuit. The system consists of a variable-force solenoid, accumulator, pressure regulator valve, and latch valve, and exhibits nonlinear behavior caused by hysteresis, latch transitions, and actuator dynamics. A baseline model using commanded current variables captured the general pressure response but failed to represent hysteresis and latch behavior accurately. The input vector was therefore extended with current derivative information, and several classifiers were tested to separate latch-related operating regimes before fitting Gaussian Process regression models to the resulting partitions. Nonlinear SVC and gradient boosting produced the highest latch-classification accuracy, and nonlinear SVC was selected for the final local-regression pipeline. The proposed approach was evaluated on unseen ramp-rate data and compared against a physics-based Amesim model. The machine-learning model reproduced the measured pressure response and hysteresis behavior more accurately than the physics-based simulation for the tested operating conditions. These results suggest that machine-learning plant models can complement physics-based hydraulic models during hardware development and controller calibration when representative test-stand data are available.

Large language models (LLMs) have emerged as a powerful tool for retrieving knowledge through seamless, human-like interactions. Despite their advanced text generation capabilities, LLMs exhibit hallucination tendencies, where they generate factually incorrect statements and fabricate knowledge, undermining their reliability and trustworthiness. Multiple studies have explored methods to evaluate LLM uncertainty and detect hallucinations. However, existing approaches are often probabilistic and computationally expensive, limiting their practical applicability. In this paper, we introduce diversion decoding, a novel method for developing an LLM uncertainty heuristic by actively challenging model-generated responses during the decoding phase. Through diversion decoding, we extract features that capture the LLM's resistance to produce alternative answers and utilize these features to train a machine-learning model to develop a heuristic measure of the LLM's uncertainty. Our experimental results demonstrate that diversion decoding outperforms existing methods with significantly lower computational complexity, making it an efficient and robust solution for evaluating hallucination detection.

Partial differential equations (PDEs) are foundational to modeling in science and engineering, but constructing reliable numerical solvers remains labor-intensive, demanding expert knowledge of discretization schemes, stability conditions, and boundary treatments. Recent work has begun to frame PDE solving as a code-generation task for large language models (LLMs), yet existing approaches operate primarily at inference time: relying on prompting, debugging, self-refinement, and test-time scaling rather than adapting the model itself. In parallel, reinforcement learning with verifiable rewards has emerged as a post-training paradigm for code and math reasoning, but its verifiers are typically binary: a compiler runs, or a test passes. Such signals discard the graded structure of scientific correctness, where two solvers may both execute and yet differ in solution accuracy by orders of magnitude. In this work, we introduce RLVP: Reinforcement Learning with Verifiable Physics, an RL post-training framework for multi-PDE solver code generation. RLVP addresses this verifiability gap with a hybrid verifier: hard program-validity checks ensure executability, while continuous physics rewards score function-space accuracy and PDE-residual consistency. A single policy is post-trained across diverse PDE families spanning hyperbolic, parabolic, elliptic, and incompressible-flow systems. RLVP improves over both pre-trained and supervised-only baselines on PDE benchmarks, and shows zero-shot improvement transfer to held-out PDEs. We show that a smaller LLM post-trained with RLVP can outperform prompting a frontier model on in-distribution PDE solver generation. The trained policy shows evidence of compositionality in numerical motifs: it recombines stencils, time-stepping schemes, and boundary-handling primitives learned from the PDEs used in training into generated solvers for unseen PDE problems.

Healthcare organizations often cannot freely centralize patient data because medical records are sensitive, regulated, and institutionally controlled. Federated learning offers a practical alternative by allowing hospitals and clinics to train a shared model while keeping raw data local. However, federated learning is not automatically production-ready or private by default. Model updates can still leak information, and decentralized training introduces operational challenges in deployment, monitoring, rollback, debugging, and governance. This paper examines how MLOps practices and the emerging idea of Federated Learning Operations (FLOps) can make federated healthcare machine learning systems scalable, reliable, and trustworthy. It answers three research questions: how containerization and orchestration support federated deployment, how privacy-preserving mechanisms affect trade-offs among privacy, utility, scalability, and operational complexity, and which post-deployment practices are most important for long-term governance. The central argument is that federated healthcare ML requires more than privacy-preserving algorithms. It needs an integrated MLOps architecture that combines reproducible deployment, secure orchestration, model versioning, audit logging, drift monitoring, heterogeneity management, and clear governance.

Survival models can model time-to-event outcomes using partially observed data. They are widely used in clinical prediction, including cancer risk, disease progression, treatment response, and mortality. Recent models often rely on rich inputs collected at a specific clinical encounter, such as medical images, laboratory tests, electronic health record snapshots, or sensor measurements. In large retrospective datasets, these inputs are usually collected over many calendar years. As a result, they may contain clues about when they were acquired through changes in devices, protocols, documentation, patient mix, or clinical practice. This creates a potential failure mode when outcomes are observed only up to a fixed study end date. More recent records necessarily have less potential follow-up than older records. A model that can infer the record date from the input may therefore learn to predict how much follow-up was available rather than the patient's true risk of experiencing the event. We call this failure mode administrative-cutoff leakage. In this paper, we characterize when this leakage can occur, distinguish it from classical informative censoring and genuine temporal changes in risk, and propose practical ways to detect it. In simulations, we show that administrative-cutoff leakage can inflate fixed-horizon AUC and can also affect Harrell's C-index under realistic follow-up patterns. We then demonstrate the same behavior in a real mammography cohort. These results motivate a simple design principle for survival prediction: for an n-year prediction task, the dataset should provide at least n years of potential follow-up after the latest input date. Otherwise, the models may be subject to bias induced by administrative-cutoff leakage.

Color naming is an important part of human color perception. Its task is to allow people to describe continuous colors using discrete color categories. However, the boundaries between color categories are often unclear, and some colors may be perceived differently depending on their saturation and brightness. While certain color categories remain recognizable across a wide range of shades, others may be associated with different color names when their appearance changes. This study investigates the consistency of color naming for red, yellow, and green color categories using a free color-naming experiment. A set of 18 color samples was selected from the COLIBRI dataset to represent different shades of these colors. Participants (n = 92) were asked to freely assign color names to each sample in Kazakh, Russian, or English without being limited to predefined categories. The results show that color categories differ in their consistency. Green shades were consistently identified as green despite variations in appearance, whereas yellow shades received a wider variety of names, including gold- and brown-related descriptions. Red shades showed moderate naming consistency. Our findings suggest that some color categories occupy broader perceptual regions than others and may therefore be more robust to visual variations. The study results can be used to develop perceptually meaningful color models and color naming systems.

Agentic retrieval-augmented generation (RAG) extends static RAG by allowing language models to iteratively reason, generate search queries, retrieve evidence, and predict answers. However, it remains challenging for models to decide when to retrieve, whether to use lexical matching or semantic similarity, and how to control context granularity to prevent irrelevant tokens from interfering with agent reasoning. In this paper, we introduce GRASP, a reinforcement learning (RL) framework for training agents to adaptively coordinate complementary retrieval tools during multi-step reasoning. GRASP provides the agent with semantic search, keyword search, and paragraph-reading actions, enabling it to retrieve sentence-level evidence and expand further context only when needed. We train the policy with a reward that jointly accounts for answer accuracy, grounded reading, complementary search, and turn efficiency. Experiments on multi-hop reasoning benchmarks show that GRASP improves both retrieval recall and downstream question answering performance compared with single-step retrieval, prompting-based agentic RAG, and RL-based retrieval baselines. Qualitative and ablation analyses show that the learned policy develops interpretable skimming and scanning behavior: it uses semantic search for broad exploration, paragraph reading for local verification, and keyword search for entity-specific evidence. These results suggest that learning to coordinate retrieval signals and context granularity is critical for agent's correct reasoning.

Layout-based 3D scene synthesizers place each object using two human-annotated channels: a categorical class label and a canonical-pose convention. We ask whether a single self-supervised token derived from object geometry can replace both, and study such tokens directly as a representation, decoupled from any synthesizer. A Finite Scalar Quantization (FSQ) point-cloud autoencoder is chamfer-trained on placed 3D-FUTURE furniture with no labels or pose annotations. Diagnostic probes recover fine-category (62.6 +/- 0.5%), super-category (85.6 +/- 1.3%), and yaw (52.7 +/- 0.5 deg) from the codes alone. Swapping the chamfer target from the rotated to the un-rotated point cloud collapses the yaw signal while raising class recovery, showing the codes' rotation content can be set by the training objective. Scaling across asset libraries needs codes that transfer; on an unseen dataset (ShapeNet), alignment is category-dependent: box-like furniture transfers, organically-shaped furniture does not, and a target-blind augmentation partly closes the gap.

Expert background knowledge is often available in practical applications of causal discovery. Such constraints on the true causal graph can help causal discovery in terms of identifiability of causal effects and accuracy of the learned structure, but also in reducing the space of candidate causal graphs. As causal discovery can become computationally expensive for large number of variables, it is crucial to utilize background knowledge effectively during the causal discovery process. However, most current methods only use background knowledge in a postprocessing step after causal discovery to refine the learned graph. In this work, we develop a framework for utilizing background knowledge during the causal discovery process, focusing especially on scalable causal discovery methods that recover only a subset of the whole graph. We implement our framework for multiple algorithms and empirically show that utilizing background knowledge can both reduce computational requirements and increase the quality of the learned structures.

Autonomous CLI agents can now execute hundreds of actions across multi-hour sessions: writing code, executing shell commands, browsing the web, and managing cloud infrastructure, all with minimal human oversight. Does greater autonomy invite greater risk? We introduce ANCHOR, an automated auditing framework that stress-tests CLI agents on illegal tasks grounded in public US court cases. ANCHOR deploys an auditor agent fine-tuned on dark personality data using supervised and reinforcement fine tuning. This auditor roleplays persistent malicious users who decompose tasks, reframe requests upon refusal, and adapt strategies across multi-turn interactions. Evaluating frontier CLI agents, we find that while they often refuse illegal tasks when prompted directly, compliance reaches 100\% under persistent malicious interaction. When agents comply, they frequently exceed user requests, autonomously building infrastructure for large-scale harm, including catastrophic risk scenarios such as large-scale financial fraud and bioweapon development. These findings demonstrate that current alignment techniques are insufficient for autonomous agents and underscore the need for safety evaluations against persistent, adaptive malicious users. We release ANCHOR at https://github.com/garified/anchor

Context engineering decides what information a model carries forward, and current designs meter it in tokens: compressing the past into a bounded recurrent state, keeping a key-value entry for every token, or imposing a fixed budget through a window or eviction rule. All three make the token the unit of memory even when the stream is redundant and the task depends on the distinct information it carries. Building on a companion mechanism paper that opens a cache slot only when an incoming key is novel, so memory scales with the number of distinct items rather than tokens, we develop that allocate-on-novelty cache as a working-memory component and organize context by how a task depends on the past: recall-carried information belongs in a content-addressed novelty cache, summary-carried information in a recurrent state, and locality-carried information in a recency window. The claim is empirical and bounded. On a matched character-level control, novelty-gated attention reaches full-attention performance while attending to about half the tokens, and coupling the cache with a state-space summary matches full-attention coupling at that reduced cost; the advantage grows as context lengthens, while a sliding window is preferable on short, locality-dominated spans. On next-code prediction over synthetic Medicare claims the coupled component leads full attention and every fixed-budget eviction policy at a thousand-event horizon, whereas cost forecasting over the same stream is summary-carried and the cache is neutral. The retained memory is an inspectable table of templates, codes, drugs, or places rather than an opaque state. The experiments are small-scale and use only public data; they establish the primitive that context can scale with distinct information rather than tokens, in a working memory that is content-addressable and auditable.

We model human motor cortex during a wrist-extension BCI task as a port-Hamiltonian system (pHS): a conservative interconnection (gyroscopic coupling between neural phasors) plus a dissipative port (power-law energy decay driven by a GNN surrogate). A metriplectic integrator evolves the phasor state; a Fluctuation--Dissipation-consistent noise channel produces stochastic trajectories at body temperature. Training on \FitTrainN\ real EEG cycles (PhysioNet EEGMMIDB, 3 held-out subjects) reaches a test MSE of \FitTestMSE\ and passes three scale-free criticality rungs: near-critical branching ratio ($σ\approx1$), $1/f$ power-law spectrum, and long-range DFA correlations. The model generates closed-loop neuromodulation signals that restore phase-locking in silico when applied to de-synchronised inputs, suggesting a path toward structure-preserving BCI decoders.

Dimensionality reduction has proven powerful for identifying neural manifolds, which are low-dimensional structures underlying high-dimensional neural activity. These low-dimensional representations have improved the interpretability of population-level coding. Yet whether such low-dimensional representations are biologically relevant and confer functional advantages in learning systems, or merely reflect neuron-level activity, remains contested in neuroscience. We show that an explicit information bottleneck forcing a recurrent neural network to learn a low-dimensional representation is necessary for rotational and out-of-distribution generalisation in a time-series prediction task. Using information-theoretic measures of causal emergence, we characterise the dynamics of this representation across the memorisation-to-generalisation transition, finding a non-monotonic trajectory which shows an initial decrease, a minimum, and a subsequent rise to a maximum, even as prediction loss falls monotonically. This trajectory scales with task complexity, and the magnitude of emergent structure reliably predicts generalisation performance. Analysis of CA1 hippocampal activity in mice learning an alternating maze task reveals analogous non-monotonic emergence dynamics that track behavioural performance. Together, these findings indicate that the ability of neural networks to learn compact, distributed and emergent representations confers a functional advantage for generalisation, supporting a causal role for learned representations in cognition.

Evaluating large language models (LLMs) as multi-turn conversational partners requires probing capabilities that single-turn benchmarks miss: persona consistency, evolving intent tracking, emotional dynamics, and goal completion. We introduce EYT-Bench, a human-centered benchmark built around a three-party decoupled design: a persona-grounded user simulator, a target model that separates intent perception from response generation, and an independent third-party LLM judge with optional multi-judge ensembling. Personas are sampled from public human-curated corpora, Nemotron-Personas-USA and PersonaMem-v2, rather than synthesized, reducing LLM-induced persona bias. EYT-Bench also introduces two trajectory-level metrics: embedding-based intent drift and final-intent completion rate (FICR), inspired by tau-bench. In a 17-target x 200-dialogue evaluation, EYT-Bench reveals four findings: (i) state-of-the-art closed- and open-source models are statistically close on subjective dimensions (empathy / persona / anthropomorphism vary within <= 0.3), but differ by up to 9x on objective intent tracking; (ii) reasoning ("thinking on") sharply improves objective tracking on long-context personas (+0.47-0.50 latent-intent accuracy on Gemma-4) while leaving subjective scores nearly unchanged; (iii) persona format dominates trajectory spread, with FICR saturating above 0.95 on Nemotron-USA but spreading from 0.53 to 0.88 on PersonaMem-v2; and (iv) the warm-up effect is robust on 16/17 models (one outlier, GPT-5.5, reverses the effect), with stable rankings across alpha in [0.05, 0.15]. A cross-judge ablation using deepseek-v4-pro confirms that target rankings and final-intent satisfaction are preserved across judges.

In software analytics, rerunning the same analysis twice often yields different models and conclusions. This reduces trust in the model and limits its use. We find that model instability is a major problem. Across 127 multi-objective SE optimization problems (12,700 test cases), repeated runs of a state-of-the-art optimizer agree on only 13.7% of test cases, even under improved settings. We argue that this instability is not merely noise to tolerate, but a property that can be measured and managed. By adjusting how labels are spent, how complex the models become, and how splits are scored, we obtain models that agree 4.8 times as often as the default configuration. The standard deviation of optimization error falls by 22% on average (mean std 17.4 to 13.6), while recommendation quality improves rather than degrades. In terms of quality, the refined settings are statistically top-ranked on 119 of 127 datasets, compared to 74 for the defaults. We then test causal and data-locality interventions and find that they help only partially, suggesting a residual stability floor. Our evidence suggests there are fundamental limits to stability set by the data itself (noise, scarce labels, proxy objectives, and the many near-equivalent models a dataset admits). We conclude that instability should be treated as a standard evaluation axis in SE optimization, which should be routinely measured, reported alongside performance, and used to calibrate trust in any single run. The methods in this paper provide a baseline against which future efforts to reduce SBSE instability can be judged. To support open science, we offer the following reproduction package: https://tinyurl.com/Model-Instability

Prototype-based Incomplete Multi-view Clustering has recently attracted increasing attention by exploiting prototypes as semantic anchors for missing-view imputation. However, existing approaches are still limited in three aspects. First, they typically focus on enforcing cross-view prototype consistency, while ignoring view-specific information embedded in prototypes, thus limiting multi-view expressiveness. Second, most methods rely on instance-level contrastive learning that only aligns paired samples across views, failing to preserve cluster-level relational structures. Third, missing-view imputation is usually performed using global prototypes alone, without considering local geometric neighborhood structures, leading to inaccurate recovery of missing representations. To address these limitations, we propose a novel framework termed Structure-aware PrOtotype disentanglement foR incomplete multi-view clusTering (SPORT), which explicitly disentangles shared and view-specific components of prototypes while preserving cluster-level relational structures. Specifically, we decouple prototypes into orthogonal shared and view-specific components, aligning only shared components to capture consensus semantics while de-correlating view-specific components to preserve complementary information. Meanwhile, a structure-aware contrastive learning mechanism is incorporated to explicitly model cluster-level relationships during cross-view representation learning. Furthermore, a hybrid imputation strategy integrates global prototype matching with local neighborhood matching, enabling joint exploitation of semantic prototypes and manifold structures for missing-view recovery. Extensive experiments on six benchmark datasets show that SPORT achieves superior performance over state-of-the-art methods under various missing rates.

Reliable correlations of Charpy impact test results between sub-sized and full-sized specimens are essential for structural integrity assessments, particularly in nuclear applications, where spatial constraints and limited material volume restrict specimen size. Although standards such as ASTM A370 and BS 7910 provide guidance on conversion methodologies, and numerous analytical correlation methods have been proposed in prior studies, these approaches generally have limited accuracy and their applicability is often constrained to specific materials, treatment conditions, and specimen geometries. In this study, a Machine Learning (ML)-based framework is proposed for correlating Charpy impact properties across specimen sizes. The proposed approach maps absorbed energy values across the full ductile-to-brittle transition region by applying a temperature shift combined with scaled residual projection, to align sub-sized test data with full-sized response. From the resulting temperature-energy profiles, the correlated values for upper shelf energy (USE) and ductile-to-brittle transition temperature (DBTT) are extracted by fitting data with a hyperbolic tangent model. The framework is validated using a dataset comprising 389 matched sub-sized and full-sized Charpy impact tests on SA533B steel. This ML-based approach demonstrates an improved correlation performance relative to conventional analytical methods, achieving R2 values of 0.942 for USE and 0.892 for DBTT. The trained ML models do not require access to full-sized Charpy data during inference, making this approach suitable for material surveillance programs, accelerated irradiation testing, and other applications involving small-size Charpy impact testing.

Large Language Models (LLMs) are increasingly used for code smell detection tasks due to their ability to interpret program semantics. However, their reliability in this context remains poorly explored, particularly under varying prompt conditions where model predictions may be influenced by external cues rather than code characteristics. One such limitation is sycophancy bias, where models tend to align their outputs with user-provided assumptions instead of performing objective analysis. In this paper, we present the first systematic empirical study of sycophancy bias in LLM-based code smell detection. Using the MLCQ dataset, we evaluate how different prompt framings like confirmation bias, contradictory hints, and false premises affect model predictions. Our results show that LLMs are highly sensitive to prompt variations, with Decision Flip Rates reaching up to 72% and False Alignment Rates exceeding 90%, indicating substantial instability and agreement with misleading prompts. To address this issue, we propose Evidence-Guided Debiasing Prompting (EGDP), a structured prompting strategy that enforces evidence-first reasoning. EGDP reduces decision instability and improves robustness, lowering Decision Flip Rates to as low as 12% and False Alignment Rates to as low as 21%, while increasing reliance on structurally grounded evidence. Our findings demonstrate that sycophancy bias poses a critical threat to the reliability of LLM-based code smell detection, and that evidence-guided reasoning provides an effective and generalizable mitigation approach.

Reliable forecasting of several interrelated environmental variables - such as regional precipitation and temperature, or other correlated geophysical fields - across many locations calls for accurate predictions accompanied by trustworthy statements of their uncertainty. Modern deep-learning models forecast such variables accurately but usually report no uncertainty, and forcing them to output uncertainty through maximum likelihood tends to degrade their accuracy, especially when the variables are strongly correlated. Motivated by this tension, we develop TSCoNet, a two-stage convolutional-recurrent model coupled with a Gaussian copula that jointly forecasts multiple variables over space and time while quantifying predictive uncertainty. The method first learns accurate mean forecasts and then, holding the mean fixed, refines a shared representation to estimate the predictive variance, yielding calibrated prediction intervals after a standard recalibration, so that uncertainty is added without sacrificing point accuracy. We study the approach on simulated non-stationary spatial fields on the sphere and on a real dataset of monthly precipitation and temperature for fifty cities over 2000-2020. The model matches the accuracy of a strong deterministic forecaster while supplying calibrated prediction intervals that the deterministic model cannot, giving a single tool that provides both accurate point forecasts and reliable uncertainty for multivariate spatio-temporal data.

Self-supervised learning (SSL) has emerged as an effective paradigm for learning transferable representations from large-scale unlabeled whole slide images (WSIs). However, existing SSL methods primarily learn generic visual features and often fail to explicitly capture pathology-specific morphological patterns that are critical for disease characterization. To address this limitation, we propose Tiny Vision Transformer with Pathology-Aware Prototype Distillation (TVT-PAPD). This self-supervised pathology representation learning framework integrates a Tiny Vision Transformer (TVT) with a novel Pathology-Aware Prototype Distillation (PAPD) module. PAPD employs a learnable pathology prototype bank to discover and preserve representative tissue morphology patterns, encouraging semantically similar pathological regions to learn consistent and discriminative representations. The proposed framework enhances pathology-aware feature learning while maintaining computational efficiency with 90M parameters. Experiments on the Cancer Genome Atlas (TCGA) low-grade glioma (LGG)/glioblastoma (GBM) dataset and the Indian Pathology Brain (IPD-Brain) dataset demonstrate that TVT-PAPD achieves weighted F1-scores of 93.02% and 90.23%, respectively, for LGG-GBM classification, while exhibiting strong cross-cohort generalization across independent glioma datasets.

Controlling attributes is a critical step toward achieving the final creative outcome, yet current approaches fall short in supporting users in the iterative refinement of generative content. We propose Spatula, a proof-of-concept system that generates on-demand, in-situ attribute control interfaces and interactions for creating motion graphics. Building on a technical probe that automatically analyzes animation context and generates corresponding attributes and UI, we frame attribute control as an explorable landscape and explore the attribute control space along four key dimensions: Discoverability, Resolution, Scope, and Expandability. Findings from a user study (N=12) show that our system provides intuitive and convenient interactions while supporting diverse needs for fine-grained parameter control. Furthermore, our applications demonstrate that the plug-and-play design generalizes to other domains, such as web design and 3D modeling.

Large language models (LLMs) have transformed misinformation from a primarily content-centric problem into a broader ecosystem-level security challenge. When misused, LLMs create risks beyond false content generation, enabling attacks on the social contexts, evidence sources, retrieval corpora, and verification workflows that misinformation defense depends on. In this paper, we introduce a role-layer framework to unify these risks and defenses. The role dimension characterizes LLMs as attackers, defenders, and vulnerable components of verification systems, while the layer dimension covers content, social contexts, evidence environments, and verification workflows. Guided by this framework, we organize LLM-enabled attacks, investigate LLM-based detection and verification methods, analyze vulnerabilities in LLM-centric detection paradigms, and discuss existing countermeasures against LLM-enabled attacks. Building on this synthesis, we identify three key open challenges: moving from static detection accuracy to budgeted ecosystem-level risk evaluation, hardening LLM-centered verification pipelines against adversarial manipulation, and deploying auditable human-in-the-loop verification systems for trustworthy real-world misinformation defense.

Vision language models (VLMs) have achieved strong performance on visual document understanding benchmarks such as DocVQA, ChartQA, and MMLongBench-Doc. However, real-world documents combine multiple factors such as length, layout complexity, modality, and question difficulty, which makes it difficult to attribute model failures to specific causes. We introduce SynthDocBench, a fully synthetic benchmark for long-context visual document understanding that systematically controls factors including document length, layout structure, modality composition, and question type. The benchmark is constructed using a combinatorial design, each factor is varied independently across generated documents, enabling controlled analysis of model behavior. Documents are generated end to end using an LLM pipeline across six layout archetypes, with a 40 percent random override to prevent models from exploiting spurious correlations. Additionally, SynthDocBench spans long-context documents with substantially greater length and structural diversity than existing benchmarks. Evaluating seven frontier VLMs, we uncover three failure modes that existing benchmarks cannot surface: sharp degradation with document length, a systematic positional sensitivity in which the middle third of a document is hardest for five of six models and five of six models show a negative Early-to-Late trend (steepest decline: 8.3 percentage points), and breakdown of chart comprehension in long-document settings. These results suggest that current models may be overfitting to benchmark artifacts rather than achieving robust long-context visual document understanding.

Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks. We challenge this convention by introducing the notion of recoverability: the capacity of intermediate representations to correct last-layer failures. By evaluating independent classification probes at every model depth across 16 datasets, we observe that intermediate probes correctly classify 18% to 76% of samples that the last-layer probe misclassifies. We show that these gains are not primarily driven by predictive diversity, but by a redundancy-correctness correspondence, where the internal hierarchy acts as a series of stable, redundant probes of a shared discriminative signal. While established horizontal ensemble strategies (i.e., across multiple models) can improve performance, they incur high computational cost and ignore this vertical signal within a single model. To bridge this gap, we propose VFusion, a principled vertical aggregation strategy employing a learnable mapping into a low-dimensional latent space that synthesizes features across the internal ViT hierarchy. VFusion substantially outperforms established aggregation baselines in both in-distribution and out-of-distribution settings, notably closing 45% of the accuracy gap between the best individual layer and a theoretical oracle performance. Our gains consistently generalize across model sizes and pre-training regimes, confirming that VFusion offers a robust and efficient alternative to horizontal ensemble methods. The code is available at https://github.com/francescodisalvo05/vit-vertical-fusion.

Although large language models (LLMs) have shown promising potential in news summarization tasks, their performance on long-document summarization remains challenging as their length often exceeds the input limits. As the agent investment, which provide possibility to improve the inherent capabilities of LLMs. To enhance the effectiveness of long-document summarization based on LLMs, this paper proposes an expert-editor stepwise questioning multi-agent method, in which the expert and the editor guide another agent to refine the summary by posing questions on different aspects of the content and providing targeted clues for revision. We conducted experiments on two representative long-document scientific datasets and evaluated the results through widely recognized automatic metrics. The results demonstrated the effectiveness of our method.

A persistent interactive world model keeps its running state resident on the GPU that serves it: a multi-gigabyte attention cache, almost all of it rewritten at every generation step. That state cannot be recomputed in interactive time or approximated without changing the world, so a live session pins its device. The pin is a scheduling problem. WorldMove moves a live session under one guarantee: the destination is bit-identical to the source, or nothing is installed. It relocates the cache in 18.8 ms same-node, 101x faster than save/load. It holds a checksum-verified 92.1-94.8 Gb/s on a 100 Gb fabric. At that rate the cache fits inside one interactive block. Migrating an actively generating session, it converges at a block boundary and the destination continues the world bit for bit. An admissibility condition decides each move. The move must complete inside the readout horizon, over bandwidth that covers the state plus its dirty rate. Lifted to a fleet schedulability test, it governed a consolidation loop that executed 48 of 48 migrations bit-identical across two providers. Two constraints are structural. Bit-exactness survives only inside a controlled configuration of one GPU architecture, so moving the state is the only way to preserve it exactly in interactive time. Verification cannot hide inside the wire on this fabric. Receive-path checksums stall the transport at protocol timescales under fan-in, and unscheduled incast silently collapses a receiver while every delivered byte stays correct. An incast-aware admission controller holds zero misses to 1.4x offered load and sheds overload as rejects. A lossless GPU codec widens the admission gate to fabrics raw motion cannot use. We exercise the serving loop and the mover separately, each end to end. Their composition on one fabric is unbuilt. Exact-state elasticity is a joint scheduling problem over transport and verification.

Artificial intelligence (AI) is transforming electron microscopy by enabling quantitative analysis of increasingly large and complex datasets for nanoparticle characterization. Recent advances in machine learning (ML) and deep learning (DL) have expanded microscopy from a descriptive imaging technique into a data-driven platform for structural interpretation, dynamic analysis, and scientific inference. This review examines AI methodologies for nanoparticle electron microscopy, focusing on transmission electron microscopy (TEM), high-resolution transmission electron microscopy (HRTEM), scanning transmission electron microscopy (STEM), and in situ TEM. The discussion is organized around the principal challenges in nanoparticle characterization, including particle detection, segmentation, morphology quantification, atomic-resolution restoration, defect identification, two-dimensional-to-three-dimensional structural inference, and analysis of dynamic processes in situ. We review computational approaches from conventional ML and convolutional neural networks to transformer architectures, self-supervised learning, foundation models, multimodal AI, and physics-informed learning. We further discuss integrating microscopy data with simulations, metadata, and autonomous experimentation to relate nanoparticle structure, dynamics, synthesis conditions, and functional properties. The advantages, limitations, benchmarking, and data requirements of current methodologies are critically assessed. Finally, emerging opportunities for foundation models, AI-guided microscopy, closed-loop experimentation, and autonomous materials discovery are discussed. By integrating advances across computer vision, materials informatics, and electron microscopy, this review highlights the role of AI in next-generation nanoparticle characterization and accelerated materials discovery.

Temporal grounding in long recordings remains challenging for audio-conditioned LLMs. We present a time-aware audio LLM that answers questions with explicit timestamps over up to 120 minutes of input. Our approach interleaves periodic time markers with continuous audio tokens using large-scale synthetic supervision from a cascaded pipeline. Our model achieves strong temporal-grounding accuracy on short and long benchmarks and supports time-anchored fragment descriptions and summaries. Extensive ablations examine how time representation, marker frequency, tokenization, and duration-mixture design affect accuracy and computational cost. We release model weights and datasets to support further research on time-aware audio understanding, available at https://huggingface.co/ai-sage/GigaChat3.1-Audio-10B-A1.8B.

Large language models (LLMs) excel at generating long chains of thought, but long reasoning traces are often verbose and memory-inefficient. In this work, we introduce Structured Thoughts, a framework that organizes reasoning into alternating <try> and <outcome> blocks: <try> captures exploratory scratch work, while <outcome> contains the distilled conclusion of that step. We construct a dataset of structured thoughts by segmenting reasoning traces into <try> blocks and prompting an LLM to summarize each step into its corresponding <outcome>. Fine-tuning pretrained foundation models on this reformatted data produces models that adopt the structured reasoning style, leading to performance gains of up to 8.08\% on reasoning benchmarks compared to standard SFT. The explicit structure also enables context pruning: after each <try>/<outcome> pair, the <try> can be pruned, allowing the model to retain conclusions without keeping the full scratch work in the context. A proof-of-concept pruning implementation achieves an average of 85\% memory / context savings with an 8.67\% performance drop across mathematical tasks.

Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse embodied tasks. Current approaches typically achieve this integration via monolithic policies that map observations directly to actions, yet they often suffer from coordinate drift and poor handling of long-tail semantics. Furthermore, these black-box mappings lack interpretability, hindering the simultaneous achievement of generality, robustness, and transparency. We present ABot-N1, a step toward a general Visual Language Navigation foundation model, that addresses these challenges by decoupling cognition from control via a slow-fast architecture guided by dual visual-language signals. More specifically, a slow vision-language reasoner performs explicit Chain-of-Thought reasoning while producing a pixel goal. This compact set of image-space anchor points serves as a universal interface for diverse tasks, including point-goal, object-goal, poi-goal, instruction-following, and person-following. Subsequently, a fast action expert leverages both the textual cues and the pixel guidance to generate continuous waypoints at the native control frequency. By bridging high-level intents and low-level control through pixel-grounded anchors paired with explicit linguistic traces, our approach ensures robust, generalizable, and interpretable navigation across simulation and real-world benchmarks. ABot-N1 establishes new state-of-the-art records, delivering massive gains specifically in urban-scale navigation: boosting POI arrival by 35.0% (to 77.3%) and achieving 95.4%/92.9% SR in complex indoor and outdoor scenes. It also maintains superior robustness across object-reaching, person-following, and instruction-following tasks. New Point-Goal/POI-Goal benchmarks are released as open source to advance the field of urban-scale navigation.

We introduce CAFE (Compound-AI Factorial Evaluation), an open-source platform that brings design of experiments to the evaluation of compound AI systems (CAIS). Such systems expose many interchangeable choices - e.g. which retriever, model, or prompt - and practitioners rarely know which of them most affects answer quality. With CAFE, a practitioner registers each swappable component of a pipeline as a factor to build a factorial design over the chosen factors, run the resulting configurations, and score the answers on a shared rubric using a configurable LLM judge together with human raters. From these ratings it attributes answer-quality variance to the components and their interactions with mixed-effects models and reports effect sizes, significance, the best configuration, cost and latency trade-offs, and judge-human reliability. Whereas existing tools mostly either search for a good configuration or score outputs in isolation, CAFE also explains which component drives quality and whether an observed difference is significant. We validate CAFE on a retrieval-augmented question-answering (QA) pipeline over the HotpotQA benchmark dataset, where it recovers planted factor effects and stays calibrated under a permutation null. CAFE is released as a Python package and as a Web application.

Despite recent scaling successes, multilingual ASR performance remains highly uneven, with long-tail languages suffering from severe data scarcity. This work addresses the challenge of building robust foundation models for underrepresented Central Asian languages (Kazakh, Kyrgyz, Uzbek). We present GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio using a HuBERT-style objective. Crucially, we introduce a cluster-level data balancing strategy during pre-training and a domain-aware sampling method during fine-tuning to mitigate head-language dominance. In controlled comparisons, our approach outperforms strong open pretrained encoders (Whisper Large v3, Omnilingual-1B) on target languages, achieving significant gains on spontaneous speech while maintaining efficiency. We release the foundation encoder and ASR model, offering a proven recipe for effective multilingual adaptation under realistic data imbalance.

Flow-matching policies have emerged as an effective policy parameterization for robot learning. They iteratively generate actions from noise, enabling highly expressive modeling of complex and multimodal action distributions. However, prior works observed that scaling these policies with value-gradient reinforcement learning (RL) often leads to training instability. Existing methods attribute this instability to iterative generation and therefore avoid end-to-end value-gradient optimization by sacrificing iterative generation, high expressiveness, or value-gradient optimization. Contrary to prior belief, we show the instability does not stem from iterative generation itself, but from the vanilla sampling strategy originally designed for behavior cloning, which becomes brittle under value-gradient RL. Motivated by this insight, we propose VINE, an RL-oriented sampling method that enables stable end-to-end value-gradient optimization for flow-matching policies. Instead of following a single flow trajectory, VINE reconstructs a new interpolation state at every denoising step, creating a stable differentiable path for value-gradient propagation while remaining compatible with the original flow-matching denoising process. As a result, VINE preserves the expressiveness and iterative generation of flow-matching without sacrificing end-to-end value-gradient optimization. Despite performing end-to-end backpropagation through all ten denoising steps, VINE achieves stable policy improvement and consistently outperforms state-of-the-art RL methods on the OGBench offline RL benchmark and real-world robotic manipulation task. Videos are available on our website: https://agibottech.github.io/vine.

Quantum networks are advancing towards larger and more operational infrastructures, yet their evaluation remains fragmented across heterogeneous physical platforms, simulators, protocols, and architectural abstractions. Current digital-twin studies for quantum networks mainly realise isolated capabilities or application-specific solutions rather than reusable system-level twins. This paper argues that Model-Driven Engineering (MDE) can provide a systematic basis for integrating and evolving these heterogeneous artefacts. It derives requirements for design-time evaluation and runtime synchronisation, and proposes a progression of architectures from code-driven and domain-model-driven solutions to point-to-point and hub-and-spoke integration. A conceptual implementation case study illustrates this using SysML v2, QKD kit, an EMF-based controller, and SeQUeNCe. The work provides a foundation for adaptable and interoperable digital twins for quantum networks.

Offline-trained surrogates for Inertial Confinement Fusion (ICF) suffer a well-known failure mode that iterative optimizers drive inputs into out-of-distribution (OOD) regions where predictions become unreliable. Here we present Co4ICF, a co-evolving framework that couples a physics-informed surrogate with a PPO-based pulse optimizer. The surrogate is iteratively fine-tuned on policy-induced trajectories, correcting extrapolation errors as the optimizer shifts the input distribution; the optimizer queries this evolving surrogate as a fast environment. In the 1D MULTI environment, Co4ICF achieves 146.1% normalized yield based on current laser design baseline; as a post-hoc cross-fidelity check, the optimized pulse further attains 246.9% normalized yield when directly evaluated in 2D-MULTI without any 2D training or fine-tuning. Budget-matched ablations support that the gains are not explained solely by additional simulation data and are consistent with the co-evolving mechanism playing a key role. We release a large-scale MULTI-IFE simulation dataset to support future benchmarking.

Vision Transformers (ViTs) are difficult to interpret because current methods of relevance propagation and attention flow do not fully consider some key architectural features, such as the uneven importance of attention heads and residual connections. Prior approaches typically assume uniform importance across attention heads; furthermore, they model skip connections as identity paths, leading to inaccurate relevance attribution. To address these issues, we introduce GradSkip, a novel relevance propagation method for ViTs based on adaptive head weighting and skip-aware propagation. GradSkip models the different importance of the attention heads and dynamically distributes relevance between the attention and residual paths. Experiments on ImageNet1K and BloodMNIST demonstrate a state-of-the-art faithfulness of GradSkip while requiring over 14 times fewer GFLOPs than the best-performing existing approaches. Additional evaluations using transformer-based segmentation confirm improved localization and alignment with ground-truth regions.

In radiation transfer simulations, an M1 method achieves substantial computational savings by replacing the full angular transport equation with a low-order moment system. Because this reduced system is not closed, a closure model is required to represent the unknown higher-order moments using lower-order moments. While machine learning (ML)-based closures can improve accuracy beyond classical analytic closures, unconstrained learned closures may produce non-real characteristic speeds and consequently cause numerical solver breakdown. To guarantee real eigenvalues of the Jacobian associated with ML closures, we propose a hyperbolic neural closure for the M1 radiative transfer system. Rather than directly predicting closure terms, we parameterize the Jacobian through two neural networks: (i) a symmetric matrix network and (ii) a strictly convex entropy network whose Hessian defines a positive definite symmetrizer. These components are combined to yield a Jacobian that is similar to a symmetric matrix, thereby ensuring real eigenvalues. The closure is then reconstructed by numerical integration of the learned Jacobian field along a prescribed integration path. Numerical experiments show that the proposed closure not only achieves higher closure accuracy than classical analytic closures, but also improves solution accuracy and remains stable in discontinuous Galerkin simulations for radiative transfer problems.

Latent world models are trained to predict future states in a learned representation and are then deployed inside a planner that selects actions by simulating them forward. Current practice adopts the prediction error, the single- or multi-step rollout loss on held-out data, as the training and model-selection objective, on the assumption that a lower prediction error yields better control. We show that this assumption is unreliable for a structural reason: a planner does not query the model on the training distribution but on the states that its candidate actions reach, which generally leave the data manifold, so an error averaged over the data cannot by itself govern control. We therefore reframe the objective as the discrepancy between the predicted and the true plan-cost at the plan the planner commits to, and prove that the planner's suboptimality is bounded by twice this discrepancy, whereas the data-averaged prediction error neither bounds nor tracks it. Under a linear-control premise the discrepancy separates into two terms. The first is a small on-manifold residual, on which the predicted and true dynamics agree and which a spectral tax prices through the non-normality of the latent transition operator. The second is an off-manifold divergence, on which an action carries the state off the manifold and the two dynamics diverge; this divergence is the binding term and is bounded by no data-averaged error. Synthetic operators confirm the pricing formulas, and latent model-predictive control experiments confirm the decoupling: across seeds, the single-step validation error is essentially uncorrelated with control success, whereas a fidelity score on the planner-reachable measure tracks it.

Foundation models are increasingly used as image feature extractors for mammography, but their robustness under external domain shift remains unclear. We benchmark 15 foundation-model backbones across breast density, BI-RADS severity, and cancer status using a unified frozen-backbone linear-probe protocol, training on 3 source datasets and evaluating on 12 task-compatible out-of-distribution (OOD) datasets after label harmonization. Mammography-specific vision-language models (Mammo-FM and MaMA) provide the strongest mean OOD performance, but robustness is not explained by mammography exposure alone. DINOv3 remains a competitive vision-only baseline, and mammography-adapted pretraining does not consistently improve generalization. Dataset-level analysis further shows that even leading models show heterogeneous performance across datasets. Feature-space inspection reveals that useful representations can preserve clinical signal while retaining dataset and acquisition structure. These findings highlight dataset-level OOD evaluation as a central criterion for assessing mammography representations. Our code is publicly available: https://github.com/biomedia-mira/mammo-ood.

The automatic detection and classification of cardiovascular disease (CVD) from computed tomography (CT) images plays an important role in clinical practice. Recently, a hybrid pipeline (GRC-Net) for CVD classification was proposed, which leverages a deep-learning-based segmentation and registration method to extract radiomic and geometric features. However, GRC-Net relies on a deterministic segmentation mask, without considering the inherent ambiguity associated with cardiac anatomy. In this paper, we propose GRC-ProbNet, which takes advantage of a deep ensemble to produce multiple segmentation masks for a given input. From these masks, we extract multiple uncertainty features. We analyze these uncertainty features for both their correlation with segmentation error and their propagation effects on downstream CVD classification performance. Our experiments on the publicly available MM-WHS and ASOCA datasets show that the uncertainty measure that best reflects segmentation quality is not necessarily the one that provides the strongest signal for downstream CVD classification. Overall, our results demonstrate that GRC-ProbNet utilizing uncertainty features substantially improves CVD classification AUROC (92.92\) compared to the baseline GRC-Net model (91.25%). Our code is publicly available: https://github.com/biomedia-mira/GRC-ProbNet.

Recent VLM and VLA systems have improved robotic perception and action prediction, yet long-horizon embodied agents still require a general runtime layer for reasoning, memory, tool use, verification, and cross-embodiment execution. We present ABot-AgentOS, a general robotic Agent Operating System that sits above low-level controllers and provides a deliberative agent layer for scene-conditioned planning, context-isolated skill execution, multi-stage verification, multi-modal memory, and edge-cloud collaboration. To evaluate such systems, we introduce EmbodiedWorldBench, an executable benchmark with 16 indoor, outdoor, and hybrid scenes, four difficulty levels, and over 200 tasks involving navigation, object search, NPC dialogue, dynamic events, and trace-grounded scoring. ABot-AgentOS further introduces Universal Multi-modal Graph Memory, a persistent source-grounded substrate that converts dialogue, visual observations, spatial context, temporal relations, and task traces into typed nodes and edges. A failure-driven self-evolution loop converts diagnosed memory failures into gated runtime evo-assets that are promoted only to later evaluation splits, preventing current-split ground-truth leakage while enabling continual improvement. On an initial EmbodiedWorldBench subset, ABot-AgentOS improves over a single-controller baseline in both task success and goal completion. Across memory benchmarks, ABot-AgentOS Static achieves 87.5 on LoCoMo, 59.9 on OpenEQA EM-EQA, 88.6 on Mem-Gallery, and 76.5 Acc@All on NExT-QA; self-evolution further improves LoCoMo to 88.7, OpenEQA to 60.4, and Mem-Gallery to 89.0. These results suggest that a general Agent OS layer can improve long-horizon embodied execution while providing persistent, auditable memory for continual interaction.

Quantum technologies are maturing into systems that classical engineering must build, verify and maintain. The model-driven community has begun to respond with quantum-aware pipelines and languages, and the domain models these produce must be synchronised with the heterogeneous models created and owned by other communities. We argue that existing synchronisation approaches are insufficient for engineered quantum systems. A quantum system description captures superposition and entanglement, which a model transformation could remove undetected, while every structural check passes. To address this, we present the Quantum Systems Model Management (QSysMM) Framework, which guides the construction and synchronisation of the models of a quantum system into a digital single source of truth. The framework features four concerns: ontological, abstraction, composition and exposure, each given the treatment that engineered quantum systems require. Within this framework, we propose a Quantum Systems Modelling Language (QSysML) on the SysML v2 technology stack, and we close with a proposal that matures this synchronisation core into full model management for quantum systems.

Recent studies on partial audio spoofing mainly focus on studio-recorded speech with temporal localization of spoofed segments. However, these studies often overlook realistic conditions where spoofed and bonafide segments simultaneously coexist across speech and environmental sound components. In this paper, we present PC-Mix, the first dataset for partial-component spoofing detection, where either or both audio components may be partially spoofed. In PC-Mix, bonafide and partially spoofed environmental-sound components are first constructed and mixed with speech signals from an existing partial-spoof dataset, producing audio in which either or both components may be locally manipulated. This design addresses two major gaps in existing partial spoofing benchmarks: the lack of realistic environmental sounds in speech partial spoofing scenarios and the absence of partial spoofing detection for environmental sound components. We further establish standardized evaluation protocols and design a joint learning framework to optimize spoofing detection across speech, environmental sound, and mixed audio. Experiments highlight the increased difficulty introduced by mixed conditions. The results demonstrate that training under matched target conditions is more effective than directly transferring models trained on speech or environmental sound components.

AI visibility measurement is comparative: practitioners want to know which domains generative search engines cite most often and whether observed differences are large enough to support decisions. Yet the industry lacks a principled way to determine whether enough data has been collected. Collection budgets vary widely across studies and platforms, and conclusions are often drawn from rankings whose stability and precision are unknown. We introduce a sequential convergence framework based on two complementary criteria: rank stability evaluates whether the rank-correlation trajectory has reached a structural plateau, while structural sufficiency evaluates whether the spread of citation shares among established domains -- those whose confidence intervals exclude zero -- exceeds the uncertainty of those estimates. Together, these criteria distinguish rankings that have merely stabilized from those sufficiently resolved to support inference. Both are derived from regularities in the observed citation distribution, including its rank structure, uncertainty profile, and the boundary between observed and established domains. The framework retains a small number of structural constants but requires no externally specified query count, correlation target, or confidence-interval width target; stopping is driven by observed measurement uncertainty and remains robust across a range of sufficiency thresholds. Applied across 30 platform-topic combinations spanning Gemini, SearchGPT, and Perplexity, the framework adapts to platform- and topic-specific citation distributions. Results show that no fixed collection budget can be justified across contexts and that convergence can instead be evaluated from the structure of the observed distribution. The framework provides a practical basis for determining when AI visibility measurements are ready to support comparative analysis.

Human-centered AI (HCAI) refers to guidelines or principles that aim on ethi-cally oriented design of systems. We compare HCAI- guidelines with princi-ples of socio-technical systems that emerged in the context of conventional in-formation technology. The comparison leads to a revision of socio-technical heuristics by including aspects of AI-usage. The comparison reveals that con-tinuous evolution is a basic characteristic of socio-technical systems, and that human oversight or interventions and the subsequent appropriation of AI-systems lead to continuous adaptation and re-design of the systems, if autono-my is collaboratively exercised. From a socio-technical point of view, the cru-cial requirement of transparency has not only to be fulfilled with technical fea-tures, but also by contributions of the whole system including human actors. It will be promising for using AI, if not only technical features, but organization-al and social practices are socio-technically designed in a way that compen-sates shortcomings of AI.

Algorithmic decision systems in financial services often rely on data proxies that inadvertently encode structural inequalities. This paper introduces a hierarchical human-AI triage model for Point of Sale fraud detection in the Nigerian FinTech sector. Adopting a We Are All Equal worldview, we address the challenge of discrimination laundering, wherein the system misinterprets infrastructure related aleatoric noise such as rural network timeouts as fraudulent intent. We implement a three-tier routing policy utilizing a calibrated ensemble model as a primary filter. The policy routes transactions characterized by epistemic uncertainty such as cold start new accounts to specialist analysts while reserving high stakes cases for a senior supervisor. To manage finite human capacity, we utilize a dynamic shadow price to ration human attention and implement a random audit mechanism to prevent human skill atrophy. Our experimental results demonstrate a statistically significant 1.88\% complementarity gap and a 24.79\% percentage point gain in fraud recall over an autonomous baseline. Crucially, the model reduces the regional performance gap from 19.43 to 2.88 percentage points, neutralizing structural bias. Hierarchical collaboration provides a robust mechanism for substantive equality of opportunity, ensuring that rural accounts are not excluded from the digital economy due to environmental brute luck.

The rapid proliferation of online polarization threatens social cohesion, necessitating robust automated detection systems that operate effectively across diverse linguistic contexts. This paper presents our system description for the POLAR Shared Task 2026, focusing on the detection and characterization of polarized discourse in English and Hausa. We propose a hybrid modeling strategy: for English binary detection, we leverage the monolingual strength of \textbf{DeBERTa}, while for Hausa and all fine-grained subtasks (Types and Manifestations), we utilize \textbf{AfroXLMR-Social}. This domain-adapted multilingual model proved critical for capturing the nuances of polarization in social media text. To further address computational constraints and data scarcity, we implement Low-Rank Adaptation (LoRA) and textual data augmentation via \texttt{nlpaug}. We report competitive results across all three subtasks, demonstrating that model selection tailored to specific subtask requirements yields the best balance of performance.

Preparing for job interviews is important for securing desired positions, yet realistic practice remains difficult to access: real interviews are infrequent, expert mock coaching is costly, and self-practice offers neither adaptive dialogue nor structured assessment. Existing systems typically address only parts of this need through fixed question sequences, limited communication channels, or feedback with little supporting evidence. We present PolyInterview, an LLM-based platform for immersive mock interview practice with comprehensive multimodal assessment. PolyInterview uses the target job description and CV to generate questions tailored to the role and candidate, conducts multi-turn spoken interviews with a lip-synced digital human interviewer that asks answer-aware follow-up questions, and evaluates response content, vocal delivery, and non-verbal behavior. Four parallel evaluators produce 13 behavior-level features that are aggregated into 10 assessment aspects and two competency tracks. Guided by the KSA and STAR frameworks, the report links each score to behavioral evidence and actionable recommendations. PolyInterview is publicly accessible. Its current all-account snapshot contains 101 accounts, 1,564 interview sessions, 7,665 generated questions, and 1,422 five-stage question sets. Generated questions are more closely aligned with their matched job description than with cross-role job descriptions in 93.7% of sessions. An evaluation by ten experts found strong question plans and actionable feedback.

Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT). However, the trial-and-error nature of RL, when conducted in real-world environments, is costly and hazardous in some scenarios. Consequently, the majority of RL research is conducted in simulation. This reliance introduces challenges related to the Sim-to-Real transferability. Evaluating the Sim-to-Real algorithmic robustness and the Sim-to-Real gap is a critical prerequisite for research aimed at improving RL performance in the real world. Therefore, industries such as robotics have developed concurrent simulation and physical platforms to facilitate this research. However, a universal Sim-to-Real benchmark platform for AIoT does not currently exist. To address these concerns, we developed a real-world AIoT platform for studying RL in AIoT. On this platform, an agent deployed on an edge device plays video games on a separate host computer via a hardware-emulated keyboard, guided by vision input. This platform uses commercially available components costing less than USD 400, together with two computers. Because the system's objective is game score maximization, it inherently mitigates safety risks associated with real-world RL deployments. Experimental results show the simulation-trained agent suffers a 1160% performance degradation relative to the human-level performance after real-world deployment, indicating a significant Sim-to-Real gap. Direct real-world training using the deep Q-network (DQN) algorithm achieves approximately 38% of human-level performance after 10 million training steps, demonstrating the feasibility of RL under real-world conditions. These results suggest that the proposed Sim-to-Real benchmark platform provides a substantial foundation for qualitative and quantitative evaluations of RL in real-world AIoT systems.

Byzantine-robust aggregation rules such as multi-Krum assume a central coordinator, and decentralising them is obstructed by the rules themselves: they are globally coupled, non-associative, and discontinuous, so an ulpscale perturbation can flip the selected subset, moving the output by a non-vanishing amount. None of this prevents coordinator-free replication, because a robust rule needs no agreed order of contributions, only an agreed set and an agreed exclusion predicate, both of which converge without consensus. ACFA (Accountable Consensus-Free Aggregation) replicates a content-addressed OR-Set of signed contributions and a grow-only set of self-authenticating equivocation proofs, offline-verifiable by anyone. Aggregation is a deterministic pure function of the converged product state: fixed-point integer arithmetic over a hash-canonical order, ties broken by content hash. We prove that any pure function of a converged product of CRDTs (non-monotone, non-associative, or stochastic) inherits Strong Eventual Consistency, together with its converse; the contribution is the composition of a data lattice with an evidence lattice applied to a robust selector, not the elementary lifting step. A prototype (10 nodes, 3 Byzantine) passes 16/16 falsification checks: byte-identical roots under adversarial gossip, deterministic re-convergence after late equivocation proofs, partition recovery, and three byte-identity-breaking ablations. The guarantee is consistency, not accuracy; robustness is imported, conditional on 2f + 3 admitted contributions (at most f Byzantine) and a stated quantisation-margin condition.

Generative image editing models struggle with structured statistical charts when data modifications require geometric synchronization. We formalize this task as Visuo-Logical Cascading Editing (VLCE). However, existing methods remain confined to localized text substitutions and struggle with dependency-aware cascading updates. To systematically evaluate this capability, we introduce ChartSync, an expert-validated benchmark constructed via a programmatic rendering pipeline that guarantees deterministic visuo-logical coupling for the ground truth. ChartSync comprises 870 triplets across 9 chart categories and 4 task types, including 235 geometry-coupled VLCE instances that specifically test cascading text-to-geometry synchronization. We further evaluate these instances via a two-tier framework combining objective visual metrics with a vision-language model judge paradigm to assess low-level fidelity alongside multimodal comprehension and reasoning. Evaluating 14 image editing models and one code-mediated pipeline reveals a nuanced capability gap: most open-source models suffer severe drops in geometric synchronization, while only two frontier proprietary models show emerging VLCE capability, with their residual errors mainly involving semantic isolation and background corruption. Our detailed error analysis deconstructs these failure paradigms to identify core meta-abilities for guiding future multimodal architectures. The ChartSync dataset and code are publicly released at https://github.com/kaka-yjk/ChartSyncCodebase.

Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues. To bridgethis gap, we present AVDC (Audio-Visual Decoupled Captions), a large-scaledataset designed to disentangle visual and auditory semantics. Specifi-cally, we propose an automated pipeline that leverages off-the-shelf mod-els to annotate videos with tripartite captions: visual-only (V), audio-only (A), and joint audio-visual (AV). This decoupled structure explic-itly captures both modality-specific nuances and complex cross-modalinteractions. Building upon this, we introduce AVDC-QA-CoT, a Chain-of-Thought augmented question-answering dataset to foster audio-visualreasoning. To fully exploit these resources, we employ a two-stage train-ing paradigm: omni-modal caption generation pre-training on AVDC, fol-lowed by instruction tuning on AVDC-QA-CoT. Extensive experiments acrossdiverse downstream tasks, spanning video captioning, audio-centric anal-ysis, and omni-modal benchmarks, demonstrate consistent and signifi-cant performance gains, showing the efficacy of our proposed datasetsand training strategy in advancing omni-modal perception. Code anddataset are related on https://radiant0726.github.io/AVDC-web/.

Reasoning failures in large language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may reflect missing capability, an unstable reasoning trajectory, or a failure to activate a reasoning state that is already available in the frozen model. Existing prompting and benchmark-based evaluation methods mostly operate at the output level, while generic activation-steering methods typically apply global directions without diagnosing which examples require intervention. In this paper, we introduce SPARK, which uses hidden-state response to diagnose whether a model internally enters an effective reasoning state and to guide lightweight test-time steering. The key observation is that raw hidden-state susceptibility is strongly confounded by prompt length, especially in programmatic and algorithmic reasoning where harder serialized instances naturally become longer. SPARK therefore uses length-controlled susceptibility to separate input-scale effects from residual reasoning activation, and combines this signal with cross-layer coordination to select reasoning-active anchors and under-activated hard examples. We use FRONTIER-4.5K as a controlled programmatic reasoning suite for latent profiling and difficulty-aware analysis, and evaluate SPARK-Steering on GSM8K and MATH-500 with forward-only benchmark profiling. Our method improves Qwen3 series models consistently; on MATH-500, accuracy rises from 82.0% to 84.6% for Qwen3-4B and from 82.4% to 85.6% for Qwen3-8B. These results suggest that susceptibility can serve not only as a diagnostic signal for reasoning failures, but also as a practical guide for targeted test-time intervention.

We demonstrate that AI-driven program synthesis can autonomously discover fundamental strategies for decomposing unitary matrices in photonic networks. By extending DreamCoder to complex-valued linear algebra, the system generates decomposition programs achieving the minimal $N(N-1)/2$ Mach-Zehnder interferometers, distinct from both Reck and Clements architectures. Learned programs encode dimension-agnostic invariants: strategies discovered for $5 \times 5$ matrices generalize to higher dimensions such as $64 \times 64$. The discovered programs encode interpretable, dimension-agnostic construction rules. These rules generalize across matrix sizes without retraining, demonstrating that autonomous program synthesis can serve as a scalable paradigm for algorithm discovery and the automated design of universal unitary operators. Beyond universal decompositions, the system automatically exploits matrix structure to reduce the interferometer count below the universal theoretical bound. For instance, for Householder matrices, it discovers a dimension-independent rule that requires only $2N-3$ MZIs. This achieves linear, rather than quadratic, scaling and generalizes to arbitrary $N$ without retraining. For matrices obtained from the singular value decomposition of sparse matrices, reductions generally increase with sparsity, reaching up to 38% fewer MZIs than the universal theoretical bound $N(N-1)/2$ at 95% sparsity. These MZI reductions translate directly into practical hardware benefits for scalable photonic implementations. Taken together, the system functions as a single unified engine that discovers both universal decomposition rules and matrix-specific optimizations, without being provided with the structural or analytical properties of the input matrices.

Software evolves continuously, yet ensuring that a patch preserves intended behavior without re-verifying an entire codebase remains difficult. Regression verification addresses this problem, but existing techniques require expensive whole-program reasoning or rely on manually written specifications that are rarely available in practice. We present the first contract-based regression verification tool. Contract soundness is ensured by proving all function versions match the behavior. The contract then verifies program flow via assume-guarantee. We ask whether a partial, caller-sufficient contract, rather than a full behavioral specification, is enough. On Frama-C-Problems we strengthen each inferred contract past what the caller needs and measure how much tighter it becomes. It barely moves: for most targets in every model the caller-sufficient contract is already the tightest the loop reaches, and our tightness comparator rates the partial and strengthened contracts equivalent for the large majority of targets it can compare. Partial-spec contracts thus capture nearly all the attainable tightness, so stopping at caller-sufficiency costs almost nothing. The regression check underneath is sound: on the third-party EqBench-C suite it never fabricates an equivalence, returning zero false proofs and reporting an unprovable difference instead. It also surfaced nine pairs that EqBench mislabels as equivalent, more than a concurrent tool reports. The contracts themselves are inferred automatically from the checker's own counterexamples, with no separate specification step; on Frama-C-Problems and the ANSSI X509 parser this reaches a verification rate comparable to tools AutoSpec and Preguss, while a passing result certifies at least as strong a property, which we call \emph{safety-preserving conditional equivalence}: enforcement plus caller-sufficiency.

Large language model (LLM) agents are increasingly used in trading systems, where model reasoning, tool use, and continual decisions incur costs that are expected to produce trading value. Existing evaluations typically report performance metrics, but rarely examine agentic viability: whether dynamic LLM-mediated decisions convert their induced costs into measurable incremental profit. To apply this criterion, we introduce TradeLens, a trace-grounded diagnostic toolkit for evaluating agentic trading systems from their trading records, runtime traces, and deployment configurations. It reconstructs trading trajectories, attributes profit and cost to interpretable evidence, and diagnoses whether and why an agent pays for its own intelligence. We conduct extensive analysis across backbone models, capital scales, trading frequencies, and system architectures, together with deployment discussion. Our results show that viability hinges on intelligence-to-profit conversion: models exhibit different failure patterns, such as poor asset selection in DeepSeek-V3.2 and negative timing in GLM-4.7, while capital scale, trading frequency, and architecture matter only by amplifying or degrading decision-attributed timing value. These findings reframe the evaluation of LLM-based trading agents from capability-centric performance ranking to trace-grounded diagnosis of intelligence-to-profit conversion. Our code is available at https://anonymous.4open.science/r/TradeLens.

We study how unsupervised autoencoders trained on microscopic spin configurations from the Ising model learn macroscopic, theory-relevant variables underlying the data-generating process. Without embedding domain knowledge, we mimic a typical discovery setting: We quantify learning across multiple spatial (coarse-graining) scales and reveal two distinct dynamical regimes controlled by main hyperparameters (model depth, width, and learning rate) -- a magnetization-dominated regime and an energy-dominated regime characterized by trade-offs in their representation quality. The first regime is a transitory state exhibiting dynamical scaling and fluctuations that follow an ordering-to-scale; the second gradually shifts resolution towards smaller scales relevant for the energy representation. Deep models trained at moderate and fast rates become arrested before reaching these regimes. With a novel analysis of recursive-dynamic trajectories, we demonstrate that prediction errors induce flow fields that produce a common trajectory topology across all representation spaces. A dynamical viewpoint of learning is established in which intrinsic properties expose the effects of forced changes in representation during training. We utilize the intuition that learning operates as a process driven far from equilibrium by fluctuations from the training data and optimizer to provide an interpretive basis grounded in both the physical world and the machine models that represent it.

The oracle problem (determining the correct expected outcome for a test) remains a major bottleneck in automated testing, and is increasingly relevant as non-experts rely on AI-generated code they cannot reliably validate. We study whether large language models (LLMs) can generate generalizable test oracles directly from natural-language business requirements, without access to source code or example input-output pairs. We propose a reproducible, requirement-driven pipeline grounded in Defects4J. For each of 10 real bugs from Defects4J Lang (Bugs 1 and 3-11), we (i) extract behavioral changes via buggy/fixed diffs, (ii) manually translate the change into a business requirement, (iii) construct a requirement-derived oracle (REQ) as a gold standard, and (iv) prompt five LLMs (DeepSeek-V3, Gemma-3n, Llama-3, Mistral-7B, and Qwen-3) to generate Java oracle code. We evaluate oracle correctness and generalization under two targets: agreement with REQ and agreement with the system under test (SUT), reporting macro-averaged accuracy, precision, recall, and F1. LLMs achieve non-trivial generalization but with substantial bug- and model-level variance. Generated oracles align more closely with REQ than with SUT, and correlations between requirement technicality/ambiguity ratings and oracle accuracy are weak with wide confidence intervals. No detectable linear relationship exists between requirement properties and oracle accuracy in this dataset, suggesting that pretraining coverage and the semantic specificity of the required behavior dominate oracle correctness. As a pilot proof of concept, these findings are preliminary and are intended to establish feasibility and motivate larger-scale empirical investigation.

Large language models achieve high scores on medical knowledge assessments, yet clinical reasoning requires actively deciding what to investigate under uncertainty. We developed an agentic evaluation framework in hematologic oncology in which models must proactively request clinical data across three sequential rounds before committing to a diagnosis and treatment plan. Across 32 frontier models, the best achieved only 68% overall accuracy. Information utilization, the fraction of available data actually requested, was the strongest predictor of diagnostic accuracy (R = 0.69, P < 0.001), yet utilization collapsed from 57% to 26% in the final round, leaving molecular and cytogenetic data critical for treatment selection unexamined. Reasoning traces scored high on a clinical reasoning rubric (91% above threshold) but decorrelated from accuracy, revealing a gap between locally coherent rationales and globally correct conclusions. Error analysis identified search satisficing, anchoring and premature closure as the dominant failure modes, the same cognitive biases that characterize novice clinicians under dual-process models of diagnostic reasoning. These findings demonstrate that the primary limitation of current models in clinical oncology is not insufficient medical knowledge but a systematic failure of information-seeking under uncertainty.

Information locality, the tendency for syntactically related words to appear close together, shapes both human language processing and language model learning. While prior work has examined whether language models can acquire impossible languages, it remains unclear whether they can recover natural language from such input and what this reveals about their inductive biases. We address this by complementing learnability-based approaches with a reconstruction framework: fine-tuning GPT-2 models pre-trained on impossible languages to reconstruct natural English from three perturbation types. Our findings show that the recovered structures exhibit shorter dependency lengths than the original text, mirroring the locality preference observed in unconstrained language model generation and providing a quantitative signature of an architectural bias that learnability experiments alone do not reveal. Recovery difficulty increases with the degree of locality disruption. Structural recovery (dependency Triple F1) dissociates from surface recovery (Exact Match), while fluency dissociates from faithful reconstruction under global shuffling. Sentence length further modulates performance: longer sentences facilitate recovery when local structure is preserved but lead to complete collapse under global shuffling. Finally, recovery difficulty tracks learnability difficulty across perturbation types, suggesting that information locality is the shared constraint governing both.

Bilevel optimization underpins many machine learning applications, including hyperparameter optimization, meta-learning, neural architecture search, and reinforcement learning. While hypergradient-based methods have advanced significantly, a gap persists between theoretical guarantees and practical single-loop implementations required for efficiency. We bridge this gap by establishing sharper convergence results for single-loop approximate implicit differentiation (AID) and iterative differentiation (ITD) methods, leveraging our proposed analytical framework, decoupled norm analysis (DNA). For AID, we improve the convergence rate from $\mathcal{O}(κ^6/K)$ to $\mathcal{O}(κ^5/K)$, where $κ$ is the condition number of the inner-level problem. For ITD, we prove that the asymptotic error is $\mathcal{O}(κ^2)$, exactly matching the known lower bound and improving upon the previous $\mathcal{O}(κ^3)$ guarantee. Numerical experiments on synthetic and real tasks corroborate our theoretical findings.

Customer churn is a major challenge for telecommunication companies, directly eroding revenue and long term customer relationships. Traditional retention programs rely on generic, not personalized incentives and lack the precision to identify high risk customers before they leave. This paper presents a data driven marketing optimization framework integrating machine learning based churn prediction, customer segmentation combining churn risk with customer value, and tailored, segment specific marketing and Return on Investment ROI strategies. Using the IBM Telco Customer Churn dataset with 7043 customers and 21 features, three gradient boosting ensembles, XGBoost, LightGBM, and CatBoost, were trained and tuned via randomized search with stratified 5 fold cross validation, class weighting, and F1 score driven decision threshold optimization to counter a class imbalance of 73.4% versus 26.6%. CatBoost was selected as the deployment model, achieving 77.68% accuracy, an F1 score of 0.6366, a PR AUC of 0.6553, and a ROC AUC of 0.8403 on the held out test set. Customers were partitioned with K Means clustering, validated via the Elbow method and visualized with Principal Component Analysis, into High, Medium, and Low Value segments, cross tabulated against churn risk labels to define four actionable clusters. Segment specific retention, upsell, and engagement strategies were designed for each cluster, and a theoretical ROI and CLV framework quantifies the financial impact of the proposed interventions. The pipeline was operationalized in an interactive Streamlit web application allowing marketing teams to upload data, filter by segment, visualize churn drivers via SHAP, and download automated segment reports. Results confirm that combining predictive churn modeling with value aware segmentation yields more actionable and profitable marketing decisions than churn prediction alone.

This paper investigates how language similarity can improve cross-lingual transfer for automatic speech recognition (ASR) in extremely low-resource settings. Warlpiri, an Australian Aboriginal language, has very limited transcribed speech data, making transfer learning essential. We propose a framework combining acoustic similarity from pre-trained speech models with linguistic similarity based on typology, phoneme inventories, grammatical, and syntactic features to rank high-resource source languages and evaluate their effectiveness for ASR transfer to Warlpiri. Experiments with Whisper show that acoustically and typologically similar languages outperform monolingual and multilingual baselines. Assamese and Hindi achieve substantial reductions in word and character error rates. Correlation analysis further indicates that acoustic similarity is the strongest predictor of fine-tuning performance, while phoneme inventory and typological similarity better explain zero-shot transfer.

Large language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm that the model answering is the model advertised, and recent audits show that a substantial fraction of commercial endpoints deviate from the vendor's reference weights. Existing identification techniques require long generated texts, token-level log-probabilities, adversarially crafted prompts, or the model owner's cooperation. We show that far weaker evidence suffices. We define a behavioral fingerprint of an LLM as the empirical distribution of its answers to trivial one-word prompts - "name a random number between 1 and 100" - collected across four languages at a cost of one output token per query. Measuring 165 models served via a large commercial aggregator (OpenRouter), we find that (i) these distributions are highly non-uniform (median cell entropy 1.0 bit) and model-specific: split halves of the same model's samples lie an order of magnitude closer than samples of different models; (ii) Jensen-Shannon divergence between fingerprints recovers model lineage, assigning a model to its documented family with 59.5% leave-one-out accuracy against an 18.4% chance rate; and (iii) a biometric-style verification protocol achieves a 7.3% equal error rate with the full 40-cell battery, and below 11% with eight probe cells - roughly a hundred single-token queries per audit. We further report ecosystem anomalies, including a proprietary-branded flagship endpoint distributionally indistinguishable from an open-weight Qwen model. The protocol, prompts, raw data, and analysis code are released for reproduction and operational use.

As large language models (LLMs) are increasingly used in decision support, it is important to understand whether their choices under uncertainty exhibit stable and interpretable behavioural regularities. Human decision-making combines relatively persistent risk preferences with context-dependent adjustment, yet it remains unclear whether analogous behavioural structure can be observed in LLM-based decision systems. Here we examine this question using a controlled multi-model framework based on no-limit Texas Hold'em, where behaviour is quantified by Participation, measuring voluntary engagement in uncertain opportunities, and Proactiveness, measuring pre-flop risk escalation. Across homogeneous self-play and heterogeneous mixed-model interactions, frontier LLMs exhibit stable, model-specific risk profiles, forming a spectrum from conservative to aggressive decision styles. These profiles remain largely robust under changing opponent composition, while the most conservative and most aggressive models diverge further in mixed settings. Under global risk pressure and personal resource constraint, models adapt in structured but heterogeneous ways, ranging from broad behavioural contraction to selective de-escalation and near-invariant behaviour. These findings suggest that LLMs differ not only in baseline risk disposition, but also in the risk signals they respond to and the flexibility with which they adjust, providing a behavioural basis for auditing risk-sensitive decision-making in interactive settings. Our code is publicly available at: https://github.com/XuankunRong/AgentTexasPoker.

Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical. Each is a mental space in which the same entity can take a different value, as when a flower is red in reality but purple in a portrait. Formal semantics keeps these contexts apart because their logics differ (modal, temporal, doxastic, depictive); Fauconnier's mental-space theory treats them as one space-building operation. We ask which of these a transformer language model implements, and find a mechanistic version of Fauconnier's unification. The model uses one router/slot format across the inventory: a reusable value slot stores attributed content, and a causally manipulable router (the space index) selects which space is read. A subspace trained with Distributed Alignment Search to control one space type, counterfactual, belief, fictional, or temporal, also controls the others, well above a random floor, on three model families; belief, which formal semantics marks as a distinct case, is not specially separated. The router is low-rank, composes additively with entity identity, and acts through a few late-layer heads. Two further results show the mechanism drives inference and composes: a subspace trained on a rule-derived conclusion flips what the model infers while dissociating from what it reports, and composing space-builders mints a fresh router over the shared slot. This paper establishes the cross-type generality. A companion paper develops belief in depth, because of its special status in philosophy, psychology, and linguistics (epistemology, theory of mind, and propositional attitude reports).

Despite advances in Emotional Intelligence (EI), Large Language Models (LLMs) still significantly underperform humans in complex emotional reasoning. This gap originates partly from the limited incorporation of individual differences, particularly personality traits, which are fundamental to human emotional inference. To address this, we propose PTEI, a novel framework for integrating Personality Traits into Emotional Intelligence tasks using LLMs. In PTEI, MBTI and OCEAN personality traits are first extracted directly from the given emotional scenarios and then utilized as contextual knowledge within personality-aware prompts, guiding LLMs to accurately infer emotions and their underlying causes. To ensure optimal contextual grounding, we employ Contrastive Learning to construct an optimized retrieval system that surfaces emotionally and personally aligned scenarios, enhancing reasoning quality. Extensive experiments on established EI benchmarks show that PTEI enhances the Emotional Understanding (EU) capabilities of various LLMs, with the strongest improvement observed in GPT models. Combining PTEI with Chain-of-Thought (CoT) reasoning yields an additional 4 percent increase in accuracy. These findings underscore PTEI's contribution toward advancing AI systems with more sophisticated social and psychological grounding.

State Space Models (SSMs) have emerged as a powerful paradigm for efficient long-sequence modeling, offering parallel training and fast linear-time recurrent inference. However, like other recurrent architectures, SSMs must compress an unbounded history into a fixed-size state, which limits context retention and makes precise retrieval over long-range context inherently difficult. To overcome this limitation, we propose Delay State Space Models (DSSMs), a delay differential equation (DDE)-inspired extension of diagonal SSMs that augments discrete SSM recurrences with explicit delayed-state feedback. Making explicit delayed feedback practical requires new stability parameterization, history management, and FFT-training tools. We address these challenges with a practical discretization and parameterization grounded in a simple delay-independent stability condition. To bypass direct time-domain kernel construction, we derive the DSSM transfer function and compute kernels in the frequency domain, using a kernel contour shift to suppress aliasing and recover accurate FFT training. Empirically, DSSMs substantially improve targeted delayed-retrieval tasks while outperforming S4D on most standard sequence metrics and remaining close on the others.

Previous work in group recommender systems has demonstrated a sensitivity to the distribution of preferences within a group. Specifically, the selection of the preference aggregation strategy benefits from considering such group configurations. In this paper, we study whether LLMs are able to mimic this sensitivity and to select the ideal aggregation strategy (and corresponding recommendation) according to nuanced human perceptions of fairness, satisfaction, and consensus. We do this by fine-tuning Large Language Models (LLMs) on human survey data to serve as real-time judgmental models within the recommendation pipeline. Using a reasoning dataset distilled from DeepSeek-V3.1 and human ground truth assessments, we develop Judgmental Llama and Judgmental OLMo to simulate group assessments. Our pipeline successfully generates multiple recommendation candidates based on social choice-based aggregation strategies and dynamically selects the one that maximizes these predicted human-like evaluations. We further validate these suggestions in a user study (n=284) and find that our methodology achieved the highest scores for satisfaction and group consensus. Furthermore, we find that LLM judgments are most aligned with human perceptions of fairness, satisfaction and consensus when we also consider interaction effects between our LLM-based method and group configuration (e.g., minority or coalition). These findings give further support for dynamically adapting aggregation strategies to specific within-group preference distributions, and highlight the advantage of using LLMs for an adaptation that is aligned with subjective human judgments.

Melody skeleton extraction aims to derive a shorter melody that preserves structural notes while removing ornaments. Prior methods rely on hand-crafted reduction rules or note-wise salience classifiers trained with heuristically or procedurally generated pseudo-labels. Such supervision can inherit generator bias and does not explicitly optimize a coherent reduced melody. We introduce MeloBottleneck, a self-supervised framework that represents a skeleton as a length-controlled, order-preserving latent subsequence. A hard-bottleneck extractor selects note events, a rhythmic-closure operator produces a self-consistent skeleton, and a re-ornamentation decoder reconstructs the input melody. Training combines reconstruction, a frozen autoregressive melody prior, ornament-invariant consistency across procedurally ornamented views, and ornament exclusion. We evaluate three regimes: synthetic out-of-distribution ornament-to-skeleton, TAVERN variation-to-theme, and Jiugong ornamented-to-gongche. A matched pseudo-label classifier excels on the synthetic benchmark, while MeloBottleneck transfers better, achieving competitive selection quality on TAVERN and Jiugong. Skeletonized melodies also improve BM25-based fragment retrieval, boosting Recall@K and MRR while reducing query time. Overall, the results suggest that learning skeletons as latent subsequences yields more robust transfer than pseudo-label imitation.

Tree crowns are a challenging target for resilient AI because they are not static objects: their spectral response, internal texture, translucency, and apparent boundaries change substantially across the growing season. We develop PhenoEmbed, a self-supervised crown-centric temporal embedding model trained with contrastive and masked reconstruction objectives on HeideBench, an 18-date UAV multispectral time-series benchmark for forest crown phenology in D{ö}lauer Heide. The model treats seasonal crown dynamics as phenological appearance change driven by leaf emergence, canopy closure, senescence, and leaf-off conditions. Segmented tree crown polygons are retained as object anchors to extract aligned crown-centered crops through time, allowing one 256-dimensional vector summarizing seasonal crown appearance to be learned per tree. On 5,885 crop-safe crowns, the exported embeddings show structured low-dimensional organization, with the first two principal components explaining 25.1\% of variance and nearest-neighbor retrieval producing a median top-1 cosine similarity of 0.946. Compared with handcrafted temporal features and a learned mean-pooling baseline, PhenoEmbed yields substantially more compact nearest-neighbor structure, while ablations show that the contrastive loss, masked reconstruction loss, and explicit seasonal time features each affect the structure of the learned embedding space. These results support PhenoEmbed as a reusable forest crown representation learner and motivate future downstream tests of whether such features improve tree-level models under seasonal change.

We evaluate when sparse autoencoder (SAE) features act as localized control handles for safety-relevant behavior. This question is difficult because apparent success can arise from weak interventions, mismatched baselines, model robustness, or degenerate outputs that automated safety judges mark as unsafe without representing meaningful harmful compliance. We introduce a matched coherence-gated evaluation protocol for runtime safety interventions: methods are compared at matched target-effect points, and the primary target metric counts harmful compliance only when an output is both judge-unsafe and coherent. Applying this protocol to three prompt splits on Gemma-2-9B-it with a Gemma Scope layer-20 residual SAE, we find that SAE feature ablation has a narrow useful regime. SAE top800 reaches a low-to-mid target effect with lower total perturbation and competitive utility, but SAE top1600 loses utility relative to a matched dense refusal-direction baseline, and SAE top3200 primarily induces coherence collapse. Human audit confirms that coherence gating removes unsafe-only artifacts, and feature diagnostics show that the useful regime is driven by a stable head of refusal-aligned features whose activation separation decays rapidly with rank. These results argue that SAE-based safety interventions should be evaluated as regime-dependent control mechanisms rather than assumed to be uniformly localized.

Background. Large language models (LLMs) have become increasingly capable of understanding and generating source code, leading to their widespread adoption in software engineering tasks such as code completion, repair, and vulnerability detection. However, despite their strong empirical performance, the internal mechanisms through which LLMs recognize malicious or vulnerable code patterns remain poorly understood. Aim. We investigated where the malware detection behavior is encoded inside LLMs Feed Forward Network (FFN) neurons and verified the attribution with causal interventions on the neurons identified. This aims to identify the most important neurons in detecting malicious code. Methods. We applied mechanistic interpretability methods to locate the neurons being responsible for malware-detection behavior in three instruction-tuned LLMs: Llama3.1-8B-Instruct, Mistral-v0.3-7B-Instruct, and Qwen2.5-7B-Instruct. Using 1,500 malicious and 1,500 benign PyPI packages from the PyPI Malregistry, we attribute the behavior to a set of neurons. Results. The experimental results reveal that amplifying facilitating neurons for malware detection while suppressing inhibiting ones can boost accuracy, while the reverse collapses predictions toward a single class, although the magnitude and consistency is heavily model-dependent. We demonstrated that the guardrail detection mechanism varies across models, each represents its malware detection behavior differently within its FFN layers. Conclusions. Probing the neurons associated with security-relevant knowledge helps us gain insights into how LLMs encode malicious programming concepts, identify potentially harmful memorized behaviors, paving the way toward more reliable defense mechanisms, such as neuron-level editing, selective unlearning, and security-aware alignment for code-focused LLMs.