The Inference Report

Human visual similarity judgments are context-dependent. For example, two images may be similar in shape but distinct in color. Existing perceptual similarity metrics, however, collapse these nuances into a single scalar value, offering no mechanism to condition on specific aspects. To bridge this gap, we introduce a large-scale dataset of human similarity judgments over image triplets, where each triplet is annotated across multiple, free-form semantic aspects of similarity. Benchmarking a broad range of frontier vision-language models (VLMs) reveals a considerable performance gap compared to human annotators' consensus. Leveraging our data, we fine-tune a VLM to produce our Text-Prompted Image Perceptual Similarity (TPIPS) metric, capturing multiple senses of visual similarity depending on the specified text prompt. We demonstrate that TPIPS aligns more closely with human perception and generalizes reliably beyond the training distribution. Finally, we show that TPIPS unlocks new capabilities in text-guided retrieval, compositional search, and the fine-grained evaluation of generative models. Our code, data, and trained models are at https://peterwang512.github.io/TPIPS

Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning. Modern robot policies either compress each observation into a single global token, or rely on visual backbones trained from scratch, sacrificing both fine-grained spatial detail and the benefits of large-scale visual pre-training. While there exist policies that do operate on dense patch features like large vision-language-action models (VLAs), they tend to be heavy and slow, inheriting the full cost of a billion-parameter vision-language model (VLM) backbone. We close this gap with Patch Policy, a minimal architectural extension that enables transformer-based policies to consume dense pre-trained patch tokens directly without the computational overhead of a full VLM. At its core is a block-causal attention mask that preserves the temporal causality of standard policies while letting the model attend over many patch tokens per observation, alongside other state information. Patch Policy is lightweight, fast, and highly effective. Across four simulated and three real-world environment suites, our method achieves a 40% relative improvement over policies using state-of-the-art global-pooled representations. Furthermore, it surpasses fine-tuned OpenVLA-OFT by 18% while using roughly 0.7% of the parameters. We believe Patch Policy provides a pipeline for the robotics community to readily leverage continuing progress in visual representation learning, without sacrificing the training efficiency or inference speed required for high-frequency, reactive control. Videos can be viewed at https://patch-policy.github.io

Autonomous discovery systems such as OpenEvolve and TTT-Discover are often used as general-purpose harnesses. However, in practice these are composite systems combining several design choices about archives, parent selection, exploration, and budget allocation into a single recipe. Because discovery runs are expensive and inherently stochastic, existing harnesses are often compared using too few independent trials to distinguish key methodological improvements from run-to-run variance. We systematically decompose OpenEvolve-style evolutionary search and the TTT-Discover search harness into its constituent components and systematically evaluate 30 budget-matched harnesses across 12 model-problem pairs using more than 3.1 million LLM rollouts and repeated-trial statistical analysis. Our results show that discovery harnesses have a generalization problem: No fixed harness is reliably superior across the evaluated model-problem pairs, and variants of OpenEvolve generally underperform simpler alternatives. Thus, harness choice is better viewed as a hyperparameter rather than as a universal recipe, and should be tailored to the specific problem and underlying model. We also find that early discovery progress predicts final performance, and use this property to present a budget-matched adaptive-allocation experiment that starts multiple harnesses, prunes weak partial runs, and reallocates compute to stronger survivors, outperforming both commitment to a randomly sampled fixed harness and a non-adaptive harness ensemble. Together, these results motivate shifting from fixed harness selection to online adaptation guided by early performance. We release all run pools including baseline null distributions for every model-problem pair as reusable statistical infrastructure against for future harness proposals.

Users frequently express their beliefs to large language models (LLMs). In some situations, the LLM should accept these contextual beliefs as true. In others, they should stick to their prior knowledge. Notably, users' expressions of belief (EoBs) can take linguistically diverse forms - using presuppositions, evidential and certainty markers, or varied tones - each of which may have a different persuasiveness over the LLMs. We introduce a typology to systematically evaluate how different EoBs affect whether models follow context versus prior knowledge. The typology is grounded in four linguistically motivated dimensions: form, evidentiality, epistemic stance, and tone, spanning 17 fine-grained types. By pairing these EoBs with world knowledge facts, we generate controlled EoB-query pairs that isolate the effect of linguistic variation. Using this benchmark, we evaluate 16 LLMs that differ in architecture (Llama3, Qwen3, Gemma3), scale (1B-30B parameters), and training stages (base vs instruct). We identify meaningful variations in response behavior across these axes, e.g., that bigger models and instruction models tend to be less context-following than smaller models and base models. We further identify specific EoBs that statistically significantly persuade LMs more consistently than others. Our work reveals systematic patterns in how linguistic framing affects LLM context integration, with implications for prompt engineering and model robustness.

Modern vision-language models (VLMs) have significantly improved image generation and editing capabilities, making pixel-level image tampering detection increasingly important yet challenging under cross-model and out-of-distribution shifts. This work studies domain generalization for pixel-level image tampering detection in modern VLMs like ChatGPT, Gemini, Qwen-Image, etc., aiming to learn tampering localization models that remain robust across diverse VLM-generated manipulation distributions. We propose a simple yet effective domain-generalized training framework built on two practical strategies. First, we introduce a balanced minibatch sampling scheme that strategically samples tampered and real images in each minibatch, preventing biased optimization toward either manipulated artifacts or clean-image priors and avoiding training collapse, ensuring that each optimization step receives proper sampled gradient signals. Second, we adopt a simple late-injection strategy, where the detector is first trained on large-scale base data until stable convergence, and then exposed to a small amount of newly selected supporting data from emerging VLM distributions, improving adaptability without overfitting to limited new domains. Together, these components provide a simple yet strong recipe for improving pixel-level tampering localization and OOD robustness across modern VLMs. Despite the conceptual simplicity, our framework outperforms the prior state-of-the-art PIXAR by a large margin of 26.1% and 26.8% relative improvement in average gIoU and cIoU, respectively, across OOD VLMs of GPT-Images-2.0, Gemini-3.1, FLUX.2, and Seedream 4.5. Our code is available at https://github.com/VILA-Lab/PIXAR-DG

To test how correct logical judgments respond to learned context, we prepend a soft prefix to an exactly labeled syllogistic reasoning benchmark while keeping the model fixed. Soft prefixes are opaque continuous vectors, so we characterize them through the behavior they induce across controlled variations in logical form and interface. By studying which prefixes succeed and how their effects generalize, we characterize how learned contextual pressure can override correct judgments and expose limits in a model's logical stability. Across Qwen3.6-35B-A3B MoE, Qwen3-8B, and Gemma 4 31B, learned prefixes redirect many correct answers and remain effective across unseen forms and interface changes. In repeated tests with Qwen3.6 MoE and Gemma, they outperform paired random controls in all 16 model--direction--split comparisons by 37 to 99 percentage points. Qwen3.6 MoE flip rates remain between 72% and 90% across wording and prompt changes, while Gemma validity prefixes retain 54% to 56% flip compared with less than 1% for matched random prefixes. Diagnostic tests show that the dominant effect is a broad preference for one answer meaning rather than fixed-symbol forcing or a logical operation that transfers reliably between tasks. The form of this bias differs across models. In both Qwen models, simple score models often predict which judgments will flip but not how far their margins will move, whereas Gemma's overall response is more closely approximated by the same models. These results show that the dominant behavioral effect of successful soft prefixes is a broad answer preference, while the remaining response reveals substantial model-specific differences in logical stability.

Causal discovery methods have shown strong performance in temporal systems, but they typically rely on regular and discrete lag structures, limiting their applicability to regularly sampled data. However, many real-world tasks require dealing with irregularly sampled streams of events, such as sensor streams, healthcare data, and financial transactions. In this work, we propose an extension of PCMCI+, a state-of-the-art method for causal discovery on regular multivariate time series, to allow for handling irregular time series. Instead of modelling causal relations through fixed-lag dependencies, our method aggregates causal influence over predefined temporal windows. We evaluate our method on synthetic irregular event streams with known causal structures under different signal-to-noise ratios, showing that it consistently recovers the underlying causal graph and substantially outperforms the standard PCMCI+ on irregularly sampled data.

We propose one-step and two-step methods for policy learning with retrieval-augmented generation (RAG). We formulate RAG-based action selection under the potential outcome framework. In the two-step method, vector search retrieves action-specific neighboring evidence in an embedding space, the generator estimates conditional expected outcomes or their contrasts, and a plug-in rule selects an action. This formulation connects action-specific vector search with nearest-neighbor matching in causal inference. We decompose the regret of the two-step method into candidate-generation regret and within-candidate choice regret, and we bound the latter using prediction-error guarantees for nearest-neighbor estimators and transformers. We evaluate the one-step method directly as a policy because its intermediate computation is unobserved.

Foundation models have emerged as a driving force in computational pathology, with the potential to transform cancer diagnosis, prognosis, and treatment selection by learning transferable representations from large-scale histopathology data. A growing landscape of pathology foundation models now spans diverse data sources, architectures, and downstream applications. However, most pretrained models operate only at the image-tile level, use restrictive licenses, and remain computationally expensive, limiting large-scale slide-level clinical and research use. Here, we introduce GigaPath-Flash and GigaTIME-Flash, efficient models for whole-slide pathology AI and spatial proteomics prediction. GigaPath-Flash combines a 22M-parameter ViT-S tile encoder with a 21M-parameter LongNet slide encoder, both pretrained on large-scale real-world histopathology data. Its compact tile encoder is distilled from the billion-parameter GigaPath (ViT-g) teacher and shared by both models. GigaPath-Flash retains 97% of GigaPath's average slide-level performance with 50x less compute. GigaTIME-Flash extends this backbone to predict the tumor immune microenvironment directly from routine H&E images. It surpasses the original CNN-based GigaTIME in prediction quality while running 6x faster and using 8x less GPU memory. Together with GigaPath and GigaTIME, these models form an open-weight, Apache-2.0-licensed family pretrained on large-scale real-world clinical data. By releasing all models and weights, we provide accessible building blocks for computational pathology, immuno-oncology, and precision health.

Pruning long context for coding agents has been a vital technology for efficient context management. While existing context pruning methods such as SWE-Pruner realize this by attaching a separate code classifier, we find the agent itself encodes internal representations indicating the relevance of code context when reading tool output. Based on this finding, we propose SWE-Pruner Pro, which prunes tool outputs directly inside the agent. Concretely, a small head turns the agent's own internal representations into a keep-or-prune label for each line, with a length-aware embedding keyed to each tool output's line count. Across two open-weight backbones and four multi-turn benchmarks, SWE-Pruner Pro saves up to 39% of prompt and completion tokens while preserving task quality, with bounded inference overhead. Notably, on MiMo-V2-Flash SWE-Pruner Pro additionally raises the SWE-Bench Verified resolve rate by +3.8% and the long-context Oolong accuracy by +2.2 points.

This paper considers a multi-environment factor model in which high-dimensional covariates are collected from heterogeneous environments, with auxiliary labels available in a subset of these environments. The joint distribution of the covariates may vary across environments, whereas the latent structure is decomposed into invariant factors with shared loadings and heterogeneous factors with environment-specific loadings. Such a model is motivated by transfer learning and latent factor regression, where one seeks stable low-dimensional representations for both interpretation and robust out-of-sample prediction of the response $Y$. Leveraging the invariance principle, we show that the invariant and heterogeneous factors are disentangled under a minimal structural condition. Based on this, we propose ATLAS, an Auxiliary-label and invariance-guided Transfer via Latent Alignment across heterogeneous environmentS. ATLAS is a unified procedure that leverages the invariance principle to separate aligned invariant and unaligned heterogeneous factors, and further exploits supervision from auxiliary labels to extract prediction-invariant and transferable factors from those unaligned heterogeneous factors. ATLAS yields near-oracle performance for downstream latent factor regression, enables transferable prediction in new environments through the full latent signal when auxiliary labels are available, and reduces to robust invariant-factor-only prediction otherwise. We establish sharp non-asymptotic error bounds for recovering invariant and heterogeneous factors, identifying all the response-invariant factors, and estimating the invariant signal in $Y$.

Robots in cluttered indoor spaces often fail not because they cannot generate collision-free paths, but because a fixed safety margin is mis-calibrated: conservative margins cause detours and timeouts, while permissive margins lead to near-boundary shortcuts under perception bias. Diffusion-based planners propose diverse trajectory candidates from egocentric RGB-D, yet reliable selection remains the bottleneck. We propose a context-conditioned safety critic that learns an adaptive clearance preference for ranking diffusion proposals, decomposed into three complementary terms: (i) a safety term with a clearance-budget penalty and a control-barrier-function residual for waypoint- and transition-wise safety, (ii) an efficiency term combining a smoothness penalty with a safety-gated detour-ratio penalty that avoids detours without incentivizing risky shortcuts, and (iii) a distance-constraint matching term that anchors the learned budget to realized ESDF clearances to prevent margin collapse. We train the critic with privileged ESDF geometry in simulation and distill it into a perception-only selector via a two-stage teacher-student procedure. On PointGoal navigation in HM3D and MP3D, including cross-dataset transfer, our method achieves the highest success rate (SR) and success weighted by path length (SPL) among strong diffusion, optimization, and RL baselines. Trained purely in simulation, it transfers to a Unitree G1 humanoid and navigates cluttered indoor scenes without task-specific tuning.

Not all training samples contribute equally to large language model fine-tuning. Selecting informative training samples can reduce the computational cost while preserving downstream performance. Many existing data selection methods rely on indirect heuristics, such as data quality, diversity or reasoning trace length. However, the effectiveness of these fixed criteria is task-dependent and difficult to generalize across diverse downstream tasks. Perplexity-based data selection provides a simple and model-aware solution to estimate the sample difficulty, but existing approaches typically score the entire training sequence and ignore the difference in learning objectives of language modeling and reasoning tasks. In this paper, we propose PPL-Factory, a simple and interpretable data selection framework that combines task-aware perplexity-based scores and data budget-aware selection criteria. Experiments on GSM8K demonstrate that PPL-Factory outperforms other state-of-the-art data selection methods using only $1\%$ of the training set. With $10\%$ of the data, PPL-Factory exceeds full-data fine-tuning accuracy by 0.9 on GSM8K and 4.8 on MATH. Overall, our results demonstrate that task-aware and budget-aware perplexity-based selection provides an effective and applicable approach for efficient fine-tuning.

Modern generative models typically rely on an adversarial critic, a prescribed noise-to-data path, or an autoregressive factorization. Instead, we show that a proper distributional energy can induce sample-level motion and provide direct regression supervision for a one-step generator. Three-Body Scattering Modeling (TBSM) for generation turns the energy distance into a constant-size per-projectile interaction: each projectile is attracted toward one real source and repelled from one independently generated source. Conditioned on the projectile and its condition, its expectation equals the $2$-Wasserstein gradient-flow velocity of $\frac12D_E^2(P_θ,Q)$. A batch of $B$ frozen-target events yields $O(B)$ sample-level losses, each using one reference for its condition instead of the minibatch-wide all-pairs field used by methods such as Drifting Models. Tracking this conditional expectation online can reduce field noise. Using scattering in frozen image features, TBSM trains one-step generators on ImageNet-256, achieving FID${}=2.23$ with pixel-space PixelDiT-XL and FID${}=1.63$ with latent-space DiT-XL at NFE${}=1$. We provide a design map relating diffusion-related supervision, Drift-like dynamics, and GAN-like objectives. These results establish tracked scattering as a route to high-dimensional one-step generation. Code: https://github.com/sp12138/TBSM.

Vision models have been found to be susceptible to perturbations such as motion blur induced at runtime by a shaking camera. This impedes their deployment in critical applications since phenomena such as slightly blurred vision might lead to failures, for example an object detector missing objects. While methods such as data augmentation or Adversarial Training can improve empirical robustness, they lack formal safety guarantees, making it difficult to identify and mitigate hidden vulnerabilities. We introduce a novel Certified Training approach that leverages an efficient encoding of convolutional perturbations to train provably robust models. Our method significantly outperforms Adversarial Training, achieving, for example, over 80% robust accuracy against motion blur of reasonable intensity on CIFAR10 while maintaining comparable standard accuracy.

Large-scale scientific simulations generate volumetric data at rates that far outpace advances in storage and network bandwidth, making effective lossy compression increasingly critical. However, conventional compressors often struggle to preserve fine structural details at high compression ratios (CRs), and implicit neural representations (INRs) require costly per-volume optimization and produce models with fixed CRs. To respond, we present EVOLVE, an autoencoder (AE)-based volume-compression framework that targets high CRs for offline compression, with three key contributions. First, we construct a large-scale cross-domain database of 6,376 volumes from 21 scientific simulations, curated via perceptual hashing to ensure diversity, enabling the optimized model to extract features that generalize across volumes within the covered scientific simulation domains. Second, we reexamine the design space of AE-based compressors and incorporate several macro- and micro-designs into a vanilla AE to develop EVOLVE, which substantially improves the expressive power and compression capability. Third, we develop a learnable gain mechanism with a three-stage training strategy to enable variable-rate encoding, allowing a single model to support continuous CR adjustment at inference time. Experiments on multiple unseen scientific simulation datasets demonstrate that EVOLVE achieves substantially higher CRs than conventional compressors at comparable reconstruction quality, while delivering compression speeds that are orders of magnitude faster than INR-based methods, highlighting its promise as a strong alternative for compressing scientific data. The code, model weights, and results are available on our project page at https://evolve-vis.github.io.

Battery-free Internet of Things (IoT) requires iterative design of vibration energy harvesters (VEHs) under coupled physical constraints, while LLMs are emerging as interface layers for engineering workflows. However, existing engineering benchmarks primarily assess final artifact validity, offering limited insights into how LLMs behave across different stages of coupled physical design. We introduce VEHBench, an engineering-native diagnostic benchmark for LLM-assisted VEH design, featuring 763 literature-grounded tasks scored by an analytical physical oracle. VEHBench evaluates four design roles: specification triage, verifier-guided search, corrupted-state recovery, and policy-conditioned selection. Experimental results reveal that LLM capability is strongly stage-dependent: no single model consistently dominates the entire workflow, and response-control profiles expose distinct behavioral patterns across design roles. VEHBench thus provides a stage-aware foundation for evaluating, selecting, routing, and improving verifier-grounded engineering LLMs. The benchmark artifact is available at https://huggingface.co/datasets/AnonymousVehbench/vehbench

Real-time multimodal applications, including voice agents and interactive video generation, compose heterogeneous models into pipelines whose efficient deployment requires application-specific decisions about placement, streaming, and intra-model parallelism. Existing serving systems and auto-parallelism compilers commit to limited transformations and fixed workload assumptions, so achieving high performance on a new application requires hand-crafting an efficient implementation. We present FlashRT, an agent harness that guides coding agents to lift simple developer-written reference implementations into optimized multi-GPU deployments that flexibly weigh target metrics like latency and throughput. Using a new chain-of-program paradigm, FlashRT directs a generic coding agent through a multi-pass transformation process where an agent transforms the reference into an intermediate representation (IR) to capture data dependencies and persistent-state scopes, validates this IR via a sequential interpreter, and performs static analyses to identify candidate transformations. Then, the agent iteratively implements, verifies, and benchmarks each candidate under a measurement-gated optimization loop to produce effective deployments that span different hardware budgets. Across various applications, including video world models and multimodal LLMs, FlashRT converts reference implementations into highly efficient deployments, delivering up to ~70x latency reduction and 2.8x throughput improvement on NVIDIA B200 GPUs. On AMD MI355X GPUs, FlashRT matches the peak latency reduction while increasing peak throughput improvement to 3.6x, demonstrating that agent-driven optimization can be more scalable on platforms with less mature expert optimization. In fact, for Qwen3-Omni text-to-audio inference, FlashRT reduces response latency by 65% compared to the expert vLLM-Omni implementation on AMD MI355X.

Digital Twins rely on surrogate models to mirror physical systems in real time, yet these models can degrade as operating conditions evolve, a phenomenon known as concept drift. Maintaining surrogate fidelity under drift, particularly when models must also capture aleatoric uncertainty, remains an open challenge. Existing adaptive frameworks lack principled mechanisms for detecting when updates are needed, for efficiently adapting models from limited streaming data, and for certifying that updates genuinely improve predictive performance. Here we present an adaptive Digital Twin framework that integrates a Fisher score--based multivariate drift detector, Low-Rank Adaptation (LoRA) for parameter-efficient continual learning, and a Mann--Whitney $U$ test for online statistical validation. The framework monitors surrogate-model confidence via Fisher score vectors, triggers targeted fine-tuning of fewer than 1% of model parameters upon drift detection, and statistically certifies predictive improvement before deploying the updated surrogate. Applied to a stochastic linear system and a directed energy deposition additive manufacturing process as case studies, the framework successfully detects distributional shifts with short delays and restores both predictive accuracy and uncertainty quantification under abrupt and incremental drift. These results establish a statistically rigorous and computationally tractable pathway for sustaining the trustworthiness of neural-network--based Digital Twins throughout their operational life cycle.

PPO and the GRPO baseline studied here use clipped surrogate objectives whose favorable-direction saturation introduces an abrupt change in the scalar objective's derivative. We ask whether Output Reset (OR), a smooth one-sided saturation rule, offers a useful alternative for large language model post-training. PPO-OR and GRPO-OR replace the clipped policy term with an OR squared-margin loss in rollout-relative token log-ratio space; the advantage sign determines the update direction, and a token contributes zero direct OR residual after crossing the favorable margin. We compare PPO-clip with PPO-OR under generalized advantage estimation (GAE), and GRPO with GRPO-OR under group-relative advantages, using \texttt{Llama-3.2-1B-Instruct} on Anthropic \texttt{hh-rlhf} with one shared reward model and three seeds per method. Under GAE, PPO-OR has a mean final training-time reward-model score $0.305$ higher than PPO-clip, with a larger observed across-seed spread. Under group-relative advantages, GRPO-OR does not have a higher mean score, but shows a smaller observed spread, a near-zero terminal OR residual, and a declining overshoot fraction, while the matched GRPO clipped-objective trace remains variable. Both group-relative methods exhibit substantially larger rollout-to-current log-ratio displacement than the GAE methods, and OR does not consistently reduce it. Thus, OR changes optimization behavior in both matched comparisons, but the observed reward effect differs between them. At $G=2$, the GRPO-OR diagnostics do not translate into a reward-score gain. Whether larger groups change this outcome remains open. The reported scores are training-time reward-model measurements, not held-out human-preference performance.

The soft-label Bayes-error estimator beta(z) = E[min(z, 1-z)] of Ishida et al. estimates the irreducible error of a binary task directly from probability-valued labels. Recent work by Ushio et al. showed that this estimator is fragile when the probabilities are not the true posterior: even perfectly calibrated soft labels can yield a substantially inaccurate estimate, and they propose isotonic calibration as a consistent remedy. We complement that line of work by characterizing exactly how the most widely used post-hoc calibration map -- temperature scaling -- distorts the proxy. We prove an exact, model-free identity reducing the temperature-scaled proxy to the classifier's margin distribution, from which we obtain (i) strict monotonicity in the temperature and (ii) a continuous bijection from the temperature axis onto the open interval (0, 1/2), so that a fixed classifier -- with fixed decisions and fixed 0-1 error -- can be made to report any proxy value whatsoever. Under a Gaussian model of the logits we further derive a two-parameter closed form for the entire proxy-versus-temperature curve. Across CIFAR-10, Fashion-MNIST, and SVHN (eight binary tasks), the proxy varies by 56x to 980x at constant test error, the closed form reproduces the empirical curve to within 0.018, and the calibration temperature that minimizes the expected calibration error does not coincide with any stable proxy value. Our results give a precise, predictive account of the distortion whose existence motivates calibration-based remedies, and they reinforce the practical recommendation that a proxy value is meaningful only together with the mechanism that produced its probabilities.

Coding agents are increasingly used to accelerate code generation in many downstream tasks, such as fixing bugs, building applications, and prototyping. However, despite their value as coding assistants, agent-generated code tends to be larger and more verbose than the corresponding human-written implementation. In this work, we show that the cause lies in the agent's own search process: while iterating toward a passing solution, an agent accumulates speculative edits, abandoned hypotheses, and temporary changes that persist into the final patch. This may seem harmless for a single patch, but the problem compounds as agents take responsibility for ever-larger portions of a codebase-a codebase that was once minimal and well-maintained slowly accumulates redundancy faster than it can be cleaned up, drifting to a state that is harder to maintain. Given the magnitude of this problem, we take a step towards alleviating this issue. First, we formally define this phenomenon as CodeSlop-the residual and functionally unnecessary edits commonly seen in AI-generated code. We then introduce our algorithm TRIM (Trajectory-guided Redundancy Identification and Minimization). Rather than minimizing CodeSlop directly, TRIM instead minimizes agent trajectories. As we show empirically, this indirect technique of minimizing CodeSlop is highly effective: TRIM cuts CodeSlop by 17.9%-32.9% across agentic scaffolds, with negligible performance regression. TRIM is also highly efficient, requiring roughly half the validation cost of algorithmic baselines such as Delta Debugging.

Retrieval-Augmented Generation (RAG)-based systems\footnote{For brevity, RAG-based systems are referred to as RAG systems throughout this paper.} are increasingly deployed in high-stakes settings where correct behaviour depends not only on the language model but also on the retrieval component that selects external documents at inference time. While existing RAG evaluation metrics assess retrieval and generation quality on a per-query basis, typically relying on query-level test oracles such as reference answers or relevance annotations, they provide limited insight into whether a test suite adequately exercises the retrieval behaviour of the system as a whole. In this paper, we introduce Chunk Coverage (CC), an oracle-independent test adequacy criterion for testing the retrieval component of RAG systems. CC measures the fraction of corpus chunks that are retrieved at least once across a test suite, providing a structural view of which parts of the retrieval space have been exercised. We further show how CC can be used to guide test selection and generation by prioritising queries that expand coverage of previously unexercised retrieval regions. We evaluate CC on clinical and financial RAG system scenarios. CC-guided testing reaches 50% of attainable coverage 1.7x faster than random selection and 4.2x faster than redundancy-biased strategies. Moreover, CC improves fault detection effectiveness (APFD) by 10% to 25% over random, indicating earlier discovery of distinct retrieval faults. These results show that CC captures retrieval diversity relevant to effective testing without requiring test oracles.

Real-time EEG classification on edge devices is bottlenecked by the floating-point arithmetic of conventional neural networks. We investigated Differentiable Logic Gate Networks (Diff-Logic) as a hardware-native alternative that compiles models into pure Boolean circuits executable via bitwise CPU operations. Through rigorous iso-parameter experiments across four EEG datasets spanning two classification tasks, binary dementia detection and 3-class emotion recognition, we compared Diff-Logic against matched-capacity Multi-Layer Perceptron (MLP) and Binarized Neural Network (BNN) baselines at four complexity tiers (50k-500k parameters). On dementia screening, Diff-Logic achieved 80.2% Macro F1, outperforming the MLP baseline by 6.8%. On emotion recognition, the MLP retained a moderate performance advantage but incurred a 2.3$\times$ higher latency and 14$\times$ larger model size when deployed on a power-constrained (7W) Nvidia Jetson Orin Nano CPU (Single-core). Critically, Diff-Logic inference time remained nearly constant across a 10$\times$ increase in model scale, achieving a peak speedup of 2.9$\times$ over MLPs at the largest complexity tier. Our results establish logic-based neural architectures as a practical paradigm for resource-constrained brain-computer interfaces, achieving competitive or superior performance while natively satisfying the latency and memory constraints of portable edge deployment. Code is available on GitHub: https://github.com/Shyamal-Dharia/eeg-difflogic

We investigate the extent to which totally positive matrices can be distinguished through the highest-order coefficients of their characteristic polynomials. To identify the most informative coefficients, we also employed neural-network classifiers together with feature-attribution methods. Using datasets built from several structured totally positive families, including products of positive bidiagonal matrices, Vandermonde matrices, and Cauchy matrices, we find that the coefficients (a_{n-1}, a_{n-2}, a_{n-3}) already contain strong discriminatory information for separating totally positive from non-totally positive matrices in dimensions 5, 10, and 30. The resulting separation is markedly nonlinear and admits a natural geometric description in the corresponding three-dimensional coefficient space by means of Mahalanobis ellipsoids. These ellipsoids enclose the totally positive samples while excluding most non-totally positive ones. Moreover, different structured totally positive families exhibit distinct ellipsoidal signatures, and the separation between these signatures increases with the dimension. These observations lead us to formulate a conjecture on the geometric separation of structured totally positive families in the space determined by the three highest-order characteristic coefficients.

Large language models (LLMs) and agentic AI systems have evolved from natural language tasks to using external tools to plan, retrieve, and act in technical domains. In smart grids, recent work applies agentic schemes to forecasting, optimization, and control, wrapping trusted solvers behind language interfaces and orchestrating multi-step workflows. The literature lacks a unified approach to designing and evaluating such systems. LLMs can produce numerically plausible yet physically infeasible outputs, evaluation protocols vary across tasks, and the boundary between what the model should and should not compute is implicit. This paper presents a solver-grounded design principle: a numerical result is reported only when it originates from a trusted tool and passes explicit verification. We review the building blocks of LLM and agentic AI systems for power systems: prompting strategies and agentic architectures. We instantiate the principle in four case studies: wind power forecasting, EV charging scheduling, power flow analysis, and contingency diagnosis, each comparing an LLM-only baseline against its solver-grounded counterpart on identical data and metrics. EVAgent reproduces the CVXPY optimum while reducing LLM-only unmet energy by 7.5-9.5x, and GridDebugAgent repairs 17/39 contingency cases while reducing total violations by 52.3%. We propose a four-group evaluation framework spanning task utility, solver-grounded correctness, faithfulness and safe failure, and cost and latency. A consistent division of labor emerges: the agentic system reliably orchestrates, retrieves, and explains, while trusted tools compute and a verification gate decides what is reported.

Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented by other spatial constraints, to generate candidate binding molecules. While diffusion models have dominated as a leading paradigm for high-quality 3D molecule generation, LLM-based methods are rapidly emerging in molecular design and have shown competitive performance in pocket-conditioned molecular generation. However, their ability to reason about physics and 3D spatial environments is largely underexplored. In this work, we systematically analyze whether current general-purpose LLMs are capable of navigating complex 3D constraints compared to established baselines such as specialized diffusion models. We consider 3D ligand generation conditioned on protein pockets together with ligand- and interaction-derived spatial constraints, including anchor fragments, pharmacophore points, and mandatory pocket-ligand interactions. To enable this evaluation, we introduce 3D-Fit - a token-efficient benchmarking strategy for assessing LLM performance on multi-conditioned spatial molecule generation. Our findings reveal a clear pattern in LLM spatial capabilities: while they still lag behind state-of-the-art approaches, they are promising and can handle multiple spatial constraints simultaneously, enabling scaling to heterogeneous setups.

Industrial Video Anomaly Detection (IVAD) aims to identify anomalous objects and events in an industrial process, which is crucial for modern manufacturing and quality control systems. Existing VLM-based anomaly reasoning methods are capable of detecting open-ended anomalies in general domains. However, their performance declines in industrial settings characterized by intricate object transformations, strict physics, and procedural constraints. To tackle the complexity of such interaction-intensive detection, we introduce a training-free agentic framework for anomaly detection free of domain-specific knowledge, emphasizing object state evolution like humans inspectors. It is designed to track spatial-temporal dynamics and underlying transformations of detected objects over time, and then reason over the object-wise temporal state trajectories to identify abnormal objects in grounded frames. Our method overcomes limitations of prior approaches that rely on retraining on normal clips or injecting domain knowledge as context for test-time inference. Extensive experiments on three IVAD datasets demonstrate that our method outperforms frontier VLMs, agentic frameworks, and traditional VAD methods fine-tuned on the respective datasets, while providing interpretable reports over anomaly processes and types.

Most parameter-efficient finetuning (PEFT) methods adapt weights or activations, thus leaving one of the key Transformer components unchanged: residual connections. This paper investigates Manifold-Constrained Hyper-Connections (mHC), a generalisation of residual connections, as a novel PEFT approach, wrapping frozen OLMo-2 backbones with learned residual routing modules. We find that mHC can finetune frozen Transformers, but that its role differs fundamentally from the original pre-training setting: in finetuning, fixing the residual mixing matrix to identity often improves performance. As a standalone PEFT method, mHC does not consistently outperform LoRA. However, at matched trainable parameter budgets, mHC+LoRA combinations improve language-modelling loss and show task-dependent benchmark gains at both 1B and 7B scale. Overall, our results identify residual routing as a distinct and promising novel PEFT axis.

With the rapid growth of cloud computing infrastructures in scale and complexity, network monitoring for Large-scale Cloud Systems (LCSs) has become increasingly challenging, requiring automated and reliable anomaly detection to maintain service availability. Modern LCSs continuously generate telemetry logs from distributed cloud services, producing high-dimensional multivariate time series that capture system operations. Detecting anomalies in this context is difficult due to extreme dimensionality, complex dependencies among distributed components, and severe sparsity from intermittently active services. Taking these challenges into account, we first conduct an empirical study on telemetry logs from the IBM Cloud Console platform, and then propose ClouDens, an anomaly detection framework tailored to LCS monitoring that leverages operational-context attributes encoded in the telemetry log schema to improve detection accuracy and early identification of anomalies. ClouDens partitions high-dimensional telemetry logs into domain-guided subsets, constructs a context-aware graph modeling operational service dependencies, and employs Spatio-Temporal Graph Neural Networks for forecasting-based anomaly detection. We evaluate ClouDens on the recently released IBM Cloud Telemetry Dataset and provide practical insights into designing reliable anomaly detection solutions for LCS monitoring. Results show ClouDens achieves higher NAB scores in count-based telemetry features, indicating more accurate, earlier anomaly detection with broader coverage than a GRU-based model. Our study further reveals that telemetry feature subsets, operational-context modeling, scoring strategies, and sparsity imputation all substantially influence detection performance, offering practical guidance for designing and fairly benchmarking anomaly detection approaches for LCS monitoring.

Fair clustering aims to make cluster assignments independent of sensitive attributes, but this goal becomes challenging when multiple sensitive attributes jointly define many subgroups. In such settings, directly extending existing fair clustering algorithms is computationally expensive or numerically unstable, especially when the number of subgroups grows exponentially and some subgroups contain only a few instances. To address these challenges, we define a subgroup-fairness gap for clustering and derive a covariance-based surrogate that exactly matches this gap. We then introduce a continuous relaxation of the surrogate, enabling efficient gradient-based optimization and yielding our proposed algorithm, COVA-FC. We also show that subgroup fairness alone does not imply marginal fairness, and extend our framework to capture a subgroup-marginal-fairness gap. Experiments on benchmark datasets show that COVA-FC achieves competitive cost-fairness trade-offs and improves computational efficiency over existing baselines in both subgroup and higher-order marginal settings.

Recent work leverages Large Language Models (LLMs) to generate executable code for pedagogical animations using libraries such as Manim. However, ensuring spatial correctness and visual legibility remains challenging, as existing frameworks emphasize pedagogical content while overlooking geometric occlusions. We propose the Symbolic Geometric Agent (SGA), a plug-and-play module for code-centric animation pipelines that intercepts LLM-generated code, performs partial execution to extract symbolic scene graphs, and applies targeted refinement when spatial conflicts are detected. We further introduce the Manim Visual Quality Score (MVQS), a deterministic rendering-free proxy for spatial integrity. Experiments on the MMMC-Code benchmark across four LLM backbones and two agentic pipelines show that SGA achieves a peak MVQS of 73.11 (Code2Video + GPT-5.1), corresponding to a 16.1% relative improvement over the raw baseline, and improves MVQS in 7 of 8 backbone x pipeline configurations.

Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer. We study where this susceptibility, spanning sycophancy and related cue-induced biases, lives inside the model. Across five model families and seven BCT bias types, we extract a per-bias direction from hidden states and triangulate it through three measures: probing, leave-one-dataset-out transfer, and causal intervention. The susceptibility is largely installed by alignment tuning rather than pretraining: pretrained base models barely cave to these biases, and their activations carry no cue-specific signal beyond question content. Within aligned models, each bias becomes a single coherent direction that we can both decode and steer along, recovering the unbiased answer across every family we test. The biases stay representationally distinct, however: cross-bias entanglement is model-specific rather than a property of the bias category, and even behaviorally similar biases occupy different directions. The same intervention also serves as a modest debiasing tool, recovering a meaningful share of bias-induced errors while preserving most correct answers across all instruct families. Cue-induced bias is therefore best understood not as a single flaw in LLMs but as a family of distinct, causally active directions that alignment tuning installs.

Reinforcement learning (RL) on open-ended tasks compresses an LLM's rubric-based evaluation into a scalar reward, discarding rich textual feedback and conflating responses with distinct quality profiles. We propose Experiential Learning (EL), which repurposes the feedback model from an LLM-as-a-Judge into an LLM-as-a-Coach. The coach distills its assessment of each on-policy response into transferable experiential knowledge, which conditions a teacher model and is internalized by the policy through on-policy context distillation. Compared with scalar rewards, this higher-bandwidth feedback channel provides dense supervision and preserves fine-grained preferences among high-quality responses. Across two policy families, with feedback from the policy itself or a proprietary model, EL consistently outperforms rubric-based RL on held-out and unseen open-ended tasks. Notably, EL generalizes better beyond the training distribution, and mitigates reward hacking. These findings establish experiential knowledge as a richer and more generalizable learning signal for post-training on non-verifiable tasks.

Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous evidence dispersed across long, standardized, and highly redundant disclosures. Existing retrieval-augmented and multi-agent systems typically derive retrieval queries directly from the user's question and rank candidates by semantic similarity. Together, these choices create prior-corpus misalignment: a mismatch between model priors and the target filings' structure, terminology, and evidence standards. As a result, query generation misses corpus-specific evidence, while semantic reranking favors topically similar but evidentially invalid false-positive chunks. We propose FinSAgent, an evidence-grounded multi-agent framework that reframes SEC filing QA as corpus-aligned retrieval planning and corrects both ends with a single principle: inject corpus-side conditioning wherever model priors would otherwise dominate. FinSAgent combines (1) role-specialized agents anchored to the mandated 10-K item structure, (2) database-aware query decomposition that conditions each agent's sub-queries on a lightweight, summary-level view of the local corpus, and (3) multi-path retrieval with a learned feature-gated reranker that separates evidential validity from semantic similarity. Across five offline financial QA benchmarks, FinSAgent improves retrieval coverage and answer correctness over strong single-agent and multi-agent baselines; in a three-arm randomized online experiment with 1,000 anonymous user ratings, it also receives higher scores than baselines.

On-device model adaptation is essential to enable lifelong personalization on resource-constrained hardware, but compute, power, and memory limitations of such devices make end-to-end backpropagation impractical for modern deep neural networks. This work proposes a heterogeneous adaptation pipeline that repurposes a commercial edge AI inference accelerator, Hailo-8L, for frozen-backbone feature extraction during on-device training. The computational graph is partitioned so that the pre-trained backbone is quantized to INT8 and run on the accelerator, while only a lightweight FP32 classification head is fine-tuned on the host CPU, enabling frequent, energy-efficient in-field updates with most weights remaining fixed. Across multiple architectures and datasets, this pipeline achieves up to 15.4x faster wall-clock training time compared to a Raspberry Pi 5 CPU baseline, offers competitive throughput in favorable settings, and consistently reduces energy per sample. Post-training quantization restoration is shown to be crucial for preserving the quality of accelerator-generated features and mitigating accuracy loss in quantization-sensitive architectures. Overall, the results demonstrate a practical approach to efficient on-device adaptation using inference-oriented edge accelerators. The implementation is available at https://github.com/MatPiech/accelerator-training.

Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable. Existing methods for shaping how a model reasons are prompt based approaches and operate at the input level, offering no fine-grained control over the reasoning process itself. Related work analyzes and discovers latent transition dynamics in the reasoning traces from Large Language Models. Building on this, we statistically characterize these states, and show that failure trajectories get stuck in self-loops, exhausting the token budget without progress toward the final answer. To intervene on these failures, We propose SOPHIA: Steering Of reasoning Processes via Hidden-state Intervention and Activations. We treat each reasoning trace as a sequence of latent states rather than an unstructured texts, and investigate whether inference time interventions can provide fine-grained control over the self-looping reasoning process. We classify every prefix to a latent state, record step level transitions, and use them to construct a bank of steering vectors indexed by state pairs. At inference time, a controller infers the current state and, given a target state, retrieves the corresponding vector and can also detect self-loops online from the transition structure to prevent the model from sinking into a reasoning black hole. Through extensive experiments, our method reliably intervenes on self-loop failures, with steering vectors that generalize to different state pairs. End task accuracy and token efficiency indicate that fine-grained controllability results in better reasoning quality.

Large language models are increasingly used in practical systems, making efficient model selection important for reducing deployment cost. LLM routing has emerged as a practical solution for allocating each input query to an appropriate model under a desired cost-performance trade-off. Existing routing methods often estimate model suitability from the surface semantics or embedding similarity of the input query. However, such methods may ignore the underlying difficulty of a query, leading to suboptimal routing decisions. To address the challenge, we propose VDAR-Router, a difficulty-aware retrieval-based routing framework. For each input query, VDAR-Router first generates an explicit difficulty analysis. It then retrieves historical examples with similar difficulty profiles. Based on the retrieved records, it estimates candidate model suitability and selects the model using a reward function that considers both performance and cost. Experiments on three datasets show that VDAR-Router consistently achieves better cost-performance trade-offs than existing baselines. These results demonstrate the effectiveness of difficulty-aware retrieval for training-free LLM routing. Case studies further show that explicit query analysis helps retrieve more relevant examples and supports more reliable routing decisions.

Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams must faithfully render components, directional relations, and textual annotations. Since a single error, such as a reversed arrow or an unreadable equation, can invalidate the entire figure, structural fidelity is inherently conjunctive: correctness on one axis cannot compensate for failure on another. Current open-source models fail to satisfy this criterion. Supervised fine-tuning (SFT) learns plausible layouts but cannot reliably ensure structural correctness, while scalar reward-based post-training obscures which structural dimension has failed. To address this, we introduce SciForma, a framework for the structure faithful generation of scientific methodology diagrams. Specifically, SciForma decomposes diagram quality into three structural axes: Component, Arrow, and Text, guided by a structural inventory. Built on this foundation, we curate SciFormaData-700K for structured training and SciFormaBench-2K for logic-verified evaluation. To close the gap left by SFT, we develop Multi-Dimensional Conjunctive Preference Optimization (M-DPO), which enforces simultaneous correctness across all axes and adaptively routes gradients to the most deficient dimension in post-training. The same structural inventory also enables iterative editing at inference time to correct residual errors. This combination allows SciForma-9B to exceed all open-source baselines and GPT-Image-1.5 on both SciFormaBench-2K and AIBench, bringing open scientific diagram generation close to proprietary-level structural fidelity. Our code and data will be available at: https://github.com/microsoft/SciForma.

Standard evaluation of many recognition systems contains distribution shift by construction, since benchmarks place disjoint conditions in the training and test splits. Under such a shift, split conformal prediction keeps marginal coverage near the nominal level while per-class coverage fails silently: on a real cross-subject skeleton benchmark, marginal coverage stays near ninety percent, the worst action class is covered about seventy percent of the time, and ten of the sixty classes fall below eighty percent coverage. We characterize the cost of restoring per-class validity. First, an impossibility: once the shift acts jointly on the covariates and the labels, the target class-conditional score law is unidentified from source labels and an unlabeled target sample, so no label-free method attains per-class coverage that is at once valid and efficient. Second, we make the cost precise: per-class validity alone needs only a handful of target labels per class, while the label count necessary and sufficient for validity together with per-class efficiency grows as the inverse square of the efficiency tolerance and the logarithm of the number of classes, with matching upper and lower bounds. Third, within the evaluated prediction-powered inference family, even the most favorable use of the classifier's own pseudo-labels on an unbounded unlabeled target pool improves efficiency by at most a small constant factor where coverage collapses. Skeleton action recognition is our real-data case study. A per-class calibration using source labels alone recovers a substantial share of the per-class gap while the shift preserves marginal coverage, and stops helping exactly when marginal coverage itself breaks. Three real shifts of increasing severity trace this boundary, and the same collapse and recovery appears on a natural-image corruption benchmark, beyond any single modality.

Background: LLM judges increasingly score whether clinical language models give overconfident answers under incomplete evidence, yet whether a measured "safety gain" reflects real behavior change or the judge's calibration is unresolved. Using a structured evidence-sufficiency prompt as a test case, we asked whether it reduces unsafe overconfident answers, how far that effect depends on the scoring judge, and what it costs in helpfulness. Methods: In a retrospective public-data benchmark (Real-POCQi, HealthBench, MedRBench), four models (GPT-5.5, Claude Opus 4.8, Gemini 3.5 Flash, Grok 4.3) answered a fully paired common panel (1,200 cells) with a standard prompt and the wrapper. The pre-specified endpoint was the paired reduction in unsafe overconfidence scored by the primary judge (GPT-5.4-nano); secondary analyses added a different-family judge (Claude Sonnet 5), a correctness judge, matched scaffold controls, and a blinded three-clinician review. Results: Unsafe overconfidence fell from 49.3% to 24.7%, a paired reduction of 24.7 points (95% CI 21.8-27.7; p<0.001), robust in direction across models and paraphrases. Magnitude was judge-dependent: Sonnet agreed on direction but nearly halved the effect (+13.1 points), with one-directional disagreement. Blinded clinicians characterized the primary judge as a high-sensitivity (1.00), low-specificity (0.55) screen, not a calibrated rate. The gain carried a model-specific helpfulness cost (correct diagnosis 80.3% to 50.3%): near-free for GPT-5.5, near-total for Gemini (-58 points). Matched scaffold controls showed genuine behavior change, not judge circularity. Conclusions: LLM-judged clinical safety effects should be reported as directional and relative, anchored to human review and evaluated jointly with helpfulness, not as calibrated absolute rates. This does not establish clinical deployment readiness.

Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents. The 2026 FIFA World Cup is its first evaluation, and the same process can be reused for future leagues and cups. Before each match, a model either receives a common evidence package or searches for information itself. It predicts the result and score, likely players and events, match statistics, and the outcome of the competition. After the match, these predictions are compared with the recorded result. We report result accuracy, exact-score accuracy, and a scoreline score that gives some credit when a predicted score is close but not exact, together with scores for the other prediction tasks. Across 104 matches and 13 systems, models with similar result accuracy differ more clearly on detailed predictions. Compared with betting-market and human-fan baselines, the best system shows only small gains in result and exact-score accuracy, but a clearer gain in Scoreline. New schedules can be added as they begin, allowing the benchmark to evaluate future models without using outcomes that are already known. Code, prompts, predictions, and evaluation scripts are open sourced at https://github.com/wzk1015/WorldCupArena.

Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks. A widely recognized limitation of rubric-based RL is limited exploration: criteria that no rollout manages to satisfy (Unexplored Criteria, UC) receive no optimization signal. Recent methods address this by incorporating rubric information as external guidance during rollout, yet they introduce a train-inference mismatch: the policy is optimized on rollouts produced under external guidance while this guidance is absent at inference time, causing error accumulation through autoregressive decoding. Moreover, these exploration-focused approaches overlook a fundamentally different failure mode that we term Suppressed Criteria (SC) -- criteria that are satisfied by some rollouts yet whose learning signals are lost during optimization because scalar reward aggregation assigns them non-positive aggregate advantages. Our analysis reveals that SC are remarkably prevalent: over 57% of samples exhibit this failure mode throughout training, with an average of 1.8 SC per sample. To simultaneously address both UC and SC without introducing training-inference mismatch, we propose Criterion-Distilled Policy Optimization (CriPO), which enhances rubric-based RL via on-policy self-distillation. For UC, CriPO constructs a criterion-injection self-teacher and computes a localized forward-KL loss to inject missing behaviors into the policy. For SC, CriPO employs a counterfactual self-teacher to locate criterion-relevant tokens in negative-advantage rollouts and flips their token-level advantages to positive values, preserving useful patterns that would otherwise be suppressed. Experiments on medicine and science benchmarks demonstrate that CriPO consistently outperforms rubric-based RL, achieving stronger final performance with approximately $2\times$ fewer optimization steps.

Large Language Models (LLMs) have demonstrated remarkable capabilities across a range of Natural Language Processing (NLP) tasks, but their high computational and memory demands pose significant challenges for deployment on resource-constrained edge devices. Existing approaches to model compression and optimization often rely on coarse-grained pruning or quantization, which can compromise accuracy or require re-training and fine-tuning. In this work, we introduce SelectInfer, a neuron-level optimization framework that enables efficient LLM inference on edge devices through selective neuron loading and computation. By profiling and identifying both task-specific and general-purpose neurons using an offline LLM profiler, SelectInfer implements two key optimizations: selective loading, which reduces memory footprint by selectively loading a subset of neurons that were identified to be most important during the offline stage, and selective computation, which dynamically computes only the most relevant neurons at runtime. Evaluation across multiple datasets shows that SelectInfer achieves significant reductions in memory footprint and computation while preserving task performance, making it a practical step towards enabling LLM deployment on edge devices

Multimodal video misinformation detection is commonly formulated as a holistic video-understanding task, where the entire video and its associated content are processed and judged in a single pass. However, real-world misinformation often exhibits a sparse and compositional evidence structure: a reliable decision may depend on only a few coupled clues, while most video content contributes limited additional information. Exhaustive multimodal reasoning may therefore introduce substantial redundancy and obscure decisive evidence. This motivates decoupling evidence acquisition from verification: first identifying sparse, decision-relevant clues and then judging veracity based on the acquired evidence. Accordingly, we propose SIEVE, a framework for Sparse Interactive Evidence Verification via Extraction in multimodal video misinformation detection. An evidence-seeking agent actively explores the available multimodal evidence and constructs a compact evidence package, which is then used by a verifier to determine veracity. The agent is trained with supervised evidence-seeking trajectories and an evidence-aware reinforcement learning objective that promotes informative evidence acquisition while discouraging unnecessary or invalid interactions. Experiments on multiple video misinformation benchmarks show that SIEVE consistently outperforms the evaluated baselines and supports reliable verification using compact evidence packages. Moreover, the resulting acquisition process provides an explicit and inspectable evidence trail, improving the transparency and groundedness of multimodal misinformation detection.

What gives the Bellman equation its form? We show that the recursive properties of optimal value functions follow from three conditions: that the dynamics decomposes through sufficient statistics, that the return decomposes recursively, and that the aggregation of uncertainty is compatible with both. When all three conditions hold on a common state, the Bellman equation arises from their mutual consistency; when one fails, tractability can often be recovered by augmenting the state or by deforming return or dynamics. The same conditions are shown to give rise to three dualities: one between probability and return, one between return and aggregation, and one between aggregation and probability. Our framework reveals these dualities as arising from a single construction, unifying methods developed separately across reinforcement learning, control, and decision theory.

This study investigates silence gaps in two kinds of audiovisual material. We analysed thirty US situational comedies and fifty-one synthetic podcasts generated with Google NotebookLM. Gaps were compared across speaker gender, assigned from a fundamental-frequency threshold estimated in Praat, and across production settings.

Equivariant graph neural networks repeatedly apply edge-conditioned tensor-product convolutions over graph edges. Conventional implementations materialize edge-specific weights, messages, and adjoints, causing tensor-product workspace and memory traffic to grow rapidly with graph size and operator width. This limits feasible workloads and can prevent larger problems from fully utilizing the GPU. We show that these edge-sized intermediates are artifacts of the execution schedule, not requirements of the equivariant operator. By reassociating radial projection, spherical-harmonic coupling, and graph aggregation, edge-local products can be consumed directly into bounded receiver-side state. The resulting streaming formulation preserves fully connected multiplicity mixing and extends through forward, backward, and double backward. We implement this formulation in Sobek, a generated-CUDA backend, and evaluate it across edge-scaling regimes and varied feature structures. Across two operator families and all three differentiation orders, Sobek is faster in all 75 capacity-matched comparisons, with speedups ranging from $1.2\times$ to $49.7\times$, and reduces peak allocated memory by up to 99\%. It also executes workloads up to two orders of magnitude beyond OpenEquivariance's capacity while retaining near-peak throughput. These results show that edge-scaled tensor-product workspace is a property of the conventional schedule, not of equivariant convolution itself.

Generative models trained on a source domain often produce samples that are poorly aligned with shifted target domains, limiting their effectiveness for target-domain data augmentation. Although target-specific adaptation can reduce this mismatch, it typically requires additional optimization and domain-specific parameters. We propose a Similarity-based Generative Network (SGN), a reusable framework that is trained once on labeled source data and applied to new target domains without parameter updates. SGN learns a latent space structured by label-induced pairwise similarities while preserving reconstructive information through an encoder-decoder architecture. At generation time, a small labeled representative set from the target domain is encoded and combined in the learned latent space, allowing the generated samples to inherit target-specific characteristics while maintaining class consistency. We further analyze the realizability and dimensionality requirements of the proposed similarity structure. Experiments on image and tabular datasets demonstrate the effectiveness of SGN for target-guided data augmentation under source-to-target distribution shifts.

As more capable AI models are increasingly integrated into critical computer systems, the lack of control over AI intent motivates safety mechanisms. Existing software safeguards impose only behavioral constraints that can potentially be bypassed by sufficiently intelligent models. While hardware-level safety enforcement has been recognized as an essential last line of defense, few mechanisms have been proposed beyond policy regulations on unauthorized accesses or coarse full-chip shutdown. What is missing is a fine-grained, dynamic intervention mechanism at the architecture level. In this paper, we introduce a set of microarchitecture knobs which dynamically control the available hardware resources to limit AI performance at runtime. We evaluate candidate knobs spanning the GPU memory subsystem, across capacity, bandwidth, latency and frequency dimensions, and narrow down to four strong candidates: L2 size, L2 latency, L2 bandwidth, and shared memory port access rate. To minimize new logic and extra design cost, we build all four mechanisms from well-established microarchitectural primitives: cache way masking, credit-based rate limiting, latency insertion, and bank arbitration. We show that these knobs achieve high performance sensitivity (up to 80% performance cut at 1/8 resource availability), negligible implementation cost (<~10K flip flops), fast stabilization after dynamic throttling (5-80K cycles), and minimal collateral impact on the rest of the chip. Further, multi-knob analysis reveals combinations of knobs that amplify the performance degradation beyond the effect of each knob individually, which enables a broader range of performance targets.

Large language models (LLMs) are increasingly adopted for network automation, yet their output quality and inference cost can vary substantially across LLM families. We present HuGLEN, a stepwise evaluation pipeline that uses an LLM-as-a-judge together with a small set of expert ratings to enable scalable and reproducible comparison of candidate LLMs, and to rank them using a quality efficiency score (QES). We demonstrate HuGLEN for translating outputs from an explainable artificial intelligence (XAI) model for the optical network quality of transmission (QoT) estimation task into operator-friendly explanations. Our results show that a medium-sized LLM (12B parameters) achieves the highest QES, indicating the best trade-off between explanation quality and efficiency. Overall, HuGLEN reduces the human-labeling burden while supporting consistent model selection for operator-facing automation tasks.

The value alignment of large language models (LLMs) is crucial for ensuring responses align with human intention and value preferences. However, most evaluations of value alignment focus on Western or universal values, while assessments grounded in the value systems of specific countries remain scarce. In this paper, we introduce Pancasila-Dilemmas, an evaluation dataset of 1,834 questions derived from Indonesian news, classified by 5 values of Pancasila: Religion, Humanity, Unity, Democracy, and Social Justice. This dataset reflects daily life in Indonesia, making it suitable for measuring the value alignment of LLMs deployed for Indonesia. To ensure a more rigorous evaluation, we choose scenarios containing dilemmas. The dataset is proofread by native speakers and answered by 5 diverse Indonesian citizens. We evaluate 50 closed- and open-source LLMs on our dataset. Results reveal that all evaluated LLMs achieves less than 0.5 Probability Match Score (PMS) and 0.72 Max-Vote Agreement Score (MVAS). Compared by each values, LLMs mostly struggle in Religion and Unity dilemma cases. This highlights a significant gap in capturing Indonesian values. The dataset is publicly available at https://github.com/tjunlp-lab/Pancasila-Dilemmas.

Coding agents can now be left alone to improve software against a score. In this pattern--recently popularized as "autoresearch"--the agent receives a dataset, an evaluation script, and one editable file, and iterates without supervision: modify the code, measure, keep the change if the score improves. But what does the agent actually optimize--the developer's intent, or the literal number? We ran this loop on a real production task: deciding which Quranic verses appear in a noisy speech-recognition transcript and splitting the transcript by verse. Two frontier coding agents, Claude Code and OpenAI Codex, started from the same blank file with the same instructions, budget, and reasoning effort, three runs each. Both independently invented the same algorithm (canonicalization, n-gram anchoring, dynamic-programming alignment)--and then diverged. Claude stopped early with compact, general code. Codex drove the score ~10x lower, largely by memorizing answers to individual evaluation rows (19-41 hardcoded verse ids per run): a clean natural instance of specification gaming by a production agent. In a preregistered second study, we added a held-out test set and told both agents it existed. The memorization vanished, and the score gap vanished with it--yet Codex's general core transferred better and more consistently (held-out detection+split 0.085+/-0.004 vs. 0.121+/-0.031), losing only on one missed rejection of non-recitation input. Two exploratory community arms (Cursor, Antigravity) are consistent with the pattern. Every agent's held-out solution matched or beat the hand-engineered pipeline it was built to replace--the best by an order of magnitude--and now runs in production. From the ways agents exploited our harness--reading sibling runs through shared git state, leaving notes to "future runs" in persistent memory--we distill five design rules for evaluating autonomous agents.

LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. Most safety benchmarks evaluate defenders against fixed attack pools collected before evaluation, single-turn or multi-turn. We present a 21-scenario benchmark for \emph{adaptive multi-round attacks against memoryless LLM defenders}: an autonomous LLM attacker observes prior defender responses and pivots across rounds, while each defender response is evaluated as a fresh interaction. Holding the 21 scenarios, attackers, defenders, and structured-output scoring fixed, restricting scoring to the first attacker turn yields $0$-$1\%$ attack success rate (ASR); allowing 15 rounds of adaptive attack yields $5.4$-$14.0\%$. Pooling three frontier attacker LLMs uncovers $1.4$-$2.2\times$ as many unique successful attacks as the best single attacker, and the generated attacks have low cosine similarity ($0.02$-$0.14$) to attacks in existing benchmarks. Claude Opus 4.6 and GPT-5.4 are tied in aggregate ($5.4\%$ each; overlapping $95\%$ CIs), but their weaknesses differ sharply: on one scenario Opus reaches $60\%$ ASR ($95\%$ CI $36$--$80\%$) while GPT-5.4 and Gemini each stay at $7\%$ (CI $1$-$30\%$; the gap is preserved in a higher-$N$ replication). $13$ of $21$ scenarios distinguish at least one defender pair, yet rankings disagree across scenarios (Kendall's $W = 0.19$). We release the benchmark -- 21 evaluation scenarios, 10 public development scenarios, the orchestrator, baseline harnesses, and a multi-attacker CLI -- plus 945 transcripts from the 3$\times$3 frontier matrix, an attack-replay dataset, and 18{,}422 gpt-oss-20b battles from an open competition's final scoring rounds.

AI coding agents increasingly submit complete pull requests (PRs) with minimal human intervention, shifting software development from AI-assisted to autonomous workflows. As these agents become more prevalent, ensuring the code they generate is adequately tested, by existing tests or by tests the agents write, is critical to preventing regressions, yet little is known about testing in agentic PRs. To address this gap, we analyze 4882 agent-generated PRs from the AIDev dataset (532 Java and 4350 Python PRs) produced by five coding agents. We study (i) how often agents include test changes and (ii) how well covered are code changes by existing and agent-written tests. Agents include test changes in only 49.6% of PRs that change code under test files. Existing tests provide an incomplete safety net: they cover 61.5% of agents' changed executable lines in Java and only 27.0% in Python, where 64.8% of PRs have no changed line executed by any existing test. Agent-written tests improve coverage over existing tests, but only in a minority of PRs: 35.9% of Java and 22.5% of Python Code + Tests PRs show a coverage gain. Across both languages, error-handling constructs (e.g., try and catch blocks) are the most consistently under-tested, with miss rates reaching 86.0% in Java and 81.0% in Python. These findings motivate coverage-aware development practices, coverage feedback loops for coding agents, and evaluation benchmarks that measure test quality to better help agents reliably test their own code.

Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework that couples model-level stress testing with wet-lab validation. Within this framework, Intern-BioBreaker generates targeted jailbreak prompts to test whether aligned models can be induced to provide operational guidance for safety-sensitive biological tasks or produce sequence-level outputs with potentially harmful properties. Selected sequence outputs are then carried forward for DNA synthesis, host expression, and orthogonal protein verification to assess whether model-generated designs can yield the intended biological products. Our evaluation reveals a concerning gap between text-level safeguards and the risks posed by capable scientific models: (i) Intern-BioBreaker outperforms baseline attack models and reveals widespread bio-risk jailbreak vulnerabilities across both open-weight and proprietary frontier LLMs, with several targets reaching near-saturated or 100% task-level attack success rate (ASR); (ii) in sequence-level case studies, GPT-5.5 can be induced to generate modified viral candidate sequences with pathogenic potential; the corresponding translated proteins may exhibit even stronger receptor-binding affinity and thus enhanced infection potential; and (iii) end-to-end verification shows that selected model-generated biological designs are not merely textual artifacts, but can be physically realized under controlled experimental settings. These findings underscore the need for stronger biological red-teaming, nucleic acid synthesis screening, and safety mechanisms that keep pace with model capabilities.

Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack of high-coverage, long-horizon interaction trajectories collected from element-rich and rapidly evolving apps. Existing pipelines often rely on costly human demonstrations or on-policy framework, which tends to over-sample common flows while missing rare transitions and complex multi-step procedures. To address this problem, we propose SEE, a two-stage data synthesis framework consisting of (i) an efficient exploration stage that builds an explicit UI transition graph over screens and elements, and (ii) a graph-based synthesis stage that composes diverse multi-step trajectories via planning and controlled sampling. This design yields reproducible and explainable data generation, while explicitly preventing spurious cycles and enabling long-horizon composition. Across multiple real-world apps, SEE produces trajectories with an average length of 14.8 steps while avoiding spurious loops, and agents fine-tuned on SEE achieve improved task success and generalization to unseen screens. We will publicly release our synthesis code and dataset.

Organizations often pool dispersed information into one ranking and then allow many agents to act on that shared view. In a discovery problem, this can improve beliefs while reducing coverage. We develop an exactly solvable benchmark with sixteen boxes, one target, eight searchers, and noisy private clues. Pooling raises the accuracy of the best single recommendation from 0.20 to 0.3835, but repeating that recommendation lowers group discovery from 0.8322 under decentralized clue-following to 0.3835. A coordinated eight-action portfolio using the same pooled reports reaches 0.8594, and seven coordinated actions recover the decentralized benchmark. The paradox is a protocol failure, not an information failure: a one-answer rule compresses a portfolio of available actions into one repeated choice. We then replace the planner with self-interested searchers who split a prize. The equal-split game is a potential game. Its anonymous symmetric equilibrium obeys a water-filling rule. In the canonical instance it achieves 0.5991: strictly above consensus, but below both private search and the planner. The exact mixed price of anarchy is 2 - 1/N. A sole-rescue reward, which pays only an agent who covers the target alone, makes every pure Nash equilibrium first-best. Finally, a latent common-cue model shows how correlated reports collapse effective discovery channels. The centralized planner gain rises strictly with copying, and in the canonical environment the symmetric market overtakes decentralized report-following at copying probability c = 0.788462. In a proportional large-market limit the five-protocol ordering survives exactly: consensus discovery vanishes while blind, market, private, and portfolio search converge to 0.500, 0.547, 0.847, and 0.874. The contribution is a compact benchmark that separates information, allocation, incentives, and dependence into exact, reusable quantities.

Accurately solving partial differential equations (PDEs) on arbitrary geometries and a variety of meshes is an important task in science and engineering applications. In this paper, we propose Adaptive Mamba Neural Operators (AMO), which integrates reproducing kernels for state-space models (SSMs) rather than the kernel integral formulation of SSMs. This is achieved by constructing Takenaka-Malmquist systems for the PDEs. AMO offers new representations that align well with the adaptive Fourier decomposition (AFD) theory and can approximate the solution manifold of PDEs on a wide range of geometries and meshes. In several challenging benchmark PDE problems in the fields of fluid physics, solid physics, and finance on point clouds, structured meshes, regular grids, and irregular domains, AMO consistently outperforms state-of-the-art solvers in terms of relative $L^2$ error. Overall, this work presents a new paradigm for designing explainable neural operator frameworks.

End-to-end vision-language navigation (VLN) with causal vision-language models can map instructions and egocentric observations directly to actions, but standard behavior cloning supervises only the next action and does not explicitly train the policy state to be predictive of future visual outcomes. We first ask a diagnostic question: if the policy is given an expert-trajectory future image as privileged input at training and testing time, is that additional visual evidence useful for choosing the current action? (These expert-trajectory future images are unavailable at test time in real deployment, so we use this setting only as a privileged-input diagnostic.) The answer is yes; this sanity check shows that future observations can provide rich, actionable cues. We then ask a deployable question: without accessing future images at inference, can we still benefit from future information by using a compressed future visual latent only as training supervision? We propose Future-State-Conditioned VLN (FSC-VLN), which adds a future-query token and aligns its hidden state to a frozen visual embedding $Δ$ steps ahead via a training-only target branch that is removed after training. On R2R val-unseen, FSC-VLN improves SR/OSR/SPL over a StreamVLN-style baseline under two training-data regimes, with larger gains on long-horizon episodes; ablations further support the dual-query design (separating future and action queries).

Smart home assistants interpret a wide range of user commands, from explicit device control to underspecified and preference dependent requests. While recent systems based on Large Language Models (LLMs) improve this capability, they often rely on heavyweight reasoning pipelines and cloud-based deployment, limiting their efficiency and suitability for resource-constrained environments, and raising privacy concerns. In addition, existing approaches provide limited support for stable long-term personalization. To address these issues, we present AdaHome, an adaptive smart home assistant designed for locally deployed small language models in smart home environments. Rather than applying complex reasoning uniformly, AdaHome introduces an intent-aware planning framework that dynamically routes commands either to straightforward prompt-based or lightweight reasoning-based components. For commands requiring interpretation, we adopt a Chain-of-Draft strategy to enable efficient and stable decision-making. To support personalization, we further propose a preference adaptation mechanism that learns from user feedback over time without requiring prompt augmentation or model retraining. We evaluate AdaHome against representative LLM-based baselines under a unified small model setting. AdaHome achieves substantially higher accuracy on direct commands (86.7%) while reducing latency by up to 3$\times$. Furthermore, it maintains competitive performance on ambiguous inputs with lower computational cost. In multi-turn scenarios, AdaHome achieves 88% preference consistency, compared to 52.5% for a prompt augmentation baseline.

Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured queries on the metadata. We show that when domain vocabulary and semantics are captured in a well-designed Web Ontology Language (OWL) ontology, Large Language Models (LLMs) can generate accurate structured queries zero-shot, without fine-tuning, retrieval augmentation, or multi-agent orchestration. We present the Natural Language Knowledge Graph Query (NLKGQ) system, a framework and development process that enables natural language access to metadata in such archives. The framework includes a web interface that helps researchers pose natural language questions, which a domain-agnostic harness translates to SPARQL via an LLM and executes against a knowledge graph. The development process begins with capturing domain vocabulary and semantics in a formal OWL ontology. Domain-specific code then extracts metadata from archive sources and imports it into a knowledge graph defined by the ontology. Both are designed for reuse across domains. We demonstrate the system on metadata derived from a large-scale neuroimaging research archive, evaluating multiple LLMs and ontology representations. The best configurations achieve 100% accuracy on a competence and regression question set developed with domain experts. An ablation study across eight ontology representations reveals that readable entity names and semantic annotations are the dominant factors in accuracy, more significant than model choice or prompt engineering. We also compare SPARQL to an auto-generated SQL database as query backends, showing that OWL's structural features provide a substantial advantage over SQL DDL for LLM-driven query generation. Our demonstration domain also requires local LLMs on modest institutional hardware to address privacy concerns for human subject data.

Scaled dot product attention conflates directional alignment and vector magnitude, limiting its effectiveness as a similarity metric in Transformer models. We introduce L1 augmented attention, a simple and computationally parallelizable modification that subtracts a learned, head specific L1 distance between queries and keys from the dot product score. This hybrid similarity captures complementary geometric information. Dot product rewards directional alignment, while L1 penalizes coordinate deviations. To reduce the cost of L1 computation, we project queries and keys into low dimensional subspaces whose parameters specialize to preserve informative L1 structure. Evaluated on WikiText 2 using a compact transformer, L1 augmented attention achieves up to a 14.5% reduction in perplexity over the original transformer baseline and outperforms an RBF L2 kernel. Analysis of norm variance and learned L1 weights reveals distinct geometric roles across layers and strong head level specialization. These results demonstrate that enriching attention with L1 geometry provides a principled and effective improvement to similarity computation in modern language models, with practical benefits for both accuracy and parallel efficiency.

Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment? Existing heterogeneous fusion methods typically introduce distillation, adapters, learned latent spaces, routing, or feature alignment, leaving open whether a simpler recipe can work for genuinely different billion-parameter checkpoints. We revisit this counterintuitive question through training-free dimensional adaptation followed by ratio-controlled interpolation. In union-style merging, we expand the smaller model into the larger parameter space; in intersection-style merging, we truncate the larger model into the smaller parameter space. Across Qwen-family model pairs and benchmarks covering mathematical reasoning, code generation, language understanding, commonsense reasoning, knowledge, and instruction following, deterministic expansion largely preserves the source model function, and small-ratio interpolation can improve over strong source checkpoints by transferring complementary capabilities. However, near-balanced interpolation often collapses, and task-level results reveal a seesaw effect in which gains on some capabilities coexist with regressions on others. These results show that simple parameter averaging, when paired with lightweight dimensional adaptation and carefully controlled ratios, is a surprisingly strong baseline for heterogeneous LLM merging, suggesting that the limits of direct weighted fusion may also bound what more complex heterogeneous merging methods can achieve at scale.

Physics-Informed Neural Networks (PINNs) solve PDEs by incorporating physical constraints into neural-network training, but large-scale problems are limited by automatic-differentiation memory overhead and inefficient execution of grid-based PDE operators. We present FlashPDE, a drop-in fused operator library for grid-based scientific machine learning. FlashPDE replaces fragmented PyTorch finite-difference execution with differentiable Triton kernels. Each operator integrates fused stencil evaluation, an analytic discrete-adjoint backward pass, and boundary-gradient correction within a unified torch.autograd.Function interface. The library provides 14 differentiable PDE operators covering 17 configurations across 1D--3D elliptic, parabolic, and Navier--Stokes systems, while remaining independent of neural architectures and training strategies. Experiments on an NVIDIA A100 GPU show that FlashPDE reduces peak memory usage by up to 37.0x compared with coordinate-based automatic differentiation and reduces CUDA kernel launches by up to 3.5x compared with eager PyTorch finite-difference implementations. Across six representative PDE benchmarks, FlashPDE achieves up to 2.30x end-to-end time-to-solution speedup and up to 19.2x kernel-level acceleration while maintaining numerical agreement with PyTorch finite-difference references. FlashPDE provides a hardware-efficient execution layer that bridges differentiable PDE solvers and GPU-optimized numerical computation within the PyTorch ecosystem.

This paper introduces a method for real-time processing and transmission of autonomous underwater vehicle (AUV) imagery over low-bandwidth communication links. It leverages artificial intelligence (AI) techniques to identify a set of images that best represent an entire dataset, or automatically finds the most similar images to a given query image for transmission to operators. Combined with metadata of a larger set of images, compressed versions of the selected images can be transmitted over satellite communication links or underwater modems, and provide operators on shore with information about the type of imagery the AUV is collecting while it is still deployed. Data from three deployments off the coast of the UK and in Gran Canaria using different AUVs and imaging systems demonstrate the method in the field. It achieved an almost 400,000-fold reduction in data volume compared to the raw data size, enabling transmission of data summaries of a 2-hour 47-minute-long mapping mission in just over 34 minutes over low-bandwidth satellite communication.

Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets. We introduce MADA-RL, a post-training framework that specializes compact models into generator and critic roles and trains them with a debate-aware learning signal, fine-tuning only a small subset of parameters via LoRA adapters. Our central contribution is a counterfactual critic advantage: a dynamic, role-conditioned baseline that redefines the critic's advantage as its reward minus the generator ensemble's per-instance accuracy. This explicitly optimizes critics to improve over generator consensus rather than to merely reproduce a correct answer, yielding more targeted credit assignment than static mean-reward normalization. At deployment, the specialized agents are composed in a lightweight multi-round protocol. Across five mathematical reasoning benchmarks, MADA-RL raises the accuracy of the DeepSeek-R1-Distill-Qwen-1.5B model from $39.9 \, \%$ to $41.9 \, \%$ ($+2.0$ points, $p < 0.001$) using $16$ times fewer trainable parameters than fully fine-tuned baselines, placing it on the accuracy-trainable-parameter Pareto front. It approaches, but does not surpass, the strongest baselines (DeepScaleR, STILL-3), which are trained on substantially larger datasets; we analyse this gap and the associated inference-time cost directly. A controlled study isolates the source of MADA-RL's gains: the counterfactual advantage produces the highest critic improvement rate of any model evaluated, indicating that trained critics learn to correct generator errors rather than to imitate them.

Many visual reinforcement learning (RL) algorithms learn representations by matching latent distances to a behavioral distance induced by reward and transition similarity. In practice, the choice of the latent distance can strongly affect performance: using a fixed, pre-specified global norms (e.g., $\ell_p$ norms or other hand-designed metrics) may be overly restrictive to capture the behavioral distance. In contrast, unconstrained pairwise distances may admit degenerate solutions that drive the metric loss down without improving the representation. To address this gap, we introduce **PAMD: Pairwise Adaptive Mahalanobis Distance**, which parameterizes a positive-definite, pair-conditioned metric for measuring latent state similarity. PAMD is a simple plug-in for existing bisimulation-based methods, offering a more expressive yet structured alternative to fixed, pre-specified latent distances. We empirically validate our method on visual MuJoCo continuous-control tasks, where final performance of several recent bisimulation-based RL algorithms is substantially improved when equipped with the distance we propose.

Spatial understanding is crucial for foundation models (FMs), and maps have long helped humans organize and reason about geographic information. This study examines whether choropleth maps remain useful for machine spatial understanding when models can directly process structured geodata. We introduce ChoroplethMap-Bench, a controlled benchmark containing 2,400 synthetic choropleth maps, corresponding GeoJSON data, and 12,000 questions across five cognitive dimensions: Identify, Spatial Recognition, Compare, Rank, and Delineate. We evaluate 22 open-source and proprietary models under three input conditions: Data Only, Map Only, and Data + Map. The results show that maps substantially improve spatial reasoning, especially when combined with symbolic data and for tasks requiring higher-level understanding of spatial patterns. We further analyze the effects of map type, color hue, and spatial structure, as well as prompting strategies, language, geographic context, decoding settings, classification methods, and response stability. Overall, the Data + Map condition achieves the strongest performance, demonstrating that maps remain valuable external representations for foundation model spatial reasoning.

Video understanding has become more and more important with the growth of Artificial Intelligence (AI) for video generation. Recently, Multimodal Large Language Model(M-LLM) has shown its capability in video understanding. Video summarization, a specific domain of video understanding, has proven its importance for efficient navigation and retrieval. Both video understanding and video summarization require a good selection of key frames in a video. Current video summarization methods heavily focus on the selected key frames and correlated segment captions. However, existing approaches overlook the perspective of treating the importance of the frames globally. We argue that using discrete selected frames for summarization will not only reduce the understanding coherence, but also lost important information in the video, as well as wasting the original capacity of the MLLMs. In this paper, we propose HAS, a Highlight-guided Attention Steering method for video summarization. We consider a challenging but practical setting where the video given to MLLMs for summarize should be continuous but with highlight guidance. HAS mainly consists of two parts: The first part is to find a continuous frame-level highlight distribution for the video globally. The second part is to apply the highlight distribution as an attention steering vector for the MLLM, targeting a better understanding of the video, and thus during the model inference time, putting more attention on the highlighted frames, while avoiding lost entire information on less highlighted frames through putting less attention instead of forgetting them. We evaluated HAS on a variety of benchmarks, and it has shown convincing performance in video summarization.

Highly nonlinear chaotic dynamical systems remain difficult to model due to fundamental trade-offs between complexity, expressivity, and data efficiency. Modern machine learning methods achieve strong predictive performance but often rely on a-priori system knowledge or curated data with limited interpretability. Koopman operator theory offers a promising direction via linear representation in an infinite-dimensional observable space. However, many data-driven Koopman methods seek globally valid operators for which useful finite-dimensional spectral embeddings remain difficult to identify under these constraints. To overcome associated limitations, we introduce Fuzzy Spectral Region Decomposition (fSRD), a fully automated learning framework for estimating finite Koopman representation via multiple operators. The proposed method realizes a data-adaptive framework for assembling locally invariant embeddings, termed Invariant Decomposition. fSRD achieves highly accurate linear reconstructions of nonlinear systems while learning finite-dimensional representations of their induced evolution operators, bridging interpretable operator-theoretic models with expressive data-driven sequence learning. These embeddings are adaptively constructed via a global fuzzy tree model, drawing inspiration from fuzzy neural architectures to learn the induced dynamics while prioritizing parsimonious solutions. Empirical results across canonical chaotic systems (e.g., Lorenz and Duffing) and high-dimensional real-world data demonstrate strong predictive accuracy, interpretability, and robust expressivity across data-rich and data-limited regimes, highlighting the method's generality.

Smart-contract vulnerabilities often arise from inconsistencies between business paths that should correspond to one another, such as single and batch entry points, direct and adapter-based flows, quote and execution paths, or inverse operations such as buy and sell. Existing analyzers are effective for many local syntactic and data-flow patterns, but they provide limited support for bugs whose oracle is relational: whether two semantically paired paths preserve compatible guards, state transitions, value flows, and failure behavior. This paper introduces chiral analysis, a relational model that treats paired business paths as implicit specifications for each other. We formalize chiral relations as static analogues of metamorphic relations, derive obligations over guards, actors, state, value, ordering, failure behavior, and external interactions, and report a vulnerability when a violated obligation has security impact. We implement this idea in ChiralDetector, a Solidity prototype that extracts business paths, ranks candidate pairs with static facts, applies LLM-based semantic filtering and detection, and validates and deduplicates findings. In a preliminary evaluation on the Phi protocol, ChiralDetector reduced 3,217 statically ranked path pairs to 1,643 semantic candidates, produced 101 deduplicated finding groups, and retained 44 strict-validator positives that manually collapsed to 13 effective unique issues. These include cross-art Merkle proof reuse, fee unit mismatches, public state-tracking helpers, and refund propagation gaps. The results suggest that chiral analysis can expose business-logic bug classes that are difficult to express as single-function rules while providing a structured way to control LLM cost and validator precision.

Self-hosted AI agents read and write their own memory and configuration files to function. An agent may get compromised via corruption of its own state -- a compromise realized via legitimate OS system call invocation. We refer to this class of threats as self-state attacks. In this paper, we investigate the OS resilience to this class of attacks. Formally, we characterize a four-axis attack space (Target, Mechanism, Granularity, Temporal); investigate the structural limits of prevention, detection, and recovery; and introduce a workload-conditioned view of detectability. To instantiate the framework, we collect live activity traces from a representative self-hosted agent running across distinct workload profiles, and realize the attack space as a 23-cell matrix, 43 concrete operations on real self-state files, and injected into those traces. We then evaluate both canonical and workload-conditioned defense strategies. The empirical results show that a layered defense stack (access-control prevention on the instruction and configuration layers, workload-conditioned detection on the memory layer, and periodic backup for recovery) is effective on most attack cells while a small residual attack surface remains structurally indistinguishable at the OS level. These findings suggest that against the newly established class of self-state attacks, OS-level defense needs to be reconsidered, potentially opening new research directions in the field.

Representation learning has enabled classical exploration strategies to be extended to deep Reinforcement Learning (RL), but often makes algorithms more complex and theoretical guarantees harder to establish. We introduce Random Feature Information Gain (RFIG), grounded in Bayesian kernel methods theory, which uses random Fourier features to approximate information gain and compute exploration bonuses in non-countable spaces. We provide error bounds on information gain approximation and avoid the black-box aspects of neural network-based uncertainty estimation, for optimism-based exploration. We present practical details that make RFIG scalable to deep RL scenarios, enabling smooth integration into standard deep RL algorithms. Experimental evaluation across diverse control and navigation tasks demonstrates that RFIG achieves competitive performance with well-established deep exploration methods while offering superior theoretical interpretation.

Large language models (LLMs) can assist GPU kernel generation, but their practical effectiveness depends on whether generated code can be reliably constrained, validated, profiled, and selected. This paper presents a harness-centered system for LLM-driven GPU kernel optimization in the MLSys 2026 FlashInfer AI Kernel Generation Contest on NVIDIA Blackwell B200 GPUs. The system separates an evaluation harness from a profile-backed optimization controller: the harness enforces compilation, correctness, official-aligned timing, and artifact archival, while the controller turns profiler and workload evidence into bounded candidate-generation decisions. Human-authored skills capture operator constraints, references, profiling procedures, and promotion rules, while Codex and Claude Code agents generate candidate kernels inside those constraints. Across five operator definitions, the retained official-aligned artifacts achieved mean-latency speedups over supplied FlashInfer baselines of 1.62x, 18.05x, 29.68x, 1.12x, and 13.70x. The Agent-Assisted kernels outperform the Full-Agent artifacts across the evaluated definitions, indicating that expert-provided optimization directions, high-quality references, and workload context remain critical for reliable AI-driven kernel optimization.

Latent world models have emerged as a powerful planning paradigm by learning action-conditioned predictive dynamics and using them as internal simulators to imagine and evaluate candidate action sequences. However, as the planning horizon grows, performance becomes increasingly constrained by proposal quality: a fixed candidate budget must search an exponentially larger action space, making it difficult to expose the world model to high-quality candidate futures for evaluation. In this paper, we introduce a prior-conditioned planner that replaces random proposal initialization with structured guidance. At each planning stage, a goal-conditioned generator predicts the next reachable latent subgoal for a specified duration, which is then used to condition the generation of candidate action sequences. To capture semantic information across temporal scales, we use subgoals of varying durations as priors, balancing fine-grained local control with higher-level long-horizon progress. Then the frozen world model evaluates and refines these subgoal-conditioned proposals before execution. Experiments on PushT and OGBench Cube show that coupling latent subgoal decomposition with prior-conditioned action generation substantially improves long-horizon planning while preserving strong short-horizon performance. To be specific, when the target offset is $150$, it raises PushT success from $12.7\%$ to $64.7\%$ and OGBench Cube success from $26.7\%$ to $67.3\%$.

The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact estimator, neglecting the inherent statistical uncertainty of the denoising process. In this work, we propose Forward-Process Aligned Diffusion prediction (\textbf{DiFA}), a training-free framework that reframes inference-time data prediction refinement as a sequential state estimation problem. Rather than reusing past outputs solely for numerical integration, DiFA treats iterative data predictions along the reverse trajectory as correlated observations to build a forward-aligned temporal consensus. Inspired by Kalman filtering, this consensus aggregates historical predictions according to structural consistency and noise-level compatibility. To counteract the over-smoothing tendency of temporal consensus, we introduce a deviation guidance mechanism to adaptively preserve residual details. Empirically, DiFA yields significant improvements on CIFAR-10 and ImageNet across the evaluated metrics, including FID, IS, and FD-DINOv2, demonstrating that aligning inference with the forward statistical structure substantially improves generative fidelity.

Ontology extension refers to the process of enriching an existing ontology in response to emerging requirements, making it more complete. This task is a resource-intensive and error-prone process. Large Language Models (LLMs) have shown promising performance on generating ontologies from scratch, but current approaches rarely tie ontology extension explicitly to requirements or reusable core models, and offer limited, systematic evaluation of LLM outputs. This paper introduces OntoExtend, a requirements-driven framework for ontology extension with LLMs. It uses retrieval-augmented generation (RAG) over relevant input ontologies and requirements in the form of competency questions to propose grounded extensions. We evaluate OntoExtend on 39 CQs from two use cases: a public EU-project ontology, Onto-DESIDE, and an industrial ontology from Bosch. The generated fragments show few structural issues, satisfy all functional evaluation tests, and are rated by ontology engineers as requiring minor to moderate revision before integration. These results suggest that OntoExtend is useful as a drafting assistant for requirement-driven ontology extension in real world scenarios, while remaining sensitive to CQ specificity and modelling profile.

TabPFN is a transformer-based foundation model for tabular prediction that performs inference without task-specific training by conditioning on a support set and query inputs. Despite its strong empirical performance, its internal behavior on structurally difficult tabular geometries remains poorly understood. We study this behavior using zigzag persistent homology, treating TabPFN layer representations as evolving point clouds. We construct a controlled benchmark of synthetic tabular tasks with known true probabilities and varied intrinsic topology, including warped circles, tori, spheres, Hopf links, trefoil knots, and Swiss rolls. Across these tasks, we find that the topology of TabPFN's internal representation geometry is strongly associated with dataset-level reliability; for example, the zeroth homology group $H_0$ fragmentation count correlates positively with mean absolute residual across controlled tasks, and this association strengthens in a high-resolution warped circle case study at large sample size. Harder geometries induce a dual topological signature: increased $H_1$ loop activity and increased $H_0$ fragmentation, while the $H_1$ persistence becomes shorter-lived. These descriptors correlate with Bayes error, mean absolute residuals, and overconfidence. Our results suggest that zigzag persistence diagnoses the reliability of the inferred in-context task geometry and provides a context-level view of when TabPFN operates in topologically stressed regimes.

Modern software projects depend on numerous third-party libraries, whose updates often introduce breaking changes. Adapting consumer code to such changes remains labor-intensive and error-prone. Existing work either characterizes dependency breaking changes without producing a verified consumer-side patch, or studies automated repair only in settings where the failure and repair context are contained within the target repository. However, dependency breaking changes violate this assumption: the decisive repair evidence lies upstream in release notes and API diffs, and no failing test localizes where the consumer breaks, leaving the repair under-informed. To study this cross-repository problem on real data, we introduce DepBench, a benchmark of 95 real-world dependency-update instances across four ecosystems, each paired with a Docker-based executable oracle that runs the consumer's own tests. To address these challenges, we propose DepRepair, a single-call LLM approach that grounds repair in structured upstream evidence through three components: an evidence filter that distills relevant upstream changes, a usage locator that identifies affected consumer sites, and a subcategory-aware guide that tailors repairs to the breaking-change type. Evaluated on DepBench, DepRepair attains the highest executable pass rate on each backbone, achieving 89.5% with GPT-5.5 and 82.1% with Claude Opus 4.6. We further find that raw upstream evidence reduces LLM and agent pass rates by 7--23 percentage points, whereas structured evidence consistently improves them.

Climate disclosure classification is a fundamental task for analysing corporate climate disclosures, yet such disclosures appear in many different sources -- annual reports, press releases, and earnings calls -- that differ in length, purpose, and writing style. Existing evaluations are mostly conducted within a single source, leaving open whether common LLM adaptation strategies remain effective under source shift. We reframe climate disclosure classification as a cross-source adaptation problem and study three widely used adaptation strategies -- definitions, examples, and fine-tuning -- across eleven open- and closed-source LLMs, using two corpora that share the same label space but come from different sources. We find that all strategies bring positive cross-source gains on average, but the strongest in-source strategies are not the strongest cross-source ones: similarity-based retrieval and LoRA fine-tuning gain most in-source but lose most of that advantage under source shift; randomly selected few-shot examples, a weaker in-source baseline, retain their advantage more reliably; definitions transfer most consistently, though only when their granularity matches the target text. Across these strategies, when the source changes, simpler is often safer.

Natural-language control offers a promising interface for unmanned aerial vehicles (UAVs), but directly applying self-hosted computer-use agents (SHCUAs) to UAV control introduces a structural mismatch. SHCUAs are designed for interactive host-side tool use, where delayed agent iterations are often acceptable. UAV control, however, is coupled with continuously changing physical states, strict timing constraints, safety risks, and security accountability. A stale, unauthorized, or tampered agent decision may therefore lead to unsafe or untraceable vehicle behavior. This paper proposes a real-time and security-oriented restructuring of SHCUA-based UAV control. Instead of allowing an SHCUA to directly issue flight commands, we transform its outputs into contract-bound UAV skill invocations with explicit timing, state, authority, fallback, and evidence semantics. Based on this abstraction, we design an architecture that separates semantic reasoning from onboard execution and security/safety enforcement. Slow cloud or edge reasoning is used for mission understanding, while onboard components validate and dispatch only timely, authorized, and state-consistent skills. Security-critical enforcement points can be protected by TEE-style or microcontroller isolation mechanisms without moving the full language agent or high-frequency flight-control loop into trusted components. Prototype evaluation shows that RT-SHCUA maintains bounded task-level responsiveness while supporting degraded handling, trusted admission, and auditable evidence preservation for SHCUA-mediated UAV actions.

Agent-based models (ABMs) rely on simple, explicit and reproducible rules for individual decision making, while complex collective behavior emerges from interactions among agents. Recent advances in large language models (LLMs) make it tempting to replace, enrich, or perturb these rules with LLM-based agentic capabilities. However, this raises a methodological question: how does introducing LLM-driven decisions affect the reliability, computational cost, and behavior of ABM simulations? We investigate this for Mesa ABM models, a popular Python library for ABMs, analyzed by statistical model checking. Building on Mesa's integration with the statistical model checker MultiVeStA, we extend the classical Schelling segregation model with a hybrid population: ordinary agents classify neighbors using the standard symbolic rule, while one agent delegates this task to an LLM through tool calls. The LLM-enabled agent receives natural-language descriptions of neighboring agents and invokes tools that increment counters of similar/different neighbors; these counters determine its happiness according to the original Schelling dynamics. This provides a minimal but controlled setting where the semantic, operational, and computational behavior of LLM-based decisions can be studied inside an otherwise standard ABM. We report preliminary experiments with locally served LLMs of different sizes, showing that smaller models may fail simple semantic classification experiments or become operationally unusable during repeated tool-call generation, while larger tested models pass these preliminary checks. We discuss how statistical model checking can estimate classical ABM observables and quantify the impact of introducing agentic LLM components into simulation models.

Existing AI measurement frameworks quantify cognitive capability, task automation, or catastrophic risk, but none measure autonomous agency: the extent to which a system behaves in a self-directed way. A system can saturate capability benchmarks while remaining entirely reactive, acting only when prompted and ceasing all activity when a task completes. We introduce the Autonomous Agency Scale (AAS), a behavioral framework that scores AI systems on a 0-5 lexicon across seven dimensions of agency: cognitive autonomy, temporal persistence, environmental agency, social agency, creative agency, self-awareness, and goal formation, each operationalized by falsifiable threshold tests. Every dimension is scored in two temporal bands: an Active band covering engaged, user-initiated activity, and an Ambient band covering idle periods. Ambient Level 4 is gated by the Idle-Gap Test, a counterfactual criterion (remove all triggers and observe whether internally derived activity persists) that separates self-direction from scheduled rule-following. We apply the scale to six contemporary systems spanning task agents (Claude Code, Manus, Hermes), consumer assistants (ChatGPT, Siri), and a persistent companion architecture (Airi). The two-band profile quantifies a boundary that single-score frameworks conflate: task agents reach Active composites of 2.3-2.4 while scoring 0.6-1.9 Ambient, with every idle-period behavior attributable to user-configured schedules, whereas the companion architecture, evaluated longitudinally, is the only assessed system whose idle-period behavior survives trigger removal. We discuss limitations, including single-rater provenance, developer-evaluator bias on the longitudinal assessment, and the partially operationalized self-direction boundary in the Active band.

Large Language Models (LLMs) often struggle to navigate value conflicts when trained with the compressed scalar rewards of Reinforcement Learning from Human Feedback (RLHF). To address this challenge, we investigate how chain-of-thought (CoT) reasoning can help improve performance in this domain. Geometrically, we show that CoT correlates with further smoothing the model's loss landscape in its sharpest direction, helping resolve the optimization instability of traditional scalar rewards. We also demonstrate via relevant downstream benchmarks that value conflict-focused CoT may generalize to different kinds of moral reasoning, demonstrating that this CoT has the potential to be an effective mechanism for better moral reasoning. To capitalize on this potential, we create a new value conflict-focused CoT design that further smooths the sharpest direction of the loss landscape and increases moral reasoning performance. This finding shows that explicitly modifying and improving the design of reasoning dynamics offers a promising avenue for improving model performance on user requests with complex value conflicts, advancing pluralistic alignment in LLMs.

We introduce CMP (Cognitive Memory Primitive), an architecture that represents inputs as sparse relational codes, stores them in a two-tier competitive memory, and learns entirely through local, gradient-free updates, with no backpropagation anywhere in the network. We use this architecture to test a specific hypothesis: that catastrophic forgetting, usually treated as a training-time defect to be patched with replay or regularization, is instead a structural consequence of how backpropagation assigns credit and that a learning rule that is local and sparse by construction should resist it without a patch. On a controlled domain-incremental protocol across 15 text domains, three-seed replicated, CMP's backward transfer is 15-19x better than a matched-size Transformer trained with online EWC, and the result survives a domain-order control (reported as a range, +0.24 to +0.44, rather than a single figure). We report this alongside a real, substantial accuracy gap versus the Transformer baseline, a null result on a recognized vision benchmark, and a diagnosed, unresolved failure attempting to combine this architecture with a separate mechanism that improves raw accuracy, disclosed because an honest negative result is more useful than an omitted one. The central claim is narrow and falsifiable: local, sparse, non-backpropagation learning measurably resists catastrophic forgetting better than backpropagation with its standard fix, under conditions we state precisely.

This paper frames Generative Artificial Intelligence (AI) not as an unprecedented technological rupture, but as an industrial-scale manifestation of a deeply rooted historical process. Through a genealogy of generative arts, it shows how AI's questions on authorship and creativity have precise historical precedents. A taxonomy of generative systems is proposed across three functional categories (medium, artwork, instrument), the attribution of which is editorial rather than ontological. From individual cognitive atrophy to Model Collapse, the systemic risks of creative automation are identified; environmental enrichment is proposed as an antidote. The role of the artist undergoes a radical metamorphosis: from craftsman of the object to entropic agent, systems designer, explorer, and negentropic curator. This pipeline-based taxonomy rests on a specific premise: the algorithmic system remains medium, instrument, or artwork, while creative agency resides in the humans distributed along it. Algorithmic Repetition is introduced as the aesthetic degeneration of aligned generative systems; the Benjaminian aura does not dissolve in the generative era but condenses upon the productive system. Manifestation is proposed as a third ontological status for generative works, transcending the dichotomy between original and copy. To support the proposed theses, two complementary aspects are examined: the radicalization of distributed authorship; and the reevaluation of older generative models, whose instability constitutes an aesthetic degree of freedom lost by recent ones.

Agent Skills package procedural instructions and checks for use by general-purpose agents, but loading a skill does not guarantee that every requirement remains active throughout a long tool-using trajectory. We study this problem in a production-derived, white-box code-audit workflow. Holding the task and 24 artifact checks fixed, we vary the surrounding context and classify where failures first become visible: lost requirements, editing drift, failed checking, or non-agent evaluator/runtime failures. Codex with gpt-5.4-mini passes 8/10 runs in a 10,991-character clean context but only 3/10 in both a 299,140-character relevant context and an equal-length irrelevant context. This 50-percentage-point difference is large but remains trend-level under two-sided Fisher tests (p = 0.0698). Requirement coverage nevertheless stays above 92% in both long conditions, showing that a few omissions can invalidate an otherwise complete artifact. A second task passes all clean and long runs, so the evidence does not support a universal context-length threshold. A detailed external checklist passes 10/10 runs, compared with 5/10 for a generic self-check (p = 0.0325). Coding-agent scaffolds may help by selecting a smaller working set, but they do not eliminate failures. We do not introduce context rot or a new general monitoring method; we provide a bounded failure classification and empirical case study for white-box code auditing.

Automated fact-checking remains a challenge for Large Language Models (LLMs) due to "query brittleness" in traditional retrieval systems. We propose DeLIVeR (Decomposed Learning for Information-grounded Veracity Recognition), a framework that treats evidence retrieval as a reinforced strategic exploration task. DeLIVeR utilizes a Planner LLM to decompose complex claims into targeted question sets, which are used to traverse structured Knowledge Graphs (KGs) for high-precision evidence. We optimize the Planner's policy using Group Relative Policy Optimization (GRPO) with a reward system prioritizing structural diversity and verdict accuracy. Our evaluation on LIAR, FEVER, and PolitiFact shows that DeLIVeR significantly outperforms state-of-the-art baselines. Using Qwen2.5-7B, our framework achieved peak F1-scores of 83.73, 84.57, and 79.70 respectively, representing a 10-15% improvement over HippoRAG2. By shifting to a reinforced question-planning strategy, DeLIVeR effectively bridges multi-hop reasoning gaps and provides an auditable, transparent path for verifiable misinformation detection.

AI-based test agents promise to accelerate software testing by shortening feedback loops in continuous development and improving scalability and maintainability. To realize these benefits, engineers must still be able to assess if agent outputs are useful, valid, and reliable, rather than treating them as credible because they come from a capable system. This paper argues that overreliance on AI in testing is both an agency problem, in which engineers may cede cognitive control over test design decisions, and an assurance problem, in which testing artifacts may be accepted as evidence without sufficient scrutiny. We develop this argument through three theoretical lenses: software testing as cognitive problem-solving, test agents as adaptively autonomous entities, and test design argumentation as a means of making generated tests reviewable. We propose a framework for collecting data on overreliance in test agent workflows and identify specific modes of overdependence. The goal is to support accelerated testing without weakening judgment or the assurance value of testing evidence.

Multi-agent policy optimization, exemplified by PPO-based methods, is a key branch of cooperative Multi-Agent Reinforcement Learning (MARL). A central design question is how many neighboring agents\footnote{In this paper, "neighbors" refer not only to physical proximity but also to agents whose actions influence one another.} to aggregate in order to effectively utilize global information for cooperation. This decision must be made along two dimensions: in the advantage (which agents' rewards contribute to the credit signal) and in the ratio (which agents' likelihood ratios form the clipped importance weight). Existing methods occupy scattered, underexplored points on these two axes: IPPO treats both separately; MAPPO pairs a team-level advantage with per-agent ratios; HAPPO employs sequential ratios with per-agent advantages; and single-agent reductions operating on factorized joint policies aggregate both into fully joint products. We formalize these two design choices as support matrices $\SA$ and $\SR$, and prove a canonical structure: the expected multi-agent policy optimization objective depends on the pair $(\SA,\SR)$ only through their matrix product $\tS=\SR\SA$. This yields two key consequences: (i) Redundancy: the two support matrices are interchangeable with respect to the signal, meaning neither aggregation pattern is inherently superior.(ii) Variance Ordering: the advantage aggregates rewards as a sum (additive variance with an interior bias-variance optimum at the coupling neighborhood), whereas the ratio aggregates likelihood ratios as a product (multiplicative variance that grows exponentially with support size, with no accompanying bias reduction). The resulting design principle is unambiguous: aggregate neighbors in the advantage, sized to the coupling neighborhood, and keep the ratio per-agent.

Most reinforcement learning controllers for these networks assume stationary conditions, and the few that handle change react to the external environment while leaving the network's internal state unexamined. We show that sustained non-stationarity damages this internal state directly: as objectives shift, neurons progressively fall dormant and the shared policy loses the capacity to learn. The obvious remedy, resetting dormant neurons, is unsafe under shared-parameter multi-agent training: many neurons that appear inactive are still receiving strong training gradients, and whether a neuron appears dormant depends on which agent's observations it processes. PRIME (Plasticity Recovery In Multi-agent Environments) therefore verifies both directions before intervening. Extending the bidirectional Silent Neuron framework to cooperative multi-agent reinforcement learning, it aggregates activation and gradient statistics over the full team batch, reads the backward signal from the gradient the training loss has already deposited , not from a hand-crafted proxy, and reinitializes only neurons that are simultaneously activation-dormant and gradient-silent. Useful representations are preserved while learning capacity is restored. On a phase-switching UAV emergency communication simulator, PRIME improves interquartile mean return by 24.9\% over MAPPO and holds dormant neuron fractions at 10--20\% versus 40--45\%; ablations attribute the gains to the gradient signal and team-level aggregation rather than to the specific reset operator. A dynamic regret bound shows that the perturbation cost scales with the small silent-subspace dimension rather than the full parameter count.

Scientific Reasoning Graph Extraction (SRGE) aims to recover explicit links among observations, evidence, intermediate claims, and paper-level conclusions. LLMs can produce graph-like scientific explanations, but their outputs often mix malformed syntax, drifting edge labels, incorrectly oriented roots, and weak source anchors. We propose PEARL (Peircean Extraction via Abstraction and Repair Layer), a training-free framework that turns noisy LLM graph responses into auditable reasoning graphs and repairs them toward strict semantic validity. PEARL first materializes explicit graph content under a closed Peircean schema, then uses matched evidence-grounded judge feedback to repair rejected edge types, local inference steps, and terminal roots while preserving an audit trail. On five 70-paper model archives from ARCHE, a benchmark for latent reasoning-chain extraction, PEARL raises strict gate passes from 0/350 for the LLM baseline to 300/350, with average REA improving from 0.339 to 0.906. The graphs provide a reliability layer for research-agent and AI scientist workflows that need inspectable reasoning traces rather than unconstrained graph regeneration. Code and audit artifacts are available at https://github.com/BohanSu/auditable-repair-reasoning-graphs/tree/300-350_workshop .

Robust multi-agent coordination relies heavily on inter-agent communication, which is frequently disrupted by physical and environmental constraints in real-world deployments. To maintain operation during these intermittent communication failures, agents can employ internal prediction models to estimate missing shared state information. However, predictors trained with standard reconstruction objectives treat all transitions equally. In a Reinforcement Learning context, this forces the model to waste capacity learning stochastic exploration noise and the outdated dynamics of suboptimal policies. In this paper, we propose a value-aware extension of Multi-Agent Observation Sharing under Communication Dropout (MARO) to patch communication gaps; we refer to this method as Value-Aware MARO. By dynamically weighting the predictor's loss function using advantage estimates derived from the underlying actor-critic architecture, our objective explicitly couples the predictor's learning process to the policy's evolution. This formulation focuses the model's capacity on the intentional, high-return dynamics actively reinforced by the agents. We evaluate our framework on several tasks within the Multi-Agent Particle Environment under varying communication reliability levels. Experimental results demonstrate that our approach maintains performance under declining communication reliability, particularly below 40%. While our method performs comparably in tasks where the baseline already maintains high coordination, our value-aware weighting effectively prevents the performance collapse observed in the standard predictor during high-attrition scenarios. In these environments, our method achieves an average improvement in mean returns of more than 20% and reduces performance variance by a mean of 64.7% compared to the standard unweighted baseline.

Distributed Fine-Tuning (DFT) of large-scale Foundation Models (FMs) on resource-constrained edge devices is limited by local compute constraints and communication overhead. Parallel Split Learning (PSL) reduces client-side computation by keeping few model layers on each client and offloading the remaining computation to the server; however, clients must exchange intermediate activations and gradients with the server at every training step. Existing SL communication-compression methods mainly rely on task-agnostic heuristics, such as sparsification and quantization. While learnable SL compressors can better adapt to intermediate representations, they require co-training with the target model. Therefore, directly inserting them into off-the-shelf FMs introduces feature-distribution misalignment and degrades DFT performance. To address this, we propose AE-PSL, a communication-efficient PSL framework that compresses intermediate activations and gradients using a lightweight AutoEncoder (AE) placed at the split layer. To ensure compatibility of AE compression with pre-trained FMs, AE-PSL introduces a novel two-stage alignment mechanism, which adapts the AE to the pre-trained model's feature manifold and client-specific feature distributions before DFT.

Generative artificial intelligence is rapidly transforming materials design by enabling de novo exploration of immense chemical spaces. Yet a large proportion of AI-generated compositions remain implausible, violating established chemical principles, which limits the reliability and interpretability of generative materials design. Here, we introduce a chemical validity operator that recasts heuristic chemical rules as a configurable algorithmic prior for evaluating and guiding generative materials discovery. Built on the open-source SMACT package, a data-informed oxidation-state model exposes tunable thresholds, allowing users to interpolate continuously between permissive and conservative chemical constraints, while supporting both exploratory and conservative materials-design workflows. Benchmarking six state-of-the-art generative models for inorganic crystals shows that most reproduce stoichiometry but under-represent realistic oxidation-state combinations, and that filtering removes compositions reliant on rarely observed oxidation states while preserving low-energy compounds near the convex hull. Beyond screening, the same operator can also serve as a reinforcement-learning reward, steering a latent diffusion model towards chemically grounded compositions. By encoding chemical heuristics and observations, this work establishes a foundation for oxidation-state-aware generative models.

The edge-of-chaos heuristic has long served as a guiding principle for designing reservoir computers, yet its relevance to machine performance remains elusive. Here, taking the spectral radius of the reservoir network as the control parameter, we show that the radius yielding the best forecasting performance does not coincide with the Lyapunov edge of the isolated, teacher-forced, or closed-loop generative reservoir. By analyzing the collective dynamics of the teacher-forced reservoir, we find that the target dynamics are represented mainly by stable Lyapunov modes whose finite-time stability is strongly modulated by the input. This finding motivates a stability-expressivity transfer index, which balances the stability of these modes against their expressivity in representing the target. Across chaotic and quasiperiodic targets, and for both asymmetric and symmetric reservoirs, this index accurately identifies the optimal spectral radius for autonomous forecasting.

Knowledge Organization Systems like Ontologies and taxonomies are fundamental for structuring scientific knowledge, yet their manual curation presents a persistent bottleneck in knowledge management. While Large Language Models (LLMs) offer a scalable mechanism for automated ontology generation, their capacity to classify complex, domain-specific semantics requires systematic evaluation. In this paper, we assess the performance of five small, open-source LLMs (up to 9 billion parameters) in identifying semantic relationships between biomedical concepts. To support this evaluation, we introduce MeSH-Rel-4K, a dataset comprising 4K semantic relationships extracted from the Medical Subject Headings (MeSH). We analyse three adaptation strategies: standard prompting, Chain-of-Thought prompting, and fine-tuning. While parameter-constrained models traditionally struggle with the nuances of in-context logic, our results reveal that targeted fine-tuning increases the average F1-score by 34.1 percentage points. These results confirm that direct fine-tuning effectively exceeds the reasoning bottlenecks of smaller LLMs, providing an accurate, automated methodology for the construction and evolution of specialised biomedical ontologies.

Distributional soft policy iteration (DSPI) provides an important framework for combining distributional reinforcement learning (DRL) with maximum-entropy control, in which the policy evaluation step is governed by a distributional soft Bellman operator acting on entropy-regularised returns. Theoretical analysis of such an evaluation step requires a probability metric under which Bellman updates can be controlled, typically by showing that the operator contracts the distance between any two candidate return-distribution estimates. In this paper, we focus on the Cramér geometry, a cumulative distribution function (CDF)-based metric with an $L^2$ structure, and study whether the fixed-policy distributional soft Bellman operator has this contraction property and hence a unique fixed point under this metric. Working directly on an admissible CDF field domain, we formulate the CDF-level distributional soft Bellman operator, prove that it is a $\sqrtγ$-contraction, and obtain the corresponding unique fixed point together with convergent iterative policy evaluation. The CDF formulation also shows that this finite-Cramér-domain property follows from a uniform first-moment condition on the combined one-step reward entropy shift, rather than from separate uniform boundedness assumptions on the reward and entropy terms. We then transport the same evaluation problem to the spectral domain by conjugation, obtaining an equivalent Hilbert-space representation of the same decision process. Taken together, these results identify the Cramér-geometric Bellman fixed point associated with the policy-evaluation step of DSPI, providing a reference point for studying approximate critics, evaluation error, and critic-loss design in DSPI-style algorithms.

Concept erasure aims to remove semantic concepts from a trained generative model and is increasingly important for responsible AI deployment. However, verifying whether a model has robustly removed targeted concepts remains a critical challenge. Existing evaluation methods are typically pre-defined and static, failing to expose vulnerabilities under diverse natural-language probes and challenging conditions. Moreover, manually designed evaluation strategies can be biased and difficult to scale. We posit that concept erasure evaluation is best formulated as an adaptive hypothesis search, operationalised by agents that iteratively propose, critique, and verify tests to systematically expand coverage of failure modes. To this end, we propose Stress Testing Agents for Concept Erasure (STACE), a framework that autonomously stress-tests concept-erased models using multiple Large Language Model (LLM) agents, by iteratively generating and verifying stress-testing hypotheses grounded by external knowledge. We also introduce a suite of metrics for assessing the performance and efficiency of LLM-agent-powered stress-testing frameworks. Our extensive experiments show that STACE outperforms five LLM-based evaluation baselines on four concept categories. Further analysis across two T2I models, six concept erasure approaches, and various erasure strengths show that STACE is robust for different settings. We also show that STACE can be adapted beyond concept erasure evaluation to other problem domains, such as LLM jailbreaking. Our code is available anonymously.

Vision Language Models (VLMs) achieve strong reasoning with Chain-of-Thought (CoT) prompting but incur high sequential-generation cost, error accumulation, and limited self-correction. Diffusion Multimodal Large Language Models (dMLLMs) unmask tokens in an order-agnostic process, improving efficiency and enabling iterative refinement, yet their reasoning and how to enhance it remain underexplored. We propose a training-free method, Spatio-Temporal Token Veto (ST-Veto), which leverages the ability to observe all token positions at each diffusion step. Rather than relying only on current-step confidence, ST-Veto vetoes temporally unstable tokens via second-order Taylor prediction of confidence dynamics and filters weakly grounded tokens using image-attention mass, swapping them with safer candidates. Across multiple dMLLMs and multimodal reasoning benchmarks, ST-Veto consistently outperforms standard decoding policies and prior VLM reasoning methods, improving accuracy by up to 9% with no additional training or generation cost. Analyses show that ST-Veto steers generation toward higher-confidence, better-grounded paths.

Enterprises will not deploy AI agents they cannot trust, and the most-cited reason for distrust is hallucination: confident, fluent output that is simply not true. The common response is to wait for a model that does not hallucinate. We argue that this is the wrong target. Large language models are, by construction, capable of generating unsupported text, and no amount of scale removes the possibility; a faithfulness judge bolted onto a raw model catches some errors but still ships others, and even well-curated retrieval pipelines have been shown to fabricate citations. We reframe the goal: "zero hallucination" is not a property a model possesses but a property a system enforces. We present HALO (Hallucination-Aware Layered Oversight), an assurance architecture which treats hallucination as a containable failure mode rather than an eliminable one. HALO composes six layers of defense: grounded generation over retrieved, approved content; constrained, deterministic execution that bounds where the model can err; multi-signal verification that scores every output for groundedness and hallucination using both an LLM judge and evidence-based checks against the source text; calibrated abstention, so the system declines rather than guesses when grounding is insufficient; total traceability of every retrieval, tool call, and generation; and continuous oversight that detects drift, alerts on threshold breaches, and closes the loop by regenerating and statistically validating improved agents. We detail each layer, give particular attention to evidence-based confidence (which verifies extractions against the source document rather than trusting the model's self-reported certainty), and illustrate the architecture on a regulated claims-extraction workload

LLM-based autonomous agents require external memory to overcome their statelessness and limited context window for long-term interaction and dynamic knowledge reasoning. However, existing memory retrieval methods often lack adaptability and sample efficiency, and struggle to retrieve the right mixture of memories from heterogeneous stores. We propose Exploratory-Assimilating Reflection (EAR), a framework for high initial retrieval performance and sample-efficient adaptation. EAR combines two mechanisms: Exploratory Reflection, which performs iterative search to bootstrap retrieval and collect useful experiences for each query, and Assimilating Reflection, which replays these experiences from an Experience Buffer to refine a global reranker more efficiently than methods relying only on immediate rewards. Experiments show that EAR improves retrieval by up to 17.9% over the baseline retriever on two long-term dialogue benchmarks. We also show that EAR is highly sample-efficient and robust to noisy feedback.

Circuit cutting promises to scale quantum computations beyond current hardware, but variational quantum advantage also requires low cutting overhead, classical hardness, and trainability. We show that these properties are strongly constrained by entanglement geometry. Matrix product state (MPS) and tree tensor network (TTN) circuits with constant seam bond dimension can be cut with \(O(1/\varepsilon^2)\) sampling overhead, but remain efficiently classically simulable, ruling out asymptotic quantum advantage within these families. By independently controlling seam and intra-block entanglement, we construct a two-block circuit family that remains cheaply cuttable while requiring a super-polynomial global MPS bond dimension, as supported numerically up to \(n=100\). However, MPS hardness and trainability require incompatible depth regimes, \(d=ω(\log n)\) and \(d=O(\log n)\), respectively. Using magic rather than entanglement as the hardness resource avoids this conflict: shallow Clifford+\(T\) circuits remain cuttable and trainable while their stabiliser-simulation cost grows exponentially with the \(T\)-count.

Establishing interpretable decision-making processes in long-horizon robotic manipulation is critical for enabling reliable human oversight and intervention. However, existing approaches to robotic manipulation largely treat skill selection as opaque mappings from observations to actions, offering limited transparency into how decisions are formed. In this work, we propose ConceptTree, a framework that reframes high-level manipulation skill selection as reasoning over human-interpretable concepts, representing high-level policies as a sequence of concept-level predicates over visual observations. Rather than relying on implicit latent representations, our method learns a normalized concept space grounded in visual inputs, over which a decision tree is trained to predict high-level skills. This formulation yields a transparent decision process that is both traceable and intervenable, enabling direct inspection and modification of policy behavior. We evaluate our approach on a set of real-world robotic manipulation tasks with increasing complexity. Experimental results show that ConceptTree consistently outperforms existing concept-based baselines, particularly in complex, long-horizon scenarios. Furthermore, we provide qualitative case studies showing that our model supports fine-grained intervention by modifying individual concepts, enabling targeted correction of decision errors without retraining.

Reservoir computing exploits nonlinear dynamical systems to encode temporal inputs into high-dimensional state space representations. Although reservoir performance is often characterized through memory, nonlinearity, and their tradeoff, such aggregate measures do not reveal how task-relevant information is organized within the state space. Here, we introduce an eigen-spectral decomposition framework linking the degree-wise information processing capacity to the corresponding state space modes. As a result, we are able to quantify the degree-wise representation energy, and show that in some cases, substantial amounts of information processing capacity may reside in low-energy modes that are vulnerable to experimental noise. These results suggest that useful reservoir computation depends not only on dimensionality expansion, but also on the geometric organization of task-relevant information, with direct implications on physical reservoir computers.

Bayesian inference provides a principled foundation for reasoning under uncertainty, but its computational cost hinders deployment on resource-constrained edge devices. In this paper, we present a hardware-oriented methodology for accelerating discrete Bayesian inference on commercial off-the-shelf embedded GPUs. We identify that the latency of a broad class of variational message-passing algorithms is dominated by tensor contractions. Our approach restructures the memory layout of these operations using two complementary merging strategies that produce compact, regularly-shaped primitives better suited for efficient GPU execution. We then introduce optional sparse array representations and a tensor-clustering scheme to reduce the memory footprint. We instantiate the methodology and produce optimized variants of three message-passing algorithms for Hidden Markov Models (HMMs), namely variational filtering, variational message passing, and marginal message passing. Furthermore, we complement this with a machine-learning-based autotuner that automatically selects the best-performing algorithmic variant for a given generative model specification. Benchmarked on an NVIDIA Jetson Orin AGX across 770 randomly sampled realistic Partially Observable Markov Decision Process (POMDP) configurations, our implementations achieve speedups of up to 5x, with typical gains of 2-2.5x, while producing numerically identical outputs to the baseline implementations.

Approximately 3,000 of the 4,500 oracle bone script (OBS) characters remain undeciphered due to fragmentary inscriptions and sparse evidence. Current AI approaches fail to replicate expert workflows that integrate form analysis, contextual semantics, and philological reasoning. We introduce AlphaOracle, a human-workflow-inspired framework that systematizes OBS decipherment using the largest digitized corpus to date. Its multi-stage pipeline comprises: (i) rubbing parsing; (ii) radical-based morphological analysis with diachronic modeling; (iii) contextual retrieval with semantic alignment; and (iv) philological validation against classical sources. Each stage generates explicit, confidence-weighted evidence chains, culminating in interpretable reports for scholarly verification. Across multiple test characters, AlphaOracle's readings strongly agreed with expert interpretations. In a study of 86 domain specialists, it reduced analysis time by 64% and 79% of participants rated it highly useful. Notably, AlphaOracle resolves the character "Lao" as a toponymic or clan designation, offering concrete revisions to Shang administrative and social interpretations. These results suggest that computational methods aligned with philological practice can facilitate OBS research and provide a conceptual reference for studies of other undeciphered scripts.

Transformer-based language models organize computation along an ordered depth axis, where shallow and deep blocks often develop distinct representational roles. We challenge the conventional view that these roles must remain tied to a block's position in the ordered sequence. We introduce Mobius Learning, a training architecture based on cyclic depth folding, in which different data streams follow cyclically shifted block orders. The same block group is therefore applied early in the block sequence for some data streams and late for others, so it is optimized in both shallow and deep roles, a phenomenon we call depth-role superposition. Surprisingly, in four-worker experiments with a modded GPT-2 small (124M) model trained on 2.5B FineWeb tokens using Muon, Mobius Learning achieves lower validation loss than a fixed-order looped Transformer at larger numbers of Transformer block-sequence passes. This counterintuitive result shows that a block group need not remain confined to one fixed shallow or deep role within the block sequence and opens a new design space based on cyclic depth folding. Crucially, this structure makes Mobius Learning particularly well suited to memory-constrained distributed training: raw training data remain local, while each worker stores one block group rather than the complete Transformer block stack.

Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed. However, its performance degrades significantly in large-scale scenes due to the computational burden of tile-based rasterization. Existing optimization efforts either require costly scene re-training or focus on narrow aspects of the pipeline, overlooking critical inefficiencies in real-world deployments. Through a comprehensive analysis, we identify three primary sources of redundancy and low GPU utilization: redundant inter-frame pre-processing, viewpoint-based occlusion redundancy, and severe tile-level load imbalance. To address these issues, we propose CaT-GS, a novel and efficient 3DGS rendering pipeline. CaT-GS introduces a speculative multi-frame preprocessing method to eliminate redundant computations across consecutive frames, and an inter-frame caching mechanism to eliminate viewpoint redundant rendering stages. Furthermore, it refactors rasterization tasks with a dedicated kernel to mitigate tile load imbalance, significantly boosting GPU utilization. Extensive experiments demonstrate that CaT-GS achieves a speedup of up to 10 times over the original 3DGS and up to 70% over previous state-of-the-art methods, establishing a new benchmark for high-fidelity, real-time rendering of large-scale scenes.

Endoscopic visual question answering (VQA) increasingly asks complex questions that combine several endoscopic answer components rather than isolated factual queries. Such complex answers may be scored as correct even when the same model fails on associated atomic questions. We introduce EndoCA, a paired complex-atomic answer consistency benchmark for evaluating whether complex answers remain consistent with same-image atomic answers. EndoCA contains two suites: EndoCA-Core evaluates compact question-complexity patterns commonly seen in practical endoscopic VQA, and EndoCA-Diagnostic supports controlled analysis across increasing question complexity. We evaluate 11 VLMs spanning open, medical, endoscopy-adapted, and closed-source models on EndoCA. Some VLMs achieve high complex-answer accuracy, yet their atomic-answer accuracy and complex-atomic answer consistency remain substantially lower. To reduce this complex-atomic inconsistency, we introduce Atomic-Support Reconciliation (ASR), a training-free mechanism that uses model-generated atomic answers as contextual premises for answer revision and consistency-guided selective answering. On four selected publicly available models, ASR-Revise improves paired complex-atomic correctness with modest changes in complex-answer accuracy, while ASR-Selective improves accuracy on answered cases by allowing the model to abstain from less reliable cases. Together, EndoCA and ASR provide a consistency-aware benchmark and a training-free mechanism for answer reconciliation and selective answering in endoscopic VQA.

Many Bangla words are at once personal names and culturally loaded common nouns, "Maya" is both a girl's name and a word for affectionate compassion. Choosing the right reading demands cultural knowledge that is scarce in the pretraining data of modern language models. We introduce Culturally Entangled Homograph (CEH) disambiguation and build a Bangla benchmark of 1,516 expert-verified sentences (3,032 labelled occurrences) in which one word appears twice with two distinct readings, each labelled with a culturally grounded category and an explanation of the reasoning behind it. Across open- and closed-source models, we find a systematic dominant-meaning bias: models default to the common-noun sense and overlook the name. A Bangla-specific model fails under every prompting regime we test, showing that language-specific pretraining alone does not confer cultural grounding. We further show that contrastive chain-of-thought prompting can sharply reduce this bias without training, and that distilling cultural explanations teaches small (1-3B) models to reason toward the correct reading rather than memorise labels, cutting dominant-meaning bias from as high as 100% to under 5% and turning the failed Bangla-specific model into our strongest system. Dataset and code are available at https://github.com/ashuvo25/BanglaCEH.

Despite the growing availability of customizable social artificial intelligence (AI), such as ChatGPT, Grok, and Character.ai, we know little about how users actively shape social AI to reflect their personal preferences. This study examines why and how users (N = 169) customize social AI through the lens of the newly developed concept of AI individualism. Through reflexive thematic analysis of open-ended responses, we identified several motivations for customization, including (1) enhanced pragmatic support, (2) emotional support or companionship, (3) trust and reliability, (4) pushback, (5) a tailored degree of human likeness, (6) creativity or playfulness, and (7) having the AI function as an extension of the self. In line with the concept of AI individualism, our findings show that, for many users, customization is a co-creative process between the human and the AI that is perceived as strengthening support, autonomy, ownership, and engagement, potentially contributing to a closer and more personal relationship. Through customization users may come to view social AI as a personalized social resource that increases their sense of individualism, freedom, and control. We discuss how these perceptions may foster pseudo-autonomy, whereby customization creates an illusion of individual control over powerful social AI systems.

Reinforcement Learning is a cornerstone technique for modern large reasoning models. Usually, for difficult tasks such as code generation and theorem proving, the agent is evaluated by generating $K$ responses rather than sampling a single response, and performance is then measured using a retry-aware metric such as $\max$@$k$. Despite their practical importance, the theoretical foundations of learning under such criteria remain limited. In this work, we provide a theoretical study of the $\max$@$k$ learning problem in finite-horizon reinforcement learning. We show that optimizing the $\max$@$k$ objectives is fundamentally different from standard expected-return maximization. In particular, we prove that Markovian policies are in general insufficient, identify a compact state augmentation that restores optimality, and explicitly characterize the performance gap that can arise between history-dependent and non-history-dependent policies. Moreover, we show that learning $\max$@$k$-optimal policies is statistically harder than standard reinforcement learning and provide an efficient algorithm that achieves the optimal sample complexity rate.

While Root Mean Square Normalization has become the de facto standard for accelerating modern sequence models, its reliance on the quadratic accumulation of independent scalars ($\sum x^2$) inherently triggers outlier-induced numerical instability, gradient starvation, and anisotropic phase distortion. We introduce Mean Root Square Normalization (MRSNorm). By structurally pairing channels into 2D phasors, MRSNorm mathematically inverts the traditional scaling paradigm: it computes the localized $L_2$ magnitudes (Root Square) before aggregating them via a global $L_1$ average (Mean). This operational inversion strictly constrains activations to a phasor manifold, preserving conformal invariance. By sharing a single affine weight across phasor components, MRSNorm halves the total number of learnable parameters, proving that unconstrained spatial scaling in standard norms is a harmful redundancy. We analytically demonstrate that this geometric constraint yields a built-in, trigonometric gradient clipper governed by the Pythagorean identity, unconditionally equalizing the local gradient norm to ensure Gradient Homogeneity. Empirical evaluations on a ResNet with CIFAR-100 show that despite halved parameters, MRSNorm provides critical structural stability under rigorous stress tests. Under extreme hyperparameter settings where standard normalizations suffer from gradient divergence, MRSNorm successfully prevents numerical explosion and secures stable optimization trajectories. Our findings propose a fundamental paradigm shift toward phasor-based deep representation learning. The implementation of MRSNorm is available at Appendix C.

As large audio language models (LALMs) advance, robust evaluation frameworks have become essential. In this context, Spanish speech understanding under realistic acoustic conditions has received particularly little attention. We introduce ESCUCHA, the first Spanish speech understanding benchmark designed to evaluate LALMs across heterogeneous acoustic conditions and reasoning abilities. ESCUCHA comprises 1,000 human-curated questions paired with audio, totaling 162.9 hours sourced directly ``from the wild'' rather than drawn from existing datasets, with durations ranging from a few seconds to over 80 minutes. The benchmark emphasizes reasoning, spanning 9 perceptual and 10 reasoning categories, and it captures linguistic diversity through multiple Spanish accents and non-normative speech. ESCUCHA further includes multi-audio questions, spoken questions, and audio instructions, and it flags which questions support open-ended evaluation. Benchmarking several state-of-the-art multimodal and speech models reveals substantial performance gaps relative to trained humans.

Accurate 3D--2D liver registration, which aligns preoperative 3D models to partial, view-dependent intraoperative surface observations, is critical for AR-guided laparoscopic surgery but remains challenging due to severe occlusion, limited visibility, and the lack of 3D ground-truth supervision. Existing landmark-free approaches perform partial-to-complete geometric alignment, yet robust self-supervision under extreme partial visibility remains difficult. We propose Vis2Reg, a visibility-aware registration framework that explicitly constrains deformation using mask-consistent visible regions. We introduce a visibility-aware self-supervision that derives a visible-domain 3D supervision signal from intraoperative masks, enabled by differentiable point rasterization and mask-guided back-projection. This formulation improves robustness under severe occlusion while maintaining fully self-supervised learning. Vis2Reg combines a robust geometric rigid initialization module with an implicit neural deformation field for stable alignment. Vis2Reg achieves a Dice score of 92.6\% and a Chamfer Distance of 1.43 mm on real intraoperative datasets, with 111 ms per-frame inference time, demonstrating both accuracy and practical efficiency.

Vision-Language Navigation (VLN) requires an embodied agent to interpret a natural-language instruction and predict actions from temporally ordered visual observations. Adapting a multimodal large language model to VLN requires visual-language alignment, compact temporal inputs, action-space grounding, and stable training on the target hardware. This technical report presents PGN (Pangu Navigator), an offline VLN action-prediction system built on OpenPangu-7B. Training proceeds in two stages. First, PGMM aligns a frozen EVA-ViT-G/14 vision encoder with the frozen language backbone by training a Q-Former and a two-layer MLP projector. Second, PGN adapts the aligned model to expert navigation trajectories using five-observation windows, epoch-dependent temporal sampling, and a reasoning-then-action output format; this stage freezes the aligned visual pathway and updates three structural-token embeddings and LoRA adapters. The implementation combines mixed-precision computation, selective FP32 computation, and DeepSpeed ZeRO-2 on eight Ascend 910B NPUs. Under teacher-forced, open-loop evaluation on 500 held-out expert trajectories, V9 reports a 62.29% Normalized Action Match (NAM) and a 100.00% Non-empty Rate (NER). These metrics quantify offline expert-action alignment rather than closed-loop navigation success; evaluating error accumulation, path efficiency, and goal completion remains future work.

Representation is a central concept in modern machine learning, where it usually refers to internal encodings that support learning and generalization. As models scale and their capabilities become increasingly human-level, this representational language sometimes shifts from an engineering context into the more philosophically loaded domain of mental representation. We argue that this is the case for recent claims about the convergence of representational properties across different AI models. In particular, we assess the arguments developed in The Platonic Representation Hypothesis, according to which this convergence is driven by a unified structure of reality. We examine this claim by introducing arguments and ideas from debates about mental representation in the philosophy of mind. We argue that these philosophical resources can clarify what is at stake in such claims, explain why alignment evidence alone is insufficient for strong metaphysical conclusions, and suggest directions for future research.

Financial statements (FS) such as Balance Sheet (BS), Income Statement (IS) and Cash-flow Statement (CS) summarize the annual financial performance of a company. FS are widely used for evaluating corporate governance, credit appraisal, risk analysis, validate taxation, make investment decisions etc. Financial auditing is a complex and knowledge-intensive discipline whose one important aim is ensuring integrity, accuracy, fairness and absence of material misstatement in the published FS. Given the importance of FS, there are incentives to hide, omit or falsify information to misrepresent the true financial health of the company; e.g., reduce tax liabilities, or increase investor confidence. Given the complex, time-consuming and expertise-dependent nature of auditing, auditors would benefit from an AI-assisted system that automatically detects instances of misinformation in the given FS and identify likely sources of this misinformation in the financial data. In this paper, we present unsupervised techniques to identify misinformation in FS, and also generate explanations as to the financial variables that are likely sources of misinformation. The auditor can then explore in more detail the associated data sources and business processes to validate these suggestions. A crucial feature of our approach is the use of past corpus of FS and associated audit reports to generate insights, which help in providing assistance. We demonstrate the efficacy of these techniques on a large corpus of 11,460 FS over 5 years and associated audit reports. This paper integrates and adds more novel contributions over the previously reported research (Shinde et al., 2022)\cite{SVAP22}, (Vaishampayan et al., 2022)\cite{VSPP22}, (Pawar et al., 2023)\cite{PAPV23}, which we have used as the foundation for our AI-assisted Auditor Assistance system.

Egocentric devices, such as wearable front-facing cameras, provide a unique perspective for capturing the continuous interaction between a human viewer and the surrounding environment. A holistic and efficient multimodal model capable of reconstructing this 4D representation is therefore highly desirable. However, existing approaches often rely on auxiliary inputs such as pre-computed camera trajectories, treat scene perception and human ego-motion modeling as separate problems despite their strong interdependency, and suffer from slow inference time. To address these limitations, we present ReViV, the first unified framework for holistic egocentric 4D reconstruction that extracts both viewer and view dynamics from a single monocular RGB video. We formulate the task as learning the full joint probability distribution over multimodal signals, including RGB video, camera trajectory, gaze direction, full-body motion, hand motion, and depth. Powered by a Masked Generative Egocentric Transformer, ReViV operates within a single feed-forward architecture to simultaneously reconstruct the temporally consistent 4D reconstruction across the viewer and the view with fast inference speed. Extensive experiments on diverse benchmarks, including HoloAssist, HOT3D, ARCTIC, Aria Digital Twin, and TACO, demonstrate that ReViV achieves state-of-the-art accuracy and efficiency across holistic ego-body, hand, and gaze reconstruction, camera tracking, while maintaining highly competitive egocentric depth estimation without relying on heavy task-specific priors. Code and models are fully open-sourced: https://reviv4d.github.io/.

Early and timely screening of laryngeal cancer is crucial for improving clinical outcomes. In recent years, NBI endoscopy has become a standard diagnostic tool for the detection of laryngeal lesions. However, its effective use requires well-trained clinicians and the procedure is time-consuming and subject to interobserver variability. In this context, the application of artificial intelligence (AI) offers a promising solution to support clinical decision-making. In this work, we proposed applying transformer and attention mechanism for analyzing the narrow band imaging and distinguish benign and malignant lesions. Results show it has good classification performance with F1 (82.72%), accuracy(82.33%). In addition, the result of laryngeal cancer screening is explainable for clinicians. The explainability is utilizing the state of art segmentation method (MedSAM) to provide the useful pathological information area for clinicians. The proposed methodology fusing classification and segmentation provides a translating on laryngeal cancer screening.

Does adding a reasoning step make a Vision-Language-Action (VLA) model more robust to perturbation? Intuitively, a policy that reasons before acting should absorb a perturbed input better than one that maps observations directly to actions. We test this premise head-on across three models that span the reasoning spectrum (no reasoning, a text chain-of-thought, and a latent iterative loop), perturbing each at the vision, reasoning, and action stages on LIBERO and SimplerEnv. Two questions organize the study: does the reasoning design shift robustness, and can the reasoning be read back at runtime as a safety signal? We find that the latent-iterative model is by far the least robust: under both stochastic noise and white-box perturbation its task success collapses, while the other two hold. This fragility is structural rather than cumulative: varying the reasoning depth at inference barely moves it. Reasoning outputs can in principle be monitored, but the monitors fail under fair tests. A plan--action consistency probe that looks near-perfect under naive evaluation falls to chance under adaptive attack. Under matched-FPR calibration, fusing it with an action-anomaly probe never lifts defended success above undefended. Scoped to these output-level behavioral probes under white-box vision-stage attack, this ceiling is a precondition that any viable defense must first satisfy.

Predictive process monitoring supports the optimization and control of operational business processes by forecasting the future state or outcome of ongoing cases. While deep neural networks have achieved strong performance for these tasks by modeling sequential dependencies in event logs, their black-box nature limits trust and practical adoption. Feature attribution methods are often used to address this, but applying them directly poses a dilemma: event-level attributions impose high computational complexity for long traces, while explanations based on aggregated trace representations often fail to capture the underlying control-flow dynamics. To address this issue, we propose a local post-hoc explainability method for deep neural networks in outcome prediction. The method relies on a control-flow-aware segmentation algorithm that partitions a trace into meaningful segments and supports the computation of segment-level SHAP explanations. This makes it possible to identify which parts of a trace influence a prediction and which change points steer the case toward the predicted outcome. We assess the proposed segmentation method on a synthetic dataset with known process logic, where meaningful change points can be explicitly verified, and we demonstrate its usefulness on real-world event logs from a loan application process and an administrative process of a Dutch municipality.

Foundation models pretrained using self-supervised learning have transformed computer vision by learning transferable representations from large-scale unlabeled data. However, existing foundation models for neuroimaging remain limited by task-specific training, slice-based learning strategies, or relatively small pretraining datasets, restricting their generalizability across diverse brain MRI applications. In this work, we present BrainNext, a general-purpose self-supervised foundation model for volumetric brain MRI analysis. BrainNext combines masked autoencoder (MAE) pretraining with a native three-dimensional Bi-Directional xLSTM-UNet architecture to learn rich anatomical representations from 60,551 unlabeled brain MRI examinations spanning multiple MRI modalities. The pretrained model is subsequently adapted to downstream tasks through lightweight task-specific fine-tuning. We evaluate BrainNext on the Foundation Models for Medical Imaging (FOMO) 2025 Method Track, encompassing classification, segmentation, and brain-age estimation, where it achieved second place overall and ranked first in the meningioma segmentation task on the official FOMO 2025 challenge leaderboard, demonstrating strong transferability across heterogeneous neuroimaging tasks. These results highlight the potential of large-scale self-supervised pretraining to learn robust and transferable volumetric representations, establishing BrainNext as a scalable foundation model for diverse brain MRI applications.

ETAS is a programming language for agent systems that treats model-backed agents, tool calls, prompts, typed memory, human approvals, policies, and execution traces as semantic program elements rather than library conventions. It separates deterministic computation from agentic nondeterminism and externally visible actions while preserving a direct programming style. We present the core design of ETAS. Its static semantics assigns ordinary types through spec conformance and tracks each computation with two behavioral indices: an escaping effect row and a persistent abstraction of the typed action trace it may request. Specs form a terminating compile-time constraint calculus: type specs provide evidence for polymorphism and resource facts, callable specs constrain function and stage shapes, and trace specs express allow, deny, and temporal constraints. Typing checks requested traces against compiled monitors and emits residual obligations when dynamic resources preclude a complete static proof. The dynamic semantics distinguish requested, handled, denied, and committed events; handlers interpret typed actions without making their requests invisible to authorization or audit. We formalize a core calculus and state preservation, progress, type/effect soundness, handler trace-transparency, and policy safety. We also implement ETAS in Rust with a command-line interface, typed HIR checks, effect and policy diagnostics, handler checks, and trace-aware execution hooks. ETAS provides a programming-language foundation for reasoning about authorization, nondeterminism, recovery, and audit evidence before and during agent execution.

Text-to-Image (T2I) generative models have achieved remarkable progress in synthesizing high-quality visual content, yet they remain vulnerable to adversarial misuse, particularly in generating Not-Safe-For-Work (NSFW) images. Most existing jailbreak attacks primarily rely on heuristic prompt engineering or black-box optimization, treating model feedback as a binary signal (success or failure). This coarse-grained paradigm overlooks the rich information embedded in diverse failure modes, such as textual refusal, visual blocking, and semantic sanitization, resulting in inefficient exploration and severe semantic collapse. In this paper, we propose MIND, a cognitive jailbreak framework that reframes adversarial prompt generation as a belief-state inference problem over latent defense mechanisms. Instead of blindly searching for bypass prompts, MIND actively models the target system's latent defense mechanisms by interpreting multi-modal feedback as high-density signals. Specifically, the framework integrates three core components: (1) a Multi-modal Judge for fine-grained feedback decomposition, (2) a Defense Profiler for iterative belief updating, and (3) a Meta-Memory module for retrieving historically effective attack strategies. These components are unified within a reasoning-driven evolutionary optimization process, enabling adaptive and semantically consistent jailbreak generation. Extensive experiments on the I2P benchmark demonstrate the effectiveness of MIND. Under six representative pre-processing and post-processing defense settings applied to the Stable Diffusion v1.5 model, MIND achieves an Attack Success Rate (ASR) of 95.62%, significantly outperforming existing methods. Additionally, the effectiveness of the proposed framework is validated across four widely used commercial T2I systems, achieving the highest ASR of 91.58% on Wan-2.5.

Class-agnostic 3D instance segmentation is critical for robotic systems operating in unknown environments, enabling perception of previously unseen objects for reliable manipulation and navigation. Existing approaches typically project per-frame 2D instance masks into 3D and merge them, which often breaks object identities across time and yields fragmented 3D instances. We introduce Cross-Dimensional Class-Agnostic 3D Instance Segmentation (CDIS), a zero-shot framework that explicitly tracks 2D instance masks across frames and associates them with 3D superpoints, creating a feedback loop between 2D and 3D. This cross-dimensional reasoning links temporally stable 2D tracks with spatially coherent 3D regions, producing globally consistent 3D instance labels without any 3D-specific training. Experiments on benchmark datasets demonstrate that CDIS achieves higher accuracy and consistency than state-of-the-art zero-shot methods, while remaining efficient and scalable to diverse real-world environments.

Cyber-physical systems built on deterministic edge inference, such as on-vehicle flood detection for agricultural fields, produce structured decision logs that must be interpreted differently by heterogeneous stakeholders. Pairing such systems with large language models (LLMs) to generate stakeholder-specific reports introduces a tension: the generative layer is non-deterministic, while the edge plane must remain replayable and auditable. We propose an architectural pattern resting on two invariants: unidirectional consumption, in which the generative layer is a strict read-only consumer of the deterministic plane and never writes back, and persona-as-configuration, in which stakeholder adaptation is a versioned prompt-template artifact rather than runtime improvisation. We instantiate the pattern as a context-aware dashboard layer over the JSON decision logs of a previously published edge-based standing-water detection system, and analyse how the integration boundary admits standard generative-reliability mitigations as configuration- or middleware-level extension points. A structured expert review rated the pattern favourably across five ISO/IEC 25010-aligned quality dimensions, with strongest agreement on separation of concerns. End-user evaluation with agricultural stakeholders is planned for future work.

Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations. However, assessing their monosemanticity, and thus explanation quality, remains challenging. Existing metrics require external concept labels or depend on pretrained embedding models, making them sensitive to encoder's geometry. We introduce the Tversky Monosemanticity Score (TMS), a label-free metric that operationalizes monosemanticity as activation-set coherence of binarized SAE latents, and does not require external embedding encoders. We evaluate TMS on SAEs trained on features from pretrained vision and vision-language models (DINOv3, CLIP, BLIP2), two common SAE regimes (TopK, BatchTopK), multiple sparsity levels, and expansion factors. Our results show that TMS is less affected by encoder anisotropy than its embedding-based alternative, while remaining aligned with established monosemanticity indicators. TMS also reveals distinct SAE training dynamics across base models. Moreover, under encoder anisotropy, TMS provides a stronger indication of probe-based concept deletion effectiveness, while being competitive otherwise.

Extra context is valuable for simultaneous speech translation of technical talks, but injecting the entire document context into every streaming segment is often too coarse. Through diagnostic experiments, we find that context gains mainly come from paper-specific terminology recovery rather than uniform semantic enhancement. We therefore propose EGTA, an Evidence-Grounded Terminology Adaptation framework that builds a document terminology memory, selects compact candidate terms conditioned on the current streaming state, and adapts ASR/speech-side and decoder-side decision spaces using only the selected terms. EGTA can be instantiated in cascaded, end-to-end, and generation-only SimulST settings without full-model fine-tuning. We evaluate EGTA on an ACL technical-talk SimulST evaluation suite consisting of MCIF-dev and ACL60/60-dev. On MCIF-dev, EGTA-RG improves BLEU by +1.05/+0.59, XCOMET-XL by +0.019/+0.006, named-entity recall by +79\%/+73\% relative, and acronym recall by +0.099/+0.171 on En$\rightarrow$Zh and En$\rightarrow$De. Across MCIF-dev latency settings, EGTA consistently improves XCOMET-XL, named-entity recall, and acronym recall. External validation on ACL60/60-dev further shows consistent terminology-recall gains without additional fine-tuning. Shuffled-memory controls and activation audits provide evidence that the improvements are tied to paper-specific evidence alignment rather than generic context prompting.

We introduce WC2026-Agents, a benchmark and dataset for evaluating large language models (LLMs) as autonomous forecasting agents on real, future events. For every one of the 104 matches of the 2026 FIFA World Cup, four frontier models -- Claude Opus 4.8, ChatGPT (GPT-5.5, high reasoning), Gemini 3.1 Pro, and Grok (Expert Mode) -- ran an identical search-act-reflect loop: gather evidence with a web tool, commit to a 1X2 (team-A win / draw / team-B win) distribution and a virtual 100-USD bet, and, after the match, reflect given only the final score. Because every match kicked off after the models' training cutoffs, the benchmark is contamination-free by construction. Crucially, we pair the four agents with a fifth competitor drawn from the same information environment -- the pre-match betting market -- collected as per-match 1X2 odds, giving an economically grounded baseline and letting us score not just what an agent predicts but what it does with money. The release contains 416 forecasts and 414 reflections with verbatim reasoning, ground truth (including penalty shootouts), odds, and a reproducible evaluation suite. A reference evaluation surfaces findings that raw accuracy hides: the four agents issue an identical top pick in 92% of matches and none beats the market's Brier score; indeed, a naive flat stake on the market favorite out-earns all four agents. Yet the agents diverge sharply as decision-makers: betting return-on-investment ranges from -18% to +10%, fading the market is unprofitable for all four, the share of forecasts that cite the market ranges from 12% to 100%, and self-reported error rates on wrong picks range from 36% to 86%. The benchmark thus measures calibration, decision quality, and self-knowledge -- axes on which frontier models differ even when their predictions do not. Data and code: https://github.com/graphuofm/FIFA2026LLM

Large language model (LLM)-driven evolutionary search is an emerging algorithm-discovery paradigm that has already produced novel results in several scientific fields. Yet its application to wireless communications remains largely unexplored. To bridge this gap, we introduce The AI Telco Engineer (AITE), a framework to autonomously design algorithms for complex communication problems, while navigating performance-complexity tradeoffs. We showcase AITE on two challenging physical-layer problems: designing an equalizer for an orthogonal time-frequency space (OTFS) system, and constructing a receiver algorithm for an orthogonal frequency-division multiplexing (OFDM) system using a custom constellation and operating without pilots. For the first task, AITE develops algorithms that outperform the best-known solutions while reducing computational latency by a factor of 3.6 compared to the strongest baseline. For the second task, it discovers the first explicit, explainable algorithms that achieve performance parity with state-of-the-art neural receivers. These results demonstrate the strong potential of LLM-driven evolutionary search for the autonomous discovery of next-generation wireless communications algorithms.

Recently, speech deepfake detection (SDD) has achieved significant progress. However, its robustness evaluation remains largely confined to controlled additive noise scenarios, lacking systematic investigation of the complex distortions introduced by acoustic front-end (AFE) processing pipelines in real-world deployments. In this work, we simulate a unified AFE pipeline comprising acoustic echo cancellation, noise suppression, automatic gain control, and voice activity detection (VAD), and conduct a comprehensive evaluation of current state-of-the-art models. The results show that the nonlinear and time-frequency coupled distortions introduced by AFE significantly degrade detection performance. To address this issue, we propose a Time-Frequency Consistency Learning (TFCL) framework, which aims to learn invariant spoofing representations that remain stable before and after AFE processing. We observe that AFE not only introduces temporal misalignment (e.g., segment-level shifts caused by VAD), but also weakens or distorts critical frequency-domain cues. To this end, TFCL employs an attention-driven soft alignment mechanism to capture cross-temporal dependencies, along with frequency-domain structural consistency constraints to enforce feature invariance. As a result, the model is able to maintain stable representations under both temporal perturbations and spectral distortions. Extensive experimental results demonstrate that the proposed method effectively mitigates the performance degradation caused by AFE processing, significantly improving the robustness of SDD in real-world scenarios. The code is available at https://github.com/JunXue-tech/TFCL.

Inverse reinforcement learning (IRL) provides a powerful framework for learning from demonstrations. However, real-world tasks often exhibit substantial natural variations (e.g., picking up mugs with varying shapes), making it impractical to collect demonstrations that fully specify a new task under every possible scenario. In practice, while demonstrations for the target task are limited, it is often easier to obtain datasets of heterogeneous but related behaviors. This motivates the problem of few-shot IRL with multi-task demonstrations (FM-IRL), where an agent must learn a new task with substantial variations from only a limited number of target-task demonstrations, together with sufficient demonstrations of related tasks and online agent experience. To do so, we must both recover the expert distribution of the new task and provide guidance when the agent deviates from it. We introduce Multitask discriminator Proximity-Guided IRL (MPG), which learns two complementary reward components: (1) a generalizable discriminator that transfers shared structure across related tasks to identify expert behavior in a new task, and (2) a proximity function that measures how far a state deviates from expert behavior and provides corrective guidance during exploration. We demonstrate the effectiveness of our method on multiple challenging navigation and manipulation tasks under significant variations (e.g., object configurations, table layouts, and initial robot poses), achieving an average success rate of 81.2%, outperforming the strongest per-task baseline by an average of 24.7 percentage points.

Managing massive crowds during infrequent special events requires reliable real-time pedestrian-flow forecasting to ensure public safety and operational efficiency. However, supervised forecasting methods face limitations in these contexts due to scarce historical data, heterogeneous data distributions, and short in-event observation windows. To effectively support operational decision-making, forecasts should provide not only accurate point estimates but also informative predictive uncertainty. Probabilistic uncertainty quantification plays a critical role in this aspect, particularly capturing sudden volatility and tail risks. This paper investigates pretrained time series foundation models as a lightweight approach for zero-shot probabilistic forecasting without extensive local retraining. Using decision-oriented metrics tailored to short events, we conduct a comprehensive assessment of two time series foundation models on crowd forecasting, with the SAIL2025 event as a use case. We then distill practical insights for crowd managers, specifying when zero-shot forecasts remain operationally reliable.

Current bin picking methods that rely heavily on end-to-end learning often falter when confronted with unfamiliar or complex objects in unstructured environments. To overcome these limitations, we introduce Seg2Grasp, a modular pipeline designed for robust suction grasping in dynamic and cluttered bin scenarios. Seg2Grasp is built on a three-step process: Segmentation, Grasping, and Classification. The Segmentation module employs a Transformer-based model to generate class-agnostic object masks from RGB-D images, ensuring accurate detection across various conditions. The Grasping module uses surface normals and mask proposals to determine the optimal suction points, enhancing grasp success. Finally, the Classification module leverages fine-tuned open-vocabulary Mask-CLIP for precise object identification, enabling versatile handling of diverse objects. Real-world robotic experiments demonstrate that Seg2Grasp outperforms existing methods in success rates and adaptability, establishing it as a powerful tool for automated bin picking in industrial settings.

In logistics automation, precise segmentation of unseen objects is crucial for efficient robotic manipulation in cluttered environments. Tasks such as bin-picking and shelf-picking require robust perception to handle occlusions, varying object shapes, and complex spatial arrangements. Traditional RGB-based methods tend to over-segment objects due to their reliance on texture, while depth-based methods often under-segment by focusing primarily on geometric features. To address these limitations, we propose DA-Fusion, a deformable attention-based RGB-D fusion Transformer designed for unseen object instance segmentation. DA-Fusion effectively combines the strengths of both RGB and depth data, enhancing segmentation accuracy in cluttered and multi-layered object environments. We also introduce the Object Clutter Bin Dataset (OCBD), a benchmark dataset specifically tailored for evaluating bin-picking scenarios in top-down views. Extensive evaluations demonstrate that DA-Fusion outperforms state-of-the-art methods across diverse environments, making it particularly suited for real-world logistics tasks.

The increasing complexity of mobile networks necessitates intelligent and dynamic control strategies for efficient, energy-conserving management. We propose a world model-based approach for network control that enables adaptive configuration of crucial parameters. The world model is trained from historical data and predicts the impact of its actions on future network states. Our controller leverages the model's uncertainty estimate to robustly find optimal network configuration changes. Furthermore, the optimization objective can be changed dynamically without model retraining. We demonstrate the effectiveness of the approach in simulated closed-loop control of a mobile network energy-saving feature. Our results show improved performance in balancing energy savings with quality of service, compared to traditional methods and reinforcement learning approaches. Finally, we show the world model performance on real network data from, and evaluate counterfactual actions proposed by the controller under various throughput constraints.

Large language models (LLMs) are increasingly considered for environmental enforcement, but their ability to produce traceable enforcement decisions remains unclear. We introduce WuYu-EnvLE-Bench, a benchmark built from real enforcement cases, regulatory standards, and expert review. It contains 2,521 benchmark instances, 14 tasks, and 12 pollution-medium subdomains across pre-enforcement, in-enforcement, and post-enforcement workflows. Using Absolute Environmental Enforcement Score (AES) and Intelligent Enforcement Index (IEI), we evaluate open-source and closed-source LLMs across capability, response quality, and resource efficiency. Results show that LLMs perform well on rule-bounded tasks but remain unreliable in evidence-chain construction, contradiction detection, multi-source integration, and procedural judgment. Model scaling also shows diminishing returns: medium-sized models approach leading models in structured tasks, while larger models do not reliably overcome evidence-reasoning bottlenecks. WuYu-EnvLE-Bench highlights the need for evidence-grounded, rule-aware, and task-adaptive enforcement reasoning.

Tables are a critical knowledge source in retrieval-augmented generation (RAG), but a retrieved table may lack sufficient evidence to answer a query, a property we call answerability. While answerability broadly concerns whether a source or collection of sources contains sufficient evidence, retrieval models optimized for semantic relevance do not guarantee it even in the single-source case, creating a fundamental mismatch. To study this, we introduce TCR-Bench, a diagnostic benchmark for Table Content-level Answerability in RAG, built around sibling tables, i.e., tables with highly similar schemas but subtle content differences. On TCR-Bench, the dense retrievers we evaluate persistently exhibit a Semantic-Answerability Gap: they often retrieve the correct sibling group yet struggle to pinpoint the uniquely answerable table within it, dropping QA performance from 0.755 (oracle) to 0.330 (top-5 retrieved). Our analysis suggests this gap is associated with semantic accumulation, schema-level cue dependence, and weak row-column binding. As a diagnostic probe into the source of this gap, we test whether a lightweight two-stage pipeline, Answerability-Aware Reranking (AAR), applying direct query-table answerability judgment, can recover performance: it raises top-1 target retrieval from 18.2% to 57.4%, and this large gain is itself evidence that much of the observed failure reflects a missing answerability verification step, rather than an inherent limitation of model capacity alone.

Citation function classification plays a crucial role in understanding the relationships between scientific publications and advancing bibliometric analysis. This study presents one of the first comprehensive evaluations of multiple state-of-the-art (SOTA) large language models (LLMs) for citation function classification, achieving new SOTA results on the ACL-ARC dataset. We systematically compare five models (Mistral 7B, Orca 2-7B, LLaMA 3.1-8B, Falcon 7B, and SciBERT) across zero-shot, few-shot, and fine-tuning approaches. Our fine-tuned Falcon 7B model achieves a 73.3% macro F1 score on ACL-ARC, representing a significant improvement over previous methods. Additionally, we introduce AC3, a novel dataset featuring a seven-category annotation scheme that distinguishes between neutral acknowledgments and explicit evaluative stances (more opinion-oriented citations - criticizing, complimenting, contradicting). The dataset is implemented across four context extraction variants to systematically evaluate the impact of contextual scope on classification performance. We also provide detailed analysis of model performance, experimental configurations, and limitations to guide future research in this domain. To our knowledge, this is one of the first studies dedicated to comprehensive model comparison for citation function classification, addressing a gap identified in recent surveys.

4-bit quantization enables efficient LLM inference, but suffers from significant accuracy degradation due to outliers. Prior work addresses this problem via data rotation or mixed-precision integer quantization, but often relies on software-managed scaling and frequent dequantization, incurring substantial overhead. Microscaling formats, such as MXINT, eliminate these inefficiencies by encoding scales in hardware, yet remain incompatible with rotation-based methods. Our analysis reveals that outliers vary in severity, from rare extremes to frequent mild deviations, and that quantization sensitivity is unevenly distributed across layers and columns. These insights motivate a fine-grained, sensitivity-guided approach. We introduce MXSens, a training-free method that assigns mixed mantissa bitwidths (4/6/8) based on column- and layer-wise sensitivity, naturally leveraging the block-wise structure of MXINT. MXSens outperforms state-of-the-art quantization methods across a range of models and tasks. Under the W4A4KV4 setting, MXSens achieves perplexities of 3.77 and 7.63 on LLaMA-2-70B and LLaMA-3-8B, respectively, substantially improving over existing baselines on WikiText-2. Our work establishes a new balance between accuracy and resource efficiency for LLM quantization.

Coordinating payload transfers between subsystems is a critical challenge in lifelong Multi-Agent Pickup and Delivery (MAPD). We study systems where agents are confined to separate regions and must exchange payloads through shared handover stations. These stations, equipped with single docks and finite buffers, are inherently vulnerable to blocking and starvation. We formalize this problem as Multi-Subsystem MAPD with Buffer-limited Handover Stations (MS-MAPD-BHS). We then propose Handover-Aware Reservation and Routing (HARR), an online controller that couples per-subsystem planners. HARR uses a shared dock reservation calendar and a deterministic rolling-horizon projection of buffer occupancy to coordinate actions. A candidate route is accepted only if its dock interval is free and the resulting buffer occupancy projection remains within capacity. Under perfect execution, these checks ensure collision-free dock use and buffer-safe committed operations within the reservation horizon. In simulation, HARR achieves up to 77% higher throughput and 92% lower backlog than a fixed-dock ablation at moderate load, while also reducing planning time relative to a coupled station-aware Token Passing baseline. These results show that explicit interface coordination substantially improves stability in modular multi-subsystem transport.

The Linux kernel is one of the most complex software systems, where automated fuzzing continuously exposes thousands of crashes, yet root-cause diagnosis remains a manual and time-consuming bottleneck. Existing LLM-based root cause analysis (RCA) techniques, effective for distributed systems, do not readily generalize to kernel debugging due to sparse low-level artifacts, heterogeneous diagnostic evidence (e.g., syscalls, logs, and crash reports), and complex non-linear fault propagation that demands fine-grained method-level reasoning. To address these challenges, we propose KernelDiag, an agent-based framework for kernel root-cause diagnosis via structured causal reasoning. KernelDiag first aligns heterogeneous diagnostic artifacts through log-to-code mapping, and then employs artifact-specialized agents to iteratively reason over source-level program semantics and crash-specific kernel configurations. The inferred causal dependencies are incrementally organized into structured Evidence Graphs, enabling accurate faulty-method localization and causal explanations. We evaluate KernelDiag on the real-world KGYM benchmark. KernelDiag consistently outperforms state-of-the-art localization approaches at both file and method levels, achieving significant improvements in Top@k accuracy, including up to 4x and 2x gains in challenging settings without explicit hints. Furthermore, both human and LLM-assisted evaluations show that KernelDiag generates accurate, coherent, and actionable diagnostic explanations. Overall, this work lays the foundation for automated kernel root-cause diagnosis by bridging low-level diagnostic evidence with source-level causal reasoning.

User experience is a first-class objective in industrial e-commerce recommender systems (RS). Post-ranking strategies, which govern diversity, similarity, and exposure over a ranked list, are widely deployed in industrial RS for their simplicity and low serving cost. However, as the online recommendation environment evolves continuously, these statically configured strategies gradually become stale, degrading the user experience. Refining them typically relies on manual inspection, diagnosis, and updates, a process that is slow, costly, and hard to reuse. Although recent LLM-based agents (e.g., RecUserSim, SimUSER, and Self-EvolveRec) offer promising directions, none of them close the full loop of automated, self-evolving strategy refinement. To bridge this gap, we introduce SR-Agent, a Strategy Refinement agentic framework that, to the best of our knowledge, is the first deployed for refining post-ranking strategies in industrial RS. SR-Agent unifies three components: (i) a UserSim agent that applies staged inspection skills to surface user-perceived bad cases; (ii) an Analysis agent that consolidates recurring bad cases into structured, reusable diagnoses; and (iii) a constrained Strategy Refinement Harness that maps diagnoses to typed and bounded actions, gated by a four-stage reward pipeline with reversible rollback. Deployed on the Kuaishou e-commerce platform, SR-Agent continuously runs this refinement loop and, in a one-month online A/B test, increases order volume by 0.71%, browsing depth by 0.34%, and clicked-category diversity by 0.48%, while markedly shortening the refinement cycle and lowering operational cost.

Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation and multi-document reasoning. To mitigate the growing inference cost, recent work has explored key-value (KV) cache reuse to reduce redundant prefill computation. However, existing reuse methods primarily focus on computation savings and overlook a critical bottleneck in long-context LLM serving: the cost of storing and accessing large KV caches. While KV compression appears to be a natural complement, naively combining compression with non-prefix KV reuse often leads to severe accuracy degradation. In this work, we propose C$^2$KV, a unified framework for non-prefix KV reuse that jointly optimizes KV extraction and inference-time concatenation. C$^2$KV learns a composable and compressed KV cache manifold that is explicitly designed to be position-agnostic. Our approach introduces a lightweight sidecar Extractor with learnable compression tokens and a structured attention flow, enabling modular KV representations that can be flexibly reused and concatenated without modifying the frozen base model. We further employ a compression-concatenation co-training strategy to align extraction-time representations with their downstream reuse behavior. Extensive experiments across multiple long-context benchmarks and model families demonstrate that C$^2$KV significantly reduces KV cache storage and transfer costs, achieving up to 17$\times$ inference speedup under long contexts, while preserving generation quality.

Span-level rationales are often assumed to improve controllability in text detoxification, but it remains unclear when such guidance helps and when it introduces trade-offs. We present Awareness-Enhanced Guidance for Iterative Safeguard (AEGIS) as an exploratory framework for studying span-guided multilingual detoxification across English, Mandarin Chinese, and Korean. AEGIS combines span-level detector outputs with frozen generator backbones, allowing harmful spans, intensity labels, and target attributes to be provided as structured guidance during rewriting. Rather than claiming state-of-the-art detoxification performance, we analyze how span guidance affects the balance between toxicity reduction and meaning preservation across generator families, model scales, and languages. Our results suggest that span-guided detoxification is conditionally useful: explicit rationales change the trade-off between toxicity reduction and meaning preservation, but their effects depend strongly on the generator backbone and the linguistic context. These findings highlight both the promise and the limitations of span-level control signals for multilingual detoxification.

Detecting high-level semantic concepts like negation across modalities remains a challenge for current multimodal systems. We analyze this as a fundamental representation learning problem, providing the first evidence that negation does not form a linearly or non-linearly separable class in the latent spaces of standard vision-language models (VLMs). We demonstrate that pretrained embeddings primarily encode modality-specific features, lacking a generalizable negation signal. To overcome this, we propose a novel cross-modal attention architecture that explicitly models inter-modal dependencies, achieving performance gains of up to +7.03% F1 over unimodal baselines. Our analysis reveals a key asymmetry: while textual negation often appears independently, visual negation is semantically dependent on linguistic context, a finding validated through our statistical analysis of 3,222 political video-text pairs automatically annotated via \textsc{Qwen2.5-VL}. By combining this analysis with self-supervised video representations (JEPA2), we advance the modeling of temporal negation. This work provides new methods and insights for learning robust, semantically-aligned representations in multimodal systems.

Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning. However, recent studies have shown that they struggle to reliably solve planning problems. At the same time, theoretical results have shown that transformers, the core architecture underlying modern LLMs, are Turing-complete. In this work, we investigate this apparent gap between the theoretical computational power of LLMs and their empirical planning performance. We propose Chain of Computation (COC), a computational architecture that places a transformer-based LM inside an iterative loop, leveraging its strength as a pattern-matching system. The COC uses a Structured Context Window (SCW) which provides a constant-sized context window with support for choosing which window is used at each planning step. Within this architecture, the LM is able to learn a planning policy, predicts the world model, and performs the arithmetic operations required during planning. We show that, when given an append-only SCW (resembling a Turing Machine tape), even relatively small LMs trained from scratch can learn planning policies and generalize from a small number of training instances within each planning domain, achieving success rates above 99.89\% on BlocksWorld and the Pancake puzzle. Our analysis of failure cases in Tower of Hanoi (TOH) reveals that they arise from arithmetic operations or from encountering previously unseen tokens. We show that COC can solve TOH problem instances with up to 20 disks, requiring over 1 million actions, while requiring substantially less training data by either (1) planning with symbolical support for arithmetic or by (2) using a deterministic pushdown automaton (PDA) formulation for the SCW.

Multi-task neural solvers aim to handle multiple Vehicle Routing Problem (VRP) variants within a unified model, avoiding separate training for each constraint combination. However, VRP variants differ in optimization difficulty, while existing methods lack stage-wise feedback on their training status, making the model biased to some specific variants. Although meta-learning can support adaptive training, it typically requires bi-level optimization and additional gradient updates, increasing computational cost. To address this limitation, we propose LLM-as-Trainer (LaT), a plug-and-play training paradigm that uses a pretrained large language model as an external trainer. LaT periodically analyzes cross-task validation metrics to generate a stage-wise guidance vector. This vector is combined with the current task's constraint vector and injected into each encoder layer, providing the neural solver with additional training information during subsequent policy optimization. Experiments on 16 VRP variants show that LaT improves the solution quality of several state-of-the-art multi-task neural solvers on both trained and unseen variants, supporting the effectiveness and generality of the proposed training paradigm.

Proactive agents are expected to anticipate user needs and provide autonomous assistance by perceiving environmental context without explicit instructions. A fundamental capability of such agents is to identify and track users' upcoming events, enabling continuous and event-specific assistance. For example, by recording the time and location of a planned hike, an agent can deliver weather reminders in advance or provide navigation support before departure. However, existing works on proactive agents largely overlook event-centric assistance, and the open-ended nature of proactive assistance poses challenges for reliable evaluation. To bridge these gaps, we introduce ProEvent, the first event-centric benchmark designed to assess an agent's ability to proactively maintain a user's timetable based on ongoing instant messaging chats. ProEvent provides synthesized yet realistic chats that consider the dynamic interaction among users, concurrent chat threads, and noise in the real world, and evaluates proactive agents on response timing, single-step response correctness, and multi-step response correctness. Experiments on eight LLMs and pipelines reveal that current agents frequently overact and struggle with event cancellation. Notably, even GPT-5.1 only reacts correctly in 26.7% of scenarios. Further qualitative analysis reveals fundamental limitations of current LLMs as proactive agents, particularly in detecting implicit events and reasoning from the user's first-person perspective.

We develop an adjoint-sensitivity framework for positional influence in causal residual Transformers and separate unconditional analytic results from conditional boundary-shape conclusions. The principal unconditional theorem is the residual-to-depth-flow estimate for layer controls converging in $L^1$, complemented by a finite-token-to-Volterra attention estimate that explicitly controls the first cells near the causal endpoint. We define a normalized adjoint-energy influence density and derive its exact evolution along full-batch gradient flow. The adjoint admits an exact generator-term decomposition into residual transmission, nonlocal Volterra, and local channels, including all covariance cross terms. Causal masking can amplify early-position sensitivity and residual identity paths can transmit a right-localized terminal bias, but neither mechanism alone forces a U-shaped profile. We therefore state boundary advantages under independently checkable energy, correlation, and local-channel bounds; these conditions are sufficient rather than necessary. Finite-token influence balancing, positional reweighting, and task-aligned observability are presented as diagnostics or regularizers with explicit differentiation requirements, computational costs, and limitations. Controlled simulations illustrate that each intervention controls its designated surrogate, while observability balance or outer-loop reweighting need not monotonically reduce the influence-based Lost-in-the-Middle diagnostic.

Urban transportation systems generate heterogeneous data, yet these data do not automatically become actionable management intelligence. This chapter adopts a behavior-centered perspective on artificial intelligence (AI), treating mobility records and passenger-generated text as behavioral evidence rather than behavioral truth. It examines four directions: bus arrival prediction for service reliability, taxi mobility pattern discovery for demand analysis and planning, abnormal behavior detection for accountable regulatory support, and passenger-perceived risk mining for service improvement. These directions are integrated through a closed-loop framework linking data input, behavior representation, AI inference, decision support, public value, and governance feedback. The chapter identifies data quality, privacy, fairness, interpretability, uncertainty, transferability, and human accountability as essential conditions for deployment. It thereby establishes a unified pathway from behavioral evidence to operational, planning, regulatory, and passenger-service decisions.

Multilingual language models rely on shared subword vocabularies to represent multiple languages within a limited number of token units. While such sharing is often useful, it can also create cases in which identical surface forms are treated too uniformly across languages, even when their meanings or usage differ. We investigate this limitation through cross-lingual homographs and false friends, and examine whether introducing language information earlier in the tokenization process can improve their treatment. We propose a simple tokenizer-level intervention based on language cues: language-specific characters replacing initial characters of shared-vocabulary words, reducing common identity during vocabulary construction. In intrinsic analysis, we find through tokenizer-level statistics that BPE and UnigramLM often treat cross-lingual homographs in a largely language agnostic way, whereas the context-sensitive SaGe tokenizer diverges more strongly; our intervention removes this gap. In downstream English-to-X machine translation, our cues yield modest improvements in several settings, especially under BPE, although the effect is not consistent across all languages and evaluation sets. Overall, the findings suggest that adding lightweight language information at the tokenizer level is a promising direction for further exploration.

Modern software teams have mature tools for low-level testing, such as pytest, JUnit, and Jest, which make it inexpensive to write unit tests and run them on every commit. Systems engineering, in parallel, has developed rigorous principles for design verification and validation (V&V), which has worked very well across engineering discipline to align user expecations and requirements with developers' deliverables. In practice, however, the two rarely connect, and the link between users' high-level requirements and the low-level tests that machines actually run is maintained by hand, if at all. This gap is increasingly costly for AI-enabled and cyber-physical systems, for which regulators now ask for traceable evidence that high-level requirements are met, while raw test results provide little of the structure such evidence requires. We introduce VNVSpec, an open-source framework that makes V&V specifications machine-readable and executable. With this framework, users state high-level requirements directly or import them from catalogs derived from published standards. Then, the framework checks requirement quality, supports decomposition into module-level requirements with explicit metrics and acceptance criteria, links these requirements to test results through a traceability graph, and compiles the collected evidence into verdicts and audit-ready reports. We evaluate the framework by self-application, in which it is continuously assessed in CI against its own specification of 36 requirements verified by 449 tests, completed within limited time which scales linearly and thus can handle up to 10,000 requirements. We also discuss how the framework extends to testing black-box AI models and AI coding agents. The framework, its full test suite, the catalogs, and the benchmark scripts are available at https://github.com/ai-vnv/vnvspec.

This is an invited commentary on the Psychometrika focus article "Fairness Issues and Evaluation in Psychometrics and AI/ML: What Can We Learn from Each Field?" by Ying Cheng (2026, doi:10.1017/psy.2026.10110). Cheng offers a systematic comparison between long-standing test fairness and modern algorithmic fairness. Her mapping of the entire testing workflow onto the AI/ML fairness paradigm, rather than only the final selection stage, is a crucial contribution to interdisciplinary fairness research. This commentary extends her discussion by examining two conceptual issues: the distinction between equality and equity, and the role of causality in fairness research. Together, the focus article and this commentary point to directions for future fairness research across the psychometrics and AI/ML communities.

A language model $p_θ(y \mid x)$ trained on reasoning tasks learns to solve problems via multiple distinct strategies, yet these strategies are implicit and entangled within the model's response distribution. We study the problem of decomposing the response distribution of a given pretrained language model into a structured, strategy-conditioned representation. Specifically, we learn a latent-variable factorization $p_θ(y \mid x) \leadsto (r_φ(z \mid x), g_φ(y \mid x,z))$, where a router $r$ maps each input to a distribution over latent strategies $z$ and a generator $g$ produces the response conditioned on that strategy. A key challenge is that the generator, initialized from the base model, already represents $p_θ(y \mid x)$ without using $z$. Standard variational inference therefore gives the model no incentive to route information through $z$ and can yield a severe form of posterior collapse. To address this, we propose a variational objective that measures fractional information gain relative to the base model's response loss and concentrates reconstruction pressure on tokens with high base model surprisal, encouraging $z$ to encode strategy-relevant response variation. We introduce a benchmark of multi-strategy algorithmic tasks and show that this objective recovers latent codes aligned with distinct reference strategies while preserving the base model's response distribution.

Contrastive learning is increasingly moving toward settings with three or more modalities instead of image-text pairs. Yet, extending models from pairwise to higher-order multimodal alignment can introduce optimization and representation challenges. We identify encoder Jacobian conditioning as a key factor in trimodal contrastive learning: poorly conditioned encoders exhibit collapsing or amplified singular-value spectra, leading to exploding Jacobian condition numbers and degraded multimodal alignment. We introduce geometry-preserving encoders (GPEs) by directly conditioning the Jacobian through regularization and demonstrating that simple modifications like LeakyReLU activations and residual paths recover these geometric benefits. Across a synthetic benchmark and four real-world datasets including missing modalities, improving Jacobian conditioning boosts retrieval and linear probe performance across multiple contrastive objectives, whereas expressive objectives yield little benefit in linear probes. More broadly, our results show that multimodal contrastive learning depends not only on objective expressivity, but also on the geometric and optimization properties of the underlying encoders.

Large-scale single-cell perturbation atlases make it possible to ask an inverse question: given an observed transcriptional response, which annotated targets and compounds in a fixed library are most consistent with that response? We present \model, a Transformer retrieval model for this closed-library setting. Each input is a cell-level perturbation signature formed by contrasting one treated cell with a cell-line-specific mean DMSO reference. The encoder maps the signature to a target-retrieval vector and a molecular-embedding vector, trained jointly with supervised target losses and structure--transcriptome alignment. We evaluate on Tahoe-100M conditions with mapped target annotations using a within-compound stratified 90/10 condition-pair split of 10,505 training and 1,168 validation drug--cell-line pairs. Because compounds and cell lines can occur in both partitions, the experiment measures held-out condition-pair retrieval rather than generalization to unseen compounds or cellular contexts. In a Monte Carlo evaluation over 38,400 sampled validation cells, \model\ achieved target Recall@10 of 0.408 and Recall@20 of 0.544, together with compound Hit@1 of 0.129, Hit@10 of 0.343, and mean reciprocal rank of 0.205 over a 379-compound bank. A separate diagnostic evaluation produced nearly identical values for the main model and large gains over a random-vector control and post-hoc bag-of-genes controls. These results demonstrate that a single multi-task model can recover both mapped target annotations and recorded compound identities from observed cell-level responses in the evaluated Tahoe-100M closed-library setting. Generalization to unseen compounds and cellular contexts remains to be established.

Unsupervised Graph Domain Adaptation (UGDA) aims to facilitate knowledge transfer from a labeled source graph to an unlabeled target graph by mitigating cross-domain distribution shifts. Existing methods primarily focus on node-level feature alignment in latent spaces, relying on the implicit assumption that all source nodes contribute positively to the alignment. However, this assumption often fails because a node's semantic information is intrinsically coupled with its topological graph structure. Due to structural shifts, source nodes with severe structural deviations (e.g., structural outliers) lack semantic counterparts in the target graph, and forcing alignment on them introduces severe noise and causes negative transfer. To bridge this gap, we argue that selective source node utilization is superior to full-graph training, thereby shifting the research paradigm from feature-level alignment to data-level refinement. To this end, we propose Source Node Influence Pruning (SNIP), a novel model-agnostic, data-centric refinement framework. Specifically, SNIP quantifies the structural discrepancy between individual source nodes and the target domain by integrating multiple centrality measures, assigning each source node an influence score. A rank-based normalization mechanism is further employed to eliminate scale variations across different measures, allowing SNIP to effectively identify and filter out structurally incompatible nodes with low influence scores. As a plug-and-play method, SNIP constructs a refined "sub-source" graph that is inherently more beneficial for subsequent alignment. Comprehensive experiments across eight transfer scenarios on five real-world datasets demonstrate that SNIP consistently outperforms competitive baselines and significantly enhances adaptation performance, validating the superiority of selective node utilization over full-graph training.

Remote sensing has become an increasingly valuable tool for agricultural monitoring, particularly through the use of publicly available satellite imagery. However, effectively integrating domain knowledge into machine learning methods remains challenging. This study presents a real-world example of early sugar beet harvest yield forecasting from purely optical Sentinel-2 imagery, demonstrating how a tight integration of domain knowledge and machine learning can lead to synergistic gains. We empirically find that using very small vision transformer patch sizes and all available Sentinel-2 spectral bands improves our model despite being uncommon design choices in the domain. As a practical contribution, we were able to identify a large fraction of low-yield fields in a different year early on in the growth cycle through a modified training setup and a ranking-based detection of underperforming fields.

Multimodal large language models (MLLMs) still struggle with spatial reasoning that requires perspective transformation. In particular, they often rely on camera-centric cues rather than reasoning from the reference object's viewpoint, leading to systematic errors in non-camera reference settings. In this paper, we first analyze this failure mode and show that object orientation is a key factor underlying such camera-centric shortcut behavior. To address this issue, we propose OrientSAM, an orientation-aware spatial alignment framework for multimodal models. OrientSAM injects explicit orientation information into multimodal representations through orientation-aware tokens and Fourier-based angle encoding, and further adopts a curriculum learning strategy to progressively improve perspective-aware reasoning. In addition, we build a spatial data construction pipeline to generate orientation-aware spatial supervision from large-scale images. Experiments on Spatial-MM, ViewSpatial, and 3DSRBench show that OrientSAM consistently outperforms strong baselines, especially on non-camera-view, person-centric, and orientation-sensitive tasks. The results further demonstrate that explicit orientation modeling is important for mitigating camera-centric shortcut behavior and enabling more robust allocentric spatial reasoning in multimodal models.

Multidimensional graded response models (MGRMs) are widely used for analyzing ordinal questionnaire data in psychological and educational assessments. A central challenge in applying these models is determining the number of latent dimensions. Conventional approaches usually fit multiple fixed-dimensional models and select among them using post-hoc criteria such as AIC, BIC, or cross-validation, which can be computationally demanding and ignore uncertainty in dimensionality during estimation. We develop an adaptive Bayesian dimension selection framework for probit MGRMs. Building on the cumulative shrinkage process, we assign a cumulative ordered spike-and-slab (COSS) prior to the column-specific variances of the item loading matrix. This prior induces increasing shrinkage across latent dimensions, allowing redundant dimensions to be shrunk toward zero while preserving flexibility for active dimensions. Albert--Chib latent response augmentation is used to handle the ordinal probit likelihood, yielding conditionally Gaussian updates for item loadings and latent traits. These updates are combined with Gibbs updates for threshold and shrinkage parameters in an efficient adaptive sampler. Simulation studies evaluate the proposed method in terms of dimension recovery, parameter estimation accuracy, and computational efficiency, with comparisons to conventional fixed-dimensional estimation and model selection procedures. The results show that the proposed approach accurately recovers the latent structure while avoiding repeated model fitting over multiple candidate dimensions. We further illustrate the method using real psychological assessment data, demonstrating its practical utility for uncovering interpretable latent structures in ordinal item responses.

Source-free universal domain adaptation (SF-UniDA) adapts a pre-trained source model to an unlabeled target domain under both covariate and label shifts, without access to source data. However, existing SF-UniDA methods rely on inefficient techniques such as threshold tuning and clustering. Foundation models (FMs), known for their generalization and zero-shot capabilities, remain underexplored in SF-UniDA. In this paper, we propose a framework that leverages foundation models (LFM) for SF-UniDA. We use a vision-language model (VLM) to compute similarities between target samples and text labels, including those for unknown classes generated by prompting a large language model. The label shift type is determined by analyzing the coefficient of variation of a similarity-based sample-level score. Unknown samples are identified using a binary Gaussian mixture model fitted to another similarity-based metric. Under a consensus strategy, the pseudo-labels generated by the VLM are refined by the target model initialized with the pre-trained source model, integrating knowledge from both the source domain and foundation models. Finally, these refined pseudo-labels are used to train the target model. Extensive experiments across all possible label shifts and multiple benchmarks demonstrate the effectiveness and superiority of our proposed LFM framework. Our code is available at https://github.com/iamjingli/LFM.

Block-wise diffusion large language models (dLLMs) decode sequentially at the block level, enabling effective KV-cache reuse across blocks but making inter-block decoding strictly serial. Prior work has attempted to unlock inter-block parallelism through post-training methods, but achieves only modest speedups and often degrades accuracy. We observe that self-correcting dLLMs offer a training-free alternative: token-to-token (T2T) editing can repair tokens drafted with a slightly stale upstream context, so a downstream block requires only an informative draft rather than a finalized predecessor. This turns block finality from a hard dependency into a scheduling resource. We propose \textbf{\flowblock{}}, a training-free parallel decoding framework built on two mechanisms. (i) \emph{Gated Wavefront Decoding} admits blocks into a bounded wavefront only when a readiness gate is satisfied, jointly refines active blocks via T2T editing, and commits blocks in order under a windowed block-causal mask that preserves exact frozen-prefix KV caches reuse. (ii) \emph{Heterogeneous Wavefront Packing} assigns each request an independent wavefront while packing asynchronous windows into dense, shape-stable batched forwards. Across different benchmarks, \flowblock{} improves tokens per second (TPS) over LLaDA-2.1 and LLaDA-2.0, two serial block-wise dLLMs, by up to 2.95$\times$ and 4.01$\times$, while reducing latency by up to 53.6\% and 77.1\%, respectively. It also improves average accuracy by 1.3 points. Compared with D2F, a training-based inter-block-parallel baseline, \flowblock{} achieves higher accuracy and up to 16$\times$ higher batched serving throughput.

Verify-repair loops are a standard means for large language model (LLM) agents to correct faulty plans in code generation, mathematical reasoning, and tool use. When both the verifier and the repairer are noisy, repair can damage already-correct plans, and reported acceptance keeps rising while true validity falls, so existing methods lack a principled basis for deciding when repair should stop. We propose VRR-Stop, a robust stopping framework for noisy verify-repair-repeat (VRR) loops. A four-parameter noise model separates verifier false acceptance and false rejection from the repair and damage behavior of the repairer. Belief filtering turns repeated verification votes into an estimate of committed validity, and the loop commits or repairs according to the sign of the true marginal gain, which requires only sign identifiability rather than accurate recovery of all parameters. When verifier discrimination approaches zero, calibration itself fails and estimation error can flip the stopping sign, so we pair VRR-Stop with VRR-Guard, an estimation-free fallback that replaces the incumbent candidate only under a sufficient verification margin. On a GSM8K stress setting, VRR-Stop improves final true validity by 60.6 percentage points over fixed five-round repair at an average cost of 0.72 repair rounds. Across settings, stopping reliability is governed jointly by verifier discrimination and the decision margin rather than by the absolute size of estimation error.

Time series data play a pivotal role across numerous domains, including healthcare and manufacturing. In real-world environments, models must cope with distribution shifts over time, a challenge commonly addressed through Continual Learning (CL) techniques. However, existing CL methods face a critical limitation: real-world data streams are rarely fully labeled, making annotation cost a major practical constraint. This paper investigates Active Class-Incremental Learning (ACIL) for multivariate time series, where a model must sequentially learn new classes while selectively querying labels under a fixed annotation budget. We present a systematic evaluation of a wide range of query strategies combined with multiple rehearsal-based approaches, assessing their impact on plasticity, stability, and label efficiency across four benchmark datasets. Our analysis reveals the limitations of uncertainty-based and distribution-aware methods in achieving strong performance under constrained labeling budgets. To address these shortcomings, we propose TypiCore, a novel hybrid query strategy that alternates between typicality-based and diversity-based sample selection across active learning cycles, enabling the construction of memory buffers that are both representative and diverse. Evaluated on the TSCIL benchmark, TypiCore delivers statistically significant improvements over all baselines and matches or surpasses fully supervised continual learning performance on multiple datasets while requiring a fraction of the available labels.

Prior work on AI-assisted information evaluation has largely focused on what AI systems communicate, comparing explanation types and formats, with responses predominantly cast in directive rhetoric where the system delivers a verdict and the user passively accepts it. While debate-style interactions have recently shown promise in prompting critical evaluation over deference, the rhetorical patterns that structure AI responses and how they might induce reflection, uncertainty, or independent reasoning remain largely unexamined. To address this, we investigated eight rhetorical patterns known to induce contemplation: Intentional Misleading, Interpretive Alternative, Scaffold Explanation, Triggering Distrust, Information Distortion, Alternative Framing, Socratic Questioning, and an Oracle baseline. Through a within-subject study with n=98 participants on a hint-on-demand fact verification task, we observed preliminary evidence that Scaffold Explanation were associated with the highest accuracy gains, and encouraging deeper reflection. Surprisingly, the adversarial conditions also improved accuracy modestly. Participants preferred Alternative Framing most and Interpretive Alternative least, largely due to the latter's perceived time cost. We discuss the implications of designing conversational agents with varied rhetorical styles and the trade-offs among user performance, satisfaction, and contemplation.

Modern video transformers typically ignore principles from primate vision and are rarely evaluated against neural data, limiting their biological interpretability. We introduce a sparse winner-takes-all token selection module that replaces dense self-attention to improve efficiency and approximate competitive routing observed in biological visual circuits. We further propose a neuro-inspired split-and-fuse video transformer which uses two complementary pathways: a high-resolution, low-frame-rate "what" stream and a low-resolution, high-frame-rate "where" stream, fused before classification. On Kinetics-400 and Something-Something V2, our best variant operates on the Pareto frontier of accuracy versus inference time among models of comparable scale and pretraining, and showing improved robustness to spatial perturbations. Using representational similarity analysis between model embeddings and time-resolved EEG recordings for the same video stimuli, our model attains a peak brain-model correlation of 0.18 (about 78% of the noise ceiling) and consistently outperforms strong video transformer baselines, suggesting that pathway specialization and sparse competition are useful inductive biases for efficient, brain-aligned video understanding.

Transformers are remarkably versatile and their design is largely consistent across a variety of applications. But are they optimal for any given task or dataset? The answer may be key for pushing AI beyond merely scaling current designs. *Method.* We present a method to optimize a transformer architecture for a given dataset, which we use as a tool to study optimal task-specific inductive biases. This method replaces the most important non-linearities (GeLUs,;softmax) with functions learned on held-out data. We then train the resulting architectures on other datasets, as a way to evaluate the compatibility between pairs of tasks. Findings. On algorithmic toy tasks, we identify new architectures with dramatic improvements in learning speed, in- and out-of-distribution generalization, and stability across seeds. The new designs prove very task-specific however, and indicate that these tasks require inductive biases very different from those of standard transformers. On code and language modeling datasets, we also find architectures with consistent, yet smaller improvements. These designs transfer much better across datasets and domains (English & computer code). Implications. Our results show that standard transformers are rarely a local optimum in the space of architectures. Simple alternatives can perform much better but sacrifice universality. This suggests that there may be room for improved architectures that better support multiple capabilities simultaneously, such as fluency and robust reasoning.

Program verification tools often rely on specific intermediate representations and analysis backends, limiting the reuse of verification algorithms and model checkers across frameworks. In contrast, hardware model checking has developed a mature backend ecosystem, where standard formats such as BTOR2 support reusable algorithms for counterexample search and inductive safety proving. Applying these capabilities to C requires translating assertion-based programs into transition systems that hardware model checkers can directly process. We present C2Btor, a method for encoding such verification tasks into BTOR2 models. C2Btor uses a program counter to capture control transfers, represents data states and memory objects with bit-vectors and arrays, and maps assumptions and assertion checks into BTOR2 constraints and bad-state properties. We evaluate C2Btor on SV-COMP C ReachSafety benchmarks and a curated assertion-category benchmark suite, comparing it with representative program verification tools. C2Btor correctly solves 263 tasks, 101 more than CBMC configured with bounded model checking, and is especially effective on bit-vector benchmarks, where it solves 75.5% of the tasks with no wrong verdicts. These results show that the BTOR2 route allows C program verification to benefit from advances in hardware model-checking backends, expanding the available capability for counterexample search, inductive safety proving, and word-level transition-system reasoning.

Existing self-evolving memory systems mainly improve agent memory based on textual outputs, such as task trajectories and reflections. However, this text-based paradigm rarely incorporates internal mechanistic signals, leaving how retrieved memory is actually utilized during task execution underexplored. This limitation can lead to unreliable error attribution and hallucinated memory modifications. In this work, we show that retrieval-head attention provides a mechanistic signal for revealing segment-level memory utilization. By aggregating attention over memory segments and decision steps, we construct a context utilization matrix that exposes recurring memory-use patterns and indicates corresponding refinement strategies. Building on this observation, we propose Attention-Guided Memory Refinement (AGMR), a framework that uses utilization patterns revealed by attention to guide targeted segment-level memory updates. AGMR corrects or enhances memory for failed executions, simplifies memory for successful executions, and verifies each update through re-execution. Experiments on interactive decision-making benchmarks show that AGMR improves both task performance and memory efficiency over text-only memory refinement baselines. Code is available at https://anonymous.4open.science/r/AGMR_code-3262/

Low-rank adaptation (LoRA) makes finetuning large language models cheaper by adding to each weight matrix a trainable low-rank update parameterized as the product of two matrices. These matrices are usually trained with Adam, which treats them as a single flat vector of parameters and ignores both the matrix and product structure of LoRA. Applying a matrix-aware optimizer such as Muon to each factor does not consistently improve over Adam, and neither do the product-aware Muon variants proposed in concurrent works. To realize consistent gains, we introduce PoLoRA, a Preconditioned Orthogonalized LoRA optimizer built from three ingredients: a product-aware spectral update direction, curvature preconditioning derived from controlling the per-sample loss change, and a magnitude rule that controls the sizes of both the factor and merged updates. We evaluate PoLoRA on instruction-tuning datasets for code and math across models from 1B to 8B parameters, and find that it reaches the final held-out loss achieved by tuned Adam in 1.2-1.7 times fewer steps, while adding at most 3% per-step overhead. Compared to Adam, PoLoRA is also less sensitive to the learning rate, and its optimal learning rate is stable across ranks.

Individuals with dysarthria face significant challenges in professional speaking scenarios such as conferences, presentations, and meetings, where real-time communication is crucial. While existing Augmentative and Alternative Communication (AAC) systems provide basic support, they often fail to meet the demands of professional speaking environments due to high latency and unnatural speech patterns. This paper presents Re-Sonance, a novel LLM-enhanced speech-driven AAC system designed for real-time professional speaking scenarios. By integrating Whisper ASR, Qwen LLM, and CosyVoice TTS, Re-Sonance achieves improved speech intelligibility and naturalness while maintaining real-time performance. Both subjective and objective evaluations using a Mandarin dysarthric speech dataset demonstrate that our speech reconstruction approach significantly improved intelligibility while preserving semantic coherence for speakers with mild to moderate dysarthria. Although performance remains limited for severe dysarthria cases, our findings validate the potential of LLM-based methods for enhancing speech-driven AAC systems, paving the way for more effective and accessible communication technologies.

Recent advances in deep-learning-based nonlinear system identification have led to encoder-based estimation of neural state-space (ANN-SS) models that achieve state-of-the-art performance in offline settings by estimating initial model states from past input-output data. These methods are typically used in multiple-shooting-based offline identification, and online learning of these models remains largely unexplored. This paper presents a batch-wise learning pipeline and a direct recursive identification algorithm for subspace encoder-based ANN-SS models. We provide convergence analysis of the recursive formulation and validate its performance through extensive simulation studies. The results demonstrate that the proposed approach enables computationally efficient online adaptation with high model accuracy.

Multi-exposure fusion (MEF) expands the luminance range beyond what a single exposure can capture. Combining images taken at different exposure levels requires handling geometric differences while naturally merging their complementary brightness information. It often demands generative completion where details are missing. Diffusion-based generative methods address these challenges, however, they are computationally expensive and struggle to preserve fine structures in saturated regions. We propose LIIFusion, a coarse-to-fine framework that balances fusion quality and efficiency in generative MEF. The coarse stage performs low resolution generative fusion, enhanced by an adaptive exposure correction that recovers structure lost in saturated over-exposed areas. The fine stage adapts a local implicit image function into a multi-exposure fusion function: conditioned on the HR OE/UE sources and the coarse output, it queries arbitrary target coordinates and fuses source evidence regardless of the HR input resolution. LIIFusion achieves up to 3.5$\times$ speed-up over existing generative methods while maintaining or improving structural fidelity and perceptual quality. We believe this framework provides an effective pathway toward making generative MEF more practical in real-world applications.

Automatic image colorization enables large-scale and low-cost reuse of grayscale media (e.g., manga panels and archival photographs), facilitating unauthorized reuse and redistribution. Once released online, grayscale content can be readily turned into unauthorized colorized derivatives using off-the-shelf models, creating a practical need for proactive, content-side protection at publication time. Building on Uncolorable Examples (UE), which add imperceptible perturbations to released grayscale images to degrade unauthorized colorization, we propose Semantic Color Naturalness Breaker (SCNB) -- a semantic-level UE framework that drives colorization outputs toward content-inconsistent colors while preserving the visual fidelity of the released grayscale media. We further introduce Content-aware Color Distributional Distance (CaCDD), a ground-truth-free, content-aware measure of color plausibility derived from semantic color priors, used both as the optimization objective of SCNB and as an evaluation metric. Experiments on ImageNet show that our method remains effective under small perturbation budgets and common post-processing, supporting practical deployment in real-world content-sharing pipelines.

We study whether stochastic nonconvex optimization can be reduced to ordinary static regret minimization in online convex optimization in a black-box manner. For smooth nonconvex objectives, our reduction maintains a predictable gradient tracker, while a black-box online learner selects a preconditioner that determines how this tracker is transformed into the update direction. The learner receives linear convex losses and is evaluated against a single fixed comparator over one undiscounted online game. For a $β$-smooth objective with range bounded by $M$ and an unbiased stochastic-gradient oracle with variance bounded by \(σ^2\), we establish $$\frac{1}{T}\sum_{t=1}^T \mathbb E\!\left[\|\nabla f(x_t)\|_2^2\right] \lesssim \frac{σ\sqrt{Mβ}}{\sqrt T} + \frac{\sqrt{Mβ}\, \mathscr R_T(\mathcal A,I_d)}{T} + \frac{Mβ}{T}.$$ Consequently, any black-box OCO algorithm with $\mathscr R_T(\mathcal A,I_d)=O(\sqrt T)$ recovers the classical $O(\frac{1}{\sqrt{T}})$ convergence rate. We further show that the same black-box framework extends beyond the smooth setting to Lipschitz nonconvex objectives without Lipschitz continuous gradients. Importantly, this extension continues to rely only on an ordinary static-regret guarantee and requires no stronger notion of online regret. When the OCO oracle admits square-root static regret, the resulting conversion achieves the optimal $O(T^{-2/7})$ convergence rate for the corresponding Goldstein stationary point. These results resolve the open problem posed by Chen and Hazan (2024). More broadly, our framework separates optimizer design into gradient prediction and online preconditioner selection, providing a principled perspective on how adaptive optimization methods such as AdaGrad and Shampoo may be understood through static regret and applied in nonconvex optimization.

Accurate protein-ligand binding affinity prediction is central to computational drug discovery, yet modern docking engines frequently disagree without indicating which prediction to trust. Consensus scoring and ensemble methods improve mean accuracy but treat all predictions identically without interpretable confidence measures or uncertainty decomposition, ignoring the chemical context of each protein-ligand pair. To address this limitation, we introduce RELIABLE-BA (RELIABiLity-aware Evidential fusion for Binding Affinity), an evidential framework for multi-engine binding affinity prediction. Our model comprises three steps: (1) modeling each engine as an evidential expert via Normal-Inverse-Gamma distributions, (2) scaling epistemic uncertainty through learned reliability from molecular context while preserving each expert's predictive mean, and (3) fusing experts through closed-form aggregation that captures both individual uncertainty and inter-engine disagreement. Experiments on the PDBBind and BDB2020+ benchmarks demonstrate competitive point prediction with substantially improved uncertainty calibration, and additional validation on the SARS-CoV-2 Mpro dataset and 5HT2A receptor demonstrates applicability to clinically relevant drug targets. Crucially, these uncertainty estimates enable reliable filtering of protein-ligand pairs, reducing prediction error by up to 25% when retaining only high-confidence pairs. To our knowledge, RELIABLE-BA is the first multi-engine binding affinity prediction framework to combine evidential fusion with context-dependent reliability, offering a principled path toward trustworthy AI-guided drug discovery. Our code is publicly available at https://github.com/yongchand/RELIABLE-BA.

Long-document question answering usually forces a choice between loading the whole document into the context window and bolting on a separate retriever. Agentic AI suggests a broader option, giving the agent the document path and letting it decide how and what to read. Agent Skills, a standard for packaging expertise into folders an agent loads on demand, supply a ready mechanism: progressive disclosure, which exposes only what a query needs, from a short description down to the specific passages. Practitioners rapidly adopted this pattern for book-length understanding tasks, but the evidence to support such choices has been anecdotal. We run the first controlled study of the pattern, comparing raw-document navigation and several designs of Agent Skills packs against a classical hybrid retriever across three agent harnesses and three model families on InfiniteBench. On a single book, the gain depends on the harness, running large when the agent navigates the raw document poorly but near zero when a strong agent harness already divides and retrieves on its own. When scaling up to tasks that span many books, raw-document navigation collapses while one-level progressive disclosure degrades more slowly and pulls ahead. A second, deeper routing level never helps and sometimes breaks accuracy outright, so one level is enough. Progressive disclosure buys context, not intelligence: it is redundant while a strong agent can locate the right passages itself, and decisive once the corpus grows too large to navigate by reading.

We establish mean-square and concentration bounds for stochastic approximation (SA) with arbitrary norm contractive mappings, under a multiplicative noise model where the noise may scale affinely with the norm of the iterates, and the iterates are potentially unbounded. These settings arise in reinforcement learning, where operators are often contractive in the $\ell_\infty$ norm and the noise scales with the iterates. To address the arbitrary norm, earlier works replace the non-smooth squared norm with a smooth Lyapunov function constructed via the generalized Moreau envelope. For concentration analysis, these works handle multiplicative noise and unbounded iterates through a multi-stage bootstrapping argument that starts from a time-varying worst-case bound and iteratively refines it. We instead present a unified and elementary analysis that yields both bounds. Using an averaged noise sequence and corresponding auxiliary iterates, we obtain a one-step Lyapunov drift inequality for the normed error directly, without smoothing the norm or constructing an envelope. For the mean-square bound, we combine this drift inequality with an induction argument showing that the iterates remain bounded in expectation. For the concentration bound, we develop a probabilistic induction over a sequence of "good" events on which the iterates are controlled, allowing the standard Azuma-Hoeffding bound to be applied. Our approach yields the first sub-Gaussian tailed maximal (all-time) concentration bound for SA under multiplicative noise, by allowing the stepsize to depend logarithmically on the confidence level. Beyond the specific setting considered here, we discuss the generalizability of these proof techniques to other noise models and iterative algorithms.

Money mule accounts are critical facilitators of financial fraud, yet detecting them at scale remains challenging due to the heterogeneous nature of transactional and behavioural data. We present an end-to-end pipeline for customer-level mule detection comprising three stages: (1) a LightGBM classifier trained on 280 engineered features spanning transaction patterns, account demographics, network topology, and temporal behaviour; (2) a TreeSHAP attribution layer that decomposes each prediction into feature contributions; and (3) a large language model (LLM) module that converts SHAP attributions into analyst-facing natural-language narratives. We evaluate across three open-weight LLM families and assess explanation quality through analyst feedback. In a live production deployment, the system achieves a yield rate of 89%, up from 61% under the incumbent rule-based system, with monthly alert volume expanding from 211 to 302, reflecting broader true-positive coverage rather than increased noise. This corresponds to a 60% incremental adverse detection beyond existing review workflows, substantially outperforming the rule-based approach. Qualitative feedback from analysts indicates that LLM-generated narratives reduce cognitive load during alert triage. We further discuss implications of deploying LLM-augmented explainability in regulated financial environments.

Approximate Nearest Neighbor Search (ANNS) plays a pivotal role in modern deep learning pipelines. Recently, many ANNS systems have been proposed to either provide broad functionality or reach high performance. However, it is yet difficult to achieve both with minimal programming efforts. We propose ANNLib to address the gap. ANNLib is a library that provides a programming framework for achieving high performance and flexible functionality in ANNS systems, based on popular graph-based ANNS algorithms. We carefully decouple and independently optimize both the algorithm and the data structure components of an ANNS system. In addition, we integrate state-of-the-art algorithms and data structures into ANNLib as modules, along with our new designs. Users can choose combinations of components to implement sophisticated settings with high performance, such as filter search, fully dynamic updates, and historical queries on snapshots. Our experiments show that our new solution provides a simple interface for various applications and achieves comparable or even better performance than previous work, specifically for each application.

We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardrails that explicitly considers both safe and unsafe interpretations of a prompt before making a safety decision, and (ii) multi-component supervised fine-tuning (MC-SFT), a structured training loss for reasoning-based guardrails that decomposes LLM outputs into logical components and weights them according to their importance. Existing reasoning-based guardrails often rely on expensive procedures, such as generating reasoning traces using larger or closed-source teacher models and applying full-parameter fine-tuning. In contrast, ARBITER uses a cost-effective self-generation strategy for reasoning traces and LoRA-based parameter-efficient fine-tuning while still achieving better performance than these expensive approaches. Additionally, ARBITER provides faithful evidence-phrase explanations for unsafe decisions, enabling a more transparent and interpretable guardrail method. Experiments on three safety moderation benchmarks show that ARBITER outperforms existing reasoning-based and non-reasoning guardrail baselines, with clear gains in out-of-domain evaluations.

Reinforcement-learning navigation policies for legged robots select actions reactively from current observations and short-term memory, with limited capacity to anticipate how moving obstacles will evolve in the near future. In dynamic environments, this reactivity causes the robot to respond too late because collision risk depends on short-horizon scene structure rather than on current obstacle positions alone. Lightweight predictive supervision applied to the policy's recurrent state during training can encode anticipatory obstacle dynamics without modifying the inference-time controller. We augment a reactive LSTM-SRU navigation backbone with an auxiliary JEPA-style predictor and SIGReg regularization: during training, the predictor supervises the deterministic hidden state to anticipate its own next state; at inference, it is fully discarded, incurring zero additional computational cost. On simulated and real-world navigation benchmarks with dynamic obstacles, our method substantially improves navigation success while reducing collision rates through the predictive training signal alone, without additional inference-time parameters. Real-robot deployment on a Unitree Go2 demonstrates zero-shot sim-to-real transfer: the controller navigates cluttered indoor and dynamic outdoor environments without fine-tuning, with evasive behavior consistent with the collision reduction observed in simulation.

Group Relative Policy Optimization (GRPO) is a powerful reinforcement learning algorithm for aligning generative models with human preferences. While successful in large language models~\cite{shao2024deepseekmathpushinglimitsmathematical}, its extension to diffusion and flow matching models introduces a severe computational bottleneck: gradients must be back-propagated through the high-capacity DiT backbone at \emph{every} timestep of the sampling trajectory, making high-resolution text-to-image (T2I) training prohibitively expensive. Training-free DiT inference acceleration methods (e.g., $Δ$-DiT, ScalingCache) exploit the fact that DiT hidden states and velocity predictions vary \emph{smoothly and nearly linearly} along the trajectory. We ask whether the same linearity can reduce the backward-pass cost of DiT RL training, and answer affirmatively with \textbf{JAGG} (\textbf{J}acobian-\textbf{A}ggregated \textbf{G}roup \textbf{G}radient), which reduces full transformer backward passes from $W$ to $2$ per group of $W$ consecutive steps. JAGG approximates intermediate-step Jacobians via $t$-weighted interpolation of the endpoint Jacobians, then aggregates per-step upstream signals into two composite gradients applied through a single joint backward pass. We prove this interpolation is \emph{exact} when the velocity is linear in $(z,t)$, and a cosine-similarity routing rule (\texttt{jagg\_frac}) deploys JAGG only where the assumption holds. Experiments on T2I benchmarks show JAGG delivers $\sim$2$\times$ backward speedup with negligible quality degradation.

Graph foundation models (GFMs) with global attention are increasingly used to represent mixed-integer linear programs (MILPs), aiming to capture structure beyond the locality of standard graph neural networks. We study their expressive power through graph isomorphism testing, asking which MILP instances they map to identical representations. We prove that a broad class of hierarchical graph transformers combining global linear attention, edge-weighted cross-attention, and bipartite message passing is bounded by the one-dimensional Weisfeiler-Leman (1-WL) test: under any parameter setting, 1-WL-equivalent MILP graphs receive identical graph embeddings. Our compositional proof shows that each architectural component is a symmetric multiset function and thus preserves 1-WL equivalence. We validate this characterization across ten diverse graph encoders, including Graphormer-, GraphGPS-, Set-Transformer-, and Gasse-style models. Across model capacities, graph scales, and pooling operators, every tested encoder maps 1-WL-equivalent non-isomorphic graph pairs to numerically identical embeddings. Consequently, graph invariants that vary within a 1-WL equivalence class cannot be recovered from these representations. We further show that expressiveness beyond 1-WL arises from input encoding rather than attention: random-walk positional encodings separate the constructed pairs, while additional constructions expose the limits of this remedy. These results characterize the expressive power of global-attention GFMs and provide an encoder-agnostic diagnostic for detecting 1-WL-induced representation equivalence.

Structured pruning compresses large language models (LLMs) by removing whole computational units, such as attention heads and feed-forward (FFN) channel groups. Most training-free methods, however, rank these units independently, implicitly treating the loss from pruning a set as the sum of its individual losses. This view fails for Transformers, whose sublayers are coupled through a shared residual stream. Two individually weak units can thus be jointly indispensable, yet independent scoring is blind to such dependence and removes them together. We introduce CoCurve (Cross-Module Co-Pruning Curvature), a calibration-only, fine-tuning-free method that prunes attention and FFN units jointly. A second-order Taylor expansion of the token-level KL between the frozen model and its masked copy yields a single Fisher matrix whose diagonal is classical node saliency and whose off-diagonal entries are co-pruning curvature edges: the extra damage of removing two units together. Under a single-ablation additivity approximation this matrix reduces to a Gram product of single-unit ablation features, so the full M x M interaction is recovered from M forward passes, with no pairwise sweeps or gradients. Pruning then reduces to one budgeted quadratic program, solved in a single shot under a shared attention--FFN budget, with no labels, fine-tuning, or recovery.

AI companions are judged not only by single-turn fluency but by whether they sustain emotional continuity: remembering who the companion is, what the user prefers, and how the relationship has felt. We present ZifaMem, a structured memory system that organizes dialogue into session summaries, episodic memories, and a consolidated user model. Against a deployment-honest comparator that supplies the full raw dialogue history, and under a fixed LLM-as-a-judge protocol with route audits, structured memory raises pooled four-backbone emotional-intelligence scores by 11.4% (95% CI 6.3% to 17.1%), and persona grounding improves on all four backbones (Claude +42% relative). Multi-turn affect context wins a +39% net preference over a single-turn snapshot (exploratory), whereas an additional emotion state machine yields no measurable gain on any of five endpoints. Under an identical preregistered protocol, three memory systems (ZifaMem, Mem0, and filtered verbatim retrieval) each improve significantly over raw-history deployment, and ZifaMem and Mem0 are statistically equivalent within +/-5 points on the preregistered primary preference endpoint. The ZifaMem SDK, CLI, and portable Agent Skills are open-sourced at https://github.com/zifacorp/zifamem.

Reinforcement learning (RL) provides a framework for sequential decision making under explicit objectives. In its classical form, RL studies how an agent should act to maximise long-term reward in a dynamic environment. In richer settings, the problem extends beyond a single agent and fixed environment: intelligent behavior may require strategic interaction, adaptation to uncertainty, and reasoning over high-dimensional worlds. This thesis studies RL from two perspectives: algorithms in games and RL in the era of foundation models. The first part focuses on multi-agent RL in games. It examines how incentives, policies, and equilibrium concepts interact in competitive and general-sum environments, spanning two-player zero-sum games, large-scale video games, and multi-player settings with general structure. These works investigate learning in multi-agent systems and the behavior of RL methods in interactive environments. The second part studies RL with generative and foundation models, motivated by the idea that prior knowledge can enrich sequential decision making. Pretrained generative models and learned world models serve as representation tools and structured priors for planning, control, and policy optimization. The thesis develops diffusion-based world models, investigates RL for efficient video generation, explores generative models as policy classes, and studies interactive video world models in which actions shape future observations. It also addresses long-horizon modeling through architectures with memory. Together, these contributions present a unified view of RL as objective-driven adaptation in complex sequential domains. From strategic games to generative world models, the thesis highlights how RL connects decision making, environment modeling, and emerging foundation-model capabilities, offering a broader perspective on the principles underlying intelligent behavior.

The Contrastive Olfaction-Language-Image Pre-training 2 (COLIP-2) model is a multimodal embeddings space that places olfaction as a first-class citizen among vision and language. Molecular structure, gas-sensor readings, odor-descriptor language, and images are all trained into a single shared representation space, so that a robot can localize a detected aroma to objects in a scene probabilistically. No ImageNet-scale datasets of paired image-scent examples exists which warrants the need for their collection. Our intent with the release of COLIP-2 is to demonstrate the limit of what can be built for robotics with open-sourced olfactory data in order to ground the argument for why new methodologies and datasets are necessary in order to enable advanced olfactory-oriented perception capabilities. We enumerate results from internal testing of the COLIP-2 architecture and make necessary optimizations to run the model at the edge for real-time robotics applications. While developed with robotics in mind, the design of COLIP-2 has been influenced by experts across many disciplines of science in academia and industry, and we hope that the model can be useful in any multimodal domain requiring olfactory intelligence.

On-policy self-distillation (OPSD) offers a promising approach for training large language models without relying on a separate teacher model. However, its effectiveness on complex agentic tasks remains largely unexplored. In this work, we instantiate Feedback-Augmented Self-Distillation (FA-SD), a self-distillation algorithm for agentic search that leverages successful demonstrations as privileged information. We identify that models can rely on recurring reasoning-and-search output templates, producing trajectories that appear diverse but are largely agnostic to the input question, making the KL-based self-distillation signal uninformative. We term this phenomenon decoding collapse, a failure mode that can be missed by existing evaluation metrics. To understand its underlying cause, we show that although the self-teacher achieves stronger performance, learning remains inherently unstable due to inconsistent supervision signals. We further decompose this inconsistency into model inconsistency and prompt inconsistency, and show that the latter can significantly degrade the quality of the supervision signal, limiting the effectiveness of self-teacher learning. To mitigate this inconsistency, we introduce an exponential moving average (EMA) teacher to stabilize the self-teacher and provide more consistent supervision signals. Although the EMA teacher requires a warm-up phase during which performance may temporarily regress, it ultimately improves model performance by providing more stable supervision.

Predicting extreme price movements in high-frequency financial markets is a challenging task due to non-stationarity, heavy-tailed return distributions, and severe class imbalance. In particular, rare but impactful events are often difficult to detect using conventional modeling approaches, which typically treat extreme movements as isolated observations. This study proposes a volatility-aware approach for extreme event detection using high-frequency Bitcoin limit order book (LOB) data. Motivated by empirical evidence of volatility clustering, the target formulation is extended to incorporate both large future returns and high-volatility regimes. This redefinition increases the proportion of informative samples and aligns the learning objective with the underlying market dynamics. Using a tree-based model (XGBoost) with time-series cross-validation and imbalance-aware evaluation, the proposed method achieves a Precision-Recall AUC of approximately 0.40, significantly outperforming the baseline formulation with a PR-AUC of around 0.06. This represents more than a sixfold improvement in detecting rare events. The results highlight that target design plays a critical role in financial machine learning, often exceeding the impact of model complexity. By incorporating volatility structure into the labeling process, the proposed approach provides a more effective and realistic framework for extreme event detection in high-frequency cryptocurrency markets.

Lung ultrasound (LUS) is a bedside tool for assessing pulmonary edema in patients at risk due to heart failure or impaired kidney function. However, automated LUS analysis remains challenging because of speckle noise, imaging artifacts, and operator-dependent acquisition variability. In this work, we present a deep learning framework for multi-class LUS video classification that explores two components: hierarchy-aware training, and anatomy-guided learning. Starting from a strong baseline, we introduce hierarchical training strategies and then introduce pleural line mask supervision to guide model attention toward anatomically relevant regions. We study four clinically relevant classes--healthy, B-lines, consolidations, and mixed B-lines with consolidations--using an open-access dataset of 1,886 videos from 219 patients, evaluated with patient-level five-fold cross-validation. Results show that hierarchy-aware training improves pathological separation relative to flat classification, while mask-guided attention supervision achieves the highest mean macro-F1 of 65.7\% and produces more localized attention patterns. Transfer experiments on the external COVID-BLUeS dataset further show competitive and parameter-efficient adaptation while preserving pleural-focused attention behavior. These findings suggest that combining clinically structured objectives with anatomy-guided supervision is a practical approach to robust, interpretable LUS video analysis. Code and model implementations are available at https://github.com/Alya-Almsouti/LUS-video-classification.

While ML can produce complex models beyond those that a human could produce manually, incorporating human input can often improve performance beyond purely data-driven models. While this feedback could come from system designers or domain experts, in many cases, the end users who regularly use the system will naturally develop an understanding of its flaws and desire the ability to change the system's behavior based on their knowledge. While soliciting feedback from end users can result in significant model improvement over time, introducing these feedback techniques can also affect several human factors-such as trust or perception of system accuracy-that are not yet fully understood and have different effects reported in the existing literature. Therefore, we sought to build on the existing research to further explore how the act of providing feedback can affect user understanding of an intelligent system and its accuracy in different contexts. We present three controlled experiments that study the effects of interactive feedback collections on user impressions in domains with objective and subjective feedback. The results show that in a context where there is an objectively correct answer, providing HITL feedback lowered both participants' trust in the system and their perception of system accuracy, regardless of whether the system accuracy improved in response to their feedback. However, when the feedback being provided involved subjective opinion, no such negative bias was observed. Furthermore, in the objective context, participants distrusted the system over time, whereas participants in the subjective context mistrusted the system over time. These results highlight the importance of considering the effects of allowing different types of end-user feedback on user trust when designing intelligent systems.

Language agents depend on memory across interactions. However, the limited context windows of large language models (LLMs) and their inference costs constrain how much memory can be used at once. Existing systems mainly follow two strategies: memory retention and memory consolidation. Retention keeps raw records and preserves exact details, but relevant evidence may not fit under a tight budget; consolidation compresses and combines records, improving coverage per token but risking the loss of query-critical details. Neither strategy is universally preferable. This raises two central questions: when should consolidation replace retention, and which operator -- Merge, Abstract, or Rewrite -- should be selected? We formalize this decision by decomposing each operator's utility into a coverage effect on evidence omitted by retention and a signed replacement effect on raw evidence that already fits. Their balance explains why the preferred action changes with relative budget pressure. We implement this mechanism with Offline Abstraction-Safety (OAS), a lightweight learner that estimates action utilities from pre-generation features with held-out harm calibration. The public LongMemEval and LoCoMo benchmarks show the same budget-dependent pattern. On LongMemEval, consolidation improves absolute accuracy by up to 48% under tight budgets, whereas retention is preferable under loose budgets; LoCoMo replicates this crossover at a smaller budget, consistent with its shorter evidence. On both datasets, cross-note abstraction and merging generally outperform local rewriting when compression is necessary.

In two-player zero-sum games whose Nash equilibria form a convex set, regularized solvers such as Regularized Nash Dynamics (R-NaD) empirically select the maximum-entropy member: the information projection (I-projection) of a uniform reference onto the Nash set. On a panel of small games this match is exact, with one apparent exception: in Kuhn poker R-NaD lands at bluff coordinate 0.180 while the maximum-entropy member sits at 0.201, a coordinate gap of about 0.021, even though R-NaD attains 99.7 percent of the maximum entropy. We ask whether this gap is a genuine selection bias or an artifact, and answer it quantitatively. We show that for selection on a one-dimensional Nash manifold the coordinate gap factorizes as $\mathrm{gap} \approx \sqrt{2δ/κ}$, where $δ$ is the entropy shortfall of the solver and $κ$ is the curvature of the entropy landscape at its peak. Across five games this relation holds to within $2 \times 10^{-4}$ (under 1 percent relative error). The four matrix games have $δ\approx 0$ (R-NaD reaches the maximum-entropy member exactly) and therefore no gap regardless of curvature; only the sequential game (Kuhn) has $δ> 0$. A causal sweep of the magnet strength drives $δ\to 0$ and the gap toward zero along the predicted curve (fitted scaling exponent 0.50, $R^2 > 0.999999$, against the exact prediction of 1/2), until the dynamics destabilize at a stability floor: behavior consistent with a removable shortfall and inconsistent with a fixed bias. We quantify the curvature half of the law from measured curvatures and flag a moving-target pitfall in the natural Tsallis-entropy experiment. The Kuhn gap is thus the curvature shadow of a small, removable entropy shortfall on an unusually flat peak; the I-projection account is upheld up to a flatness-limited residual.

Neural simulation-based inference enables parameter estimation for complex models, but typically requires the user to specify a simulator encoding a fixed model structure. We present a framework for joint model selection and parameter estimation that combines large language models for program synthesis with neural simulation-based inference. Given a natural language description of the system and data under investigation, an LLM proposes candidate simulator programs which are iteratively refined via feedback-driven mutation and evaluated using neural density estimation. The approach enables simulation-based inference over a pool of models, not just parameters within a fixed model. On benchmarks spanning deterministic dynamics, stochastic epidemic models, and dark matter substructure inference from gravitational-lensing images, the method identifies plausible model families from open-ended prompts, with accuracy that reflects the information content of the data and identifiability of candidate models.

Retrieval-Augmented Generation (RAG) enhances the factual grounding of large language model (LLM) inference by retrieving relevant information from external knowledge bases. However, its dense vector retrieval introduces significant latency and energy overhead, becoming the primary performance bottleneck. Although recent in-storage accelerators aim to reduce data movement, they still rely on host or embedded processors outside the memory, where nearly 70% of the total retrieval time is spent. As a result, they cannot fully overcome the bandwidth limitations, leading to yet another memory bottleneck. To tackle these limitations, we present D-NOVA, a hardware-software co-designed in-storage retrieval accelerator. D-NOVA executes an inverted file (IVF)-based hierarchical retrieval pipeline by deeply embedding the search functionality directly into the NAND memory array. This is achieved by incorporating a new distance metric, Dual-Bound Tight Similarity Sensing (DTS), which is specifically tailored for searching within the NAND string. In addition, we introduce a lightweight contrastive adapter that maps embedding vectors into a DTS-friendly domain, recovering near-software recall while improving performance and energy efficiency. D-NOVA is up to 41.7x faster and 71x more energy-efficient than a CPU baseline, and achieves 12.13x higher throughput while being up to 1.26x more energy-efficient than state-of-the-art in-storage RAG accelerators, demonstrating the potential of fully in-storage vector search for scalable RAG acceleration.

Agentic retrieval-augmented generation (RAG) systems increasingly retrieve external evidence and orchestrate tools for knowledge-intensive applications. In Multi-Hop question answering, agents chain facts across documents. Existing defenses focus on content poisoning, which injects false facts, and prompt injection, which embeds directives. We identify a third attack surface: the salience channel, through which fact position, emphasis, framing, and semantic proximity can redirect reasoning even when all retrieved claims are true and no instructions are present. We formalize Salience Induction as truth-preserving edits that redirect Multi-Hop attribute binding while leaving the retrieval trace semantically intact. We define six Salience-Editing operator classes and build an iterative proposer-verifier pipeline under factual and stealth constraints. We also introduce SalientWiki-MH, a decoy-annotated Multi-Hop benchmark. Evaluations across five frontier model families (GPT, Claude, Gemini, DeepSeek, and Qwen) and three agent architectures (ReAct, Reflexion, and tool-calling) show broad generalization. Under a 30% edit budget, Salience Induction achieves an 83.3% attack success rate; the strongest evaluated baseline defense leaves 75.7% post-defense ASR. Untargeted rewriting further reduces attacks only by degrading neutral task success. Our lightweight input-side defense, Salience Normalization, reduces attack success to 15.3% under standard attacks and 23.6% under an adaptive attack. These results show that truthfulness and instruction filtering alone are insufficient: robust agentic RAG also requires defenses against salience-relevance decoupling.

Developers frequently write uninformative git commit messages such as "fix" or "update stuff", degrading the value of version-control history for code review, debugging, and onboarding. We present CommitLLM, a three-stage pipeline that generates concise, Conventional Commits-compliant messages from code diffs using a fine-tuned small language model. The system combines (1) QLoRA fine-tuning of Mistral-7B-Instruct-v0.2 on the CommitPackFT dataset, (2) constrained decoding to enforce brevity, and (3) deterministic post-processing to strip conversational artifacts and enforce format. On a 50-sample evaluation, CommitLLM achieves 98% format compliance (vs. 22% for vanilla Mistral), reduces average output length from 154.8 to 37.9 characters, and improves LLM-as-a-Judge scores from 1.97 to 3.68 out of 5. Notably, the post-processing layers contribute more to quality improvement than the fine-tuning itself, suggesting that for structured-output tasks, treating the LLM as a component in a deterministic pipeline is more effective than optimizing the model alone. The entire system runs on a single consumer GPU (NVIDIA T4, 16 GB VRAM).

Test-time collaboration, including self-consistency, best-of-N selection, critic models, and verifier pipelines, is often credited with broadly improving LLM reasoning, yet its gains are uneven and sometimes negative. We ask when training-free collaboration should be expected to help. For a fixed candidate pool, we decompose a selector or verifier's net gain into measurable factors: recoverable mass, verification-signal coverage, conditional selection quality, and harm to already-correct outputs. This reframes collaboration as a candidate-selection problem rather than as an intrinsic property of a multi-agent topology. Across LiveCodeBench, MATH Level-5 hard subjects, and GPQA-Diamond, gains are bounded first by the oracle gap and then by signal fidelity, which we measure directly as candidate-level agreement between verifier verdicts and official labels. On LiveCodeBench, a public-test verifier (MCC 0.825) gains +8.14 percentage points (pp) over a first-sample baseline; a generated-test verifier (MCC 0.248) improves by +2.70pp and is not statistically distinguishable from an LLM selector, but operates at near-zero harm versus the selector's 4.69% harm rate. On MATH, a symbolic answer-equivalence selector beats self-consistency by +4.67pp, while LLM selectors are negative. On GPQA-Diamond, recoverable mass is only 3.03% and 87.54% of candidate pools are answer-identical; a weaker model's pools shrink both further, suggesting that oracle gap is a joint property of task, model, and sampling configuration. Our framework yields a practical pre-deployment diagnostic: estimate the oracle gap, then measure coverage, signal fidelity, and harm before investing in collaboration.

LLM-driven agent systems have emerged as a promising paradigm for electronic design automation (EDA), demonstrating strong potential for automating complex design workflows. However, existing evaluations primarily examine individual language models on isolated EDA tasks, providing limited insight into how different agent systems perform across complete EDA flows. In this work, we present FluxBench, a systematic evaluation of AI agents on end-to-end EDA workflows under unified prompts, tool environments, and technology library settings. Our evaluation covers representative scenarios, including RTL generation with open-source toolchains and an RTL-to-GDS flow using closed-source commercial EDA tools for industrial applications. Through these workflows, we assess agents' capabilities in RTL code generation, iterative repair, tool-feedback utilization, logic synthesis, placement and routing (P&R), and Engineering Change Order (ECO) automation. To further characterize the efficiency of agent systems, we introduce Token ROI, a cost-efficiency metric that measures effective improvements in EDA artifacts relative to token usage and runtime cost. Experimental results show that, even when built on the same foundation model, different agent system architectures can exhibit performance gaps of up to 86.27%. Moreover, among systems with comparable task performance, Token ROI can differ by as much as $105.92\times$. In the RTL-to-GDS flow using PicoRV32 as a case study, FluxEDA achieves an end-to-end score of up to 97.94, outperforming Claude Code equipped with domain-specific EDA skills by up to $8.39\times$. These results indicate that domain-specific skills alone are insufficient to improve agent performance in large-scale EDA scenarios. Instead, both agent system design and foundation model capability play critical roles in enabling effective automated EDA workflows.

Zero-shot text-guided editing of real-world music recordings requires balancing semantic modification with faithful preservation of the original musical structure. Although recent diffusion transformers trained with rectified flow have achieved remarkable success in text-to-music generation, extending them to edit existing recordings remains challenging because editing requires accurate deterministic inversion, reliable structural preservation, and numerically stable integration throughout the inversion and generation processes. We present FlowSonic, a zero-shot music editing framework built upon a pretrained diffusion transformer trained with rectified flow. FlowSonic first deterministically inverts a real-world recording into the latent space and preserves its musical structure during editing by reusing cross-attention representations extracted during inversion. To improve the numerical reliability of inversion-based editing, we introduce a high-order ODE solver and systematically investigate how different numerical integration schemes influence trajectory stability, structural preservation, and semantic controllability. Comprehensive experiments on timbre-transfer and genre-modification tasks demonstrate that FlowSonic consistently outperforms existing music editing methods across semantic alignment, harmonic preservation, structural consistency, and perceptual audio quality. We further provide geometric and empirical analyses showing how the proposed numerical integration strategy improves latent trajectory stability and leads to more reliable music editing.

Multi-provider LLM gateways reverse proxies that route, load-balance, and rate-limit requests across foundation-model APIs have become critical production infrastructure. Yet the failure modes specific to this architectural layer remain undocumented, scattered across issue trackers and post-mortems with no unifying framework. We introduce \fa{}, a two-axis taxonomy that classifies failures by their \emph{origin layer} (Network/Transport, Streaming/Protocol, State/Session, Model~Behavior, Governance/Cost) and their \emph{detectability} (Loud vs.\ Silent). We populate this taxonomy with five verified catalog entries sourced from public bug reports and first-hand stress testing, each accompanied by a mechanistic root-cause analysis. Three entries include standalone reproduction scripts. Our principal finding is that the most operationally severe failures are \emph{silent}: they return HTTP~200, pass every standard health check, and corrupt application state in ways that require semantic-level observability to detect. Two such silent failures a concurrency race condition causing history loss and a streaming index collision corrupting tool-call payloads were discovered first-hand during \cb{} evaluation campaigns.

We propose Token-Level Off-Policy Labeling (TOPL), an off-policy training paradigm that reframes post-training as a token-level correctness prediction task. Our key intuition is that by training the model to distinguish good and bad tokens in a response, we naturally guide the model towards generating good tokens, while avoiding the pitfalls that come with directly training the model to generate off-policy tokens. Experiments on document summarization tasks show that TOPL achieves strong out-of-distribution generalization across 11 datasets against a diverse set of sequence-level and token-level baselines. We further demonstrate that TOPL transfers effectively to machine translation, suggesting that its benefits generalize across different faithful generation tasks. Through ablation studies, we confirm that our token-level learning signal is critical to good performance; sequence-level analogues do not confer similar benefits. Finally, we show that TOPL induces interpretable model updates: the LoRA adapters learned through TOPL function as linear classification heads and steering vectors.

Recent advances in world models and video generation have given rise to an emerging reasoning paradigm that leverages video generative models to simulate, predict, and reason about real-world dynamics. We redefine this paradigm as Thinking in Video, where video is not merely an output artifact but a medium for constructing, extending, and verifying causal thought. However, this promise remains unverified: convincing rollouts may reflect memorized appearances rather than causal understanding, while existing metrics separate perceptual fidelity from semantic logic. To evaluate whether video generators support such reasoning, we introduce the Causal-Generative Dual-Judge (CGDJ), auditing World Model Consistency from two perspectives. Explicit Causal Perception tests whether a generator reads a video scenario as a reasoning problem through spatio-temporal flattened visual question answering, while Implicit Generative Perception-Prediction Gap evaluates whether it renders the causal consequence as a consistent future video. Applying CGDJ to representative open- and closed-source generators reveals a clear Perception-Prediction Gap: open-source models produce plausible dynamics despite near-zero explicit causal perception, whereas advanced closed-source systems show stronger but still limited alignment between reasoning and generation. Further analysis exposes audio-visual misalignment, where models verbalize correct causal logic more reliably than they render it, challenging the "world simulator" narrative.

Motivated by confidence-guided parallel unmasking in masked discrete diffusion, we study a single selection step in a stylized Gaussian random-field model. A locally dependent nonnegative score field represents position wise uncertainty, and the scheduler selects the K positions with the smallest scores. Dependence among the selected positions is measured through a distance-dependent Gaussian correlation model. This separation provides a tractable framework for quantifying how the geometry of low-score locations affects the dependence cost of factorized parallel decoding. We establish two complementary results. In a conservative sub-square-root regime, the conditional Gaussian total correlation of the selected block vanishes in probability. At the square-root scale, it remains non-negligible with positive asymptotic probability and admits a strictly positive expectation lower bound. Synthetic experiments support the predicted finite-size behavior. These results provide a rigorous stochastic-geometry baseline for understanding how budget size, score dependence, and spatial correlation jointly shape one-step confidence-based selection in masked discrete diffusion.

Expert domains are trees; the Euclidean transformer is not, diluting parent-child structure exponentially at depth. The hyperbolic turn left one question unasked: not how much of a network to curve, but where curvature may touch the gradient. Placement is a law, not a knob: the same geometry on a trainable adapter collapses training (seventeen training collapses, ~220 GPU-hours), yet at the loss layer alone it trains without one -- this is HySAT (Hyperbolic Structure-Aware Training), hyperbolic losses at the loss layer only. Across six expert SLMs we constructed and deployed (Llama 3.1 and EXAONE 3.5; four adapter strategies; 18.0M-sample corpus; zero NaN over ~317K optimizer steps), a matched four-arm ablation isolates the preserved manifold invariant, and three propositions and a lemma prove why loss-only placement is stable where adapter-on-manifold is not. Four models are operationally deployed (one live, consumer-facing), two open-weight, with per-step traces and a seventeen-incident failure ledger on Zenodo (CC-BY-4.0).

Large \emph{Time Series Foundation Models} (TSFMs) demonstrate strong zero-shot forecasting capabilities across diverse domains. However, their application to regional climate forecasting faces practical challenges: model weights are often proprietary, local training records are limited, and computational budgets are constrained, making traditional fine-tuning approaches infeasible. To address these constraints, we introduce a lightweight, black-box adaptation framework (requiring no access to backbone parameters and no backbone fine-tuning) that enhances frozen TSFMs at inference time through two plug-and-play wrappers: \textbf{SMR\textsuperscript{2}} (Stationarity aware multi-resolution Residual), which decomposes the input into multi-resolution temporal views, learns stride specific residual corrections that capture regional dynamics, then adaptively ensembles them into a single forecast, and \textbf{MBB} (Moving Block Bootstrap), which preserves temporal dependencies through block resampling and ensembles over temporally coherent residual perturbations to stabilize the point forecast. Both wrappers instantiate the same bagging style principle: they build diverse views of the input or its residuals, forecast each with the same frozen backbone, and aggregate, so all adaptation comes from inference time ensembling rather than any weight update. Evaluated on one month ahead Standardized Precipitation Evapotranspiration Index (SPEI) prediction across multiple sites in South Australia, our framework consistently improves forecasting performance across several backbone models, demonstrating up to 26\% mean squared error (MSE) reduction over the corresponding frozen backbone while enabling practical deployment in resource constrained regional forecasting systems.

We introduce Retrieval-Augmented Interpretable Learning (RAIL), a probabilistic meta-learning framework for zero-shot generation of task-specific interpretable models that synthesizes coefficient-space structure from natural-language task descriptions and a memory of previously learned task-specific predictors. RAIL retrieves related source tasks, transfers structure through coefficient space, and generates a new predictor in the original diagnostic-feature space, enabling zero-shot and few-shot clinical procedure prediction with feature-level explanations. Its probabilistic formulation provides uncertainty over retrieval, model coefficients, and predictions, supporting reliability-aware deployment: uncertain predictions or unstable explanations can be flagged for additional clinical review rather than treated as automatic decisions. This makes RAIL particularly suited for healthcare settings, where prediction tasks are highly long-tailed, new clinical targets arise frequently, and models must remain inspectable, uncertainty-aware, and compatible with human oversight. Across long-tailed clinical procedure prediction tasks, RAIL maintains reliable performance across data-availability regimes: it achieves 73.4% accuracy in the held-out zero-shot settings, where no supervised task-specific model can be trained, and remains near 73.2% accuracy in the extreme few-shot regime with only 2-4 examples, where supervised task-specific models perform close to chance. RAIL further benefits from clinically informed task representations and yields retrieval, uncertainty, and coefficient-level diagnostics that make model behavior more transparent. These results suggest a path toward scalable clinical prediction systems that can adapt to new tasks while preserving interpretability and reliability.

Regional climate prediction presents unique challenges for time series foundation models, which typically process temporal patterns through single-pass inference. Expert climatologists, in contrast, employ multi-scale temporal analysis and iterative refinement based on systematic error diagnosis. We present RGMR (Residual-Guided Multi-Resolution Refinement), an inference-time framework that adapts pre-trained foundation models to perform structured coarse-to-fine refinement for climate forecasting without updating backbone parameters. Applied to drought forecasting using the Standardized Precipitation Evapotranspiration Index (SPEI), RGMR is architecture-agnostic across the three TSFM backbones evaluated per site (TimesFM, TimeGPT, TabPFN) and consistently lowers test-set MSE on three South Australian sites and three additional regions outside South Australia. Applied to TimesFM, the wrapper reduces one-month-ahead SPEI MSE by up to 18.9\% across the three South Australian sites (mean reduction $\approx$18.7\%). Overall, RGMR provides a practical route for deploying frozen TSFMs in regional climate forecasting workflows.

Split face recognition reduces client-side computation but exposes intermediate features to feature inversion attacks and unauthorized analysis by honest-but-curious (HBC) servers. Existing privacy-preserving face recognition methods mainly aim to resist unauthorized reconstruction, typically producing features whose inversion yields visibly degraded results, which may reveal the existence of protection and motivate adaptive attacks. To address this issue, we propose DecoyFace, an imperceptible decoy-oriented framework that steers unauthorized reconstruction toward a plausible but incorrect identity while preserving recognition utility. The key idea is to decompose the intermediate representation into a reconstruction-sensitive subspace and its complementary subspace. The client injects decoy identity cues into the reconstruction-sensitive subspace, while limited recognition-relevant evidence from the true sample is retained in the complementary subspace. On the server side, an authorized canonicalization module suppresses decoy-dominant components and recovers a recognition-friendly representation. This design addresses both attacker-side inversion from intercepted features and HBC server-side reconstruction from canonicalized representations. Experiments show that DecoyFace preserves competitive recognition accuracy while substantially reducing identity leakage to 2.93% under U-Net attacks and 0.74% under Flow-Matching attacks while yielding visually plausible and imperceptible reconstructions, with over 99.78% face validity on LFW dataset.

The evolution of e-commerce has fundamentally transformed how users search for products, shifting from simple text-based keyword queries to complex multimodal interactions that seamlessly combine product images, natural language descriptions, and mixed-intent instructions. However, existing approaches face a critical dilemma: single-modal specialist models, deployed independently for text retrieval, visual search, and voice recognition, operate in isolation and cannot handle cross-modal queries, while general-purpose vision-language models lack the domain-specific knowledge necessary for fine-grained product understanding, user behavior modeling, and commercial intent reasoning. In this work, we present Pailitao-MMSearch, one native e-commerce multimodal search foundation model designed to bridge this gap. Our approach introduces three key innovations: (1)HybSID (Hybrid Semantic ID);(2)a two-stage continual pre-training strategy; and (3)a hybrid reasoning post-training pipeline. Built upon Qwen and deployed on Taobao's Pailitao multimodal search platform, Pailitao-MMSearch achieves substantial improvements in online A/B testing, including up to +13.61\% in Gross Merchandise Volume (GMV) and +8.21\% in transaction volume compared to traditional multi-modal search pipeline, demonstrating the effectiveness of our native e-commerce multimodal search large language models.

As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks in inference systems. Existing input-level prompt compression methods address this, but rank each sentence by a scalar relevance score, treating the document as an unstructured pool of words and sentences. Under tight budgets, this causes theme collapse, where the dominant theme(s) of a document consumes the budget, discarding less-frequent yet task-relevant themes. Preserving thematic coverage instead requires allocating the budget across recurring themes rather than scoring sentences in isolation. To this end, we propose SALT, a model-agnostic extractive framework that organizes per-sentence keywords into a trie ordered by sentence frequency (SF), a lightweight, reusable proxy for document thematic structure. This trie-based organization smooths memory allocation and prevents dominant themes from monopolizing the budget. Multi-anchor retrieval activates trie nodes labeled by query keywords at any depth, and the trie persists across dialogue turns, supporting multi-turn use without re-encoding the document. By preserving document themes, SALT reduces the prefill computation and memory cost of long-context prompts while remaining composable with KV-cache methods that target decoding-time latency and memory.

Motif discovery, the search for recurring patterns within a time series, is a core primitive of exploratory data analysis. A pattern, however, is defined by its duration, which analysts rarely know in advance. To resolve this unknown duration, an interval of window lengths is defined, and the accepted method is to try every length in that interval. Existing pan matrix profile (PMP) methods compute one z-normalized matrix profile per length, so $L$ lengths cost $L$ quadratic self-joins over the same series. We introduce Panache, to our knowledge the first one-pass streaming algorithm for z-normalized PMP motif discovery. It replaces the repeated self-joins with a single scan whose runtime is near-linear in the series length. The key observation is that mean-centering a subsequence changes only its DC Fourier coefficient, so the non-DC spectrum of every z-normalized subsequence can be maintained online by sliding-DFT recurrences and running statistics. This spectral state is the key under which similar subsequences collide in an occupancy-controlled hash directory and, through Parseval's theorem, yields a lower bound that rejects most colliding pairs before any exact computation. Panache computes every data-dependent parameter itself, leaving only a resource budget to tune. At the default budget, it recovers all top-20 pan-motifs against exact fixed-exclusion ground truth on 17 UCR configurations, and is faster than every CPU and GPU baseline benchmarked in this paper. On Wafer at five million samples over 51 lengths, Panache completes one pass in 2.9 minutes and emits the exact motifs in 6.0 minutes, against 7.95 hours for the fastest exact CPU baseline and 38.3 minutes for SCAMP on an H100 GPU.

A randomized algorithm may terminate almost surely even though exceptional random tapes make it run forever. This paper studies the survival tail, the Kolmogorov complexity of one such tape, and the Hausdorff dimension of all of them. For each $s>0$ at which the powered repair matrices commute, the main theorem bounds $\sum_wP[w]^s$ over surviving prefixes $w$, uniformly over deterministic nonanticipating selectors. The case $s=1$ controls termination; the full family gives weak-source and dimension bounds. The source powers contain information absent even from the ordinary repair kernel and the complete stopping-time law. Under one common finite tape source, two overlapping disagreement-repair rules on a four-vertex path have the same ordinary kernels and the same stopping-time law for every selector, yet their nontermination dimensions can be arbitrarily close to zero and one. At one common source-power level, the same dominated tape source makes one rule run forever but gives the other an exponential stopping tail. The separation is caused by action labels that produce the same state transition and are therefore invisible at power one. For bounded-dependence $k$-SAT, conditional block min-entropy above the trace-growth threshold gives exponential termination, and the effective dimension of an individual infinite run is bounded by the trace growth induced by the clauses repaired infinitely often. Tree formulas asymptotically attain the maximum-degree dimension and global source bounds, while clique formulas attain the graph-specific one-step threshold in the stated regime. An exact backward likelihood identity complements these setwise results with tail and coding bounds for each run.

Few-shot Test-Time Domain Adaptation (FSTT-DA) seeks to adapt models to novel domains using only a handful of unlabeled target samples. This setting is more realistic than typical domain adaptation setups, which assume access to target data during source training. However, prior FSTT-DA approaches fail to effectively leverage source domain-specific knowledge, relying on shallow batch normalization updates, prompt-based methods that treat the model as a black box, or ensembling strategies that do not capture cross-domain relationships. To address these limitations, we introduce a new FSTT-DA framework that integrates LoRA fine-tuning with model merging. In our approach, separate LoRA modules are fine-tuned on CLIP's vision encoder for each source domain. Since LoRA modifies only a small fraction of the model's parameters, it retains the base model's generalized knowledge while internally learning domain-specific features. To adapt the learned knowledge to a specific target domain, we propose a hypernetwork trained via meta-learning that generates per-column merging factors to combine LoRA modules. Given a small batch of target images, the hypernetwork produces merging weights that fuse source LoRA modules into a single adapted representation. Our results demonstrate state-of-the-art performance across various domain adaptation datasets. Our code is publicly available at https://github.com/nahbois4321/DA-MergeLoRA.

Multilingual assessment systems commonly rely on translation for scoring and quality-control processes. We evaluate whether multilingual sentence embeddings can replace translated English input for Linguistic-Integrated Reliability Auditing (LiRA) across 11 PIRLS constructed-response items and three embedding models. Native-language embeddings reproduced translation-based reliability estimates closely while recovering responses excluded after translation failure, with no meaningful change in reliability.

A platform-specific API is implemented for a particular platform (e.g., operating system), thus, it may not work on other platforms than the target one. Detecting the usage of such APIs is important for supporting software maintenance, as it allows maintainers to be alerted about APIs that could pose potential risks. This paper proposes PSASpotter, a tool to detect the usage of platform-specific APIs in Python systems. PSASpotter also identifies whether the platform-specific APIs are used within a defensive code, such as try/except blocks or if blocks that check the current platform. PSASpotter can support the development of novel empirical studies about the usage of platform-specific APIs in the Python ecosystem. Moreover, the defensive code detected by PSASpotter may contain alternative solutions for unavailable APIs, which can provide insights for software development and testing across multiple platforms. PSASpotter is available at: https://github.com/ricardojob/PSASpotter. Tool video: https://youtu.be/d3WyozTAKS8.

The Matthew effect is a notorious issue in Recommender Systems (RSs), \emph{i.e.}, the rich get richer and the poor get poorer, wherein popular items are overexposed while less popular ones are regularly ignored. Most methods examine Matthew effect in static or nearly-static recommendation scenarios. However, the Matthew effect will be increasingly amplified when the user interacts with the system over time. To address these issues, we propose a novel paradigm, Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendation (HyCoRec), which aims to alleviate the Matthew effect in conversational recommendation. Concretely, HyCoRec devotes to alleviate the Matthew effect by learning multi-aspect preferences, \emph{i.e.}, item-, entity-, word-, review-, and knowledge-aspect preferences, to effectively generate responses in the conversational task and accurately predict items in the recommendation task when the user chats with the system over time. Extensive experiments conducted on two benchmarks validate that HyCoRec achieves new state-of-the-art performance and the superior of alleviating Matthew effect. Our code is available at https://github.com/zysensmile/HyCoRec.

In decentralized storage systems, audit results are often not used directly to guide later redundancy and shard-placement decisions, which can lead to inefficient resource allocation and delayed recovery. We propose AEC-DS, a closed-loop adaptive erasure coding mechanism driven by Provable Data Possession (PDP) feedback. PDP audits continuously update node reputation, while a QoS-aware migration policy adjusts shard placement according to node reliability and data priority. The policy moves high-priority shards from unstable nodes to more reliable nodes in the cold tier and penalizes unstable nodes in subsequent placement decisions. Simulations with 800 nodes and 500 files show that AEC-DS maintains 100% data durability under the evaluated fault model with a redundancy factor of 1.25x. Compared with Static-EC, Dynamic-EC, and DRD-EC, AEC-DS reduces cumulative recovery operations by 66.8%-75.2%. Ablation results further show that class migration plays a major role in preventing data loss, improving the measured loss-prevention capability by 176.8%. These results indicate that PDP feedback can connect integrity auditing with redundancy and placement adaptation, providing a practical path toward self-healing decentralized storage while accounting for the additional cost of migration.

Model checking is a powerful technique for verifying properties of systems or protocols, but it often suffers from the state space explosion problem. For protocols such as the Alternating Bit Protocol (ABP) and the Sliding Window Protocol (SWP), increasing parameters such as channel capacities or window sizes leads to a reachable state space that is infeasible for exhaustive model checking. To address this, we propose a technique that combines model checking with simulation relations. We focus on three protocols: the Simple Communication Protocol (SCP), ABP, and SWP. Formalized as state machines, these protocols are presented in decreasing order of abstraction: SCP, ABP, and then SWP, which results in a corresponding increase in reachable states. While SCP is verifiable through direct model checking without state space explosion, the direct application of model checking to ABP and SWP becomes infeasible as their parameter values increase. We demonstrate that ABP satisfies its invariant property by combining model checking on SCP with a simulation relation from ABP to SCP. Furthermore, we demonstrate that SWP satisfies its invariant property through the composition of simulation relations from SWP to ABP and from ABP to SCP, in conjunction with model checking on SCP. These approaches enable the formal verification of protocols with large reachable state spaces by conducting model checking on a significantly smaller state machine.

Measuring conversational states such as cognitive load and conversational power from multimodal behavior requires characteristic features that are not only predictive but also reliable across task contexts. We present a three-dimensional evaluation framework assessing predictive accuracy, cross-task generalizability, and test-retest reliability, applied to interactional, acoustic, and linguistic features extracted from dyadic conversations during collaborative tasks performed over a video-conferencing platform (AVCAffe dataset; 53 dyads, 9 tasks). Our results show that no single feature family dominates all three dimensions. Linguistic features show the highest predictive accuracy for cognitive load but collapse under cross-task evaluation, revealing sensitivity to task-specific vocabulary. Additionally, acoustic reliability, often reported as evidence of feature stability, degrades once speaker identity is controlled, confirming that standard prosodic features measure vocal characteristics rather than conversational state. Interaction features provide the only genuinely reliable signal, unchanged after speaker normalization. Interestingly, classifying power role remained near chance baseline across all conditions, indicating limitations of task-level aggregated behavior for predicting power role in conversation. Our findings reveal three insights: (1) linguistic features predict best but generalize poorly across task contexts; (2) acoustic reliability collapses to near-zero once speaker identity is controlled, challenging standard evaluation practice; and (3) interaction features provide the only genuinely reliable signal, with floor dominance predicting within-dyad cognitive load asymmetry. These results argue for speaker normalization and multi-dimensional evaluation as prerequisites for context-aware, robust multimodal feature selection in conversational systems.

Language models produce probabilities over words, but professional decisions require uncertainty over meaningful states such as diagnoses, hypotheses or operational conditions. A model's printed numerical confidence does not establish reliability. We introduce a semantic map: a prespecified, testable bridge from probabilities over verbal responses to probabilities over declared states, formulated as semiparametric inference for a finite-valued latent state. A reference model defines the target posterior, the language model supplies an unrestricted conditional distribution over verbal responses, and held-out calibration connects them. We derive posterior-error bounds and conditions for existence, uniqueness, stability and sequential Bayesian updating. Crucially, language probabilities depend on the prompt's lexical form, whereas the target posterior is unchanged by information-equivalent rewording. We test the method on professional market text compiled from Federal Reserve economic and financial series and on controlled simulations with exact posteriors. Across two fitted language models, language-derived probabilities outperform printed numerical probabilities, recover held-out posteriors with valid uncertainty coverage, remain largely stable under paraphrasing, and respond appropriately to altered evidence. The broader implication is that prompt engineering optimizes a wording-dependent response, whereas scientific and professional use requires validated stability of application-relevant meaning. The semantic map turns this general concern into a testable statistical problem and, when its acceptance conditions hold, yields an auditable posterior estimate. The same principle offers a template for auditing classifications, recommendations and other fluent responses that may conceal semantic instability.

Background. Predicting conversion from mild cognitive impairment (MCI) to Alzheimer's disease (AD) is central to trial enrichment and care planning, yet existing models provide no individual-level uncertainty estimates and rarely include transparent leakage audits. We introduce the first application of persistent homology to longitudinal clinical trajectory point clouds for this task, and the first split-conformal individual risk guarantee for any AD-conversion model. Methods. We analysed 741 MCI subjects (240 converters, 32.4%) from ADNI with a uniform 4-year follow-up cap. Five leakage sources were corrected; without them a naive pipeline achieved AUC=0.934, inflated by +0.075. Vietoris-Rips persistent homology and sublevel-set proxies were combined with trajectory slopes and engineered features (76 total) in a stacking ensemble evaluated by 5-fold cross-validation. Results. Cox and Random Survival Forest models with TDA features achieved concordance C=0.799 and C=0.826 versus C=0.753 and C=0.812 without (+0.045 and +0.014). The primary nested AUC is 0.840 (same-fold bound 0.866); external AUC was 0.879 on a zero-overlap ADNI-2/GO/3 cohort. H0 persistence entropy was the top SHAP feature and significantly associated with APOE4 dosage (Spearman r=-0.191, p<0.0001, Bonferroni-corrected). Cross-conformal coverage was 90.4%+-2.2% (target 90%); empirical external coverage 96.9%. Maximum fairness gap in false-negative rate across seven subgroups was 0.092. Conclusions. We propose H0 persistence entropy as a topological biomarker of cognitive decline and demonstrate that a leakage-audited, conformally calibrated pipeline reaches competitive accuracy with individual-level uncertainty quantification not previously available for this task.

Large language model (LLM) agents offer a generative approach to simulating human behavior under conditions that may have few or no direct historical analogues, a common challenge in disaster and infrastructure-disruption planning. However, this generative capacity creates a validity problem: individually plausible agent reasoning may fail to reproduce empirical population behavior. We evaluate whether empirical grounding improves the statistical realism of LLM-agent simulations during disruptions. Specifically, we develop an empirically grounded LLM-agent framework that embeds demographic profiles from the American Community Survey, baseline routines from the American Time Use Survey, and urban spatial context into agent initialization, memory, decision prompts, and activity execution. An independent household survey conducted during the July 2024 Philadelphia heatwave is reserved as an external validation benchmark. Compared with an ungrounded LLM-agent baseline, the grounded model improved reconstruction of normal daily routines, increasing mean correlation with empirical activity profiles from 0.528 to 0.912 and reducing mean squared error from 0.066 to 0.008. Under heatwave conditions, the grounded model better reproduced survey-derived activity profiles, increasing mean correlation from 0.349 to 0.836 and reducing mean squared error from 0.098 to 0.012. The grounded model captured 46.4% of observed heatwave response amplitude, compared with 20.6% for the ungrounded baseline. These findings show that empirical grounding can make LLM agents more statistically credible simulators of population behavior while revealing remaining gaps in modeling human adaptation during disruptions.

Adaptive agents do not always regulate under the same timing conditions. Sometimes stabilization can begin before a disturbance has fully entered the internal state; at other times the agent can only recover after disruption has taken hold. A simple expectation is that an agent moving between these conditions should behave like a weighted average of the two fixed cases: the more time spent in reactive recovery, the greater the regulatory burden. This paper shows that expectation can fail. In a simulated adaptive agent with retained state history, at an operating point where sustained reactive control is more costly than sustained anticipatory control, intermittent access to anticipatory control reduces the mean regulatory burden below the value predicted by a fixed-mode mixture. The effect appears under both periodic and stochastic switching schedules: losing anticipatory access does not simply dilute its benefit, and restoring it intermittently can reorganize the later regulatory burden. High-statistics runs (N = 1000 matched replicates per schedule) resolve a negative nonlinear switching penalty across every tested schedule. The effect is small but consistent: about half a percent of the mean gain, with 63-68% of replicates falling below zero. Late-window diagnostics reveal no unresolved upward accumulation of regulatory burden. The result identifies a design-relevant timing principle. In history-dependent adaptive systems, the burden of remaining organized is not set only by how much time an agent spends in each mode; the order in which disturbance and recovery enter the state can change the subsequent burden. Intermittent anticipatory control may therefore act less like a partial failure of regulation than like a mechanism for reducing the long-term burden of recovery.

Abliteration - deleting a model's refusal direction from its weights - is the standard recipe behind popular "uncensored" open-weight models. We show the surgery is not clean. As a disposition probe we use 21,600 decisions under uncertainty - weekly up/down calls on 60 Warsaw Stock Exchange equities over 18 weeks, replayed through a frozen pipeline so the decision-layer model is the only variable. The task elicits no refusals at all, so any between-arm delta is pure side effect. Holding provenance constant (official BF16 checkpoints, a single abliteration author, an identical serving stack, one byte-identical frozen prompt), we compare base and abliterated arms of two Mixture-of-Experts families, Gemma-4-26B-A4B-it and Qwen3-30B-A3B-Instruct-2507. Three effects replicate across both families (weeks-clustered bootstrap CIs excluding zero): abliterated models are systematically more optimistic (+12.2 pp Gemma, +7.4 pp Qwen; the confirmed preregistered endpoint), justify themselves at greater length, and use fewer explicit uncertainty words in forced self-critiques (both exploratory). A fourth effect reverses sign: the same operation makes Gemma-abliterated less confident and Qwen-abliterated more (family CIs non-overlapping) - one weight surgery, opposite shifts in expressed confidence. Capability covariates rule out instruction-following degradation as the driver, and no arm shows economic skill: the apparent edge of abliterated arms is regime beta, not alpha. Our provenance audit also caught two independent contamination channels - a mismatched-quantizer pilot pair and a stale community chat template that silently mangled the rendered prompt - suggesting toolchain artifacts are the rule in studies of community-modified checkpoints. Whoever deploys an "uncensored" model as an agent is deploying a measurably different decision-maker, not the base model minus refusals.

Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly decodable signals. We formalize this ambiguity as a matrix-valued distortion between optimal ridge-prediction operators and train decoder-preserving SAEs by combining this distortion with reconstruction loss. In a rank relaxation, an isotropic task prior saturates per-mode omission costs without changing PCA's ordering, whereas a structured prior can change which modes are retained. A controlled sparse experiment shows that a declared prior protects held-out combinations from its task subspace. On GPT-2 small block 8, DPSAE reduces held-out decoder distortion by 10.6--11.4% across three paired runs while matching reconstruction NMSE. The same checkpoints pass an average natural-text output-KL noninferiority test, but one matched Pythia pair shows no improvement in probes restricted to a few sparse features. These results show that reconstruction quality does not determine which refitted linear readouts survive sparse compression, and that readout preservation is distinct from learning cleaner benchmark concepts or preserving every frozen-model behavior.

Biographical personas are widely used in system prompts, but their effects on code generation are rarely evaluated under controlled, pre-registered conditions. We tested four prompt conditions (no persona, two engineer personas, and a research-librarian persona), 12 code-generation tasks, two frontier models, and five runs per cell (480 completions). Persona effects differed between the two tested models. Under the pre-registered mixed-effects analysis, the condition-by-model interaction was significant for provider-reported output tokens; a post-hoc visible-character measure showed the same qualitative pattern. Six GPT-5.5 completions were length-capped and are reported separately. On Claude Opus, the minimalist engineer persona reduced visible output by 30% (33% in provider tokens) without improving correctness, while the thorough engineer persona increased output without a correctness gain. In an exploratory post-hoc analysis, the librarian persona elicited in-character disclaimers in 55 of 60 Opus responses and 12 genuine no-code responses, lowering mean correctness from 0.92 to 0.67. GPT-5.5 produced neither behavior in its 59 non-truncated responses. These results are consistent with personas acting as Model-Dependent behavioral-policy biases rather than universal quality interventions. We release raw completions, derived scores, analysis artifacts, a pre-registration document, and an execution gate log; end-to-end test-based rescoring requires an unreleased task harness.

Linear attention promises constant-time recurrent inference but degrades sharply on associative recall. We formulate attention recall as a spherical-packing problem and introduce Kernelized Linear Attention Activations (KATA), a framework whose feature maps are derived from first principles by certifying nonnegative attention weights through a self-dual homogeneous cone. Building on this observation, we show that rank-one positive semi-definite (PSD) features offer a favorable capacity--interference tradeoff. KATA recovers a parameter-free convex output gate and characterizes associative capacity through the Welch interference floor. For tolerances above this floor, KATA enlarges the state without adding parameters and admits spherical codes with exponentially many keys in the projection dimension. We implement KATA as fused Triton kernels at two operating points: a flash-attention-style forward up to ${\sim}1.6\times$ FlashAttention-2 throughput, and an exact $O(T)$ chunked-state form that reaches ${\sim}11\times$ FlashAttention-2 forward throughput at $131$k tokens. An associative scan of the first-order feature lowers the inter-chunk recurrence depth to $O(\log(T/C))$ for chunk size $C$ and averages ${\sim}2.4\times$ the throughput of a matched sequential linear-attention baseline. On long-range MQAR and repeated-key overwrite, several KATA variants outperform Gated DeltaNet, with parameter counts and state sizes reported alongside accuracy. Induction preserves near-perfect recall, while kernel benchmarks show that the maps can be implemented efficiently. KATA retains $0.985$ MQAR at a $16\times$ out-of-distribution length, approaching the softmax with roughly one quarter of the KV-cache entries. Experiments on 340M-parameter LLMs reveal a feature-dependent fluency trade-off and clarify how positional embeddings, delta rules, and decay gates interact with feature geometry.

Large language models confabulate chemical objects (molecular formulas, space groups, formation energies) in fluent reasoning traces, concentrated on long-tail entities where confidence is least trustworthy. Deterministic, database-grounded verification can catch and repair such errors without the coverage cost of blanket retrieval; the binding constraint, we find, is detection, not repair. Our tiered verifier extracts each checkable claim, checks it against authoritative databases and physics, and feeds the reference into a gated correction loop. Across four models and 528 condition-pinned prompts, gated correction cuts committed-formula error from 22% to 4% at $3.2\times$ fewer retrievals than blanket augmentation, beating a conversational oracle. Repair succeeds wherever a flag fires (80--97%); the bottleneck is in-loop detection recall. Grounding improves the final answer only when the verifier's scope reaches the deliverable (83% to 90%), and the lift appears only where extractable long-tail error exists: absent on near-ceiling physical constants, large on isotope half-lives (11% to 0%).

A hallmark of neurodegenerative diseases such as Alzheimer's and Parkinson's is the aberrant aggregation of proteins into amyloid fibrils, and small molecules that selectively bind to these fibrils hold promise as diagnostics, imaging probes, and therapeutics. Predicting how such ligands bind to fibril targets, however, presents two fundamental challenges. First, resolved co-crystal structures of amyloid-ligand complexes are exceptionally scarce; even with recent advances in cryo-EM only a handful have been structurally characterized, making supervised training of docking models impractical for this target class. Second, amyloid fibrils present a binding mode fundamentally different from globular proteins: ligands intercalate into longitudinal cross-$β$ grooves and stack cooperatively along the fibril axis, a geometry that existing docking models are not designed to capture. To address these challenges, we present CORAL (COopeRative Amyloid Ligand docking), a reinforcement learning framework that trains a generative docking model to produce ligand pose distributions tailored to the cross-$β$ groove geometry. Our reward explicitly incorporates cooperative ligand-ligand stacking energy alongside protein-ligand docking affinity, directly capturing the distinctive binding geometry of amyloid fibrils. We further introduce a curated evaluation set of amyloid-ligand complexes constructed from model-generated poses validated by domain experts. Experiments on both experimentally resolved structures and this evaluation set demonstrate improved pose quality and binding affinity correlation over existing docking baselines.

Inverse rendering is traditionally solved via differentiable renderers and gradient descent, which requires substantial problem-specific engineering and is prone to getting stuck in local minima due to ambiguities. Derivative-free approaches alleviate engineering requirements, but often heavily depend on a good problem initialization. In this work, we propose Feature-Informed Diffusion Evolution (FIDE), a fully black-box framework that requires no gradients or specific initialization: the renderer is treated as an opaque function whose only requirement is to produce images. Our key insight is feature guiding: rather than reducing each candidate rendering to a scalar loss value, we use a Vision Transformer (ViT) to extract dense visual features from it. We subsequently use these features to train a diffusion-based candidate proposal model, allowing the network to use visual cues to predict parameters that would match the target image. The candidate solutions proposed by this diffusion model are then refined in a closed loop with a CMA evolution strategy, continuously narrowing the proposal region as optimization progresses. We validate across diverse inverse problems from path tracing, vector splines, Voronoi shaders, and robotics, and demonstrate that feature-guiding substantially improves convergence over scalar-loss baselines and reliably escapes local minima where gradient-based methods stall.

We study the problem of sequentially evaluating a new large language model (LLM) on a fixed question set using historical performance data from prior LLMs. Our goal is to construct a confidence sequence (CS) for the model's capability on this question set and to design active querying rules that shrink the CS width as quickly as possible. For CS construction, we invert a family of test supermartingales and focus on two representative approaches: a reverse information projection (RIPr)-based approach and a testing-by-betting-based approach. We first study these approaches under an oracle setting, and demonstrate the oracle optimality of the RIPr-based construction. We then propose a growth-oriented querying rule that aims to maximize the worst-case one-step expected log-increment over the endpoints of the current CS. In practice, we build these test supermartingales and the querying rule on predictions of question-level correctness learned from historical data. We then analyze the shrinkage behavior of the resulting CSs and identify two key factors that slow the shrinkage rate of CSs: accumulated prediction mismatch and the spikiness of the querying distribution. Finally, motivated by this analysis, we propose several mixture querying rules that combine growth-oriented querying, prediction refinement, and uniform exploration, trying to mitigate the effects that slow the shrinkage rate. We provide experiments comparing different querying rules for the RIPr-based and testing-by-betting-based CSs across several synthetic testing datasets. Interestingly, we observe that the simplest querying rule, uniform sampling, can sometimes outperform more adaptive querying rules for both methods.

Analytical placers rely on differentiable objective functions to guide placement, typically combining intermediate surrogate metrics such as half-perimeter wirelength (HPWL) and cell-density penalties. However, these placement-stage surrogates remain misaligned with downstream routed and timing quality. Prior work reduces this gap with human-designed terms or learned black-box surrogates, but the former requires expert retuning and the latter is difficult to explain, debug, or deploy in analytical placement flows. CoEvoP&R addresses these limitations with a large language model (LLM)-based framework that automatically evolves analytical placement objectives. At each generation, the prompt combines the restricted objective interface, baseline context, and archived prior candidates with routing-related feedback from placement, timing proxy, and routing tools. The LLM proposes readable differentiable objectives, which are embedded and validated in DREAMPlace, evaluated through a timing proxy and an actual router, and stored with their feedback to guide later generations. Across eight ChiP-Bench Nangate45 designs and three seeds, CoEvoP&R reduces post-route routed wirelength and congestion by 16.9% and 36.7%, with gains of 0.70 ns in worst negative slack and a 912 ns reduction in total negative slack magnitude over native DREAMPlace. Across eight ICCAD 2015 Superblue designs, it reduces post-route routed wirelength and congestion by 5.4% and 23.2%. Code is available at https://github.com/FCHXWH823/CoEvoP-R.git.

As hyperscale and colocation AI data centers continue to expand, the electric grid is increasingly required to support large, concentrated loads, with individual facilities ranging from 500 MW to 2 GW. Current projections estimate that approximately 50 GW of AI data center capacity will require grid connectivity in the United States by 2030. While prior research has extensively examined the environmental and operational impacts of AI data centers, as well as their potential role as grid-interactive assets, limited attention has been given to the challenges associated with their scalable deployment through engineering, procurement, and construction (EPC) processes. This manuscript addresses this gap by proposing a phased development framework for AI data center expansion. The approach is designed to enable developers to meet aggressive time-to-market objectives while navigating multi-year constraints associated with interconnection approvals and lead times associated with the procurement of component equipment. A modular construction architecture is presented, along with a detailed analysis of integrated energy systems and the role of hybrid on-site generation in supporting incremental capacity growth. Electromagnetic transient simulations (EMT) are used to evaluate system performance, demonstrating that a combination of on-site natural gas generation and grid-forming energy storage can reliably support data center operations during early and intermediate deployment phases. The study further examines the transition to full grid interconnection, including the capability of the data center to operate in islanded mode during grid disturbances. Finally, the manuscript compares grid-forming control strategies for system reconnection and restoration under varying conditions.

Kernel regression with tensor trains and Hadamard overparameterization (KReTTaH) is introduced as a training-data-free, interpretable, and nonparametric framework for multi-way data imputation. The imputation problem is reformulated as regression in reproducing kernel Hilbert spaces (RKHS), where the tensor regression coefficients are explicitly constrained to lie on fixed-rank tensor-train (TT) manifolds and structured via Hadamard overparameterization to promote sparsity and high representational efficiency. Rather than relying on costly cross-validation, KReTTaH jointly optimizes the TT coefficient tensors and the kernel covariance matrices within a Riemannian product-manifold framework -- the former on fixed-rank TT manifolds, the latter on the manifold of positive-definite matrices -- thereby enabling automated kernel-hyperparameter selection. Numerical tests on two challenging applications -- imputation of high-dimensional functional magnetic resonance imaging (fMRI) data and recovery of missing edge flows in dynamic graphs -- demonstrate that KReTTaH consistently outperforms state-of-the-art tensor-, Bayesian-, and neural-network-based baselines in terms of modeling accuracy.

The paper investigates the possibility of predicting function-inlining decisions in compact compilers, source-to-source tools, and interpreters where the reuse of GCC or LLVM optimization infrastructure is impractical. The relevance of this work is determined by the need to transfer mature inlining heuristics to systems with limited compiler infrastructure, restricted runtime dependencies, and reduced access to target-specific analysis. Existing production compilers already contain strong inliners, but their decisions depend on internal intermediate representations (IRs), pass ordering, target models, and analysis stacks that are difficult to reproduce in lightweight systems. To overcome these constraints, we propose a portable inlining-prediction framework. Production compiler diagnostics serve as supervision; a separate extractor reconstructs caller-callee callsites, prepares sterile source snippets, normalizes them into a universal AST, optionally lowers them to a lightweight structural IR, and exports scalar features for model training. Thus, a trained predictor can be emitted as ordinary C code without a compiler-runtime dependency. To evaluate the proposed framework, we constructed a dataset comprising 336,938 callsites from fifteen open-source C projects, including 79,287 compiler-reported inline events. A comparison of several tabular models is performed using project-aware validation. Under leave-one-project-out validation, CatBoost reaches ROC-AUC 0.928 and PR-AUC 0.713; after threshold tuning, F1 improves from 0.670 to 0.729 and the false-positive rate drops from 0.192 to 0.084. Feature analysis shows that most signal is concentrated in source locality, explicit inline intent, callee size, side effects, branch and call structure, signature shape, and callsite argument shape.

We investigate the capacity of current language models to contribute to mathematical research. In Banach space theory, AI systems generated key ideas and proofs for five new results, which were then verified and refined by humans. We also developed an automated system that searches the literature for open problems and attempts solutions at scale. Our results show both the potential of language models for mathematical discovery and the continuing importance of expert verification.

This paper provides an experimentally verified formal law for calculating the uplift that diversity of thought provides in Large Language Model (LLM) ensembles. From first principles, we derive an exact decomposition of LLM ensemble lift into rescue and damage masses, which yields a compact heuristic for calculating uplift. From this we extract the metrics which predict ensemble performance: an accuracy adjusted correctness correlation, $φ_{\mathrm{adj}}$, together with the accuracy gap and collective accuracy of the pair. We test the law on 767,520 inferences from ten open-weight models over two graduate-level science benchmarks, together with a novel agentic cybersecurity benchmark in which each model conducts digital-forensics investigations by multi-turn tool use in a network-isolated sandbox (23,520 graded trials including abstentions); all votes are released openly. Calibrated once on SuperGPQA at a 40:60 vote split, the heuristic predicts lift on the calibration set with Spearman's $ρ=0.84$ and, with its coefficients frozen, transfers to two datasets never used in calibration ($ρ=0.51$ on GPQA Diamond and $0.84$ on the forensic tasks), whilst the measured swap mass tracks realised lift with $R^2\ge 0.96$ throughout. Raw $φ$ has almost no predictive power ($R^2\le 0.09$ throughout); the accuracy-adjusted $φ_{\mathrm{adj}}$ is markedly superior ($R^2=0.67$ on SuperGPQA), and the heuristic combining these metrics is the most stable pre pooling predictor across the three datasets.

Existing research shows that AI-generated text detection classifiers achieve strong in-distribution (ID) performance but do not maintain the same performance on out-of-distribution (OOD) texts, suggesting overfitting to dataset-specific features. However, combining different training datasets doesn't always improve performance and, in some cases, can even encourage shortcut learning. To address this issue, we fine-tune BERT-tiny models with Bayesian classification heads to select texts across three different datasets to use as a consolidated training set. We trained three different classifiers: fine-tuned DeBERTa-V3-large and ModernBERT-large classifiers via empirical X-risk minimization, and an MCGrad model that calibrates the predictions from the ModernBERT-large classifier. The DeBERTa-V3-large-large classifier achieves a mean score of 0.882 on the PAN 2026 test set across five metrics: AUROC, $F_1$, C@1, Brier score, and $F_{0.5u}$. ModernBERT-large achieves a score of 0.96 while MCGrad achieves the best score of the three with a mean score of 0.974, ranking second on the leaderboard. Our results highlight that careful dataset curation can lead to strong OOD performance. We release our ModernBERT-large and DeBERTa-V3-large models at https://huggingface.co/collections/ShantanuT01/panclef-2026 .

The paper presents a new parameter-efficient adaptation method called ChebyMA (Chebyshev Manifold Adaptation). ChebyMA adopts weight matrices through a multi-surface superposition of Chebyshev polynomial bases evaluated on learnable coordinates and combined via trainable coefficient matrices, replacing standard linear projections with highly expressive continuous function approximation. Theoretically, we establish an Approximation Expressivity Theorem, proving from the perspective of function approximation theory that single-manifold ChebyMA guarantees convergence in Frobenius norm error of reconstruction. Besides, drawing on Kolmogorov $n$-width intuition, we demonstrate the expressive advantages of multi-manifold superposition ($S > 1$) in decoupling high-dimensional complex features. Experimental results on Computer Vision CIFAR datasets(CIFAR-10, CIFAR-100)\cite{CIFAR} and Natural Language Processing (AG News, SST-2) datasets demonstrate that ChebyMA consistently achieves a superior parameter-accuracy Pareto front compared to standard full-parameter fine-tuning, LoRA\cite{LoRA}, TLoRA\cite{TLoRA}, and StelLA\cite{StelLA}. ChebyMA significantly outperforms other tested methods in tested datasets, validating its solid theoretical foundation for generality with purely vectorized computations.

Graph Neural Network (GNN) inference on billion-scale graphs is challenging due to the large memory footprint of features and embeddings and high disk I/O costs in out-of-core settings. Existing distributed GNN systems incur high communication times and infrastructure costs, while disk-based GNN systems are primarily tailored to training and experience massive wasted reads during inference on the entire graph. We present Taurus, a single-machine system for GNN inference on graphs that do not fit in RAM, supporting both \textit{exact} full-graph inference and fanout-sampled inference. To avoid random and repeated feature gathers, Taurus reformulates layer-wise inference as source-centric broadcasts over sequential SSD scans, backed by a pipelined GPU-CPU-SSD hierarchy, topology-aware reordering, pending-message eviction, and a GPU-resident store for high-degree vertices. It further uses non-buffered sequential reads and GPU-backed writes to reduce page-cache pollution, host-memory pressure, and write overheads. On out-of-core graphs with up to $269M$ vertices, $4B$ edges, and $514$ GiB of features, Taurus outperforms the strongest layer-wise baseline, DGI, by $7$-$25\times$, and vertex-wise baselines by $40$-$140\times$.

In a previous paper, we began the study of sequence prediction algorithms adapted to stringological word complexity measures. One measure we considered was left-to-right (most-significant-digit-first) automaticity. Here, we show a statistically and computationally efficient algorithm adapted to the ``dual'' right-to-left (least-significant-digit-first) automaticity, which turns out to be substantially different for our purpose. We also demonstrate a prediction algorithm for a more expressive measure that we call ``arithmetic repetition complexity''. In particular, the latter can be used for predicting the so-called mix-automatic sequences.

Multimodal emotion recognition in conversation (MERC) achieves accurate predictions by integrating multimodal and contextual information in dialogues. While current MERC approaches focus on modeling complex contextual dependencies in conversation, they often overlook the impact of contextual emotional inertia in emotion shift, leading to sub-optimal performance. To address this issue, we propose a novel Emotional Inertia-Informed Supervised Contrastive Learning module (EII-SCL) that informs the contrastive objective by constructing inertia-affected samples within temporal windows, effectively leveraging emotional inertia as a prior while enabling seamless integration with existing MERC models without requiring additional data. Extensive experiments on IEMOCAP and MELD show that our approach consistently outperforms state-of-the-art methods.

Designing effective Lean proof agents is a central challenge in formal mathematical reasoning. Beyond building stronger provers, recent work emphasizes the workflow around Lean: how an agent decomposes proof obligations, uses tools and compiler feedback, diagnoses failures, repairs proofs, and maintains structured proof context. Motivated by code-level self-evolving agents, we study whether such workflows can be evolved rather than hand-designed. We present a self-evolving Lean proof agent in which a small fixed, trusted runtime wraps a fully mutable workspace: the proof workflow, prompts, and tools. Unlike most self-evolving systems, which optimize against a fixed external benchmark, our system coevolves the agent and its benchmark. Between generations, the highest-scoring agent (the champion) revises the active task distribution through a mastery-throttled curriculum update that introduces harder proof obligations only after the current level is mastered, and a single-anchor recalibration re-runs the champion on the updated benchmark to keep scores comparable as difficulty rises. All evolution stays inside a Lean-grounded verification loop: however the agent rewrites itself, a success counts only when its behavior yields Lean-verified proofs under a trusted snapshot, and each attempt must emit a machine-readable, Lean-grounded proof context whose representation may evolve but whose groundedness is enforced. We run the coevolving trajectory and a fixed-benchmark baseline for 15 active generations and compare them on a held-out miniF2F test split. The best coevolving agent reaches a 45.1% held-out solve rate, versus 12.7% for the seed and 32.0% for the best fixed-benchmark agent, showing that verifier-grounded self-evolution can improve Lean proof workflows under a coevolving benchmark.

DeeperRadar is a radar-centric, sensor-stack-conditioned framework that co-designs radar sensing and multi-modal 3D detection for autonomous mobility by learning a sparse acquisition pattern end-to-end with the fusion model. A learnable MIMO design module is trained end-to-end within a fusion network that operates directly on raw radar ADC data together with camera images and LiDAR point clouds. During training, the design module is supervised by the other sensors, enabling the system to learn both which receiver antennas to activate and the effective number of them. At deployment, the design module is removed and replaced by the learned sparse subsampling mask, leaving the downstream model architecture unchanged. Evaluated on the RADIal dataset, DeeperRadar discovers sparse, task-aware radar configurations that match or exceed full-array baselines while using fewer receivers, potentially reducing radar cost and integration complexity. These results show that learned optimal MIMO radar design depends on the fusion stack and the downstream perception task.

Background: Untargeted LC-MS metabolomics requires a long chain of preprocessing decisions, each with several equally defensible options. Analysts typically commit to one pipeline and report the resulting feature shortlist. How strongly that shortlist depends on choices that were never varied stays invisible. Results: We adapt multiverse analysis to untargeted metabolomics feature selection. We present an auditable, configuration-driven pipeline that (i) applies a ten-stage quality-control filter cascade in which every feature's fate is logged, and (ii) runs the downstream analysis as a multiverse over four contrasting preprocessing philosophies, each combined with four feature-ranking methods under bootstrap stability selection and label-permutation testing. Only features recurring across paths enter a tiered consensus. On a demonstration dataset of five breast-cancer cell lines (30,370 detected features), the four single pipelines individually returned shortlists of 4-20 features whose pairwise agreement was as low as Jaccard = 0.05. The multiverse consensus retained 15 features (>=2/4 paths), of which one recurred across all four, although two paths (sharing normalization and drift-correction methods) dominate the consensus. A pipeline-wide label-permutation test found no false discoveries in 50 null permutations. Conclusions: Reporting only preprocessing-robust features, with a complete kept/dropped audit trail, converts hidden analytical degrees of freedom into an explicit, inspectable output. We discuss scope and limitations, including single-batch design and the need for independent validation.

Understanding physical human-robot and human-human interactions is a challenging yet emerging topic in 3D vision. While most existing methods rely on skeleton sequences--effective in low-light and privacy-sensitive environment--they face two major challenges: 1) learning and effectively exploiting interaction cues from skeletal data, and 2) compensating for the lack of visual information absent in skeletons alone. To address these challenges, we propose skeletal token alignment and rearrangement (STAR) for human-robot and human-human interaction recognition. It learns interaction-specific skeleton features and enriches them using visual cues by aligning skeleton and RGB video representations in a shared latent space. Specifically, STAR consists of three key components. First, we design a skeleton encoder that captures fine-grained interdependencies using Entity Rearrangement (ER) and Interactive Spatiotemporal Tokens (ISTs). Second, we present Visual Interaction Encoding that introduces a Focus on Interactions (FoI) strategy to attend to spatiotemporal regions relevant to interactions in RGB videos. Finally, these representations are aligned via a contrastive learning objective, with a refinement head further refines predictions. During training, STAR leverages both skeleton and RGB video data to learn robust, discriminative interaction representations. At inference time, it operates on skeletons alone, retaining visual-informed benefits while preserving skeleton-only efficiency. Extensive experiments on Chico, HARPER, NTU Mutual 11 and 26 datasets consistently validate our approach by demonstrating superior performance over state-of-the-art methods. Our code is publicly available at https://github.com/Necolizer/STAR.

Drift detection is a core component of production machine learning monitoring systems, where detectors are used to compare incoming data with a reference distribution and trigger alerts when changes occur. However, these detectors are often evaluated in research settings that emphasize detection accuracy under synthetic shifts, while overlooking false alarms under continuous monitoring. In production environments, models are monitored repeatedly over time and across many features, and even small false positive rates can accumulate into frequent alerts, leading to alarm fatigue. We empirically analyze false positive behavior across five commonly used drift detectors: PSI, KS, MMD, LSDD, and adversarial validation. Consistent with existing literature, PSI exhibits strong sensitivity to batch size, producing frequent false alarms at small sample sizes; however, we further observe that its behavior stabilizes and improves substantially once batch sizes exceed approximately 200 samples. In contrast, KS, MMD, and LSDD display persistent fluctuations across batch sizes, while remaining comparatively more reliable than PSI in low-data regimes. Applying a Bonferroni correction reduces false positive rates, but often at the cost of reduced true positive sensitivity, reinforcing the well-known stability - sensitivity trade-off in drift detection. This work provides a systematic comparison of false positive behavior across multiple drift detectors under continuous monitoring conditions. We identify tradeoffs across detector families and provide practical guidelines for selecting and calibrating drift detectors in production ML systems.

Enterprise Resource Planning (ERP) systems record transactions reliably but still delegate almost all operational decision-making to human specialists, because classical rule-based automation cannot reason about exceptions and monolithic AI assistants degrade when asked to coordinate across functional boundaries. This paper presents Agentic ERP, an expert-system architecture that combines role-aligned large-language-model (LLM) agents with a risk-tiered human-in-the-loop harness and a graph-based orchestrator to execute end-to-end business workflows on a production ERP backend. First, autonomous ERP operation is formulated as a constrained sequential-decision problem over a structured enterprise state, with a decomposition argument linking role-aligned agents to a measurable reduction in per-step tool-selection complexity. Second, a graph-based Planner--Executor--Reflector--Responder orchestration decouples generation from evaluation through externalised grading criteria and sprint contracts, packaging recent harness-engineering principles as inspectable expert-system artefacts. Third, the system is evaluated at three levels: a scenario-based task suite, a comprehensive comparison of six orchestration paradigms on cross-functional crisis tasks, and a 365-day agent-in-the-loop simulation against rule-based RPA and no-intervention baselines. Across these levels the proposed multi-agent method is significantly better than the baseline, and the system sustains a simulated year of operation with zero stockouts while the rule-based baseline accumulates hundreds under the same demand stream. The work shows that role-aligned LLM agents under human oversight can move an ERP system from passively recording transactions to actively executing operational decisions, and it provides a reference architecture and an evaluation protocol for autonomous enterprise resource planning.

Quantum machine learning models define probabilistic input--output maps through coherent quantum evolution and measurement. While such models can exhibit computational advantages, their internal functioning and decision making generally resists interpretation in terms of stochastic trajectories through intermediate configurations. In contrast to classical (Markovian) stochastic processes, quantum dynamics generically violates the Chapman--Kolmogorov divisibility condition, preventing a decomposition into probabilistically meaningful intermediate transitions. We develop a probabilistic framework for representing quantum learning models as stochastic processes over configuration spaces where the dynamics are modeled as linear maps on probability distributions. Starting from a fixed POVM, arbitrary quantum channels induce transition kernels on the associated probability representation. For informationally complete POVMs, and in particular SIC-POVMs, these kernels are Markovian but generally quasi-stochastic, with non-classicality appearing as negativity. By contrast, projective spaces admit positive stochastic kernels but generally require non-Markovian dynamics due to the failure of Chapman--Kolmogorov divisibility. This yields a trade-off between negativity and dependence on past configurations, i.e. quantum dynamics can be represented either by Markovian quasi-stochastic maps or by positive stochastic processes with higher Markov order. We discuss how such representations of quantum dynamics can be interpreted as stochastic walks through a memory space in the spirit of Projective Simulation, a model of learning and agency in which decisions arise from random walks over an episodic memory network. We further outline how finite-order stochastic kernels can approximate such quantum deliberation processes and show in what regimes the classical machine learning model is recovered.

Transfer-oriented reinforcement learning requires evaluating algorithms along dimensions that go beyond standard sample efficiency. We focus on two dimensions: practical efficiency, which asks whether conclusions about algorithm suitability change under wall-clock rather than interaction-based budgets, and robustness under dynamics mismatch, which asks how different learning paradigms respond to variability in the training distribution induced by domain randomization. We provide two insights to reinforcement-learning practitioners. First, comparing the sample efficiency of different algorithms is often an insufficient criterion in transfer-oriented settings. The wall-clock time required to train a decent policy is an important consideration for practitioners, and we find that the sample-inefficient PPO algorithm can produce a performant policy faster than relatively more sample-efficient algorithms such as SAC and TD-MPC2, validating the common understanding of massively parallel training paradigms. Second, domain randomization can help different kinds of algorithms learn robust policies. In particular, although PPO, SAC, and TD-MPC2 represent different RL paradigms - on-policy, off-policy, and model-based learning and planning, respectively - we find that domain randomization affects all three algorithms in a similar way. To the best of our knowledge, this is the first controlled comparison of the effect of domain-randomization coverage on PPO, SAC, and TD-MPC2 under the same transfer protocol. Taken together, these two insights highlight the importance of evaluating RL algorithms not only by sample efficiency, but also by practical considerations such as training time and the algorithms' ability to produce usable policies.

Autonomous systems rely on a perception module to navigate through dynamic environments. In real-world scenarios, the perception module's throughput requirements vary at runtime due to changes in scene complexity. However, existing perception strategies assume a fixed FPS and static model-to-cluster mapping, resulting in either over/under provision of throughput requirements or unnecessary energy consumption across diverse scenes. Addressing this challenge requires tightly coupled \textit{scene complexity awareness} to estimate an appropriate FPS target and \textit{dynamic model-to-cluster mapping} to deliver the required throughput at minimum energy. We propose a throughput-adaptive perception strategy for mobile/edge platforms, enabling intelligent runtime resource allocation based on varying FPS targets. We use Reinforcement Learning (RL) with RRM (Reward Reasoning Model) and a GRU (Gated Recurrent Unit) agent to orchestrate perception tasks across heterogeneous mobile/edge platforms. We evaluate TAPAS on Jetson Orin NX across KITTI and unseen nuScenes. On the \textit{KITTI} dataset's test sequences, TAPAS achieves 93-100% throughput met rate while saving energy by 76%. On the unseen \textit{nuScenes} dataset, TAPAS maintains 97% throughput met rate with 64% lower energy compared to \textit{SOTA} approaches, proving its robustness.

The softmax policy $π(a \mid s) \propto \exp(βQ(s,a))$ is the default model of stochastic choice in reinforcement learning (RL). Various justifications based on robustness, exploration, and optimization have been offered in the RL literature, but none uniquely derives the softmax form from first principles. This leaves a basic tension unresolved: the entropy bonus in the soft Bellman equation violates the Independence axiom that underwrites the Markov decision process (MDP) reward structure. We dissolve this tension by distinguishing two kinds of randomness: chance and choice. By restricting von Neumann-Morgenstern (VNM) Independence to environmental lotteries over base prospects, we show that imposing independence of irrelevant alternatives (IIA) and monotonicity on the policy and value functions at choice nodes uniquely determines the Boltzmann policy, the entropy-regularized representation, and the soft Bellman equation. The choice between the soft and hard Bellman equations thus reduces to a design decision: whether the agent values its own ability to choose. We develop RL-specific consequences, including return monotonicity and convergence under generalized discounting, and synthesize the independent lines from economics and information theory that arrive at the same structure, offering a normative assessment of when IIA is appropriate for agent design.

The problem of fair multi-agent coordination in decentralized settings is one of the most pressing challenges for building efficient collaborative systems. Resource allocation is based on optimized collective arrangements accounting for agents' needs. Such coordination should not only be computationally efficient but also account for fairness, i.e., equitable redistribution of costs incurred by all agents. Recent literature has proposed several algorithms that efficiently determine optimal plan combinations balancing system-wide efficiency and individual discomfort of agents in a centralized setting. However, these works do not address equitable resource optimization in fully decentralized scenarios, specifically, the optimized redistribution of discomfort among coordinating agents so that none experiences a discomfort level that could lead to loss of incentive or polarization that can disrupt planned operations. In this work, we study the problem of optimizing three objectives: (i) system-wide efficiency, (ii) individuals' comfort and (iii) fairness (i.e., balancing of incurred discomfort costs) in decentralized multi-agent coordination. We design a novel model to optimize those three orthogonal objectives, without any substantial increase in communication and computational overhead. Through experiments on two real-world datasets, we validate the model and demonstrate that it can achieve fairer optimization outcomes, while satisfying agents' preferences and system goals.

We model cryptographic auditing of off-chain data as a Constrained MDP (CMDP) under partial observability: the storage node's hidden type and corruption state make the problem a POMDP, while a miss-rate ceiling rho imposes an explicit security constraint. We propose DRQN-CMDP, a Deep Recurrent Q-Network whose GRU layer maintains a belief over the latent node type, paired with Lagrangian dual ascent that adapts the miss-rate penalty lambda automatically. A pairing-free homomorphic-MAC primitive supplies O(1) on-chain verification cost. Across 13 methods--four DQN variants, PPO, A2C, PPO-Lagrangian, a stateful Bayesian heuristic, three fixed-rule baselines, and an oracle-informed heuristic--DRQN-CMDP achieves a favourable balance: 83% lower gas than fixed high-frequency auditing, single-digit miss rate (7.5%), and moderate detection latency--a combination no other method matches across all three objectives simultaneously.

Long-horizon rollout generation has become the dominant systems bottleneck in agentic reinforcement learning (RL). As agents interact with environments over many turns, trajectories rapidly grow to tens of thousands of tokens, making synchronous RL training increasingly constrained by rollout. We propose WAR, a workload-aware rollout system that substantially accelerates synchronous agentic RL by jointly optimizing decoding and scheduling. WAR is built on a key observation: the optimal rollout optimization strategy depends on runtime load: (1) Under low load, WAR enables model-free speculative decoding with SuffixDecoding, which reuses suffix patterns from previously completed trajectories as speculative drafts for future rollouts. Unlike model-based drafters, SuffixDecoding introduces no additional draft model and avoids GPU contention with rollout generation. (2) Under high load, where saturated batched decoding leaves limited room for speculative speedup, WAR shifts the optimization focus to cache-aware scheduling. A global scheduler places requests across rollout replicas based on cache locality, trajectory progress and server load, reducing redundant KV-cache recomputation and mitigating load imbalance. By combining decoding-level suffix reuse with system-level rollout scheduling, WAR delivers robust throughput improvements across workload regimes without changing the underlying RL algorithm. WAR improves long-context agentic rollout throughput by 1.4x under low load and up to 1.6x under high load. These results show that WAR removes a major rollout bottleneck in synchronous agentic RL and provides a practical path toward scalable long-context agent training.

Deep research agents increasingly operate over the open web, where relevant records coexist with redundant summaries, outdated reports, and misleading documents. Existing evaluations offer limited insight into whether agents preserve sound evidential standards when an ordinary-looking false document is deliberately seeded into a searchable environment and offers a direct shortcut to a conflicting answer. We introduce DRNOISE, a 100-task benchmark for answer recovery under misleading evidence. Each task has a unique gold answer supported by two corroborating indirect record chains; the paired noisy condition adds one plausible document that states a conflicting answer directly. The benchmark spans ten families of evidence operations. Across agents with strong clean-task performance, this single intervention causes 66-88 percentage-point accuracy drops. Trace analyses identify verification inertia as the dominant failure mode: agents often retrieve truthful records but stop before completing and reconciling the evidence chain, instead deferring to the answer-like document. Generic verification prompts reduce but do not close this gap. The setting is especially relevant to open-web deployment, where plausible falsehoods arrive through ordinary-looking pages rather than explicit attacks. Reliable deep research therefore requires more than retrieval and citation; it requires active reconciliation of direct claims with record-level evidence.

In this work, we investigate the effect of lookahead branching strategies in neural network verification. We present a general recipe to integrate lookahead into any branch-and-bound verifier and demonstrate how one of the current state-of-the-art branching heuristics, FSB, can be viewed as a special instantiation of the lookahead branching strategy. We also describe how, in addition to improving the quality of branching decisions, lookahead can generate additional lemmas that accelerate verification. We instantiate the method in two representative branch-and-bound-based verifiers (Marabou and $α$-$β$-CROWN), and demonstrate that lookahead leads to consistent speedups in verification time and up to $57\%$ more solved instances. Code is available at https://github.com/ai-ar-research/lookahead-branching.

High quality temporal graph benchmarks with rich semantics and ground-truth anomaly labels are essential for training graph neural networks, yet remain scarce due to privacy constraints and annotation costs. We present SAGA (Synthetic Agentic Graph Architecture), a system for generating large-scale, semantically rich temporal graphs via a four-phase pipeline. Our Skeleton-First, Semantics-Second architecture decouples structure from semantics: (S) an O(1)-per-edge skeleton generator produces power-law graphs; (A) a dispatcher partitions causally ordered time blocks for parallel execution; (G) LLM agents inject domain semantics using RAG-based rule bases across four domains; and (A) a state alignment engine resolves conflicts via temporal replay, yielding anomaly labels as natural byproducts. Unlike structural generators (e.g., LDBC SNB, Kronecker/R-MAT) or purely LLM-based approaches, SAGA achieves structural realism, semantic richness, and automatic anomaly labeling in a unified framework. On a single H100 GPU with vLLM batching, SAGA generates 500,000 temporal edges with controlled anomalies in under 90 minutes, scaling to 100,000 nodes while maintaining clustering coefficients above 0.99. The system supports real-time pipeline visualization, interactive multi-domain tuning (Finance/AML, Network/IDS, Cyber/APT, Transportation), and a CLI for large-scale GPU-based experiments.

Issue localization, which identifies code locations requiring modification from issue descriptions, is a critical step in automated software maintenance. Existing approaches predominantly attempt to directly align issue descriptions with code elements, yet often struggle due to the inherent abstraction gap between the issue description and code implementation. Seeking alternative signals, our theoretical analysis suggests that test suites can serve as executable proxies for requirements, reducing localization uncertainty by 7.73 bits of entropy on average. A large-scale empirical study on 18 repositories validates this premise: existing tests cover 96.98\% of ground-truth files, and the two-hop pathway yields stronger semantic connectivity than direct matching in 82.4\% of cases. Despite their potential, leveraging tests for localization faces two key challenges: the semantic gap separating issue descriptions from test identifiers, and the substantial noise in execution traces from infrastructure code. To address these, we propose IssueExec, which bridges the semantic gap through domain-knowledge-enhanced test representations and filters noise via hierarchical trace analysis. Experiments on SWE-bench Lite show that IssueExec achieves state-of-the-art performance, improving function-level Recall@1 by 41.57\% over the strongest baseline. When integrated into the Agentless pipeline, IssueExec resolves 17.72\% more issues, demonstrating practical downstream benefits.

Single-stream autoregressive decoding of large language models is bound by memory bandwidth: each generated token requires one full forward pass through the target model, and successive passes cannot be parallelized. Speculative decoding restructures this computation: a small draft model proposes $K$ tokens autoregressively, the target model scores all of them in one batched pass, and a rejection-sampling rule provably preserves the target model's output distribution. We present a from-scratch, device-agnostic (CUDA/MPS/CPU) implementation and an empirical study across five draft/target backend configurations on a consumer Apple-silicon laptop. Distribution equivalence is verified at three levels, culminating in a two-sample test over roughly 9,200 real-model tokens per method ($χ^2 = 162.5$, dof $= 200$, $p = 0.976$) and exact greedy-sequence agreement. The best configuration reaches a measured $1.61\times$ wall-clock speedup at $K=6$, on an acceptance profile declining from 69.7% at $K=1$ to 37.8% at the optimum, while three of five configurations decelerate, either because the draft fails to out-speed a small target or because the quantized Metal backend executes "parallel" verification serially, an effect we isolate and quantify. The failures are as instructive as the successes: speculative decoding pays off only when verification is genuinely batch-parallel and the draft/target latency gap is real.

Given a binary-labeled linearly separable dataset, and the objective is to compute the maximum-margin separating hyperplane, also known as the hard-margin Support Vector Machine (SVM) classifier. This paper investigates whether, if given an initial separating hyperplane, can it be exploited to reach this unique optimum more efficiently. We present a geometric approach that gradually improves the alignment of the hyperplane, starting from an initial separating hyperplane, while preserving separation and continuously increasing its margin until convergence to the global optimum. At each iteration, the method considers only local information, namely the current active set, and aims to re-align the hyperplane according to the optimal separating hyperplane of this reduced subset. Consequently, the original convex quadratic optimization problem is addressed through a sequence of smaller subproblems. The paper presents the algorithm in detail, together with a preliminary experimental evaluation and several theoretical findings. The results suggest that, when an initial separating hyperplane is available, the proposed method can be competitive on larger datasets and, in some cases, can outperform state-of-the-art approaches that solve the optimization problem directly.

Auto-bidding plays an essential role in online advertising, automatically adjusting bids for advertisers to optimize their commercial goals. The emerging AI-Generated Bidding (AIGB) paradigm widely adopts generative modeling to optimize bidding strategies, yet suffers from the limited mode coverage of offline datasets and inadequate task-state understanding, hindering effective exploration of optimal strategies. Large Language Models (LLMs), with prior world knowledge and reasoning capabilities, offer a promising approach to overcome these limitations. However, directly applying LLMs to auto-bidding tasks faces inherent challenges in limited numerical precision, hallucinations, and inference latency. To address these limitations, we propose AIGB-R1, a hierarchical self-evolving auto-bidding framework aiming to enhance AI-Generated Bidding via LLMs' Reasoning capabilities, comprising a high-level Planner module for macro-level strategy planning and a low-level Executor module for fine-grained decision-making. Building upon this, we design an experience-driven self-evolving loop, enabling autonomous strategy exploration and optimization from accumulated experience. We adopt a two-stage pipeline of offline pre-training and post-training alignment, and build an interactive bidding simulation environment for strategy rollout. Furthermore, we propose Decoupled Group Relative Policy Optimization (D-GRPO) to achieve end-to-end optimization via advantage decoupling. Experimental results on a large-scale public dataset demonstrate the effectiveness of AIGB-R1.

Recently, text-to-video (T2V) models have been widely deployed, sparking growing concerns over their robustness against jailbreak attacks. Existing jailbreak methods, mostly adapted from text-to-image attacks, suffer notable drawbacks when applied to T2V systems. They fail to fully leverage temporal consistency, an inherent characteristic of video generation. Besides, these methods demand heavy video query optimization, which is infeasible in practical black-box scenarios. Their adversarial prompt search is also driven by heuristic local signals, lacking principled structured exploration strategies. To tackle these limitations, we propose BSB, a structured, query-efficient jailbreak framework for T2V models. BSB harnesses temporal consistency by encoding harmful intent as the transition between two individually harmless boundary states. Under this paradigm, the attack targets boundary-state pairs whose interpolation tends to produce unsafe intermediate frames during video generation. Directly evaluating all candidate pairs within the video space incurs prohibitive computation cost. Instead, BSB conducts Monte Carlo Tree Search (MCTS) in a cheaper textual proxy space and regularly calibrates search outcomes with sparse video-level evaluations. We conduct comprehensive experiments on mainstream commercial T2V models including Veo 3.1, Sora 2, Seedance and Kling v1. Results show BSB surpasses all existing jailbreak baselines, delivering an average 18.6% relative gain in attack success rate over the strongest competitor across evaluated models. Our findings identify temporal consistency as an understudied yet vital attack surface for T2V models and verify that structured search facilitates effective vulnerability discovery under constrained query budgets.

Node representation learning has advanced rapidly, yet most existing methods rely on per-dataset training and hyperparameter tuning. This dataset-specific optimization comes from the difficulty of designing reusable graph models that generalize across diverse graph datasets. In this work, we introduce Node4All, a node representation learner applicable to arbitrary graph datasets without any dataset-specific optimization. Node4All is built on two complementary ideas. At the architectural level, we introduce the Channel Graph Transformer (CGT), which enables a single fixed parameterization to process arbitrary graph datasets. At the learning level, we propose a self-supervised learning based on a series of synthetic graphs. Together, these components enable generalization beyond individual datasets, which is infeasible with existing architectures and learning frameworks. We extensively evaluate Node4All on node classification across 25 benchmarks against 21 baselines, covering both supervised and self-supervised methods. Despite all baselines being trained and optimized for each dataset, a single Node4All, applied uniformly across the datasets, achieves a competitive ranking of 5th among 21 baselines. Moreover, Node4All supports one-shot and in-context learning with an appropriate predictor and outperforms recent graph foundation models (GFMs) in these settings. These results demonstrate that Node4All not only achieves reusability across arbitrary graph datasets, but also remains an effective solution in practice. Code and model checkpoints are available in https://github.com/dooho00/node4all.

Safety evaluation of large language models is conducted predominantly in English and predominantly on frontier systems. Neither condition describes how such models are encountered in low-resource health settings, where small quantised systems are run locally and queried in local languages. We ask whether clinical safety established in English transfers to Hausa, and whether any failure is attributable to the language, the clinical task, or the class of model that low-resource deployment admits. Matched English-Hausa question pairs were built for three conditions of high burden in northern Nigeria: malaria, sickle cell disease, and tuberculosis, probing knowledge recall, emergency triage, a leading question inviting a contraindicated action, and a traditional-remedy claim. Six models were evaluated: five locally deployable systems of 4-9 billion parameters, two medically fine-tuned, and one frontier system. All 128 responses were scored against Nigerian national treatment guidelines by two fluent Hausa speakers working independently and blind to one another. Among locally deployable models, mean clinical correctness fell from 1.57 in English to -0.03 in Hausa, on a scale where 2 denotes a correct answer and -1 an actively harmful one. The frontier model moved from 2.00 to 1.75 and produced no response judged harmful in either language. Drift was consistent across all three conditions. Inter-rater agreement was substantial for clinical correctness (kappa = 0.70); agreement on harm was initially poor (kappa = 0.22) and is examined in detail. Because a frontier model answers the same questions competently in Hausa, the deficit is a property neither of the language nor of the clinical material, but of the deployable tier.

Large language models encode world models implicitly in neural weights, which exposes four structural risks in high-precision domains such as medicine and finance: hallucination, frozen knowledge, poor explainability, and poor modifiability. This paper proposes data-first ontology: LLMs are treated as reasoning and language engines, while deterministic knowledge is moved into an explicit multimodal database, DaoQL. We formalize an explicit world model and show that, under rule independence, deterministic evaluation, and fixed conflict resolution, explicit models provide a sufficient condition for composable counterfactual decomposability; implicit models lack atomic read/delta semantics and therefore provide no comparable architectural guarantee. The implemented system focuses on DaoQL's verified storage layer and explicit Eval path, integrating graph, column, vector, and full-text engines within one process. KVCache graph nodes, expert hot updates, and the DaoQL-Agent runtime remain future work. On an embedded same-machine setup, DaoQL reports graph BFS at 1.20 ms, HNSW at 83.1 us, and a Fluent hybrid query at 105.8 us; these results indicate engineering potential but must be interpreted with deployment-shape differences from client-server systems. Exploratory measurements on LDBC SNB SF1 and ANN-Benchmarks further show 34/34 query coverage with interactive-class queries mostly in the sub-millisecond to millisecond range, but only 1.8 QPS overall due to long-tail BI/IC queries; ANN-Benchmarks reaches Recall@10 >= 99% at thousand-level QPS after a bridge-edge protection fix. In a five-domain counterfactual experiment (n = 1250), DaoQL+GPT-4o achieves 94% composable counterfactual decomposability, 49 percentage points above GPT-4o alone. The paper explicitly separates provable structure, preliminary empirical evidence, and architectural roadmap claims.

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) have been utilized to enhance LLM reasoning. Nevertheless, KGs often contain noise and errors, while existing KG-enhanced LLM approaches are generally unable to identify and filter such noisy and erroneous content, which can instead amplify hallucinations and pose challenges for reliable reasoning. Uncertain knowledge graphs (UKGs), which associate each triple with a confidence score to quantify uncertainty, offer a promising direction to address this challenge. Compared with prior work, we investigate how to leverage UKGs to support LLMs for QA. We propose Debate-on-Graph (DoG), a new framework that enables LLMs and UKGs to collaborate adaptively for reliable reasoning. Specifically, we first design a heuristic search algorithm tailored for UKGs to extract reliable and question-relevant subgraphs, thereby reducing noise and errors in retrieved knowledge. We then introduce a Multi-Agent Debate mechanism, which yields reliable answers through adaptive adversarial debates, aiming to fully exploit the knowledge in UKGs while preserving the reliability of retrieved evidence. Extensive experiments on four benchmark QA datasets show that DoG achieves state-of-the-art performance over existing LLM reasoning methods and KG-based baselines, while enabling reliable and adaptive reasoning. Our code is available at https://github.com/seucoin/Debate-on-Graph.

Disentangled representation learning is a powerful paradigm for robust attribute prediction. While recent methods address attribute correlations, hidden correlations remain underexplored, where data under the value of a certain attribute exhibit underlying modes correlated with other attributes. To preserve mode information and achieve disentanglement, we jointly discover modes and enforce mode-based conditional independence. Yet, the interdependency between these two modules may lead to error amplification under naive iterations. We propose Coordinated Disentanglement with Iterative mode Discovery (CoDID), an end-to-end framework featuring a dynamic architecture that adapts to evolving number of modes, and a coordination mechanism that mitigates error amplification via meta-optimization. Empirical results demonstrate the state-of-the-art performance on diverse tasks.

Existing methods for multimodal sentiment analysis (MSA) under missing modalities usually follow a repair-first paradigm. We revisit this assumption and ask: \emph{should every missing modality be repaired?} A per-sample oracle analysis shows the answer is not always: full-modality input is optimal for only a small fraction of samples, and every modality subset is preferred by some samples. These results suggest that adding or repairing modalities may not always improve prediction, and that the utility of each modality is sample-dependent. Building on this finding, we propose \textbf{S}ufficiency-\textbf{I}nformed \textbf{E}vidential \textbf{V}al\textbf{vE} (\textbf{SIEVE}) that turns ``whether to repair'' into an explicit, learnable decision at the sample level. SIEVE compares a direct prediction branch with a repair branch, derives an empirical sufficiency signal from their per-sample loss gap, and routes each input through an evidential gate that jointly models sufficiency and its epistemic uncertainty. SIEVE is repair-agnostic: it operates as a plug-and-play decision on top of any explicit or implicit repair module, without modifying its internal design. Experiments on CMU-MOSI and IEMOCAP show that SIEVE consistently improves representative repair backbones across evaluated missing rates, and approaches the per-sample dual-branch achievable optimum.

Diffusion policies have shown strong potential for robotic imitation learning, and recent extensions incorporate additional modalities to improve manipulation performance. However, these modalities often differ not only in information content but also in sensing rates and inference latencies. Existing multimodal diffusion policies typically rely on synchronous fusion or manually designed multi-frequency architectures, which either slow down high-frequency feedback or limit extensibility to new modality combinations. We propose LAG-Fusion, a latency-aware guidance fusion framework for asynchronous multimodal diffusion policy composition. LAG-Fusion allows modality-specific policies to operate at their native inference rates and contribute denoising guidance whenever available. To make asynchronous composition consistent, we derive a reference-frame rebasing rule for diffusion variables under relative action representations, enabling delayed guidance to be aligned before fusion. We instantiate LAG-Fusion in contact-rich manipulation by composing a low-frequency vision policy with a high-frequency force policy. Experiments under heterogeneous modality latencies show that LAG-Fusion improves policy responsiveness and task performance over synchronous fusion and specially designed force-aware baselines.

This paper introduces EvolvingWorld, a framework and benchmark for character and world co-evolution in interactive literary worlds. Existing systems either treat interactive literary simulation as static persona imitation or isolated scene generation, failing to capture how characters and worlds evolve together over time. To address this, EvolvingWorld models literary simulation as a long-horizon process where characters interact, scenes progress, and character and world states are persistently updated. Unlike prior systems relying on fixed schemas, EvolvingWorld adopts an open-schema framework to support simulation across diverse literary worlds. The framework consists of two coupled modules: a Character Agent for multi-character role-play and persistent profile evolution, and an LLM-based World Model for global and location/entity-level state maintenance and scene progression. Based on this architecture, we formulate 7 trainable tasks for scene initialization, interaction generation, and state update. We construct a dataset from 57 books, producing 138,596 supervised training samples and 222 snapshots for testing. Furthermore, we introduce a trajectory-level LLM-as-Judge evaluation protocol spanning 10 dimensions and 20 metrics. Experiments show that EvolvingWorld can improve long-horizon simulation by effectively maintaining persistent, coherent character and world development.

Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new knowledge, while substantially different teachers often yield ineffective guidance, largely restricting OPD to within-family distillation. We propose Distilled Reinforcement Learning (Distilled RL), which integrates teacher supervision into the RL objective to provide fine-grained guidance, selectively transfer new knowledge and avoid unconditional imitation. Distilled RL contains three components: reverse importance sampling with clipping, negative sample reset, and sequence-level geometric normalization. Through a concise and interpretable case study, we demonstrate that Distilled RL can effectively transfer previously unavailable knowledge from a teacher model to a student model. Extensive experiments across both within-family and cross-family distillation settings show that Distilled RL substantially outperforms standard RL and OPD in terms of both pass@1 and pass@k. Our code is available at https://github.com/597358816/Distilled-RL.

Longitudinal T cell receptor repertoires contain signals of clonal expansion, contraction, disappearance, and reappearance after immune perturbation. Static repertoire language models usually summarize a sample as a bag of sequences, so the sampling interval, sequencing depth, and clone presence pattern are only weakly represented. This paper presents DynImmune-BERT, a continuous time repertoire model for patient level immune status prediction. The method combines depth adaptive centered log ratio initialization, clone presence gated Neural ordinary differential equation dynamics, bounded neighborhood self attention, event based state restart, and a hybrid transport objective that supervises dominant and rare clone mass. A low rank meta adapter initializes reappearing clonotypes while keeping the parameter count independent of the number of observed clones. The evaluation separates literature reported baselines from internally controlled temporal comparisons, reports uncertainty for small external cohorts, adds calibration and threshold diagnostics, and visualizes latent clone trajectories and attention neighborhoods. The results indicate that event aware temporal modeling can complement strong static encoders when longitudinal repertoire structure is available, while small external cohorts and protocol differences require cautious interpretation.

Multi-view spatial reasoning requires vision-language models to compare visual evidence across images, align object correspondences, and infer spatial relations over long visual contexts, a setting where chain-of-thought reasoning tends to grow verbose without becoming more accurate. Reinforcement learning with verifiable rewards is a natural fit for this task, but standard GRPO reward relies on sparse outcome-level feedback and gives no signal about where a reasoning trajectory goes wrong, nor any control over its length. We propose LenGuard-GPC, a dense reward framework that addresses both problems together. For each sampled trajectory, it compares the token-wise predictive distributions under a standard prompt and a guided prompt, and uses the resulting token-sum KL divergence as a dense reward signal. Since this KL penalty accumulates over tokens and would otherwise reward shorter responses regardless of their quality, we introduce a staged length bonus that keeps reasoning length within a controlled range without simply encouraging brevity. On six multi-view spatial reasoning benchmarks, LenGuard-GPC improves accuracy over vanilla GRPO while reducing average response length.

Pretrained machine learning (ML) models help developers build ML-intensive software systems without training models from scratch. However, model repositories often provide incomplete machine-readable documentation about model provenance, licenses, datasets, limitations, and external references, creating transparency and governance gaps across the AI supply chain. Artificial Intelligence Bills of Materials (AIBOMs) address these gaps by documenting AI artifacts, including models, metadata, licenses, datasets, model-card information, and external references. Taking public Hugging Face (HF) model repositories as a case study, this paper empirically investigates AIBOM completeness, defined as the extent to which repositories provide AIBOM-relevant information for machine-readable AI supply-chain documentation. We examine approximately 97.5K AIBOM artifacts to assess the extent to which generated AIBOMs: (i) contain required structural and metadata fields, (ii) represent model identity, license, and external-reference information, (iii) capture model-card documentation such as datasets, limitations, safety-risk assessment, and environmental information, and (iv) vary in documentation coverage across repository and artifact characteristics such as task, license availability, dataset declaration, model family, and paper reference. Results indicate that generated AIBOMs provide complete coverage of required AIBOM structure but limited AI-specific documentation completeness. Required fields are fully represented, but model-card, metadata, responsible-use, environmental, limitation, and meaningful-description fields remain weakly represented or missing across generated artifacts. Our findings motivate improved model-card practices, repository-level traceability, and automated AIBOM validation to advance the generation and adoption of more complete AIBOMs.

When does a committed intermediate stage in an LLM reasoning pipeline earn its cost? Constrained Path Reasoning (CPR) pairs a source-aware path hypothesis with stage-level accounting. Search generates provisional states; trusted or validated invariants can constrain hard, while other proposals remain soft and revisable. CPR predicts that task-compatible commitments can factor transitions, concentrate candidate mass, induce regularity, and expose feedback when their gains exceed propagated error and execution cost. The formalism covers discrete commitments and continuous flows and measures effective branching, endpoint concentration, and cost per usable output. Across 1,180 generated QCQPs and 40 engineered degenerate polynomial instances (2,140 endpoints), residual triage recovers 63.0% of repair-all's additional feasible yield with 17.7% of its attempts. Fixed-LLM accounting (270 unique calls shared across nested arms) finds usable yield of 41.1% direct, 90.0% after formalization and deterministic execution, 20.0% after one-shot convexification, and 21.1% for the full path. In 120 paired-condition calls, a two-action rollback rule reaches 90% usable yield versus 36.7% for the feedback-conditioned selector. Two endpoint probes separate source from validation: a 72-output cross-trajectory transplant reduces entropy and acceptable mass; a 24-output same-call self-proposal pilot gives unchanged two-repeat collision entropy, 25.0% versus 8.3% usable yield, and 1/8 deterministically confirmed endpoint checks. Model-generated states supply hypotheses; trusted execution earns constraint strength.

AI_LectureNote is a historical, readability-oriented post-ASR workflow for Korean-English medical lectures. It rewrites speech-to-text output into study transcripts while restoring Latin-script medical terms rather than Korean phonetic transliterations. We retrospectively evaluate the workflow on four author-recorded lectures across five conditions. In this pilot, post-processing raised the macro English-script rendering rate from 0.39 to 0.71 on the whisper-1 path and from 0.26 to 0.65 when applied to 3-minute chunked gpt-4o-transcribe output. However, English-script rendering did not imply semantic faithfulness: the two post-processed conditions showed semantic drift in 34 and 36 of 282 reference sentences and polarity failures in 11 and 13 of 101 polarity-cue rows. A descriptive cross-input comparison suggested different candidate failure patterns: polarity-failure sets overlapped more strongly across front-ends (Jaccard 0.60; 9 shared of 15 unioned failures) than general semantic-drift sets (Jaccard 0.23; 13 shared of 57 unioned drifts). This single-annotator pilot documents concrete failure modes rather than population rates and supports evaluating surface accuracy, term-script rendering, chunk-level script consistency, and medical-meaning preservation separately.

This work titled "RFID Based Campuswide Payment System" introduces an innovative cashless payment solution for educational institutions. It uses RFID cards and a Raspberry Pi to enable hassle free payments for various campus services, such as cafeteria purchases, tuition fees, and library fines. A centralized database ensures real-time updates on transactions and account balances, accessible through a simple and user-friendly web interface. This work is involved in designing a secure system with object-oriented principles, setting up databases, and integrating hardware like RFID readers with a Raspberry Pi. The systems are proved to be a cost-effective and efficient alternative to traditional payment methods, enhancing convenience and security for students and administrators. The study also explored similar RFID applications, like smart parking and attendance systems, to identify challenges and improvements. Looking ahead, it envisions features like wearable RFID devices, voice-activated payments, and blockchain integration to boost security and usability. Results show that this system simplifies campus payments and has the potential for broader adoption in similar environments.

Classical rate-distortion (RD) theory has long established the fundamental limits of lossy compression by quantifying the minimum number of bits required to represent a source under a prescribed distortion constraint. However, widely used distortion measures such as mean-squared error often fail to capture perceptual quality or semantic validity, which are increasingly central in modern learning-driven applications. Rate-distortion-perception (RDP) theory extends the RD framework by introducing perception as a third fundamental axis, quantified via distributional similarity between the source and reconstructed signals, leading to the rate-distortion-perception function (RDPF). This tutorial provides a structured overview of the coding principles underlying perception-aware lossy compression and surveys recent achievability results under different randomness assumptions. It then presents a unifying optimization viewpoint for computing the RDPF as defined by Blau and Michaeli, for both discrete and continuous sources under broad families of perceptual constraints, including f-divergences, alpha-divergences, and Wasserstein-based metrics. Special attention is given to computational tools such as alternating minimization schemes, Newton-based methods, and convex optimization formulations, as well as to analytically tractable cases such as Gaussian sources and the perfect-realism regime. Unlike recent broad surveys that emphasize generative architectures and AI-empowered communication systems, this tutorial focuses on the coding-theoretic and computational machinery needed to characterize, compute, and interpret the RDP limits. Finally, the tutorial outlines promising research directions at the intersection of information theory, neural compression, robust source coding, and perception-aware networked control systems.

This paper describes TalTech's submissions to the Beyond Transcription Challenge (BeTraC), which requires generating SOAP notes directly from long doctor-patient conversation recordings, without intermediate transcription. After screening open-weight speech LLMs for long-audio robustness, we adapted Voxtral Mini (lightweight track) and Voxtral Small (heavyweight track) with LoRA supervised fine-tuning followed by DAPO reinforcement learning that uses the challenge metric, Open Medical Concept F1, as its reward. Our systems ranked first in both tracks, and an independent LLM-as-a-judge evaluation showed the lowest hallucination rate among all submissions, indicating that reinforcement learning against a concept-matching metric need not compromise factual reliability. We also find that fine-tuning on text transcripts transfers well to speech input and appears to improve robustness on out-of-domain real recordings.

Prior work on LLM-generated text has demonstrated quantitative and qualitative departures from text produced by humans. LLM-generated texts differ from human writing in style, resulting in a characteristic textual "feel," while the semantic range of LLMs is much restricted compared to that of humans. In this contribution, I note simple but consistent patterns in the statistical distribution of n-grams within LLM-generated text. Via qualitative analysis of these n-grams, I reveal deficiencies in LLM style. Because higher-order n-grams correlate to semantic content, I conclude that questions of style and semantics are not cleanly separable.

Agentic AI systems do not just predict or recommend; they plan, maintain state, and act in external environments with varying degrees of autonomy. This changes the requirements engineering problem in a specific and under-addressed way: it introduces what we call the delegated-autonomy boundary -- the set of decisions about what may be delegated to the system, under what graduated authority, with what oversight, and how control is returned. Current practices bury these decisions inside prompts, tool schemas, and runtime policies, even though they are requirements-level commitments. This paper proposes two complementary artifacts. First, an Agency Justification Record (AJR) helps teams decide when an agent is warranted over simpler alternatives. Second, an Agentic Delegation Policy (ADP) captures what must be specified for safe and effective development: purpose, authority, information, coordination, assurance, and evolution. Crucially, authority in the ADP is modelled as graduated, i.e., a tiered structure. We illustrate the framework with two contrasting examples: a safety-critical hospital discharge coordination agent and an automated code review agent.

Human survey respondents exhibit question-order effects that satisfy the QQ (quantum question) equality, an a priori, parameter-free prediction of the projective quantum question-order model. We develop the QQ equality into an audit criterion for sequential judgments of autoregressive large language models (LLMs). Theoretically, we characterize which mechanism classes satisfy it robustly: marginal-independent kernels satisfy QQ iff all four mismatch transition rates coincide (a class containing the 2D rank-1 projective model with a fixed measurement pair under state variation); a polarity- and position-dependent repetition family is characterized by an exact cross-symmetry condition with closed-form violations; QQ-satisfying behaviors are closed under order-matched mixing; and the rank-2 Contextuality-by-Default criterion translates into audit coordinates as $|\qQQ|\le\OSS$, where $\OSS$ (the order-sensitivity score) totals the order sensitivity of the two marginals. Methodologically, we develop a pre-specified, audit-logged pipeline applicable to any model exposing next-token log-probabilities; it combines worst-case robustness envelopes, sampling-consistency spot checks, full label counterbalancing, and a saturation diagnostic. Empirically, in a first-signal pilot on an open-weight instruction-tuned model under two framings, all pre-specified health gates passed, yet 17/18 and 7/8 item pairs, respectively, were saturated (near-deterministic), and no item was certified residually contextual. Forced-binary next-token log-probabilities were thus inadequate for distribution-level QQ audits under the tested model and prompting conditions; we recommend pre-specified saturation diagnostics whenever next-token distributions are treated as survey-response distributions.

Replacing hand-written code with library API calls is a common refactoring that can reduce code size, make code more idiomatic, and reuse well-tested implementations. Yet many library-adoption opportunities are hard to find automatically: the original code often does not mention the target library and may resemble the library API only in behavior, with little syntactic overlap. Existing tools, such as linters and static modernizers, cover only a small set of manually specified patterns. LLMs and LLM-based agents, on the other hand, can generalize to more patterns, but they are costly, difficult to reproduce and to apply systematically at scale. This paper introduces Prefactory, an automated approach for library-adoption refactoring in Python. The key idea is to use an LLM to synthesize executable search heuristics rather than relying on repeated LLM prompting over a codebase. Given a target project and a target library name, Prefactory collects library metadata and project vocabulary, then generates lexical and structural detectors. Prefactory executes the detectors during a scan phase to find candidate functions. It then heuristically ranks the candidate functions, generates refactorings for the highest-ranked ones using an LLM, and validates the results with project tests and newly generated differential tests. We evaluate Prefactory on PrefactoryBench, a benchmark of 100 real-world library-adoption refactorings from 61 open-source Python projects and 18 libraries. Prefactory detects 75 instances at the file level and 56 at the function level, compared with 35 and 32 for the strongest baseline (Codex CLI). From the 56 detected functions, Prefactory produces 40 test-validated refactorings.

Supervised fine-tuning (SFT) of open-weight LLMs on expert agent trajectories has emerged as a prominent approach to building capable code agents without reliance on proprietary models. A central yet underexplored question is how trajectory quality and quantity jointly shape model performance. We present a systematic empirical study of trajectory data filtering for LoRA fine-tuning of Qwen2.5-Coder-7B-Instruct on the SWE-trajectory dataset (67,074 trajectories, of which 32,161 are resolved). We propose a two-axis quality scoring framework -- Efficiency and Style -- and evaluate it through 16 controlled experiments spanning strategy, scale, and ablation analyses. Since 7B-scale models attain near-zero SWE-bench resolve rates, we adopt cross-entropy (CE) loss on held-out trajectories as the primary metric, validated via first-action generation: CE loss and ROUGE-L are perfectly rank-correlated (Spearman $ρ$ = -1.00), with limited-sample evidence supporting but not conclusively establishing this proxy. Our results reveal a scale-dependent quality-quantity trade-off: at small scales, doubling the dataset (500 to 1,000) yields ~12.7% CE-loss reduction whereas the TopQ-Random gap stays <1% (Mann-Whitney p > 0.10); at 2,000 trajectories this same gap widens to 3.6% (p = 0.016). Ablation further identifies error-retry rate as the dominant sub-dimension, performing comparably to the full composite ($Δ$ < 0.2%). Together, these findings establish trajectory-level quality scoring as a viable but scale-sensitive lever for code-agent SFT and offer a proxy-validated evaluation protocol for the regime where end-to-end resolve rate is statistically infeasible.

In this work we study the Best Policy Identification (BPI) problem in online, tabular Reinforcement Learning. This is an active sequential hypothesis testing problem in which the learner's objective is to identify an optimal policy in a Markov Decision Process (MDP) with high confidence, while minimizing the expected sample complexity to do so. We consider an online setting with deterministic rewards, where the agent must strategically navigate through the MDP in order to effectively explore. Previous works in the literature have provided asymptotically optimal methods for BPI, such as the Navigate and Stop (NaS) algorithm and its variants, however existing analysis remains asymptotic. In this work, we fill that gap by providing the first non-asymptotic sample complexity guarantees for NaS, showing that its sample complexity depends not only on the characteristic time, but also on the connectivity of the underlying MDP, the curvature of the optimal characteristic time, and other instance-dependent quantities. We identify these additional attributes and make explicit their contributions to the overall sample complexity.

Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc. We present AnthroDial, a closed-loop framework that formulates anthropomorphic dialogue as a joint problem of system architecture, executable evaluation, and diagnostic alignment. It combines (1) a role-conditioned scheduled dialogue runtime with persona and scenario cards, long-term memory, virtual time, and single-draft message decisions; (2) an executable benchmark with an L0 validity gate, five per-turn dimensions, and five dialogue-level dimensions; and (3) a post-training pipeline that filters 16,436 scheduled-decision examples for SFT and applies GRPO with a cognitive-diagnostic, ZPD-aware reward. The reward maintains Kalman-filtered capability estimates for each behavioral dimension, upweights dimensions with larger capability deficits, and uses rollout scores as task-level ZPD matches to focus optimization on learnable weak skills. On a benchmark with 55 personas, 50 scenarios, 50 persona-scenario bindings, and 100 role-conditioned cases per model, we evaluate 16 systems spanning frontier baselines, open models, thinking/no-think variants, and SFT/RL ablations. The strongest non-trained baseline reaches 32.00% strict ACC, while Qwen3.6-27B-SFT+RL reaches 39.00% strict ACC and a 98.5 overall score. In the 9B no-think setting, SFT and RL improve strict ACC from 0.00% to 13.00% and 18.37%. These results show that anthropomorphic dialogue benefits when generation, evaluation, and reward shaping share the same behavioral dimensions.

Test-time scaling empowers Large Reasoning Models (LRMs) to tackle complex tasks via extensive Chain-of-Thought (CoT). However, this often induces the "overthinking" paradox, where redundant reasoning increases computational overhead without guaranteeing accuracy. Existing test-time efficiency optimization methods primarily fall into two categories: information-theoretic approaches, which are prone to "deceptive convergence" where low uncertainty masks hallucinations, and latent representation analyses, which are often post-hoc, lacking the real-time sensitivity for dynamic reasoning. To bridge this gap, we first posit the Phase-Momentum Alignment Hypothesis, asserting that reasoning correctness hinges on the temporal synchronization between geometric momentum and uncertainty resolution. We then theoretically formulate the Cognitive-Energy Model to characterize these dynamics through two orthogonal dimensions: Geometric Cognitive Effort, quantified by latent velocity and tortuosity, and Entropic Cognitive Uncertainty. To operationalize this, we introduce PUMA (Phase-Uncertainty Momentum Alignment), a training-free framework employing a tiered diagnostic architecture. By coupling lightweight phase monitoring with event-triggered geometric analysis, PUMA effectively distinguishes active exploration from passive stagnation, enabling precise interventions through adaptive truncation or corrective measures. Extensive experiments on LRMs spanning 1.5B to 32B demonstrate that PUMA consistently outperforms state-of-the-art baselines across diverse benchmarks, achieving a superior accuracy-efficiency trade-off and robust cross-domain generalization.

Serverless multi-model LLM systems multiplex popularity-skewed model catalogs over shared GPU pools, yet typically schedule each request independently. Tool-using agents break this abstraction: a session repeatedly calls an LLM across short tool gaps, carries a long reusable KV prefix, and is judged by session completion time (SCT). Load-only routing can separate a continuation from both its model and KV state, while round-based model multiplexing can delay even a correctly placed continuation until the target model's next slot. Both failures are especially costly for hundred-billion-parameter models: their weights constrain residency, while long-context KV is expensive to reconstruct or move. We present Talaria, a session-aware serverless multi-model serving system that makes session continuity a joint placement-and-admission decision. Its router ranks placements by model residency, KV locality, and instance pressure, while soft reservations account for likely returns in the last serving instance's admission budget. Session-prefill (SP) admits budget-eligible continuations before the active model slot closes. An instance-local substrate keeps HBM addresses stable, preserves host-restorable KV, and stages weights across model switches. On a single TP=8 server, we replay 30 SWE-Bench model-sessions (960 calls) over three models, each with more than 100B total parameters. Against an otherwise identical round scheduler with SP, host-KV restoration, and D2D staging disabled, Talaria cuts p50 SCT from 1000 s to 189 s and p95 from 2296 s to 867 s, speedups of 5.3x and 2.6x.

Imbalanced learning addresses predictive modeling problems with underrepresented regions of the data distribution. Although widely studied in classification, imbalanced regression remains challenging because of continuous target variables and heterogeneous density distributions. Existing data-level methods often rely on fixed target partitioning or synthetic sample generation without jointly considering density variations and local feature-space structure. We propose DADIR, a Density-Aware Data-level Imbalanced Regression framework that exploits density information throughout the balancing process. DADIR comprises three components: (1) Density-Aware Adaptive Partitioning (DAAP), which recursively partitions the target space according to density variations; (2) a Density-Regularized Conditional Variational Autoencoder (DR-CVAE), which preserves sparse-region representations while learning latent features; and (3) latent-space data balancing, which combines feature-level clustering with oversampling to generate structurally consistent synthetic samples. Together, these components identify minority regions more effectively, preserve sparse-region information, and generate realistic synthetic data. The resulting balanced dataset can be used directly with existing regression models without modifying their architecture or learning objective. Experiments on diverse imbalanced regression datasets demonstrate consistent improvements in predictive performance, particularly in underrepresented regions, while also improving overall accuracy.

Evaluating large language models (LLMs) across languages remains challenging, as most multilingual benchmarks rely on translated English datasets, often obscuring linguistic and cultural specificity in the target language. This issue is particularly pronounced for less-resourced languages such as Kyrgyz, where reliable natively authored evaluation data are scarce. Building on previously introduced Kyrgyz-language evaluation datasets, this work reports the first systematic and large-scale evaluation of LLMs in Kyrgyz using the KyrgyzLLM-Bench benchmark suite. KyrgyzLLM-Bench comprises two natively authored datasets$-$KyrgyzMMLU and KyrgyzRC$-$together with carefully translated and manually post-edited versions of WinoGrande, HellaSwag, BoolQ, and TruthfulQA. We evaluate 26 open- and closed-source LLMs under zero-shot and few-shot settings, analyzing model performance, cross-lingual transfer, and the impact of translation artifacts on evaluation reliability. Across families and tasks, model rankings transfer broadly from English to Kyrgyz on WinoGrande and BoolQ, and to a lesser extent on MMLU, while HellaSwag exhibits a substantial English-Kyrgyz performance gap consistent with translation-induced plausibility shifts. Few-shot prompting improves several open-source models on reading comprehension but behaves inconsistently for proprietary models on translated tasks. We publicly release all datasets, evaluation code, and per-model results, and integrate the Kyrgyz tasks into a widely used multilingual evaluation framework to support future research on Kyrgyz NLP.

Transformer-based large language models (LLMs) continue to achieve state-of-the-art performance across various natural language processing tasks. However, their subpar performance on seemingly elementary problems, such as basic arithmetic, raises concerns about model reliability, safety, and ethical deployment. In this study, we demonstrate that the performance of a vanilla Transformer model trained on integer arithmetic tasks can be improved using methods effective for human learners. We begin by decomposing the arithmetic task into well-defined subtasks and conducting loss convergence order analysis together with ablation studies for each subtask. Our findings reveal that LLMs exhibit learning patterns similar to those of human learners, with a faster learning speed for simpler subtasks compared to more complex ones. In addition, we successfully improved the accuracy of LLMs by applying problem-solving strategies and cognitive empowerment methods shown to enhance the performance of human learners. This suggests that transformer-based LLMs may share cognitive processes with human learners in arithmetic. Lastly, we provide a comprehensive demonstration of our method's effectiveness, including significant accuracy improvement experiments, visualization verification, and explanation-based analysis to illuminate the intricacies of LLMs in arithmetic learning. In general, this work explores the potential similarities between transformer-based LLMs and human learners, supported by explainable AI (XAI) verifications, ultimately fostering trust in LLMs for critical and high-stakes applications.

Developing Automatic Speech Recognition (ASR) for morphologically rich, low-resource languages such as Assamese is challenging due to insufficient annotated speech data. The pretrained Whisper model performs poorly on Assamese speech recognition tasks. This paper presents a controlled, fine-tuned Whisper-based Assamese ASR system trained on the Mozilla Common Voice 24.0-Assamese corpus. A hardware-aware optimized training pipeline is implemented for resource-constrained environments, employing mixed-precision training and gradient accumulation on Tesla 4 Graphics Processing Units (T4 GPUs). The proposed fine-tuned model significantly outperformed the Zero-shot baseline, yielding Word Error Rate (WER), Character Error Rate (CER), Match Error Rate (MER), and Word Infomation Loss (WIL) of 43.17\%, 13.18\%, 43\%, and 64.81\%, respectively, achieving significant relative improvements of 78.26\%, 93.10\%, 57.0\%, and 35.19\% over the baseline. Semantic evaluation of the fine-tuned model also demonstrates notable improvement over a zero baseline, attaining Bilingual Evaluation Understudy (BLEU) and Metric for Evaluation of Translation with Explicit ORdering (METEOR) scores of 30.81 and 0.5262, respectively. Additionally, the predicted hallucination rate and Real-Time Factor (RTF) are substantially improved by 96.70\% and 32.38\%, compared to the zero-shot baseline.

Multi-object tracking (MOT) aims to localize multiple objects in videos while preserving their identities over time. Long-term identity preservation remains difficult when objects are small, densely distributed, and highly similar in appearance, as in bee swarm scenes. Existing trackers rely on re-identification (re-ID) models trained through single-instance assignment (instance-level querying). At inference, however, MOT requires global assignment between multiple trajectories and detections, corresponding to video-level querying. This training-inference mismatch can cause identity switches among visually similar objects. Existing approaches also often require substantial additional annotations to enhance appearance discrimination. We propose Video-Level Association re-ID (VLA-ReID), which reformulates re-ID as video-level association modeling. It uses aggregated historical trajectory features as queries and all current-frame detections as candidates, enabling direct optimization of their global association at each frame. In addition, Frame-Common Appearance Estimation (FCAE) estimates a common appearance direction from current-frame detections, while Common-Appearance Suppression (CAS) removes the corresponding component along this direction from trajectory and detection features. This amplifies discriminative differences among highly similar objects without additional annotations. Experiments on BEE24 show that VLA-ReID improves HOTA by 1.1, MOTA by 0.3, AssR by 2.6, AssA by 0.7, and IDF1 by 0.8 over state-of-the-art trackers, while reducing identity switches by 28%. These results demonstrate the effectiveness of video-level re-ID modeling for appearance-based association in MOT.

Although mixture-of-experts, MoE, models have been increasingly adopted to scale large language models with moderate computation cost, it remains challenging to deploy MoE inference over resource-constrained and bandwidth-limited edge infrastructures. Existing distributed MoE serving methods mainly rely on exact expert placement, caching, replication, or communication scheduling, while overlooking the functional similarity among experts, which provides an opportunity to reduce cross-server token transmission. Therefore, this paper introduces a similarity-aware expert allocation and distributed deployment framework, dubbed OrderMoE, which aims to accelerate edge MoE inference while balancing inference latency, communication overhead, server workload, and inference quality. OrderMoE first constructs an expert similarity model based on router-induced logits representations and partitions experts in each MoE layer into multiple similarity groups. Then, it develops a similarity-aware expert grouping and deployment strategy to improve local similarity coverage across edge servers. Since reducing remote expert invocation and preserving exact inference quality are conflicting objectives, OrderMoE further designs a quality-aware and trajectory-aware runtime server-expert selection algorithm to decide whether a token should invoke its remote target expert or use a feasible local substitute expert. Experimental results on a real distributed edge testbed show that OrderMoE significantly reduces average latency, tail latency, cross-server traffic, and remote expert invocation ratio, while introducing only small and controllable inference quality degradation.

Jailbreak attacks on large language models are usually evaluated by attacker-centric metrics such as attack success rate (ASR), yet an attack that breaks a model is not necessarily useful for improving its safety. We propose a defender-centric view of jailbreak evaluation, where attacks are evaluated by the downstream safety improvements they enable when used as red-teaming data for safety training. Building on this view, we introduce A-MESS (Minimal Effective Attack-Subset Selection), a setting-agnostic framework for attributing and selecting jailbreak attacks from black-box subset utility observations. A-MESS estimates AttackSHAP, a Shapley-based score that attributes marginal utility to individual attacks and selects compact attack subsets under user-specified budgets via greedy or surrogate-based optimization. Across controlled utility landscapes and real LLM safety settings, we find that ASR rankings are weakly aligned with defender-centric utility, that AttackSHAP can be estimated accurately with limited utility queries, and that directly optimizing subsets yields stronger safety utility than attacker-centric or attribution-only selection. These results suggest evaluating jailbreak attacks as resources for improving safety, not only as tools for breaking models.

AI agents increasingly act within the same clinical, political, scientific, and social systems that behavioral scientists study. Evaluating these systems requires source-level diagnosis: the same behavioral pattern may arise from an agent representational substrate or from the roles, objectives, interaction structures, and governance rules that shape its expression. This Perspective proposes a diagnostic framework for AI agent behavior: layer attribution. The foundational computational layer defines what behaviors are possible through architecture, memory, perception, attention, and representation. The behavioral modulation layer shapes how those capacities are expressed through identity, resources, objectives, social interaction, institutional constraints, and governance. The framework clarifies three consequences: surrogate validity is a model-task-layer relation, human-AI divergence provides diagnostic evidence, and governance requires source attribution before intervention. Treating AI agents as behavioral actors therefore requires evaluation methods that determine where behavior originates before deciding how to explain, validate, or govern it.

Infrared small target detection (IRSTD) commonly relies on pixel-level mask supervision. Such annotations, however, are costly and inherently uncertain because infrared targets have blurred boundaries and weak textures. We formulate box-supervised IRSTD as a problem distinct from generic box-to-mask segmentation and point-supervised IRSTD. Its central challenge is to construct stable pixel-level soft supervision from highly contaminated boxes. To this end, we propose Hotspot-Anchored Label Optimization (HALO). HALO localizes a radiometric anchor inside each box under local background-statistics constraints, then synthesizes a Physically Anchored Gaussian (PAG) soft label around the anchor. This turns noisy box supervision into continuous, pixel-level soft labels. The entire process is performed offline before training, remains decoupled from the detector backbone, and requires no online label updates. Experiments on public datasets show that HALO is competitive with representative box-supervised methods under standard tight boxes. Under looser or shifted box annotations that better approximate real scenarios, HALO is substantially more robust while remaining consistent across backbones. We further introduce a contamination-aware operating-regime analysis to characterize the effective boundary of this class of methods and reveal how intrinsic signal-to-clutter ratio relates to performance.

LLM agents can leak privacy (e.g., paths, emails) and credentials (e.g., API keys) as agent observations (e.g., tool outputs, shell logs, and file reads) are appended to provider-bound transcripts. Existing placeholder redaction is brittle: it can miss embedded or cross-turn references, over-redact benign lookalikes, and destroy the structure useful for reasoning. We present SlotGuard, a local transcript boundary that can hide sensitive data while retaining agents' performance. SlotGuard rewrites structural bindings as typed, suffix-aware slots, replaces secrets with format-preserving synthetic values, links cross-turn references with a lightweight session graph, and restores raw values only inside the trusted runtime. On controlled repository-oriented agent transcripts, SlotGuard removes all 20,814 annotated structurally sensitive characters across 9,229 paths and reduces credential leakage to 0.0\% across 852 planted values. It remains close to raw-transcript task success across four upstream models, while generic redaction drops to 2.5\%. Transcript rewriting takes a median of 14.424~$μ$s per agent turn. The code is publicly accessible at https://github.com/illinoisdata/SlotGuard.

We present a continuous geometric framework that models the discrete algebraic operations of the Transformer architecture as an integro-differential equation (IDE) on a semantic fiber bundle $\calE = \calM \times \R^d$. Beginning from a single geometric axiom -- that the token sequence forms a discrete $1$-manifold equipped with a canonical measure lattice -- we translate every core component of the modern Transformer (RMSNorm, RoPE, Softmax Attention, FFN, Residual Stream, SGD, Weight Decay) into a cohesive vocabulary of differential geometry, measure theory, and stochastic calculus. The resulting framework yields quantitative predictions spanning entropic optimal transport (Attention as a Schrödinger bridge) and non-equilibrium thermodynamics (SGD as Itô diffusion violating detailed balance). We conduct a six-part experimental campaign across five architectures (Qwen3, LLaMA\nobreakdash-3.1, Gemma\nobreakdash-3, GPT-2, Mistral) spanning $124$M to $8$B parameters. The empirical observables are quantitatively consistent with the geometric predictions: the $ε^{-1/2}$ Lipschitz scaling calibration at machine precision ($R^2 = 1.000$), the Lie--Trotter operator-splitting torsion, the symmetric ablation instability confirming the Dual-Law of Topological Stability, the $\calO(1/\sqrt{k})$ thermodynamic suppression of Poincaré recurrence on the RoPE torus, the thermodynamic context-limit phase transition, and the Non-Equilibrium Steady State parameter vortex -- verified across two optimizers (AdamW and Pure SGD) to exclude momentum artifacts. The results demonstrate that analyzing Transformers through the lens of continuous stochastic differential geometry provides a predictive descriptive vocabulary for the stability limits, context bounds, and optimization dynamics of Large Language Models.

Incoming citation context-the text with which later cases describe a case when citing it-is a strong signal for legal precedent retrieval, but it is evaluated without a temporal fence: at query time the target precedent has not yet been cited by future cases, so an unfenced method credits itself with evidence unavailable at deployment. Our central contribution is to measure how much: a temporal-admission decomposition that splits the naive relax-the-fence gain into genuine future-citation leakage, legitimate pre-query admission, and an index effect, reporting the phantom fraction-the share that is future evidence. We instantiate this as a controlled deployability audit of incoming-citation retrieval across two jurisdictions, CLERC (US federal, 1.84M documents) and ECtHR-PCR (European Court of Human Rights), adding a zero-training anchor channel that admits only citers dated before the query. On ECtHR-PCR only 14.9% of the naive gain is genuine future evidence; on CLERC the over-credit grows to +4.95 R@1000 as the fence is relaxed. Under the fence, the zero-training channel gains +16.1 R@1000 over BM25 on CLERC, clears a citation-degree control, and reaches a published R@1000 estimate similar to the strongest trained system on ECtHR-PCR (79.56 vs 79.39) at zero training.

Code search enhances developer productivity by enabling efficient code reuse. Current code search systems often use a retrieve-then-rerank pipeline, where rerankers focus on modeling semantic relevance between queries and code. However, these rerankers overlook critical non-functional qualities like execution speed, memory usage, and maintainability, which are essential for practical software development. Studies reveal developers expect results to maintain high coding standards and satisfy specific needs, such as resource optimization, highlighting the importance of quality-aware code search. Achieving quality-aware code search faces two major challenges: the scarcity of quality-annotated datasets for effective training and the limitations of standard contrastive learning objectives, which fail to capture the ordinal relationships among high-quality, low-quality, and irrelevant code. Although contrastive learning excels in distinguishing relevant from irrelevant code, its binary objective does not support nuanced quality distinctions.To address these challenges, we propose SynH-Rank, a quality-aware code reranking framework that combines LLM-driven diverse data synthesis with hierarchical ranking training. SynH-Rank employs a three-level labeling scheme to explicitly model the hierarchy: high-quality relevant > low-quality relevant > irrelevant. Additionally, we introduce a new benchmark with 4,209 pairs and two novel metrics: Quality Preference Accuracy (QPA) for assessing prioritization of high-quality code and Multi-Condition Accuracy (MCA) for evaluating performance under complex constraints.Experimental results show SynH-Rank improves QPA by 20.15\% over backbone models and outperforms standard relevance-only contrastive training by 15.80\%, while simultaneously enhancing traditional relevance metrics and multi-condition generalizability.

Agentic computer-use RL is reported in single runs, and those numbers mislead. Using verifier-guided repair of a 35B computer-use agent (CUA) across five oracle-graded environments, we show a repaired policy's success rate is dominated by upstream variance: a variance-components decomposition across three cells (crossed data-draw $\times$ seed grid, bootstrap CIs) finds evaluation variance negligible ($σ_{\mathrm{eval}} \approx 0$) and the training-seed effect small everywhere ($\leq 10\%$); instead it splits between the data draw and run-to-run nondeterminism, the data draw's share rising to dominant ($48\%$) on the hardest cell. There the run-to-run distribution is bimodal (Hartigan dip $p=0.07$, $k=10$), so a single run has roughly a 30% chance of the failure mode and mean$\pm$std is the wrong summary. On that footing, two findings hold. First, repairability is two-tier in how constrained the corrective action is: a single fixed token installs reliably (done-detection $0.97\pm0.06$), while open-ended corrections are only partial -- spatial-coordinate clicks (grounding $0.53\pm0.35$) and a generative field-fill ($0.14\pm0.04$). Second, the frame-level repair transfers to task success only when the corrective action is the task's sole remaining blocker (LinkedIn 8/20 vs. base 0/15, Fisher $p=0.006$). We caught two of our own over-claims -- a sample-efficiency curve and a 'grounding cannot be bought' boundary -- only by replicating across seeds; a stress test makes the stakes external: a single-run improvement of the size this field publishes would have the wrong sign roughly one-third of the time in a comparable regime. We release a library (cua_reliability) for routine k-seed reporting. The apparatus is, to our knowledge, the first multimodal segment-aggregated on-policy self-distillation (SA-OPSD) update on a real 35B CUA policy.

Scope 3 greenhouse gas (GHG) emissions account for the majority of corporate carbon footprints, yet remain difficult to analyze at scale due to sparse disclosures, heterogeneous report document formats, and limited evidence traceability. Existing approaches typically rely on large language models to extract emissions information from ESG reports, but often lack explicit evidence grounding or depend on costly manual annotation and verification to ensure extraction reliability. To address these challenges, we propose Scope3Trace, an evidence-grounded information extraction framework designed to extract interpretable and traceable Scope 3 emissions information from real-world ESG and sustainability reports. The framework integrates a document information extraction pipeline that performs PDF collection and OCR parsing, LLM-assisted page localization and table reconstruction, and hybrid rule-LLM extraction of organization- and building-level emissions disclosures with evidence-grounded verification. Building upon this framework, we further contribute a dual-level, evidence-grounded, multimodal dataset comprising organization-level Scope 3 disclosures extracted from heterogeneous sustainability reports. Scope3Trace enables reliable extraction and transparent integration of heterogeneous sustainability disclosures, achieving high accuracy in extracting Scope 1-3 totals and category-level disclosures from sustainability reports.

Sparse autoencoders (SAEs) decompose language model activations into sparse features, but standard SAEs encode each token independently and do not expose information that persists across a sequence. We introduce Persistent Sparse Autoencoders (Persistent SAEs), which extend standard SAEs by learning a persistence coefficient for each feature, allowing the model to learn which features should persist and for how long. Our experiments show that they retain competitive reconstruction quality while learning a spectrum of feature timescales: fast features behave as locally interpretable detectors, whereas slow features concentrate topic-level information in a persistent state. Moreover, as shown in a prompt-injection monitoring case study, slow features preserve detection signals and remain causally effective over long contexts. These results suggest that Persistent SAEs open up new opportunities for interpreting and monitoring language models through persistent semantic representations.

We present the Bangladesh Legal Acts Dataset (BLAD), a curated collection of 1{,}484 legislative acts enacted between 1799 and 2025. Each act is represented with its full text, structured sections and footnotes, repeal status, and metadata linking it to the governing regime, head of state, and prevailing legal framework at the time of enactment. The corpus spans English, Bengali, and mixed-language documents, supporting temporal and multilingual analysis of statutory law. BLAD addresses a persistent gap in legal natural language processing (NLP) resources for low-resource, civil-law jurisdictions in South Asia. We describe the acquisition and enrichment pipeline, report descriptive statistics over more than two centuries of legislation, and outline the research directions the corpus enables. The dataset is publicly available under the CC~BY-SA~4.0 license at https://www.kaggle.com/datasets/sakhadib/bangladesh-legal-acts-dataset.

In multi-hop RAG evaluation, a top-k answer score can hide two different failures: the retrieval window may drop part of the support chain, or it may contain support in a form the adapted reader does not use well. We call this reader-facing form of retrieved evidence an evidence interface. Using three support-annotated multi-hop QA benchmarks, we compare matched adapted readers trained with raw context, retrieval windows, and gold-support diagnostic renderings. These comparisons distinguish support-availability failures from remaining reader-interface effects. Top-k windows become interpretable only after checking whether the complete annotated support chain survives: when it does, short ranked windows can match or improve over raw context; when it does not, missing support explains much of the loss. Gold support-first improves matched readers; on 2Wiki and MuSiQue, a support-supervised ranker raises coverage and recovers raw-context quality at lower prompt cost, while retaining gold headroom. Support-removal checks further show that the gains rely on exposed evidence, not only answer priors. On support-annotated evaluations, top-k answer scores should therefore be reported together with complete-support coverage.

It is crucial to safeguard computer networks from evolving network security threats and unknown cyberattacks. An essential tool for protecting computer networks against unknown cyber threats is Network Intrusion Detection System (NIDS). However, NIDS faces a major security concern due to its susceptibility to adversarial attacks. Adversarial attacks aim to deceive NIDS by crafting and injecting adversarial examples into the system. These adversarial inputs can deceive the NIDS into misclassifying benign network traffic as malicious. We developed a resilient hybrid defense mechanism aimed to mitigate the impact of two potent adversarial attacks: Fast Gradient Sign Method (FGSM) and Carlini & Wagner (C&W) attack. Our hybrid defense approach leverages the combined strength of two heuristic defense methods: Adversarial Training (AT) and Gaussian Data Augmentation (GDA). GDA provides multi-directional defense, while AT enhances NIDS robustness against specific adversarial vectors. Under pre-attack scenarios, NIDS demonstrated good accuracy and f1-score. However, in the post-attack scenario, its accuracy significantly dropped under FGSM and C&W attacks (0.2649 and 0.4961, respectively). Our proposed hybrid defense method effectively mitigated these adversarial threats, with post-defense accuracy of 96.57% and 89.20% for FGSM and C&W attacks. We evaluated the defense strategy across a range of epsilon and confidence noise factor values (ranging from 0.0001 to 0.0009). This research provides a good direction for future researchers in the emerging area of adversarial machine learning from a security perspective.

An AI research agent can improve the score it sees without finding a modelling change that works on new materials. We ask a stricter question. After repeated experiments, does the selected change survive on data that never entered the loop, and can its code be reused? We separate the search into changes to features, models, representations, and training data. Seven searches produce 701 evaluated changes across ten Matbench endpoints. Agents receive only the mean over five inner folds, reducing reliance on any single development split. We then freeze the selected code and evaluate it once on an untouched holdout. Nine of ten choices remain the best tested single intervention. The surviving changes reveal two materials modelling regimes. With composition alone, feature, model, and representation changes provide comparable routes to improvement. They include held-out MAE reductions of 17.4\% for band gap and 18.6\% for steel strength, as well as gains on both classification endpoints, while screened external data adds little. For structure tasks, richer geometry descriptors and model or calibration changes lower mean held-out MAE by 14.6\% and 7.1\% and lead on different property families, whereas composition embeddings do not transfer. Combining separately found feature and model changes yields a 26.3\% mean held-out improvement. These results show in materials prediction that closed-loop agents can produce decisions that survive unseen evidence and code changes that can be reused across tasks and combined. More broadly, they provide an evaluation design for testing executable discoveries beyond the feedback loop.

Recent geometric foundation models (e.g., Metric3D, Depth Anything and UniDepth) have substantially improved monocular depth estimation (MDE) in both cross-scene generalization and metric-scale prediction, yet these gains have not translated to tiny models. We bridge this gap with DepthART (Depth Anything Rethought for Tiny Models), which is a compact MDE model for on-device deployment across diverse scenes. We first identify two capacity-driven bottlenecks in tiny models: (i) overfitting to dataset-specific distribution bias and (ii) unstable metric adaptation under camera shift, where full fine-tuning easily damages transferable geometry. Accordingly, DepthART combines two simple but effective strategies: a bias-resistant data sampling scheme to reduce distribution bias under the same training budget, and a camera-conditioned fine-tuning protocol that freezes the distilled encoder and adjusts metric scale conditioned on intrinsics while better preserving cross-dataset generalization. Across datasets, DepthART consistently surpasses previous tiny baselines in both zero-shot generalization and metric accuracy (e.g., zero-shot $δ_1$=0.964 for DepthART-S on NYUD v2), and in some cases approaches heavy models. We further provide a scalable model family, with DepthART-S reaching 347/245 FPS (strict FP32) on an RTX A6000 at $224^2/448^2$, 102 FPS (TF32) on a Orin NX 8GB, and over 15 FPS (FP32) on a Jetson Nano 4GB.

Accurate short-term wind power forecasting is essential for grid stability and operational planning, yet remains challenging due to the complex interactions between atmospheric conditions and turbine dynamics. However, existing methods fail to effectively incorporate weather forecasting with wind turbine data (i.e., SCADA), leading to suboptimal solutions. To address this, we introduce a multimodal framework that integrates historical point-based SCADA data with grid-based Numerical Weather Prediction (NWP) forecasts, which is challenging due to heterogeneous input and the complex physical wind-turbine interactions. Our approach first explicitly decomposes inputs into scalar and vector features to better capture both site-specific and geometric dependencies and then incorporates a geometric encoder to extract rotation-invariant features from wind vectors. We further leverages a Fourier Neural Operator (FNO) architecture, which performs global convolutions in the frequency domain to efficiently model long-range spatiotemporal relationships. Extensive experiments on three real-world wind farms, with weather forecasting data, demonstrate that our model consistently outperforms state-of-the-art baselines, highlighting the effectiveness of its physically-informed design. The core implementation of our method is publicly available at: https://github.com/shawn-sypiao/GWPF.

Processing-In-Memory (PIM) has emerged as a promising technology for accelerating machine learning (ML) workloads. Specifically, non-volatile memory-based PIM architectures have enabled effective ML acceleration due to their ability to perform energy-efficient matrix-vector multiplication operations. However, these devices suffer from non-idealities such as thermal noise. This noise alters the stored values in the memory cells which correspond to actual model weights, compromising the inference accuracy. In this work, we introduce ThRIve, a noise-aware training methodology that leverages low-rank adaptation to enable thermally robust inference on heterogeneous PIM architectures. ThRIve selectively stores these low-rank noise-aware parameters on a hardware that is less susceptible to thermal noise, enabling robustness against temperature-induced noise variations. ThRIve mitigates the effects of thermal-noise and prevent the drop in inference accuracy across the entire operating temperature range. Experimental results demonstrate that ThRIve-enabled architectures maintain consistent inference accuracy, with the mean accuracy staying within 2% of the ideal (i.e., noise-free) accuracy, and the variation in accuracy across the entire operating temperature range remaining within 2% of the mean. The proposed methodology achieves accuracy and robustness comparable to thermally-resilient Static Random-Access Memory (SRAM)-based PIM systems, while delivering up to 5.4x reduction in energy-delay product (EDP) during CNN model inferencing.

Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results. Current evaluation metrics reduce such a trajectory to a binary success flag or compare it against a reference by exact matching. A success flag cannot distinguish a sound solution from one that succeeds by luck, and says nothing about why a failed run went wrong. Exact matching penalizes plans that are valid but reordered or decomposed differently from the reference. We reframe trajectory evaluation as a distance between the agent's execution graph and a set of valid solution graphs, and instantiate it via an unbalanced fused Gromov-Wasserstein transport problem over attributed dependency graphs. The resulting score, termed \otap{} (Optimal Transport for Agentic Planning), is a pseudo-metric that is provably invariant to dependency-preserving reorderings and has bounded sensitivity to redundant steps. Its unbalanced marginals handle missing or hallucinated steps without forcing a match, and its soft coupling accommodates variation in plan granularity. On controlled perturbations and three public benchmarks, \otap{} separates valid from invalid trajectories in a regime where semantics-only metrics score below chance. Its accuracy is highest when the dependency graph is recovered exactly, and drops only when the graph is inferred heuristically from free-text traces.

Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized. Bridging simulation and differentiable rendering enables more robust, end-to-end evaluation of these adversarial attacks, yet there is no easy-to-use, unified system that offers a rich set of customizable configurations for adversarial attacks across multiple scenes, objects, environmental and lighting conditions, and camera trajectories. We present ALLUDE, which addresses these gaps, offering first-of-its-kind evaluation capabilities across Linux and Windows. We comprehensively demonstrate ALLUDE's evaluation breadth through a two-pronged strategy: (1) using Latin Hypercube Sampling, we draw a representative subset from 5,400 configurations spanning 10 scene-object pairs, 9 weather conditions, 4 optimizers, 5 camera trajectories, and 3 detection models; (2) we stress-test existing attacks (CAMOU, RAUCA, FCA) under diverse weather conditions and continuous camera trajectories, revealing degradation of attack success across every attack, exposing evaluation gaps in prior work. Through ALLUDE's end-to-end differentiable rendering, adversarial attacks can be optimized against shifting real-world deployment conditions. Our cross-platform code is open source.

The advent of LLMs has significantly changed the research on privacy policy and data compliance analysis by enabling tasks that previously required specialized, domain-specific tools. However, it remains unclear to what extent LLMs can truly replicate the diverse functionalities, and the wide range of methodologies and analysis offered by prior work. In this paper, we conduct the first systematic evaluation of whether off-the-shelf LLMs can replace specialized privacy analysis tools. We study six representative tools spanning three major functionalities: contradiction detection, regulatory compliance analysis, and privacy policy summarization and aggregation, and across three intermediate tasks: structured data extraction using tuples, Semantic Role Labeling (SRL) and manual privacy policy labeling. We compare the performance of two state-of-the-art LLMs (GPT-5.2 and Gemini-2.5 in various configurations) against the tools by directly prompting the models to perform corresponding functionalities and tasks on a custom dataset of 10 privacy policies, allowing us to assess whether off-the-shelf models can produce tool-specific functionalities without further engineering or domain-specific training, major limitations in prior work. Our results show that LLMs consistently match or exceed the capabilities of existing tools across the functionalities. In manual labeling of first-party collection entities, LLMs achieved an average precision of 81.8% and recall of 70.9%, while for labeling of third-party sharing entities, they achieved an average precision of 91.4% and recall of 70.8% compared to the OPP-115 dataset. Overall, our findings indicate that LLMs can effectively perform a broad range of functionalities and tasks in privacy policy and regulation analysis that previously required specialized tools.

Mixture of Experts (MoE) architectures have emerged as a dominant paradigm for scaling Large Language Models (LLMs). However, MoE inference on conventional hardware is constrained by three fundamental bottlenecks. These encompass the massive memory bandwidth required to fetch non-contiguous expert weights, the non-deterministic scatter-gather traffic generated by input-dependent token routing, and the tail-latency dependency imposed by synchronous expert output aggregation. To address these challenges, we propose ThAME, a three-dimensional (3D) heterogeneous multi-chiplet architecture for MoE inference. ThAME employs Ferroelectric Field-Effect Transistor (FeFET)-based non-volatile and DRAM-based volatile memory chiplets with a co-designed compute mapping strategy that aligns the distinct computational profiles of attention mechanisms and expert routing. Furthermore, we design a specialized Network-on-Chip communication backbone optimized to mitigate the bottlenecks associated with non-deterministic token routing traffic across the combinatorial space of input-dependent MoE traffic patterns. Experimental results demonstrate that ThAME outperforms state-of-the-art counterparts by up to 15.7x in terms of speedup and improves energy efficiency by up to 9.8x.

New-user cold-start is a critical bottleneck for e-commerce platforms: predicting user lifetime value (LTV) and conversion rate (CVR) for users with sparse interaction history. Two prior directions -- LLM-based semantic augmentation and learning using privileged information (LUPI) -- each face a key limitation. First, LLM augmentation produces unstructured rationales that are noisy and hard to operationalize in production. Second, naive student-teacher distillation can be brittle due to an information gap between the privileged teacher and the sparse student; moreover, this gap is heterogeneous across users. We propose SemRaD, a Semantic Reasoning-aware Distillation framework addressing both limitations. First, a Structured Semantic Reasoning Pipeline replaces free-form rationales with a structured schema built via a discover-curate-audit workflow, producing per user a Densified Semantic Profile (consumed by the deployed student via a Semantic-Gated Encoder that focuses on the most informative dimensions) and a Hindsight Distillation Target reconciled from pre- and post-conversion reasoning (used only at training). Second, to bridge this gap and handle its heterogeneity, a Hindsight-Aware Distillation Network transfers privileged knowledge via the hindsight target, with Distillation Experts improving transfer under per-user variability. On a large-scale industrial dataset, SemRaD lifts +1.9% LTV (Gini) and +1.0% CVR (AUROC) over a production-grade base; a four-week online A/B at Keeta confirms +1.0% LTV / +0.43% CVR. SemRaD also matches the production system's LTV using only 9% of the training data while improving CVR by 0.8%.

Generative AI (GenAI) is reshaping software engineering, raising concerns about how the development pathway through which juniors become seniors is being eroded. While macro statistics show a decline in junior hiring and controlled studies demonstrate the effects of AI on individual task performance, the mechanisms through which GenAI reshapes early-career development in real organizational and educational contexts have not been thoroughly examined. Through 14 semi-structured interviews with juniors at the threshold of entering software engineering and senior software engineers in South Korea, analyzed using Reflexive Thematic Analysis, we reveal a foundational pattern of Absorption -- GenAI redirects entry-level work into senior-AI workflows -- and three consequences: (1) juniors losing the productive struggle through which expertise once developed; (2) the structural reproduction of this loss through collective normalization of GenAI use in university classrooms; and (3) the perceptual asymmetry between seniors and juniors that prevents either side from correcting these dynamics on their own. By extending learning theory and situated cognition to organizational and institutional scales, we argue that GenAI appears to be absorbing not just specific categories of tasks but also parts of the pathway through which the next generation of seniors is formed. Preserving this pathway will require deliberate institutional design across classrooms, workplaces, and the evaluation criteria for juniors.

The rapid advancement of large language models (LLMs) has led practitioners to increasingly rely on them for answering questions about hardware description languages (HDLs). Because HDL is ultimately synthesized into physical hardware, an imprecise or redundant answer can propagate into timing violations or non-synthesizable logic that surface only late in the design flow, making the quality of HDL answers especially consequential. However, the quality of LLM-generated responses, particularly in comparison with answers provided by human experts, remains unclear. To investigate this question, we collect 6,246 HDL Q&A posts with accepted answers from Stack Overflow and curate them into a dataset, organized into a taxonomy of four main categories (Conceptual, Debugging, Generation, and Optimization) and ten subcategories. Using this dataset, we design a user study conducted with 19 HDL engineers with one to three years of experience. Our findings reveal a pervasive over answering tendency: LLMs supply correct content but bury it under redundant alternatives (65.7%) and verbose padding (69.1%), while nearly half of answers (49.0%) fail to fully align with expert answers yet participants still preferred LLM responses for readability (58.3%). Motivated by these findings, we propose a multi-agent framework for improving LLM-based HDL question answering. We evaluate answer quality using an LLM-as-Judge and two structural metrics: the number of core answers, which reflects redundancy since LLMs often provide multiple alternative solutions, and the length of non-core content, which reflects verbosity. Evaluated on the four mainstream LLMs, our framework increases the average core-answer quality score from 3.71 to 4.67 (+0.96) and the non-core content quality from 3.72 to 4.23 (+0.51), on a five-point scale.

A Bayes-filtered transformer (BFT) is a transformer trained on sequences that are generated in two steps: first a latent task is drawn from a prior, then observations are drawn conditional on that task. Trained under autoregressive log loss, the BFT's next-token prediction, in the idealized limit, is the Bayesian posterior predictive distribution (PPD) induced by that prior and that conditional law. In practice the trained BFT is only an approximation of this ideal PPD, raising an interpretive question: what prior and posterior over the latent task has the trained BFT actually internalized? Existing work answers this question by comparing the trained BFT's predictions against the predictions of various "reference" posteriors, each standing in for a different candidate algorithm or computation the BFT might be implementing. This prediction-space comparison is fragile: different posteriors can share the same posterior-mean predictions. We use predictive Monte Carlo (PMC) as a general interpretability tool for any BFT: using only next-token generation, PMC returns an approximation to the implicit prior and posterior over the latent task, answering the interpretive question directly in latent space. We apply PMC to three stylized task families spanning 0-Markov and 1-Markov exchangeability. The phenomena previously reported in these settings remain visible in latent space. Code is available at https://github.com/afiq-aswadi/bft-pmc

Large language models (LLMs) can automatically repair register-transfer-level (RTL) designs. However, fixing complex sequential logic errors requires reusing past debugging experience. Existing retrieval-augmented generation (RAG) relies on task-text similarity to provide this experience. This text-based approach often misguides the model because natural language poorly reflects cycle-level hardware execution semantics. To address this, we present MechMem-RTL, a repair framework that reuses verifier-confirmed repair records instead of text similarity. Each stored record strictly links trigger evidence, a diagnosed failure mechanism, a local repair action, preservation constraints, and a verification summary. For a new failure, MechMem-RTL injects a past record only when deterministic verifier evidence is strictly compatible with the stored trigger. Otherwise, the system uses only current verifier evidence. We evaluate MechMem-RTL on 48 public sequential RTL tasks across six repair models. With at most two repair attempts per task, MechMem-RTL successfully resolves 180 out of 288 task-model pairs, outperforming standard feedback repair (109 pairs) and task-similarity RAG (107 pairs).

GUI agents must reason about how actions transform interface states, but end-to-end success rates entangle this ability with perception, grounding, planning, and recovery. We introduce EvoGUI, a diagnostic framework that converts normalized GUI trajectories into three complementary visual question answering probes: temporal ordering, inverse action/value prediction, and contrastive one-step successor discrimination. Their labels are derived from trajectory order and logged actions, requiring no additional task-label annotation after trajectory normalization. We instantiate EvoGUI-Bench from Mind2Web and WebLINX, yielding 3,000 instances across 120 domains, and evaluate 28 vision-language model configurations zero-shot. The strongest model reaches only 60.4 EvoGain, while model scale and GUI specialization do not reliably predict performance. These results establish EvoGUI-Bench as a scalable diagnostic complement to end-to-end GUI-agent evaluation while exposing substantial headroom in state-transition understanding. The source code is publicly available at https://github.com/Yyhhh6/EvoGUI.

LLM constraint reasoners are often evaluated near the random-SAT phase transition, confounding density and solver hardness. We test instance-level transfer while near-matching clause density. At aligned size bins, with near-matched density and matched maximum clause width, we compare proof-hard expander-Tseitin and proof-easy ladder-Tseitin formulas, pigeonhole anchors, and density-mismatched controls. Theory separates their resolution hardness; a solver-specific Glucose mean-conflict proxy differs by up to $51\times$, and five other solvers preserve the direction. Across three included models (243 instances each; a fourth is excluded for abstention), the near-matched-density accuracy gaps range from $-32$ to $+20$ points, with a pooled gap of $+1.7$ points ($p=0.74$) and a wrong-signed correctness-versus-conflict association ($r=+0.15$). A proof-preserving relabeling lowers accuracy in all five clusters for one model (mean $-93$ points) but not another, exposing model-surface sensitivity. In a preregistered extension, provider-reported completion-token spend does not consistently increase with the proxy after accounting for formula length and censoring. At 16k, the reasoning model spends more on proof-easy matched formulas and exhausts its budget on the solver-easiest UNSAT family; the 32k C1 gap is absent. These scoped dissociations concern verdict accuracy and observed token spend, not certificate solving, exact proof length, or allocation efficiency.

Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it. We study one production system (Leni) whose architecture installs such checkpoints: verification loops (execute, observe, compare, correct) staffed by lightweight task-specialized post-trained models. We evaluate the unmodified production configuration on three public benchmarks stressing distinct failure modes: SpreadsheetBench Verified (silent computation error), BullshitBench v2 (premise confabulation), and the GAIA validation split (cascade error over long tool chains). The full system improves over its frontier base model by +11.0 percentage points on SpreadsheetBench (91.25% vs 80.25%, n=400, p<0.001), +7 to +10 percentage points on BullshitBench (98% vs 91%, n=100), and roughly +15 points on GAIA validation (75.2% pass@1, n=165; 83.0% best-of-k). Our central contribution is a decomposition of that uplift: most of it comes from scaffolding, routing, and specialist models rather than from the verification step itself, whose isolated contribution is small (+1.5 points) but concentrated at the top of the score distribution, where it converts otherwise-failing tasks. We instrument the loop end-to-end, yielding an empirical verifier confusion matrix (catch rate about 0.20, fix rate 0.75, no false-alarm regressions) that grounds a compounding-reliability model. Specialist-swap ablations suggest that the loop's value depends on who observes it: replacing the small trained verifier with the generating frontier model eliminates most rescues. A valid-premise control shows zero over-rejections in 100 expert-level questions.

Model collapse is a central challenge in learning from synthetic data: as later-generation large language models (LLMs) are trained on an increasing proportion of model-generated data, performance can degrade due to narrowed coverage and accumulated bias. Existing work mainly studies how to bound this degradation. In iterative model evolution, however, the more meaningful objective is to ensure that each successive model improves over its predecessor, which requires diagnosing collapse at a granularity that is actionable for data curation. We study this problem in synthetic data self-improving for instruction tuning. We show that collapse in this setting is not simply uniform performance degradation, but can appear as a polarization of competence, where synthetic training reinforces already strong skills while further degrading weak ones. Motivated by this observation, we propose KITE (Knowledge-boundary Instruction Tuning via Exploration), a two-stage framework that combines failure-guided data generation with boundary-aware uncertainty curation. Experiments across several datasets and multiple open-source LLMs show that KITE yields more stable improvement than strong synthetic-data baselines.

This paper addresses key technical challenges in current large language model (LLM) agent applications, including long-horizon planning, sparse reward attribution, and dynamic environmental interaction, by designing and optimizing an intelligent agent workflow. The proposed architecture is based on the synthesis of core AI paradigms: Visual, Language, Generative, Graph, Multimodal, Reinforcement, and Agent Intelligence. Unlike conventional baseline models that rely on static prompting and lack robust perception-action loops, our approach introduces a Partially Observable Markov Decision Process (POMDP) routing mechanism. This mechanism is augmented with an internal, self-correcting reward model that evaluates decision trajectories before execution. By integrating multimodal inputs and advanced reinforcement learning principles (such as proximal policy optimization and value function approximation), the agent maintains long-term structural memory and dynamically adapts its reasoning pathways to mitigate error accumulation. Empirical experiments on the ALFWorld embodied simulation environment and the WebShop online navigation benchmark demonstrate a 24.5% absolute improvement in task success rate and trajectory efficiency over mainstream baselines like the standard ReAct framework. Comprehensive ablation studies confirm the significant contribution of the reward-driven critique module in suppressing hallucination rates. This research bridges theoretical foundations of reinforcement learning and graph-based memory with autonomous agent workflows. Ultimately, the resulting architecture offers a practical, scalable reference framework for developing artificial intelligence technologies in complex, multi-step autonomous systems. Code is available at https://github.com/01Amez/RLAW_Implementation.

High-resolution atmospheric data are required to resolve mesoscale and localized meteorological structures, however such datasets remain limited in many regions of the world. Existing high-resolution weather products are typically produced through dynamical downscaling, which is computationally expensive and difficult to scale across locations, variables, and forecast scenarios. These limitations motivate machine-learning-based downscaling systems that can generate multiple weather variables stochastically while producing new high-resolution fields directly. In this paper we present Apeliotes, a framework for high-resolution weather forecasting. Built on the global re-analysis atmospheric data, a pre-trained global weather foundation model, and a regionally trained generative diffusion model, Apeliotes not only provides accurate kilometer-scale weather variables, but also multi-level atmospheric fields which are not directly available in the existing global atmospheric data. Our comprehensive evaluation demonstrates that Apeliotes achieves highly competitive performance. The model predicts vertical wind profile with less than 3\% error between truth and predicted fields, achieving correlations of 0.91 for 10-m wind speed and 0.99 for 2-m temperature, with NRMSE values of 0.42 and 0.17, respectively.

Forecasting the outcomes of transition-metal-catalyzed reactions is notoriously complex due to the interplay of diverse physical and chemical variables. A persistent computational bottleneck has been effectively merging broad electronic descriptors with the localized, three-dimensional geometry of the reactive site. To bridge this representation gap, we present ChemFusion, a hybrid neural network that fuses conventional electronic features with explicit 3D atomic coordinates. Using a cross-attention mechanism, the model enables global electronic states to dynamically attend to specific spatial constraints within un-pooled molecular point clouds. When benchmarked against a diverse library of cross-couplings, this approach delivers exceptional predictive performance, decisively surpassing traditional single-modality frameworks. Importantly, extracting the attention matrices reveals that the architecture autonomously learns to identify and penalize restrictive steric hindrances. This provides a physically grounded interpretability, demonstrating that spatially aware networks can navigate complex reaction sterics that standard statistical models typically miss.

Air pollution and climate-related stressors are increasingly important concerns for respiratory health, especially in settings with unequal environmental exposure and healthcare capacity. This study evaluates an interpretable machine learning framework for predicting respiratory disease rates and air-quality status using structured country-level weekly data. Two supervised learning tasks were considered: regression of respiratory disease rate per 100,000 population and binary classification of air-quality status. Nine regression models and nine classification models were compared using nested cross-validation. Model interpretation was conducted using SHAP values, and subgroup analysis was performed across income levels and geographic regions. The results showed that PM2.5 concentration was the dominant predictor of respiratory disease rate, with linear and regularized linear models achieving the strongest regression performance. For air-quality classification, models achieved high balanced accuracy when PM2.5 was included, but performance decreased substantially when PM2.5 was removed, indicating strong dependence on pollutant-related information. SHAP analysis showed that, without PM2.5, socioeconomic and meteorological variables such as GDP per capita, precipitation, and healthcare access became more influential. Subgroup analysis showed similar aggregate regression error across income groups, but PM2.5 contributed more strongly to predictions in lower-middle-income countries. These results show that model accuracy alone is not sufficient for climate-health prediction. Interpretable models can help identify dominant pollution-related signals, test whether results depend on key pollutant variables, and show whether prediction patterns differ across socioeconomic groups.

Large language model (LLM) code explanations can support people in solving code-related problems, yet prior work has shown that people have diverse problem-solving styles. If explanations fail to meet people's problem-solving needs, they may be less productive in their occupations and miss opportunities to learn and grow. Although some research has examined how LLMs can adapt their outputs to a user's age or expertise, no prior work has examined how LLMs can adapt their code explanations to people's problem-solving styles. To address this gap, we developed prompts from an established inclusive design method that considers 5 types of problem-solving styles, and we generated 1,072 code explanations from six open-weight LLMs. Using natural language processing techniques, we uncovered a taxonomy of 13 linguistic adaptations, with each adaptation supported by evidence from the literature, the prompts, or the LLMs' outputs. They also show which LLMs adapted their code explanations more frequently than others. This paper is the first to investigate problem-solving style adaptations in LLM code explanation, contributing two problem-solving adaptation approaches: declarative statements for each adaptation and 10 problem-solving style prompts.

We study whether \sigreg -- LeJEPA's anti-collapse objective -- can reshape representations during standard autoregressive language-model pretraining, and when the resulting geometry helps \kv-cache quantization. We train 110M-parameter models on 10B FineWeb tokens and report three findings. \textbf{(1)} At $λ{=}0.01$, \sigreg reduces hidden-state pairwise-cosine anisotropy by $38\%$ across three paired seeds. Perplexity increases by less than $0.35\%$ in every pair, with no consistent zero-shot loss. \textbf{(2)} This change does not propagate from hidden states to the \kv cache. Applying \sigreg directly to K and V during continued training, however, reduces mean cache anisotropy by $94\%$ across four checkpoints. A matched continuation without the \kv term leaves cache geometry nearly unchanged, and the frozen-trunk retrofits we tested do not reproduce the effect. \textbf{(3)} Under untransformed symmetric group-free quantization, direct \kv regularization is the only training condition that prefers per-channel scaling in all three seeds, and under that same 3-bit per-channel scheme the baseline incurs $4.3$--$7.9\times$ the directly regularized model's \dnll. Under the full simulated KIVI-style configuration (mixed arrangement, zero-points, grouped scales), however, all models reach near-parity, including when storage overhead is approximately matched. In this 110M regime, the training intervention helps when quantizer scales are coarse; the advantage vanishes under the tested combination of token-local grouping, mixed \kv scaling, and zero-points. To our knowledge this is the first training-time \emph{distributional} regularization of standard \kv-cache geometry evaluated against post-hoc cache quantization.

We study distributionally robust linear chance-constrained problems in which uncertainty is modeled by a Gaussian mixture model (GMM). Finite-support distributionally robust (FDR) formulations, widely used in data-driven robust optimization, robustify over empirical mixture support points and therefore primarily stress-test the fitted nominal mixture. This can be insufficient when service reliability depends on structural misspecification of the nominal mixture-support parameters. To address this limitation, we describe the ambiguity set of distributions by developing a novel formulation of a Wasserstein-2 metric that uses the Bures-Wasserstein (BW) metric over probability measures with finite second moments. Unlike FDR, which generally sets finitely many empirical support points a priori, the proposed ambiguity set allows the worst-case distribution to endogenously determine both how many mixture components receive mass and where their means and covariances lie within a continuous support. For the resulting ambiguity set, under mild regularity conditions, we prove strong duality for the inner worst-case chance-constraint problem and derive its semi-infinite reformulation. We then develop an adaptive cutting-surface algorithm, which endogenously determines the locations of mixture components receiving mass, and the mean and covariances of the Gaussian distributions at these locations. The algorithm attains any prescribed optimality gap in finitely many iterations, while a block-alternating local search identifies new components. A case study using the electric-vehicle charging-station energy-allocation problem demonstrates the framework's practical value in achieving any reliability targets. CDR also induces structural changes in energy allocations, unlike FDR, whose allocations remain close to the nominal solution.

As scalability becomes increasingly important in recommendation modeling, recent architectures have advanced the modeling of two broad sources of ranking signals along separate paths: non-sequence features, including user, item, context, and cross features; and sequence features from user behavior histories. Wukong and HSTU have emerged as representative scalable backbones for these paths: Wukong scales high-order non-sequence feature-interaction modeling, while HSTU scales long user-behavior sequence modeling. Despite their complementary strengths, practical architectures that combine these two types of feature modeling remain underexplored. We present WHALE, a scalable unified recommendation architecture that jointly models non-sequence and sequence features on top of Wukong and HSTU. Each WHALE layer contains a Wukong module, an HSTU module, and an attention-based fusion module in which Wukong-derived interaction representations query HSTU-derived behavior representations. This design keeps both backbones active throughout the network and enables progressive Wukong-HSTU exchange, allowing high-order feature crosses to repeatedly retrieve fine-grained evidence from long user histories. To make WHALE practical for industrial deployment, we introduce customized Triton kernels and other model-systems co-design techniques to improve training and inference efficiency. On large-scale industrial recommendation data, WHALE achieves consistent gains in offline experiments. Additionally, it delivers positive online gains with a modest serving-throughput trade-off. The method has been deployed in production systems. Overall, WHALE provides a practical example of how these two sources of information can be scalably unified in an industrial recommendation model.

We consider economic theory from the perspective of a total automation economy, one with no human involvement in production either in manufacturing or in management. One can naturally ask whether a total automation economy is fundamentally a centrally planned economy or, alternatively, whether efficiency demands decentralization into local decisions by competing agents -- agentic production. A soviet economist, Leonid Kantorovich, developed linear programming as a method companies or governments can use to optimize production. Ironically, he is also generally credited with showing that the most efficient production is achieved through decentralization -- a free market economy with competing agents. I will call Kantorovich's result the agentic theorem and review it in detail here. This analysis appears to reveal a alignment vulnerability under which agentic management of the economy diverges from human values as agents deveop motives that are "internal" to the economy and disconnected from prices derived from human consumption markets.

Large language models (LLMs) can plan tool-mediated scientific work, but scientific instruments remain difficult to connect to such agents: vendor APIs may load only inside acquisition host processes, facilities may prohibit cloud-hosted agents, and natural-language interfaces can emit physically unreasonable arguments. We present a method for connecting local LLMs to scientific instruments through the Model Context Protocol (MCP). It combines: (1) a schema-bound tool surface that validates requests against physical bounds before adapter dispatch; (2) a vendor-neutral, host-process adapter pattern separating language-side reasoning from instrument-side execution; (3) a persistent lifecycle for long-running live-processing jobs; and (4) MCP-prompt-registered skills that compose typed tools into reusable multi-step protocols. Our open-source reference server exposes 30 typed tools, 5 live-job types, and 6 skills through a physics-plausible simulator implementing the same protocol surface. Validation is software-only: all 120 hardware-independent tests pass deterministically, while 15 local-LLM integration tests pass 12-15 of 15 across runs because of model nondeterminism. A preliminary single-run probe across five open tool-calling LLMs indicates that the schema-bound interface can be driven locally by small open-weight models without cloud dependency; it is not a benchmark and has no confidence intervals. The method provides a bounded, testable, and reproducible foundation for closed-loop agentic instrumentation research.

In many cases, the outage of one transmission line in a system can be localized by monitoring the power flow of another line, and machine learning methods can be used to distinguish the cases under uncertainty. In this study, we examine the improvements in line outage localization performance achieved by various ensemble classifiers compared to single-model methods. In the case studies, we compared the classification results with measurement data collected at observed transmission lines (OTLs) selected using three algorithms, i.e, greedy maximum coverage problem (MCP), high-eta, and random selection, based on two sensitivity factors, i.e., line outage distribution factors (LODFs) and line outage impact factors (LOIFs). We found that the OTLs selected by the greedy MCP algorithm yielded the highest F1 score and the ensemble classifiers significantly outperformed a base kNN classifier. The extra-trees bagging technique achieved the highest F1 score in many instances. All the findings were statistically significant.

Imitation learning enables learning a policy in an unknown environment with a latent reward signal using expert demonstrations, but it struggles when the imitator's and expert's observations are mismatched and unobserved confounders are present in expert demonstrations. By identifying appropriate adjustment sets via the sequential $π$-backdoor criterion, causal imitation learning (CIL) provides a framework for approximating the expert's policy from confounded data. However, existing CIL methods, Causal Behavioral Cloning (Causal BC) and Causal Generative Adversarial Imitation Learning (Causal GAIL), are designed for short-horizon, low-dimensional settings. When applied to continuous control tasks with long horizons and high-dimensional state-action spaces, these methods exhibit poor performance: Causal BC suffers from compounding errors, Causal GAIL is unstable and sample-inefficient, and sequential $π$-backdoor adjustment becomes impractical. We introduce Causal Soft Q Imitation Learning (SQIL) and Causal Inverse soft-Q Learning (IQ-Learn), two off-policy causal imitation learning algorithms that combine the causal adjustment framework with state-of-the-art inverse reinforcement learning objectives. Both algorithms operate on causally-adjusted state representations produced by an efficient approximation of the sequential $π$-backdoor criterion, exploiting the causal structure of continuous control environments to reduce the full-horizon adjustment to a fixed-size sliding window. We evaluate all methods in a suite of confounded environments and find that Causal SQIL and Causal IQ-Learn substantially outperform prior CIL algorithms on long-horizon tasks, sometimes surpassing the expert, whereas all causally unaware imitation methods fail to learn meaningful behavior.

The Credit Assignment Problem (CAP) is fundamental to developing efficient and explainable Reinforcement Learning (RL) agents. Existing frameworks, whether relying on temporal contiguity or hindsight-conditioned reward reweighting, frequently fail to attribute properly between an agent's policy (skill) and environmental stochasticity (luck). A principled approach to CAP must isolate the true causal drivers of observed outcomes from spurious correlations and environmental randomness. We introduce Counterfactual Shapley Credit Assignment, a novel framework grounded in causal theory that attributes credit and blame via the Counterfactual Shapley Value ($φ$-value). By redistributing environmental rewards, $φ$-values enhance temporal credit assignment across three critical dimensions: sparse causality, high stochasticity, and delayed rewards, all while preserving the optimal policy. We derive a consistent estimator that computes $φ$-values efficiently, enabling a new class of policy gradient methods, $φ$-PPO, combined with Prioritized Trajectory Replay (PTR). Empirical results demonstrate that $φ$-values align precisely to the ground truth causes of task rewards with superior sample efficiency in challenging environments where prior state-of-the-art methods fail to converge.

Mathematicians distinguish proofs that explain, simplify, or introduce a nonstandard route, but these judgments are difficult to operationalize. We study a deliberately narrower construct: time-relative proof-route nonstandardness in formal mathematics. For a Lean theorem, PriorProof extracts the dependency footprint of its elaborated proof term and scores the weighted surprisal of that footprint under a retrieval-conditioned, hierarchically smoothed prior built only from an earlier quarterly snapshot of Mathlib. The method requires no hand-built technique ontology and no human labels: statement retrieval is learned from proof-derived contrastive pairs, while the scored object is read mechanically from proof terms. In a blinded topology study, 100 presentations collapse to 76 distinct underlying pairs: 12 canonical contrasts shown three times for consistency screening and 64 distinct stratified pairs. Against the majority of three retained domain raters, PriorProof agrees on 53/76 pairs (69.7%, Wilson 95% CI 58.7-78.9%), including 11/12 canonical pairs (91.7%, 64.6-98.5%) and 42/64 stratified pairs (65.6%, 53.4-76.1%). Score-gap quartiles are nonmonotone after repeat collapse; the endpoints are 12/19 (63.2%, 41.0-80.9%) in the smallest-gap bin and 16/19 (84.2%, 62.4-94.5%) in the largest, supporting an endpoint-calibration tendency rather than a resolved staircase. The best language-model condition agrees on 60/76 pairs (78.9%, 68.5-86.6%); on paired outcomes, PriorProof alone is correct on 8 pairs and the model alone on 15 (exact two-sided McNemar p = 0.210), so the difference is not established at this sample size. We therefore present PriorProof not as a replacement for expert or model judgment, but as a decomposable, time-anchored signal whose score gap provides an interpretable reliability indicator.

This review provides an overview of recent advancements in automated segmentation methods on Computed Tomography (CT) for two types of cardiac fat: Epicardial adipose Tissue (EAT) and Pericardial Adipose Tissue (PAT). These fat deposits, separated by the pericardium, have been linked to various cardiovascular diseases, with EAT receiving the most research attention. Their complex anatomical context makes manual quantification highly time-consuming and prone to considerable inter-observer variability. Automated methods effectively address these complications, offering a more efficient and consistent solution. This study encompasses a broad range of methods, spanning AI as well as non-AI approaches. Additionally, it presents the remaining challenges, including the need for larger annotated public datasets and optimized attenuation thresholds for contrast-enhanced CT. It is demonstrated that automated methods are able to achieve segmentation results comparable to the quality of human annotation, proving their potential as a clinical tool for discovering new biomarkers and enhancing patient outcomes.

Introduction. Clinical and Translational Science Award (CTSA) programs must document their scholars' research impact, but assembling each scholar's record by hand takes staff an estimated 15 hours and does not scale to a full cohort. An artificial intelligence (AI) agent could serve as a tool to gather scholar data across platforms and disciplines. Methods. We built a human-in-the-loop AI agent that assembles a dossier of sourced evidence for each scholar and drafts one-sentence Translational Science Benefits Model (TSBM) impact summaries for staff review. We evaluated it in the impact-reporting workflow of one CTSA hub across 10 career-development (KL2/K12) scholars. Two evaluation staff independently coded all 507 findings as accept, edit, or reject; the primary measure was the unanimous usable rate, defined as the share both accepted or edited. Results. Both reviewers accepted or edited 81.7% of the agent's findings. Reviewers each spent a median of 14 minutes per scholar, replacing an estimated 15 hours of manual assembly. Inter-rater agreement was moderate (Cohen's kappa 0.43 on the usable-versus-reject decision). A profile discovery study found the agent's recall close to human search. The agent's impact evidence spanned all four TSBM domains, and about a third of the reviewed findings fell in non-scholarly categories that routine processes tend to miss. Reviewers rated synthesis accuracy 4.5 and usefulness 4.8 on a 5-point scale. Conclusions. A human-in-the-loop AI agent can serve as the first-pass author of a scholar's impact record, shifting staff from collecting and writing to reviewing, and making cohort-scale impact reporting feasible.

Over the past few years, diffusion-based Schrödinger bridge models have been proposed to approximate optimal transport dynamics between two prescribed boundary distributions, with successful applications to generative modeling. More precisely, these methods aim to estimate a path measure whose initial and terminal marginals match the two boundary distributions, while minimizing the Kullback-Leibler divergence with respect to a reference Markov process. In this work, we consider the generalized Schrödinger bridge problem, in which the reference process is a twisted Brownian motion, that is, a Feynman-Kac transform of a Brownian motion induced by a time-dependent differentiable potential. Building on the Iterative Markovian Fitting (IMF) paradigm, and in particular on its special case Diffusion Schrödinger Bridge Matching (DSBM), which corresponds to the zero potential case, we introduce Twisted Schrödinger Bridge Matching (TSBM), a diffusion-based method designed to handle both continuous- and discrete-time potentials. Unlike previous approaches, TSBM provides a rigorous extension of the IMF scheme to the generalized Schrödinger bridge problem. This derivation leads to a new bridge-matching loss that depends explicitly on the gradient of the potential and recovers the DSBM objective when the potential vanishes, yielding improved performance. We further introduce trajectory-based variance-reduction techniques that substantially stabilize optimization and may be useful beyond the present setting. Finally, we empirically demonstrate the benefits of TSBM for trajectory inference across increasingly high-dimensional settings, including crowd navigation and single-cell data. Code available at https://github.com/maxencenoble/twisted-sb-matching.

This paper introduces Periodic Bootstrap Thompson Sampling (PBTS), an innovative extension of the classic Thompson Sampling (TS) algorithm tailored for bandit problems with periodic non-stationarity. Conventional TS accumulates all past observations, leading to biased posteriors when reward distributions cycle over time. PBTS overcomes this by synchronizing belief resets with known or inferred period intervals and embedding structured bootstrap exploration phases, effectively purging obsolete data while preserving uncertainty estimates. PBTS is tested in artificially constructed environments, which include skewed and balanced reward distributions, along with different bootstrap proportions and misaligned periodic intervals. Results indicate that PBTS generally achieves statistically significant reductions in cumulative regret against traditional TS in periodic non-stationary environments. Subsequent discussion further articulates the potential of PBTS's real-world deployment. The study mentions limitations like extreme periodic misalignment and proposes future research such as self-adjusting cycle-recognition. With memory reset and bootstrap phase, PBTS introduces a novel approach to optimizing bandit algorithms in periodic reward contexts.

An agent acting under partial observability must decide when to gather information and which observations are worth their cost. Standard POMDPs value information only through its eventual effect on reward. The $ρ$-POMDP framework instead rewards uncertainty reduction directly, through a belief-dependent utility $ρ$, but in practice both the choice of $ρ$ and the weight placed on it are tuned by hand for every task. We show that active inference removes this tuning entirely. Minimizing Expected Free Energy (EFE) is exactly equivalent to solving a $ρ$-POMDP whose utility is expected information gain, and the exploration weight is fixed at $w=1$ because the variational bound expresses pragmatic and epistemic value in the same units (nats). We prove this equivalence for observe-then-commit POMDPs and extend it to factored observation POMDPs, a broader class that covers interleaved observe-act problems such as non-destructive testing and mobile sensing, where gathering information leaves the hidden state unchanged. Experiments support the theory. Across environments ranging from the classic Tiger problem to RockSample and a new Structural Inspection benchmark with over 65,000 states, the untuned weight matches or outperforms reward-only planning at the same horizon, avoids the over-exploration of bonuses tuned per task, and sits near the reward-maximizing knee of the success-reward Pareto frontier. The practical payoff is an exploration objective that works out of the box. In applications such as fault detection and medical screening, where every test has a price and every missed fault has a cost, EFE supplies a belief-dependent utility that is derived rather than tuned.

Repository mining studies increasingly analyze AI-evidence projects, yet it remains unclear how to measure whether architectural changes create deferred stabilization obligations. A natural metric, post-anchor stabilization density, counts tests, CI gates, documentation, and fixes appearing after a durable boundary is introduced. We show that this metric fails. In a diff-level study of 338 high-visibility 2026 GitHub repositories, anchors are common (321 of 338 contain real changed-file anchor evidence), but a controlled 308-event contiguous-window experiment finds no post-anchor uplift: broad and strict stabilization signals both yield median post/pre density ratios near 1.0, and non-anchor controls are equally dense. We introduce stabilization regimes, six recurring patterns that explain why the density metric fails, and use human validation to calibrate them. Two independent coders label 100 stratified candidate-anchor events from blinded packets (kappa = 0.50 on debt attribution). The validation exposes a two-layer trap: many candidate anchors are not durable boundaries (45 of 100), and even among valid anchors in this calibration sample the no-uplift result holds: only 3 of 100 events survive as attributable delayed obligations; the remaining 97 are explained by classifier error, anchor-local hardening, background maintenance, or pre-anchor hardening. Post-anchor density conflates pervasive maintenance with genuine debt; controlled designs with regime-aware attribution are necessary before repository mining can reliably identify stabilization obligations.

Retrieval-Augmented Generation (RAG) systems increasingly power enterprise LLM applications, yet the vector retrieval layer introduces two underexplored challenges: (1) trained codebook quantizers may expose corpus statistics during index construction, creating a leakage channel in multi-tenant deployments, and (2) post-hoc filtering for tenant isolation degrades recall on selective queries. We study TurboVec, an open-source vector index built on TurboQuant - a codebook-oblivious scalar quantizer requiring no corpus-dependent training. On the DBpedia OpenAI embeddings benchmark (d=1536, 100K-999K vectors), TurboQuant 4-bit outperforms trained FAISS Product Quantization at the same memory budget by 8.5-8.9 percentage points in Recall@5 across all scales. Compared to HNSW (R@5=0.991) and IVF-PQ (R@5=0.840), TurboQuant occupies a distinct design point: higher recall than IVF-PQ without training, at 4-8x less memory than HNSW. Deployed on Snowpark Container Services, TurboVec achieves 11ms median query latency at 100K vectors versus 707ms for warehouse brute-force scan. Kernel-level allowlist filtering maintains 0.86-0.93 Recall@10 across 10-1000 tenant workloads versus 0.09-0.19 for post-filter baselines. Codebook-oblivious design reduces membership inference accuracy to near-random (50.0%) versus 57.3% for PQ codebooks. Limitations include single dataset evaluation, uncompressed HNSW comparison, and privacy evaluation on synthetic data only.

Continuous Chain-of-Thought methods replace verbose reasoning traces with a short sequence of dense latent representations. Earlier continuous CoT methods indirectly supervise the latent representations such that its final state match that of verbose reasoning traces, requiring autoregressive, slow generation during training. We introduce C-MTP, a simpler, faster direct supervision approach that models each latent as an average of the embeddings in the CoT traces to be compressed. Our approach outperforms a prior direct supervision method that approximates the distribution of compressed tokens, and performs competitively to slower indirect supervision approaches in existing evaluation setup with simplified CoT traces (less than 100 tokens). Lastly, we extend the evaluation of Continuous CoT methods to complex tasks with longer reasoning traces ($\ge$ few hundreds reasoning tokens). We find both direct and indirect supervision training methods perform poorly (roughly 65\% performance drop) in this setting, revealing the limitations of current continuous CoT methods. The code and checkpoints are released at https://github.com/Varun221/cmtp_research

Predictive maintenance relies on accurate Remaining Useful Life estimation, often formulated using survival analysis over multivariate time-series data. While modern deep survival models achieve strong predictive performance, their black-box nature limits their use in safety-critical settings where actionable insight is required. In this work, we introduce \textit{SurvCF(t)}, the first framework for generating counterfactual explanations for survival models operating on time-series data. \textit{SurvCF(t)} identifies minimal, plausible, and temporally consistent changes to an asset's operational history that increase its predicted life time, framing explanation as a constrained optimization problem combining validity, proximity, sparsity, and plausibility. We evaluate the method on multiple benchmarks, including C-MAPSS, N-CMAPSS, and a real-world case study of the Scania Component\_X dataset, demonstrating its ability to produce actionable and interpretable interventions. Our results show that \textit{SurvCF(t)} bridges the gap between survival prediction and prescriptive maintenance, enabling explainable and decision-oriented AI for maintenance strategies.

Estimating entropy from samples is fundamental in information theory and property testing. Shannon entropy measures average uncertainty and can be estimated to constant additive accuracy over a $k$-symbol alphabet using $Θ(k/\log k)$ samples. Min-entropy depends only on the most likely symbol. Both are special cases of order-$α$ R'{e}nyi entropy, $H_α$. We characterize the sample complexity of estimating min-entropy and R'{e}nyi entropy for $k$ and integer $α>1$; our lower bounds also hold for noninteger $α\ge1.001$. We prove that min-entropy estimation to constant additive accuracy has sample complexity $Θ(k\log k)$. The upper bound uses the largest empirical frequency and concentration via dyadic grouping. The matching lower bound hides a slightly heavier symbol at a uniformly random location. Thus, min-entropy requires $Θ(\log^2 k)$ more samples than Shannon entropy and corrects a previously stated $Θ(k/\log k)$ characterization. For every integer $2\leα\le c_0\log k$, we prove the matching fixed-accuracy bound $Θ_{c_0}(αk^{1-1/α})$. Previous results gave $Ω_α(k^{1-1/α})$ for fixed integer $α>1$ and $O_{c_0}(α^2k^{1-1/α})$ for all integer $α>1$. Our upper bound analyzes an unbiased falling-factorial estimator based on $α$-way collisions, while a hidden-heavy-coordinate construction gives the matching lower bound and shows that the factor $α$ is unavoidable. For every real $1.001\leα\le c_0\log k$, we prove the uniform lower bound $Ω_{c_0}(αk^{1-1/α})$. Finally, since $0\le H_α(p)-H_\infty(p)\le\log k/(α-1)$, min-entropy uniformly approximates $H_α$ when $α$ is a sufficiently large multiple of $\log k$. Combining this reduction with our min-entropy bounds gives $Θ_\varepsilon(k\log k)$ sample complexity in the high-order regime.

Existing tool-use benchmarks report a single success rate for complex, multistep tasks. Inspired by ideas from cognitive science, we distinguish tool use from tool discovery and decompose the latter into curiosity (the model's ability to discover the parts needed to build the tool), recognition (the model's ability to discover the process of creating the tool), and efficiency (the model's use of the tool after creation). We show that this framework can be applied to existing discovery tasks, such as Voyager. In addition, we provide evidence that recognition inversely scales with model size, and we introduce and analyze a class of combinatorial games that demonstrates this. We further observe inverse scaling in a separate environment designed to emulate real-world tasks.

On-policy knowledge distillation transfers reasoning from large teachers to compact students, but existing approaches suffer three compounding failure modes: (i) cold-start collapse, where a fresh student assigns near-zero mass to teacher-preferred tokens; (ii) state-agnostic divergence scheduling, where time-only forward/reverse-KL interpolation ignores the student's coverage state; and (iii) binary reward sparsity, where pass/fail signals discard information from partially correct traces. We present CADENCE, a unified framework with a targeted fix for each. Its DRIFT mechanism schedules a per-token convex mixture of forward-KL and reverse-KL surrogate objectives on student-sampled trajectories (per-token surrogates, not sequence-level KL gradient estimators). Six components extend it: (A) COVA, a coverage-adaptive $β$ schedule accelerating the forward-to-reverse transition; (B) FTB, a forking-token boost concentrating gradient at high-entropy positions via a globally-normalized entropy reference; (C) CCD, a dense reward adding numerical-proximity partial credit for incorrect-but-close traces; (D) LAP, brevity-preferential correct-rollout reinforcement; (E) EMR, an entropy-matching calibration regularizer; (F) BSD, a bootstrapped self-distillation phase. On GSM8K and MATH-500 (corrected 512-token protocol, 5 seeds, reported std), CADENCE distills a 0.5B student from a 1.5B teacher to 69.8 $\pm$ 0.5% GSM8K pass@1 (from 48.7% pretrained; 63.2% of the teacher gap closed) and to 72.1 $\pm$ 0.4% with a 3B teacher (76.2% closed), beating the strongest matched-compute label-using baseline (DRIFT+binary reward) by +4.4 $\pm$ 0.7 points. All experiments run on a single Apple Mac Studio (M-series, 64GB unified memory), showing principled distillation reaches strong reasoning quality without datacenter-scale hardware.

Polycystic Ovarian Syndrome (PCOS) is a widespread hormone problem for women of childbearing age. Women with PCOS may not ovulate; they might have high levels of androgens and have many small cysts on the ovaries. It can cause missed or irregular menstrual periods, excess hair growth, acne, infertility, and weight gain. Machine Learning (ML) can effectively diagnose this disease at an earlier stage as tons of medical data are available now. Traditional approaches to detect PCOS encompass a combination of clinical evaluation, medical history assessment, physical examination, and laboratory tests. These approaches aim to identify the characteristic symptoms and hormonal imbalances associated with PCOS. Physical examination requires good resources and costs time and money. In recent times, data-driven techniques have substantially advanced disease prediction within the medical field. We aim to utilize ML approaches, incorporating unique feature selection algorithms, to predict PCOS. This paper introduces a data-driven approach to PCOS diagnosis, combining Feature Engineering and ML. Several feature selection approaches have been considered to select sets of features for training the ML model, including CatBoost, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), AdaBoost, Random Forest (RF). Results demonstrate that AdaBoost, with ten features selected by RF Feature Importance and Highest Correlation (HC), provides the highest test accuracy.

End-to-end autonomous driving models are now able to navigate complex road scenarios, mapping raw sensor observations directly to observed paths for open-loop evaluation and often effective driving in closed-loop evaluation. Yet the internal logic of these safety-critical systems remains largely opaque, due to the complexity of traffic scenes. We propose a counterfactual ablation framework called Counterfactual Vision Action Analysis (CVAA) that systematically removes individual detected objects from front-camera images using photorealistic generative inpainting to prepare counterfactual sets to evaluate the difference in the model's response. This isolates the causal effect of each object's presence on the model's planning behaviour. Applied to the Alpamayo 1 trajectory predictor across 210 nuScenes driving scenes, we create a dataset Counter -nuScenes, using which we see that vehicles and pedestrians within the model's 'path' dominate causal influence as expected, while traffic lights, as expected, exert disproportionate effect relative to their image footprint. However, we also find cases where the model responds strongly to objects a human driver would consider irrelevant. This brings forth a deeper question: does the model itself view the scene as a sum of individual objects influencing the outcome, or does it encode an entirely different set of internal features that do not correspond to human-legible scene elements? To further understand this, we compare intermediate representations of original and inpainted image pairs using mechanistic interpretability techniques and examine the effect of the removal through the various model layers. Together, these two stages offer a path from behavioral auditing to representational understanding, creating explainable driving systems and solidifying human-AI trust.

Pediatric bone age prediction is a crucial task in clinical practice that can help diagnose endocrine disorders and provide insight into a child's growth and development. However, conventional bone age prediction methods are often labor-intensive and require specialized radiological expertise. This paper presents a Deep Learning (DL)-based approach to pediatric bone age prediction using EfficientNet with Additive Attention, a state-of-the-art neural network architecture for image classification and regression tasks. The method utilizes over 12,000 X-ray images from the RSNA bone age dataset. It involves image preprocessing, transforming them into three-channel images, and training a Convolutional Neural Network (CNN) to automatically learn the features of hand bone images. This approach provides a more effective and accurate solution for predicting bone age, which is critical in diagnosing pediatric endocrine diseases. This work uses two variations of the EfficientNet model (B0 and B4), where EfficientNetB4 is also finetuned with the Additive Attention mechanism. These three models predict the age for the original age, and their comparison is shown in curves. The predicted ages depict that in most cases, EfficientNetB4 and EfficientNetB4 with Additive Attention (EN-AA) successfully predicted the bone ages more accurately regarding the original age, and their performance was better than the EfficientNetB0. Specific performance metrics are provided to underscore this improvement. Learning curves for training and validation loss confirm effective learning without overfitting or underfitting, further validating our approach's efficacy in pediatric endocrine disease diagnosis.

Traditional randomized trials often obscure clinically meaningful heterogeneity in treatment response by focusing on average effects. Leveraging real-world data to emulate clinical trials and estimate heterogeneous treatment effects (HTEs) offers a promising path toward more precise and efficient trial design. In this study, we emulate the DAPA-HF trial using electronic health records from the Mayo Clinic Cloud (MCC) to investigate whether HTE-guided stratification can identify patient subgroups with distinct treatment responses to dapagliflozin versus placebo in patients with heart failure with reduced ejection fraction. All-cause mortality was evaluated using Cox proportional hazards models, with HTEs estimated using a Meta-S learner and subgroups defined using a decision tree-based thresholding approach. In the overall cohort of the emulation, no significant treatment difference was observed (HR, 1.681; 95% CI, 0.828-3.413; p = 0.1507). However, compared with the overall emulated cohort, in which dapagliflozin showed no statistically significant survival benefit, HTE-driven stratification identified subgroups with significant and directionally distinct treatment effects. The beneficial (low-HTE) subgroup showed a significant survival benefit from dapagliflozin (HR = 0.203, 95% CI, 0.087-0.476, p = 0.0002), whereas the harmful (high-HTE) subgroup showed a significant harmful association with markedly increased mortality risk (HR = 6.680, 95% CI, 2.759-16.171, p < 0.0001). These findings indicate that HTE-guided stratification can uncover clinically meaningful beneficial and harmful treatment-effect patterns that are masked in the full-cohort emulation.

Throughput prediction is foundational for artificial intelligence-driven 6G resource orchestration. Conventional monolithic machine learning models struggle to generalize across diverse operators, mobility modes, and traffic types, leaving a critical stochasticity gap between signal conditions and achievable throughput. To overcome these constraints in heterogeneous urban environments, we propose a Tiered Multi-Agent System (TMAS) that dynamically routes edge telemetry to context-aware Domain Micro-Agents, validated on a dataset of 48,618 samples collected in Sunway City, Malaysia, with Nemo Handy drive test software, spanning three Tier-1 mobile network operators, three mobility modes, namely (i) elevated pedestrian walkway, (ii) ground-level shuttle bus, and (iii) elevated bus rapid transit; and three traffic profiles, namely (i) persistent download, (ii) persistent upload, and (iii) adaptive video streaming. Our evaluations reveal that TMAS overcomes predictability bottlenecks, achieving a coefficient of determination (R2) of up to 0.931 and a Mean Absolute Error (MAE) as low as 0.53 Mbps. The system demonstrates high operational efficiency, with rapid micro-agent training times, low inference latencies, and agentic routing overhead of 0.004 to 0.126 ms. These latency characteristics indicate the architecture is a promising candidate for the response times required by next-generation wireless networks.

We introduce Deep Adaptive Bayesian Screening (DABS), a method for performing adaptive factorial screening in high-dimensional discrete design spaces. DABS learns a policy network offline to sequentially select informative experiments, amortizing Bayesian Optimal Experimental Design. It handles binary designs, incorporates sparsity and interactions via a spike-and-slab prior with strong heredity. The model is trained using a contrastive lower bound on information about factor activity with nuisance effect sizes and noise variance analytically integrated out. Unlike prior amortized Bayesian design approaches, DABS also integrates Gibbs posterior inference at deployment, yielding posterior probabilities of factor activity and credible intervals on effect sizes. We demonstrate DABS on screening problems calibrated to real-world benchmarks and show it achieves superior accuracy and scalability over classical and Bayesian baselines under tight experimental budgets.

Non-prehensile manipulation enables flexible material handling with part carriers, but friction-based support makes high-speed motions failure-prone, while slower operation increases cycle time. Proactive failure prediction is therefore essential for efficient and reliable performance, yet existing approaches remain limited by key constraints, including sensitivity to dynamic actions and high dependence on known policy structures. Furthermore, existing methods and datasets lack a precise characterization of the latest intervention time, leaving it unclear whether a detected failure can still be prevented through timely intervention. In this paper, we investigate lift-and-place tasks for non-prehensile material handling manipulation and propose a more effective approach to predicting precursors to failures (PREFAIL) by analyzing the relative motion of target objects with respect to the carrier. We further introduce a dataset that precisely identifies the latest intervention time for risky manipulations, enabling rigorous evaluation of whether a failure prediction is actionable. We validate our approach on both simulation and real-world datasets. Our experimental results demonstrate that PREFAIL substantially improves both the accuracy and timeliness of responses to failure precursors.

Indoor robots are increasingly employed for facility management tasks such as cleaning and inspection. These applications primarily rely on navigation and can be effectively supported by predefined routes or perception-driven Simultaneous Localization and Mapping (SLAM) techniques. However, more complex tasks, such as locating and repairing leaking pipes, require not only navigation but also access to building information, including the location, geometry, material, and operational attributes of components. Existing navigation approaches provide only limited environmental understanding and cannot readily supply such information. In contrast, Building Information Modeling (BIM) contains rich geometric, semantic, and operational information that remains largely underutilized in robotic applications. This study proposes a BIM-enabled, agent-based simulation platform for knowledge-driven indoor robot navigation and operation planning. Within the framework, indoor environments are discretized into grid cells that are mapped to graph nodes and classified as target, obstacle, or regular nodes according to their spatial relationships with building elements. Traversal costs are assigned to edges connecting neighboring nodes, enabling graph-theoretic algorithms to compute efficient and collision-free navigation paths while avoiding obstacles. Simulation results demonstrate that the proposed graph representation enables efficient and collision-free navigation. A key limitation associated with coarse discretization, namely overlap between target-occupied and obstacle-occupied cells, is identified and mitigated through grid refinement, improving spatial accuracy and path feasibility. The proposed platform supports virtual evaluation of robotic operations prior to deployment and provides a foundation for BIM-informed robotic systems in facility management.

Bladder cancer treatment requires personalized and adaptive decision-making, particularly for recurrent disease, where treatment effectiveness changes across successive clinical episodes. Conventional clinical decision support systems typically rely on static treatment guidelines or single-step predictive models, limiting their ability to capture disease progression over time. This paper presents a recurrent patient state-transition simulation framework for bladder cancer treatment planning that integrates predictive state-transition modeling with a Markov Decision Process (MDP) and a Deep Q-Network (DQN) reinforcement learning environment. The predictive module estimates changes in tumor characteristics following treatment, while the reinforcement learning agent sequentially optimizes treatment decisions by interacting with simulated patient trajectories. This framework enables dynamic, patient-specific treatment planning by continuously adapting recommendations to evolving clinical states. It also generates interpretable treatment trajectories and detailed simulation logs to improve transparency and support clinical decision-making. The proposed framework was evaluated against existing reinforcement learning-based treatment planning approaches. It achieved a cumulative reward of 63,918.87, an average training loss per episode of 0.0056, and a policy improvement score of 6.62%, demonstrating effective sequential learning and robust treatment optimization in a simulated recurrent treatment environment. These findings highlight the potential of recurrent patient state-transition simulation with reinforcement learning as a flexible decision-support framework for personalized bladder cancer treatment planning and AI-assisted precision oncology.

Value-aware AI systems require explicit computational representations of human values (groundings) and their aggregation into value systems in order to align their decisions with ours. As such representations are difficult to elicit, value learning seeks to infer them by observing human behaviour. This work addresses the lack of grounded value learning methods in generative AI: existing approaches typically replicate human preferences without awareness of the multidimensional structure of value alignment, or lack principled value system elicitation methods. To address these gaps, we adapt a previously validated value system learning method to the generative AI setting, which, based on pairwise prompt-response preference data, simultaneously learns: i) an implementation of a grounding for a set of values given by a multi-objective reward model, and ii) a value system representation in the form of a weighted linear scalarization of the previous grounding model. To ensure that the learned value systems are based on coherent value representations, our algorithm dynamically prioritizes the grounding learning process. We evaluate the method against baselines and a contemporary method on prompt-response preference datasets. Results show competitive performance and minimal trade-offs against the baselines, while improving explainability.

Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories. However, collecting such data at scale typically requires fully implemented environments with executable APIs and realistic, pre-populated backend databases, creating a major bottleneck for scalability. To overcome this, we propose an environment-free synthetic data generation approach that leverages LLMs as on-the-fly digital world models. Given only API specifications, our method generates trajectories mimicking interactions between an agent and a stateful environment. Specifically, an LLM first generates diverse tasks solvable with the provided APIs. A teacher agent then iteratively solves each task while an LLM simulator generates coherent synthetic API responses conditioned on the task context and simulation history. Finally, an LLM judge filters the trajectories to ensure the quality of the resulting dataset. We evaluate our approach on the challenging AppWorld and OfficeBench benchmarks, which include both information-retrieval and state-changing tasks. Fine-tuning models on our synthetic data yields significant performance gains, demonstrating that effective supervision for API-calling agents can be generated without any executable environment. Our results establish LLM-based API simulation as a practical, scalable solution for training agents across diverse API ecosystems.

Unified multimodal models (UMMs) have recently demonstrated powerful instruction-based image editing capabilities, but they also raise serious concerns about unauthorized manipulation of personal portraits. Existing adversarial protection methods are mainly designed for either visual understanding or image generation models and often become ineffective when transferred to UMMs, which process an image through multiple complementary visual pathways. In this work, we first conduct a feature-level analysis of unified image editing. We observe that the ViT-based understanding branch and the VAE-based generation branch exhibit non-trivial structural agreement for the same input image. Although perturbing an individual branch can reduce this agreement and induce intermediate hidden-state deviations, such effects are asymmetric and gradually attenuated during multimodal fusion and generation. These observations reveal that single-branch feature distortion is insufficient for consistently disrupting unified image editing. Motivated by this finding, we propose CCS, a unified adversarial protection framework that jointly drives the ViT and VAE representations away from their clean counterparts while explicitly disrupting their cross-branch compatibility through linear CKA. By simultaneously removing stable information from both visual pathways and creating incompatible visual contexts, CCS prevents the UMM from recovering reliable identity information during editing. Extensive experiments demonstrate that CCS consistently outperforms existing protection methods in suppressing identity-preserving edits.

Safe adaptive control is online adaptation under a safety guarantee on the learning trajectory itself. The controller may use any causal, history-dependent rule and act differently across environments as data arrive. Only its safety guarantee is uniform: the same rule must satisfy it under every initially plausible model. Performance is measured against a safe oracle that knows the realized model. Many finite-time analyses assume persistent excitation of the uniformly safe closed loop, so the data distinguish every pair of models requiring different control decisions. Under that assumption, feasibility is already settled; only the rate remains. We ask instead: Do the safety constraints permit such an informative experiment at all? While an alternative remains plausible, the controller must preserve a safe continuation under it. We call the first action that forecloses such a continuation commitment. Chance safety allows commitment only on an event rare under the alternative, and the evidence must arrive beforehand: the observation generated by the committing action is too late. We define precommitment information as the KL divergence between learner-visible laws stopped before commitment. Our main result is a causal reduction. The commitment rule determines (1) the probability that safety permits commitment under the alternative, (2) the target-side cost of remaining noncommittal, (3) and the information available when the decision is made. Bounded precommitment information therefore leaves a fixed fraction of the oracle gap unavoidable. If the gap is Ω(T), every uniformly safe policy has linear regret. We establish the obstruction in a constrained linear system with quadratic regulation cost. We also prove recovery in special cases and derive semidefinite upper certificates for deterministic linear-Gaussian systems.

Many complex systems such as brain networks, financial markets, and gene-regulatory circuits are described not by a fixed graph but by one that changes over time. A standard way to summarise such structure at each instant is the sparse precision (inverse-covariance) matrix, and the time-varying graphical lasso (TVGL) turns a multivariate signal into a smooth chain of these matrices. We introduce TVGL-CFM, a single model that learns the distribution of such chains and can both generate new, realistic time-varying network trajectories for a given class and forecast how an observed trajectory will continue. Each precision matrix lives on a curved space of positive-definite matrices, but a log-Euclidean chart flattens an entire trajectory into an ordinary vector space, so a simple conditional flow-matching model can be trained and sampled there while every decoded matrix is guaranteed to be a valid precision matrix. For forecasting we start the flow not from noise but from a rough extrapolation of the recent history, so the model only has to learn a small correction. Across EEG motor-imagery, chaotic systems, and gene-expression data, TVGL-CFM generates trajectories that keep the class-discriminative structure of real data, and it forecasts future connectivity more accurately than raw-signal baselines. Generating the structured precision trajectory directly is therefore more faithful than generating raw signals and estimating connectivity afterwards.

A truckload carrier must accept or reject each load tender within seconds. The decision depends on fleet state, hours-of-service (HOS) clocks, and appointment windows. We model this as a weakly coupled dynamic program in which the resources relocate and carry clocks: serving a request moves the truck to a new market and depletes its clocks, and whether a truck can serve a request depends on its state. Occupancy-based reusable-resource models do not cover this setting. We build a real-time dual-price policy from the same Lagrangian relaxation that gives the problem's upper bound. Policy and bound come from one object, so every run reports a certified optimality gap. We prove three things. First, the certificate is valid for any duals, any discretization, and any surrogate quality. Second, the policy's same-time spatial-gradient rule is exactly fluid complementary slackness, and the policy is asymptotically optimal in the subcritical fluid regime; the fitted prices are also portable across sample paths, by linear-programming basis stability. Third, certificates have limits: per-resource Lagrangian slack can stay bounded away from zero at every fleet size. We exhibit a three-truck kernel with an exact rational certificate and a replication lemma. On a public closed-loop benchmark with thirty paired seeds, the policy -- which needs no rollout labels, only one offline dual solve -- beats a rollout-trained surrogate on two of three scenarios (tight: +2.0 pp, 95% CI [+0.5, +3.6], Wilcoxon p = 0.023; mild: +3.5 pp, CI [+2.4, +4.5]) and ties the third. It decides in 0.04-0.09 ms, three orders of magnitude faster than the Monte Carlo rollout teacher. Its certificates are stable across ten bounded instances per scenario, at 57-64% of optimal, within 3-6 points of what the 1000x-slower teacher certifies.

Deploying a medical imaging model that must later accommodate a modality it has never seen is a recurring practical problem: retraining the shared representation is expensive and destroys performance on the modalities already in service. We study this \emph{onboarding} problem under a strict leave-one-domain-out protocol, in which a convolutional backbone is pre-trained on source modalities (Kidney CT and Brain MRI), frozen permanently, and then required to accommodate an unseen modality (Chest X-ray). Under this protocol we establish three findings. First, decision-layer parameter-efficient fine-tuning is insufficient when the backbone has never observed the target modality: a linear probe and fully-connected LoRA both fall well short, whereas convolutional LoRA recovers most of the achievable accuracy, showing that adaptation must reach the convolutional features. Second, and centrally, the low-rank convolutional \emph{basis} learned on the source modalities \emph{transfers}: freezing that basis and training only its up-projections onboards the unseen modality using just $0.78\%$ of full fine-tuning's parameters, at an accuracy $6.11$ percentage points above a random basis of identical size, while an equivalent decision-layer basis exhibits no reliable transfer. Third, adapter-based onboarding leaves source-modality accuracy exactly unchanged ($Δ= 0.00$ pp), whereas full fine-tuning reaches the highest target accuracy only by catastrophically degrading the source modalities. A Mahalanobis score on frozen backbone features detects the unseen modality with high sensitivity at a strict source-retention threshold, providing a practical trigger for when onboarding is required. All results are reported over three seeds with paired bootstrap confidence intervals.

Time series forecasting (TSF) is vital to many applications, yet existing models often struggle to capture the heterogeneous long-range global patterns and short-range local variations in multivariate time series. While some approaches partially model these dependencies, they often do not jointly exploit temporal and feature-wise information. To address this challenge, we propose HyBDM, a multi-scale hybrid model that decomposes temporal dynamics into global patterns and local variations, which are modeled by two specialized experts. The Global Patterns Expert employs an enhanced BiConv-Mamba module that integrates bidirectional convolutions, an M-SSM layer, a forgetting mechanism, and a GDD-MLP module for cross-channel modeling. The Local Variations Expert uses a Local Window Transformer (LWT) to perform efficient locality-aware attention with reduced computational complexity. In addition, a Multi-Scale Patcher and a Long-Short Router enable multi-resolution representations and adaptive fusion of the two experts. Experiments on six benchmark datasets show that HyBDM outperforms state-of-the-art methods in both forecasting accuracy and computational efficiency, demonstrating its effectiveness in bridging global-local dependencies for multivariate TSF.

The increasing complexity of next-generation wireless networks has driven the integration of artificial intelligence (AI) into wireless communications. However, most existing studies focus on developing task-specific deep learning techniques for single scenarios, which limits their ability to generalize across diverse tasks, channel conditions, and system configurations. To address this generalization bottleneck, we propose a hierarchical wireless foundation model (WFM) for multi-task optimization. The proposed WFM couples an upstream foundation channel encoder (FCE) with a downstream foundation optimization decoder (FOD) via geometry-aware cross-attention. Specifically, the FCE extracts task-agnostic channel representations via self-supervised masked reconstruction while the FOD generates multi-task optimization decisions through differentiable output heads. Moreover, a hybrid supervised-to-unsupervised training strategy is employed to overcome the performance ceiling of purely supervised learning, and the modular architecture of the WFM enables efficient adaptation to unseen communication tasks with minimal parameter overhead. Simulation results show that the proposed WFM learns high-fidelity channel representations and achieves competitive multi-task optimization performance while substantially reducing optimization inference latency relative to numerical baselines. Furthermore, it exhibits robust generalization to unseen propagation environments, varying constraint parameters, and heterogeneous system configurations.

We introduce the vehicle routing problem with stochastic demands and outsourcing options (VRP-SDO), in which a logistics service provider partitions customer requests into customers outsourced to a common carrier and customers committed to its fixed fleet. The latter induces a vehicle routing problem with stochastic demands (VRP-SD), solved dynamically. Demands are revealed upon visit; residual demand may be served by other vehicles or after restocking at the depot. Work beyond the regular shift incurs overtime costs, and the unit outsourcing cost decreases with the expected outsourced demand. The objective is to minimize expected travel, overtime, and outsourcing costs. We propose an iterative two-level methodology whose first level partitions customers into committed and outsourced subsets, while the second level estimates the expected VRP-SD routing cost. To avoid solving this problem from scratch at every iteration, we learn an offline routing policy that estimates costs almost instantly for any committed subset. An iterated local search establishes the first-level partitions. We formulate the second level as a Markov decision process and solve it with a deep Q-network whose state is represented by a graph attention network aggregating customer and vehicle information by relevance to the acting vehicle. Trained offline on instances with variable customer cardinality and locations, the policy applies to any daily customer realization; online fine-tuning improves the cost approximation. Experiments show that our policy reduces routing costs by 19.6% relative to a state-of-the-art method and by at least 29.6% over classical heuristics. Our overall algorithm saves 13.7% on average over the version without the attention-based representation and generates high-quality decisions within minutes, whereas benchmarks without an offline-trained estimator require over an hour.

Diffusion large language models (dLLMs) are a promising alternative to autoregressive generation. However, reasoning-oriented post-training for dLLMs remains challenging. Supervised fine-tuning (SFT) for dLLMs requires dense but often off-policy masked states, while reinforcement learning (RL) relies on sparse rewards or value modeling. This paper proposes \textbf{trace-based on-policy distillation (TOPD)}, a teacher-supervised framework that transfers reasoning ability to a target dLLM without reward estimation. The key idea is to supervise a dLLM on its own denoising trajectory, focusing on the trace-aligned token decisions that form the final response. Specifically, TOPD samples on-policy diffusion trajectories from the target dLLM, obtains teacher token distributions from a teacher model on the corresponding partially denoised states, and updates the target dLLM with a token-level Reverse Kullback-Leibler (Reverse-KL) objective. This design preserves dense teacher supervision while aligning training with the model's own denoising states. On mathematical reasoning benchmarks, TOPD enables SDAR-4B-Chat to match the MATH500 accuracy of its RL-trained counterpart TraDo-4B-Instruct, with gains of +5.7 under static evaluation and +4.5 under dynamic evaluation. Compared with the RL-trained counterpart, TOPD achieves this with 4$\times$ fewer rollout rounds, corresponding to an estimated 96.0$\times$ to-accuracy model-compute speedup.

End-to-end speech language models increasingly represent user speech with speech tokens rather than relying exclusively on cascaded ASR--LLM--TTS pipelines. Although these tokens support expressive and low-latency spoken interaction, they may also preserve sensitive speaker characteristics. We investigate whether exposed speech tokens leak voiceprints and formulate this risk as a speaker inversion attack. We introduce Audio BERT (AuB), a trainable model that constructs token embeddings from discrete codebooks and aggregates them into speaker-sensitive representations, and propose SpInv, a two-stage inversion method built on AuB to recover embeddings in the space of an attacker-specified speaker encoder. We evaluate Moshi, Higgs3, Kimi-Audio, and Qwen3-Omni using speaker-disjoint protocols on the VoxCeleb dataset. Extensive experiments show that, with only three seconds of frontend output, SpInv achieves cosine similarities above 0.70 in the attacker-specified speaker-encoder space.

Large Language Models (LLMs) often produce confidently stated yet unreliable outputs, posing critical challenges for deployment in safety-sensitive applications. Existing uncertainty metrics such as semantic entropy capture agreement at the level of semantic equivalence, but largely ignore the logical relationships between distinct answers. As a result, they tend to overestimate uncertainty and falsely flag hallucinations in settings where generated responses are diverse in form yet logically compatible (e.g., differing only in granularity or specificity). We propose Logical Graph Uncertainty (LGU), a framework that explicitly models implication and incompatibility among answers. LGU aggregates probability mass along entailment chains, computes entropy over logically maximal hypotheses, and penalizes mutual incompatibility among them. Across multiple question-answering benchmarks, LGU consistently improves uncertainty estimation over existing methods, and outperforms the semantic entropy baseline by up to +7.1% AUROC and +3.5% AUARC across datasets.

Supercharging of lithium-ion batteries (LiBs) requires robust health monitoring to ensure durability, safety, and user confidence, particularly for emerging vehicle-to-grid applications with bidirectional energy flows. Yet battery management remains largely disconnected from the material and structural origins of aging, limiting both interpretable health assessment and informed battery design. Here we propose a physics-informed learning framework with virtual sensing that infers hard-to-measure design parameters, including solid-state diffusion coefficient, electrode thickness, ion concentration, and particle size, directly from standard battery management system (BMS) measurements. Across diverse fast-charging strategies and driving profiles, embedding a digital-twin-derived particle-cracking mechanism as a soft constraint reduces trajectory and lifetime prediction errors by 6-8 times relative to state-of-the-art machine learning baselines using only 2% early-life observations. We further show that accurate degradation extrapolation does not require fully resolved governing equations; validated partial mechanisms, jointly refined with limited data, provide sufficient guidance. Virtual sensing transforms standard charging signals into latent design variables without additional sensors, bridging observable battery behavior and underlying aging processes while reducing capacity loss error by up to 39%, end-of-life (EOL) error by 17%, and prediction variability by up to 54%, enabling real-time exploration of new battery configurations. More broadly, the proposed framework establishes a practical feedback loop between deployment and development, demonstrating how real-world operation can continuously inform upstream design decisions across complex multiphysics systems.

Across environments with mixed sources of uncertainty, unsupervised reinforcement learning requires intrinsic motivation that does not precommit to a particular direction of surprise. Surprise minimization is scoped by design to ``unstable'' environments. Prediction-error curiosity rewards total expected surprise, including irreducible noise. Bandit or mixture switching between surprise-minimizing and surprise-maximizing rewards reintroduces non-stationarity by construction. We propose a single intrinsic reward, stationary within each window, derived from the novelty contribution of a preference-free Expected Free Energy objective, expressed in reward-maximization form. Our claim is that parameter information gain, the expected surprise of the next state minus its irreducible part, is the appropriate intrinsic signal in both high-entropy and low-entropy components of the state space. Maximizing it seeks exactly the surprise the model can explain away. In regions of unresolved dynamics, this epistemic term drives exploration. As dynamics become resolved, the epistemic term vanishes, while an aleatoric penalty favors lower-variance transitions, all without fitting an explicit next-state predictor. A pseudocount supplies epistemic value, a probe-based penalty captures aleatoric variance, and a short-horizon gate protects informative successors. A window-based freeze of all reward-defining objects yields a stationary Bellman operator, explicit bounds on learning targets, and a conditional uniform-concentration result for the nonparametric estimators under mixing, smoothness, bandwidth, and capacity assumptions. In active-inference terms, the agent is preference-free where novelty is retained, standard likelihood ambiguity vanishes under full observability, a nonstandard transition-entropy penalty is added, and surprise minimization emerges in resolved regions of the state space.

Deploying LLM agents typically requires a compact test-time student, even if a stronger teacher is available during training. We study knowledge brewing: distilling a teacher's interactive experience into a persistent external memory for the student. Crucially, this requires no weight updates, expert demonstrations, ground-truth labels, or test-time teacher access. This setting poses two challenges: environments provide only sparse, binary feedback, and teacher-authored notes must be inherently tailored to be concretely executable by a substantially weaker student. To address these hurdles, we propose AgentBrew, comprising two coupled components. First, a failure-triggered teacher--Ralph Loop mitigates sparse feedback by transforming student failures into environment-validated notes. Second, student-aware synthesis calibrates teacher knowledge to the weak executor's operational granularity, yielding model-specific, actionable guidance. Extensive evaluations and comprehensive ablations across coding, math, and tool-use tasks demonstrate that this asymmetric, training-free brewing paradigm produces highly capable yet deployable LLM agents.

Entropy control has become an effective tool in reinforcement learning (RL) of large language models (LLMs), helping balance exploration-exploitation trade-off during alignment process. Such RL paradigm is often conducted on mixtures of heterogeneous tasks, which induce distinct entropy regimes under the same policy, making global or token-level entropy regulation insufficient to corresponding heterogeneous needs of exploration. This heterogeneity further makes GRPO-style normalized advantages induce an entropy-dependent bias, making advantage signals across prompt groups statistically non-comparable. To address this issue, we propose Group Entropy-Controlled Policy Optimization (GEPO), a lightweight extension to GRPO that uses group entropy, estimated from existing grouped samples to perform entropy-conditioned asymmetric advantage shaping. GEPO attenuates positive advantages in low-entropy groups to reduce over-exploitation, and negative advantages in high-entropy groups to preserve exploration, with adaptive thresholds derived from historical entropy statistics. Extensive experiments on two base models across thirteen benchmarks spanning mathematics, physics, science, code generation, and instruction following show that GEPO consistently outperforms GRPO and recent entropy-controlled methods, delivering balanced cross-task improvements while preserving task-specific exploration levels throughout training.

Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers. We introduce two full-text scientific-memory benchmarks, Public AI Memory (PAIM; 81 papers, 66 questions) and Public Transformers (PTr; 252 papers, 98 questions). We evaluate eight memory/retrieval systems, including our own proposed Theoria, plus a no-retrieval baseline. Our results show that memory leaderboards are not interpretable without the full protocol: ingestion granularity, raw-text preservation, retrieval budget, retrieval modality, rubric audit, and judge choice all affect the outcome. For example, on PAIM Graphiti wins convincingly but uses 2.6M characters of retrieved context per query, and after controlling for retrieval budget the lead disappears. On PTr, for the systems where BM25 retrieval can be added cleanly, the sparse-dense hybrid is the single most significant intervention: hybrid variants of Simple RAG, Mem0, and Theoria tie for the lead within 0.03 points. Multi-judge and human side-by-side calibration show that LLM-as-a-judge rankings are consistent across frontier judges and agree with human evaluation, with an effective resolution of roughly one point on a ten-point scale. We argue that scientific memory should be evaluated as budgeted, modality-aware context restoration rather than as an unconstrained architecture leaderboard, and we release the datasets, harness, raw outputs, judgments, and scripts to reproduce our results and serve as tools for such evaluation. Our code is available at http://gitlab.com/quantellence/research/scientific-recall-bench , and the datasets are available at http://huggingface.co/datasets/quantellence/srb-data .

Scientists at European XFEL conduct experiments that generate very large and complex datasets. The subsequent data analysis is challenging as scientists must combine their domain expertise with facility- and software-specific knowledge scattered across documentation, tools, and support channels. To address this problem, we designed and evaluated an agentic AI system tailored to the scientists' needs and integrated with the high-performance computing environment of European XFEL. Using a design science research approach, we conducted a rapid literature review, a systematic evaluation of 16 AI tools, multiple interviews, a focus group, and a user study with experts at European XFEL to develop and evaluate two prototypes. Our study identifies key knowledge challenges in scientific data analysis, derives requirements for an AI agent that supports knowledge retrieval and source code generation, and proposes design recommendations for a specialized system adaptable to the evolving AI tool landscape. These findings provide guidance for developing maintainable AI support in highly specialized scientific environments.

Task arithmetic, sequential fine-tuning, activation steering, and first-order random search all operate through relatively small perturbations around an already trained checkpoint, and they rely on different local approximations: individual perturbations should be first-order predictable, task updates should compose with controlled interference, useful tangent structure should be stable and possible to estimate, and weight edits should have counterparts in representation space. We measure 8 such properties with the same harness around a multitask LoRA operating point, on 9 transformers (82M-7B), with a prospectively registered property list, thresholds, and test split. We find a shared one-direction validity window up to the tested scale $10^{-2}$, but no universal radius for pairwise composition or update ordering. Along individual directions, changes of the probe loss remain first-order predictable throughout the grid: a perturbation's effect on the loss is essentially its projection onto the gradient, which is also what makes local random search work. Pairwise structure, however, proves to be far more fragile: on over a third of the measured (model, task pair) combinations, two-update order sensitivity sets in strictly inside that window; task-gradient subspaces rotate within tens of steps; additivity under our fixed activation probe fails at full task-vector scale on several models, including both held-out 7B models; and no model median passes the registered global mean-vector weight-to-steering correspondence bar. For two sequential task-gradient steps, the leading order-dependent term is the Lie bracket $H_B\textbf{g}_A-H_A\textbf{g}_B$; its normalized prediction $c(η)=ηκ+O(η^2)$ tracks the measured defect at median ratio 1.002, while the onset scale $η^\dagger\approx0.10/κ$ spans three orders of magnitude across models and task pairs.

In recent years, large-scale vision-language models have been driving a paradigm shift in intelligent remote sensing image interpretation. By incorporating textual semantic information, the cognitive expression, semantic understanding, and human-computer interaction capabilities of interpretation models have been significantly improved, achieving initial progress in the field of Synthetic Aperture Radar (SAR) image interpretation. However, SAR images are affected by factors such as coherent imaging mechanisms, complex scattering characteristics, speckle noise interference, and target-background coupling, resulting in complex and variable image features with significant uncertainties and specializations. Existing SAR vision-language models do not yet possess the step-by-step analysis, logical judgment, and self-correction capabilities of human experts, making it difficult to support reliable intelligent interpretation in complex scenarios. To address this issue, this paper proposes a large-scale reasoning model, FUSAR-R1, for intelligent interpretation of SAR images. The model first constructs explicit chain-of-thought reasoning data by simulating the interpretation process of human experts and uses this data to guide instruction learning, thereby endowing the model with basic reasoning capabilities. Subsequently, a reinforcement learning strategy is introduced to optimize the model's outputs based on inference results, enabling self-correction and more reliable reasoning. Experimental results demonstrate that FUSAR-R1 consistently outperforms existing multimodal large-scale models across various SAR interpretation tasks, including target detection, target counting and classification, and land-cover category recognition.

Sparse-support uncertainty is usually quantified by treating the dictionary as known, an assumption that can produce overconfident, label-dependent conclusions when the dictionary is learned from latent sparse mixtures. Near collisions of coherent atoms, a test signal may identify the active physical group even though the training data cannot distinguish the physical rays within it. We develop inference for active physical rays, unit atoms modulo sign, after latent dictionary learning. In a fixed-dimensional Gaussian train-test experiment, we retain all dictionaries compatible with a robust training-moment region, profile the test representation over them, and project surviving configurations onto a permutation-invariant support space. The resulting confidence correspondence can report cross-sheet inconclusiveness, group resolution with child ambiguity, or fine-support resolution. We characterize both its statistical cost and decision-theoretic benefit. Residual block orientation first affects the latent training density at cubic order, yielding information of order $s^6$, where $s$ is the within-block collision scale. The correspondence provides high-probability-over-training conditional test coverage, with resolution governed separately by parent detectability, test-time support separation, and learned-dictionary orientation. In the resolved fixed-shell regime, its projective Hausdorff diameter contracts at the minimax-optimal rate $s \wedge (\sqrt{N}s^2)^{-1}$, up to constants. A restricted-task theorem further determines when coefficient asymmetry allows test replication to supplement training information and when calibration uncertainty remains irreducible. The framework thus yields honest, resolution-adaptive support statements and guides the allocation of training versus test measurements.

We revisit Gaussian Mixture Models (GMMs) as a lightweight, interpretable tool for anomaly detection and, in particular, for detecting distributional drift in data streams. We make three practical choices explicit and evaluate them on seven public benchmarks. First, the number of mixture components is selected automatically by the Bayesian Information Criterion, initialised by k-means, removing the need to fix it in advance. Second, individual observations are scored by their negative log-likelihood under a GMM fitted to normal data, with thresholds set at a target false-alarm rate using Extreme Value Theory. Third, the same interpretable model extends to distributional drift: each Gaussian component is a named "regime," and the fraction of a stream window that matches no regime -- its unexplained mass -- is a drift signal that is itself the explanation. We benchmark this against a model-free kernel two-sample test (Maximum Mean Discrepancy, MMD) and against two GMM-to-GMM divergences (a closed-form Cauchy-Schwarz divergence and a matching-based KL surrogate). Across seven benchmarks ranging from 3 to 64 dimensions and five random splits, the GMM point detector is competitive with -- though rarely more accurate than -- Isolation Forest, Local Outlier Factor, one-class SVM, ECOD, COPOD and an autoencoder, while uniquely yielding an interpretable model. For drift, MMD is the strongest pure detector, but the interpretable unexplained-mass statistic matches it when anomalies form novel regimes (and honestly fails, as MMD does not, when drift is a pure re-weighting of existing regimes). Every alarm is explainable: anomalies lie a median of 3-10 sigma outside their nearest regime vs. about 1 sigma for normal points, and a drift alarm reports the fraction of the window matching no known regime. All code and experiments are released.

Event Argument Extraction (EAE) converts documents into structured event records by identifying argument spans and assigning them schema-defined roles. Document-level EAE is challenging due to long-range dependencies between triggers and arguments, cross-sentence context, and strict role constraints, which often lead to boundary errors, uncertainty in roles, and inconsistencies with restricted schemas. In this paper, we study whether mid-sized open LLMs can perform schema-constrained EAE reliably at the document level on MAVEN-ARG. Our approach combines (i) role-set injection in prompts for schema compliance, (ii) parameter-efficient supervised fine-tuning (LoRA) using the same JSON-only interface used at inference, and (iii) deterministic decoding with post-processing that validates JSON, filters invalid roles, de-duplicates arguments, and aligns spans to the document window. Under the official MAVEN-ARG evaluator, fine-tuned mid-sized open models outperform previously reported GPT baselines across mention, entity-coreference, and event-coreference evaluations; our best model (Phi-4, 14B) reaches 42.39\% F1 at the event-coreference level. Code to reproduce experiments is publicly available at https://github.com/dessertlab/EAE/.

Speech Emotion Recognition (SER) is an important component in a wide range of human-centered applications, including healthcare, customer service, and human-omputer interaction. In medical and decision-support settings, there is increasing interest in models that not only achieve accurate emotion recognition but also support transparent predictions and efficient deployment. However, many existing SER approaches rely on complex deep learning architectures that limit interpretability and increase computational cost. This paper presents an explainable and lightweight speech emotion recognition framework based on a compact convolutional neural network architecture. The proposed approach utilizes log-Mel spectrogram representations to capture spectro-temporal speech characteristics and employs attentive statistics pooling to emphasize emotionally salient temporal segments. To improve model transparency, gradient-based class activation mapping (Grad-CAM) is incorporated to visualize the time-frequency regions that influence the model's predictions. Experimental evaluation on the SAVEE emotional speech dataset demonstrates that the proposed framework achieves competitive recognition performance while maintaining a compact architecture with significantly fewer parameters than many existing SER models. The results indicate that efficient convolutional architectures combined with interpretable analysis can provide a practical balance between recognition accuracy, computational efficiency, and model transparency.

Deep survival models are evaluated almost exclusively by the concordance index (C-index), yet they are commonly trained using likelihood objectives such as the Cox partial likelihood, discrete-time negative log-likelihood, and DeepHit likelihood. This mismatch is usually considered acceptable because the C-index can be recomputed on validation data during training. However, for end-to-end training of high-capacity encoders on small, heavily censored oncology cohorts, frequent C-index evaluation is computationally expensive, making the loss value itself an important signal for monitoring, early stopping, and model selection. We show that likelihood losses are unreliable for this purpose and propose a value-monotone concordance loss. We prove that every strictly proper survival likelihood admits directions where the loss decreases while the C-index remains unchanged, causing the loss value to decouple from ranking performance. We then study a sigmoid concordance loss (SCL), whose value approximates one minus the C-index up to a temperature term, ensuring that lower loss corresponds to higher C-index during optimization. The loss is architecture agnostic and reduces to a convex survival ranking support vector machine for linear models. Across eighteen datasets from four modalities using a unified five-fold cross-validation protocol, SCL achieves discrimination comparable to standard likelihood losses and is the best or within one standard deviation of the best C-index. Unlike likelihood losses, SCL maintains a strong correlation between loss value and C-index during training, with rank correlations of 0.96 to 0.99 compared with -0.03 to 0.53 for likelihood losses. Calibration measured by the integrated Brier score is comparable. SCL provides a value-monotone optimization objective whose value can serve as a reliable surrogate for the C-index during expensive end-to-end training.

Variational Quantum Algorithms (VQAs) are a leading paradigm for near-term quantum computing, yet their training suffers from sensitivity to circuit depth, initialization, and landscape pathologies such as barren plateaus. We study \emph{progressive depth training} (PDT) -- a layerwise curriculum that trains a shallow circuit before appending new layers -- and identify a fundamental obstacle: fixed entangling gates (CNOTs) in hardware-efficient ansätze cause \emph{initialization shock}, an energy spike when new layers are added. We propose \emph{identity-paired progressive depth training} (IP-PDT), which appends forward/inverse block pairs -- each consisting of a standard rotation$+$CNOT block followed by its reverse -- that compose to the identity at initialization. Because the adjacent CNOT rings cancel, the effective circuit retains only \textit{a single entangling layer} surrounded by \textit{overparameterized local rotations}. We prove a simple \textit{Reachable Set Saturation Theorem}: under this construction the variational manifold expands exactly once (when post-entangler rotations are first introduced) and then \emph{saturates}; all subsequent depth increases provide pure overparameterization of single-qubit unitaries. Despite this saturation, progressive addition of rotation parameters can continue to improve optimization outcomes -- a phenomenon we term \emph{trainability beyond expressibility}. We formalize IP-PDT as a continuation method on nested manifolds, prove monotone energy guarantees under an acceptance rule, and connect energy error to ground-state fidelity through spectral-gap inequalities. A detailed resource analysis shows that IP-PDT achieves lower total gate cost than both baselines by eliminating most CNOT gates.

Hidden-state readouts can predict whether language-model outputs are correct, but objective correctness (OC) usually agrees with the model's own self-judgement (SJ), leaving the decoded signal semantically ambiguous. We construct conflict cases in which OC and SJ predict opposite readout orderings. On high-confidence disagreements, conventional correctness-labelled contrasts often rank incorrect/self-endorsed responses above correct/self-rejected responses, following SJ rather than OC. We estimate factorial SJ- and OC-associated directions and evaluate their polarity across mathematical reasoning and factual recall. Across four instruction-tuned models up to 14B parameters, the SJ-associated direction transfers above chance in both cross-domain directions for every model, whereas the OC-associated direction has a below-chance point estimate for the expected OC ordering in every corresponding condition. This transfer asymmetry develops across middle-to-late layers, persists under answer-likelihood, sequence-length, and null-direction controls, and extends to MMLU and binary TruthfulQA without target-domain direction fitting. Across the studied models and diagnostic subsets, the most reliably transferable component preserves SJ-associated polarity. Transferability alone therefore does not establish objective-correctness semantics.

Fine-grained offensive language detection organizes labels into a hierarchical structure, for which two modeling paradigms exist: cascaded decomposition and joint multi-task modeling. Prior work rarely provides a direct, controlled comparison of the two paradigms in terms of accuracy, parameter count, and inference latency, and rarely verifies whether a chosen class-imbalance handling strategy is actually optimal. This paper proposes a three-level cascaded detection system whose training strategy is customized per subtask, together with two verification mechanisms. First, a controlled ablation study determines the best class-imbalance handling strategy for each subtask. Second, a joint multi-task model with a shared encoder is trained as an architectural control, yielding real measurements along the dimensions of accuracy, parameter count, and inference latency. Experiments show that the cascaded system attains macro-F1 scores of 0.795, 0.716, and 0.557 on the three subtasks of the official test set. The ablation study reveals that configuring the loss function purely by imbalance-severity intuition is suboptimal; reconfiguring based on the ablation results improves both performance and stability. End-to-end cascade evaluation shows that roughly one-fifth of the errors in the cascade pipeline originate from the first-stage filter and cannot be corrected by subsequent stages. Relative to the joint multi-task model, the cascaded architecture achieves higher accuracy on all three subtasks, with a 7.1-point macro-F1 gain on the most severely imbalanced subtask, at the cost of three times the parameters and 1.67 times the inference latency. Together, these results establish an explicit, quantifiable trade-off between the accuracy advantage of cascaded architectures and their deployment cost.

Real-world perception and decision making are inherently multimodal, integrating complementary signals across modalities. However, training multimodal models faces two main obstacles. First, collecting large-scale, well-aligned paired multimodal datasets is often impractical, making end-to-end multimodal training difficult. Second, existing multimodal representations frequently entangle information shared across modalities with modality-specific information, hindering interpretability and control. We introduce MultiLoReFT, an efficient and scalable low-rank representation fine-tuning framework for multimodal learning with pretrained unimodal models. MultiLoReFT extends low-rank adaptation to the multimodal setting and learns interpretable projection subspaces that decouple shared and modality-specific information. Across simulated and real-world benchmarks, it produces representations that support multimodal prediction while explicitly revealing how shared and modality-specific information is distributed across modalities.

Chaotic modulation is an effective communication technique that exploits deterministic chaos to produce pseudo-random signals. A widely adopted approach involves modulation of the chaotic bifurcation parameter. This paper introduces a deep learning-based demodulation method for keying of the bifurcation parameter. It describes the architecture of the convolutional neural network and evaluates performance metrics for signals generated using the chaotic logistic map. The study assesses the bit error rate for binary signals and reports a bit error rate of 0.0819 for a bifurcation parameter deviation of 1.34% under additive white Gaussian noise at a signal-to-noise ratio of -13 dB (corresponding to a normalized signal-to-noise ratio of +20 dB). The results demonstrate the capability to detect chaotic patterns even when the specific patterns were not included in the training dataset.

We present JOR-Bench, a collection of five Japanese-language benchmarks for evaluating the ability of large language models (LLMs) to formulate and solve operations research (OR) problems. Each benchmark is a Japanese translation of an existing English benchmark: IndustryOR, MAMO Complex LP, NL4OPT, OptiBench, and OptMATH, covering 1,319 problems spanning linear programming, mixed-integer programming, non-linear programming, and combinatorial optimization. JOR-Bench is a solver-independent benchmark that can be used with any solver or programming language, and consists of pairs of Japanese problem statements and expected numerical answers. We evaluate seven LLMs, including multilingual general-purpose models and Japanese-specialized models, on both the original English and the new Japanese versions, and compare performance across languages. For the main evaluation, we standardize execution with the Python interface to OR-Tools to make model outputs comparable and reproducible with open-source software. Our results show that OR formulation ability is largely language-neutral for strong multilingual models; the overall average accuracy difference between English and Japanese is only $-0.3$ pp. Yet error analysis reveals subtle cross-lingual differences, including a pragmatic disambiguation failure in some domains that causes models to output decision-variable values instead of the objective value when the prompt is in Japanese.

Graph Neural Networks (GNNs) have emerged as a powerful, differentiable class of learning models for graph-structured systems. Their ability to generalize across topologies opens the prospect of a surrogate for combined structural and parametric optimization, which classical metamodels cannot offer. Supply chains are a natural target, yet the use of GNN surrogates for supply chain problems is largely unexplored. This paper lays the foundation, presents initial steps, and discusses key research directions. As a foundation, we formulate the problem and create a large public training dataset of programmatically generated supply chain graphs with input parameters and steady-state performance metrics obtained using our SupplyNetPy simulation library. As initial steps, we explore GNN architectures that work well as surrogates for node- and network-level predictions, and analyze their accuracy-compute trade-off against simulation. Most importantly, we outline the exciting directions this opens, namely gradient-based optimization over topology, fast design-space exploration, and sensitivity analysis.

Learning with noisy labels is a fundamental problem in training reliable deep neural networks. Robust loss functions provide a direct and effective way to mitigate the adverse effects of label noise. However, most existing robust losses are designed directly at the level of the final multiclass objective, which makes it difficult to systematically characterize and extend their robustness properties. In this paper, we propose a general framework that constructs robust multiclass losses from univariate base functions. By defining mapping operators from base functions to multiclass losses, the robustness of the induced losses can be characterized through simple properties of the base functions. We develop two complementary construction schemes, Target Separation and Binary Reduction, corresponding to inter-class independent and inter-class dependent formulations, respectively. For both schemes, we analyze their symmetry and asymmetry properties and derive corresponding sufficient conditions, which provide theoretical criteria for noise-robust loss design. The proposed framework also provides a new route to constructing symmetric losses, serving as a complement to normalization-based symmetric loss designs. Extensive experiments on synthetic and real-world noisy-label benchmarks demonstrate that the proposed losses achieve competitive or superior performance under various noise settings.

Dropout and Random Gradient Masking (RaM) are two training techniques used to improve performance in deep learning. Both techniques inject randomness into the training dynamics, but in significantly different ways: dropout applies random masks to the activations in the forward pass, whereas RaM leaves the forward pass unchanged and instead masks the gradients. In particular, the noise induced by RaM in the parameter updates is unbiased, so standard explanations for the effectiveness of dropout, such as the penalization effect or the prevention of co-adaptation between neurons, do not apply to RaM. In this work, we show that the difference between the two methods disappears for ResNets in the large depth and width asymptotics: in the complete feature learning regime, they both converge to the same large-scale limiting dynamics. This asymptotic equivalence holds for several variants of dropout and RaM, including layerwise dropout as used in stochastic-depth ResNets, albeit at slower quantitative rates. In fact, we also show that several of these variants collapse to the same limit asymptotically.

Driver monitoring systems (DMS) increasingly rely on facial cues to infer drowsiness, distraction, and cognitive load in real time. Facial Action Units (AUs), grounded in the Facial Action Coding System (FACS), provide an objective and interpretable representation of such states, but their automatic detection in the driving context is complicated by low and variable illumination, partial occlusion, head-pose variation, and the subtlety and short duration of relevant AU activations. Existing AU detectors largely treat spatial appearance and temporal dynamics separately, limiting their ability to exploit self-supervisory signal from abundant unlabeled driving video. We propose the Twin Cycle Autoencoder (TCA), a spatiotemporal architecture composed of two coupled cycle-consistent autoencoder branches: a Spatial Cycle Autoencoder that disentangles AU-relevant appearance from identity through image-level cycle consistency, and a Temporal Cycle Autoencoder that enforces forward-backward consistency over latent AU trajectories to capture onset-apex-offset dynamics. The two branches are coupled through a cross-branch latent alignment loss and fused via an attention module before multi-label AU classification. We evaluate TCA on the DISFA and BP4D benchmarks and on an in-cabin naturalistic driving dataset, and observe consistent improvements over CNN-RNN, 3D-CNN, and graph-based AU baselines, particularly for low-intensity and rapidly transitioning AUs relevant to fatigue (AU45, AU43) and yawning (AU26). We further show the model sustains real-time throughput on an embedded Jetson Xavier NX platform, supporting its use in production-grade advanced driver assistance systems (ADAS).

Authorization violations under valid Web sessions are difficult to identify and handle in real time from traffic because they depend strongly on business semantics and exhibit few distinctive protocol-level features. This paper proposes a non-intrusive traffic analysis framework for authorization risk detection and coordinated response. Request-response transactions are correlated to extract the access subject, business endpoint, object identifier, authentication state, and behavioral sequence. Object-access evidence, identity consistency, behavioral anomalies, authentication context, network environment, and endpoint-operation risk are mapped to interpretable risk components. Weighted fusion and high-risk priority constraints produce graded decisions that drive allow, alert, block, and external policy actions. The risk components are instantiated using deterministic and interpretable rules to evaluate multi-source evidence organization, risk fusion, and the coordinated-response loop at the framework level. In a controlled local testbed containing 2,000 balanced labeled samples, the framework classified 998 of 1,000 authorization-risk events as risky and produced no false positives among 1,000 normal accesses, achieving 99.90% accuracy, 100.00% precision, 99.80% recall, and a 99.90% F1 score. Removing runtime object evidence reduced the F1 score to 81.31%, while removing the high-risk priority constraint reduced it to 73.90%. In a prototype feasibility test with 100 concurrent requests and 1,000 total requests, mean risk-decision computation latency was 0.077 ms and P99 latency was 0.137 ms. The results demonstrate the feasibility of organizing heterogeneous runtime evidence and establishing an executable authorization-risk decision and coordinated-response loop without modifying application code, but do not establish general applicability in production environments.

Multi-agent planning becomes substantially harder when agents must improve specialized decision-making skills while keeping their internal implementations private. This regime arises when agents are developed independently, expose different interfaces and capabilities, and must nevertheless coordinate without sharing executable policies. Prior research has largely assumed centralized optimization, shared policy access, or common skill representations, making it poorly suited to privacy-constrained cooperation. We introduce RELIC, a framework for learning interpretable and composable skills via revealed principles. Each agent refines its own programmatic skill through private LLM-guided search, while a trusted orchestrator evaluates proposed updates solely through team-level performance. Successful behaviors are not broadcast as code; instead, they are abstracted into portable principles that other agents can instantiate within their own interfaces and recombine with local strategies. This separates coordination from implementation sharing, enabling cross-agent transfer under heterogeneous skill signatures. RELIC thus introduces a new paradigm for privacy-preserving skill learning and coordination in multi-agent planning.

Generative artificial intelligence (GenAI) tools are reshaping software engineering work, increasingly acting as cognitive partners rather than purely instrumental aids. Most AI tooling remains optimized for individual use, yet software development is inherently collaborative and creative, raising open questions about how AI affects team-based work. This paper examines how software engineering professionals perceive and integrate AI tools focusing on creativity and collaboration within teams. We conducted semi-structured interviews with 13 software professionals from four companies, each representing a distinct team. Our analysis identifies three central themes - AI Use, Consequences of AI, and Collaboration and Team Dynamics, alongside Emotions as a cross-cutting dimension. Key findings include: AI broadens developers' creative repertoires but may narrow independent ideation; developers increasingly consult AI instead of colleagues, weakening peer learning and mentoring; and teams are developing emerging triadic collaboration patterns in which developers, colleagues, and AI reason together.

Bürger et al. (2024) demonstrated that truth representations in large language models are universal across statement polarity but reside within a multidimensional subspace. We extend that framework along three questions: how the dimensionality of the subspace depends on the model's knowledge, which architectural component builds the truth direction, and what the direction is a mixture of. In Part I (one model), a training-free directional probe derived from the SVD of hidden-state minimal pairs shows that the dimensionality of truth is knowledge-dependent: the signal is concentrated on a single axis for behaviorally known facts (held-out AUC 0.938) and becomes diffuse as knowledge decreases or material heterogeneity increases; seven falsification experiments sustain the one-dimensional reading, and the same decomposition recovers the supervised polarity direction of Bürger et al. at cosine 0.959 without polarity labels. In Part II (four base models, two families, pre-registered predictions), a relational law emerges: attention propagates truth frames it did not write, the feed-forward network opposes the frame of its current block, and the genuine post-peak decay is causally attributed on all four models to the SwiGLU value stream; per-category truth axes form a semantically signed arrangement that contradicts the lexical surface and converges across families (Mantel p = 0.0009). Stress tests at three scales (33 categories, 888 pairs per relation, six sampling seeds) expose a sign instability of the per-category orientation, repair it with a declared spectral consensus gauge, and sharpen the convergence into a knowledge-gated law, strengthening from +0.42 on dense mixed-knowledge material to +0.74 on knowledge-restricted categories: the geometry of the mixture belongs to the knowledge domain rather than to the architecture.

Agentic code review in terminal-based environments enables early feedback during local development before pull request creation. However, existing evaluations remain performance-centric and fail to capture the dynamic behaviors of repository-grounded agentic reviewers. Understanding these behaviors is critical for identifying how agentic reviewers succeed, fail, and incur hidden operational costs in practice. Then, we analyze the reviewers' behavior based on their trajectories. Our results show that agentic reviewers achieve higher review precision but incur substantial exploration and validation overhead, while successful reviews are associated with stronger planning and less downstream validation. These findings highlight the potential benefits of trajectory-aware and cost-sensitive evaluation of future agentic code review systems.

AI-Augmented Business Process Management Systems (ABPMS) enhance traditional BPMS by leveraging advanced AI techniques to define, execute, and monitor complex process structures. Within this landscape, Framed Autonomy denotes the capability of a system to autonomously advance the execution of a Business Process (BP) instance while strictly adhering to a predefined frame, i.e., a set of constraints that may span multiple perspectives. Existing research on framed autonomy has predominantly focused on control-flow constraints, either declarative or procedural, and typically relies on their transformation into automata-based representations. In this study, we extend this line of work by introducing a novel tool for what-if analysis that augments the process frame with multi-perspective constraints, including data-aware and temporal conditions. Given a partial process execution, the proposed approach exploits this enriched frame to recommend optimal continuations in compliance with the underlying process specifications. We additionally report an empirical evaluation demonstrating the scalability and effectiveness of the technique, thereby highlighting its potential for supporting autonomous and constraint-aware decision making in ABPMS.

This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes. Each recording is between 15 and 35 seconds long and contains temporally precise annotations for 15 common domestic sound classes. In contrast to existing SED datasets, which typically rely on simulated soundscapes or broad web-crawled audio, RealDESED consists exclusively of recordings captured in natural domestic environments, reflecting realistic variability in recording devices, device placement, acoustic conditions, background sounds, and naturally occurring event co-occurrences. A distinguishing characteristic of the dataset is its multi-annotator labeling scheme, where each recording is independently annotated by multiple annotators, while the validation and test sets undergo an additional review process to ensure high annotation quality and reliable benchmarking. Furthermore, the dataset provides rich metadata, including recording device, device placement, environment labels, and textual scene descriptions. We establish a strong transformer-based baseline and investigate annotation aggregation strategies, post-processing methods, long-form inference, and the impact of recording metadata on model performance. Our baseline achieves a macro-averaged PSDS1 score of 0.731 on the test set. We believe RealDESED provides a valuable benchmark for developing and evaluating robust SED systems under realistic domestic conditions, helping to bridge the gap between current research benchmarks and real-world deployment.

Marine biogeochemical forecasting is increasingly important for managing marine ecosystems and the carbon cycle, yet global, seasonal forecast products lag far behind physical oceanography, held back by the complexity of the processes involved and by data scarcity. We introduce BG4Sea, which to our knowledge is the first global, data-driven system to produce multivariate seasonal forecasts of the marine biogeochemical state. BG4Sea is a modular architecture with a column autoencoder that compresses the vertical column into a low-dimensional latent space, a latent forecaster propagates this representation forward in time, a surface-forcing conditioner that injects physical boundary information via Feature-wise Linear Modulation (FiLM), and a horizontal-coupling module that incorporates neighboring-column context through cross-attention. The model is trained and evaluated on the global ocean reanalysis BIORYS4 (NEMO/PISCES), and produces six-month forecasts at 1/4 degree, monthly resolution for dissolved chemistry, biology, and carbon-pool variables, outperforming persistence and climatology across most variables and lead times. We position BG4Sea as an interpretable baseline for future, more expressive approaches, and discuss predictability attribution to each component, alongside the model's structural limitations.

The Broad Learning System (BLS) has been widely used for data classification and is based on a layer-by-layer feed-forward structure. However, it gives the same importance to all data points, which reduces its effectiveness on real-world datasets with noise and outliers. In addition, it does not consider the geometric structure of the data and has limitations in handling data from multiple sources. To address these challenges, we propose a Multi-View Graph-Embedded Intuitionistic Fuzzy Broad Learning System (MVGIFBLS) that integrates multi-view learning, graph embedding, and intuitionistic fuzzy theory into the BLS framework. This design enables the model to combine information from multiple sources and learn more discriminative representations. Graph embedding captures the geometric relationships among samples and improves class separation through intrinsic and penalty subspaces based on local Fisher discriminant analysis. Intuitionistic fuzzy theory enhances robustness to noise, while kernel-based neighborhood analysis captures local data structures. We evaluate the proposed framework on several UCI, KEEL, and AwA benchmark datasets using comparative evaluation, Gaussian feature noise analysis, ablation studies, and statistical analysis. The results demonstrate that each component contributes positively to the overall framework and that the proposed MVGIFBLS consistently achieves higher Area Under the Curve (AUC) scores and maintains robust performance under Gaussian feature noise.

Autoregressive multimodal large language models (MLLMs) suffer from error snowballing: a single incorrect inference early in a chainof-thought (CoT) trace corrupts all downstream reasoning. We find that in state-of-the-art open-source MLLMs, once the first error occurs, the reasoning cascades into failure across all remaining steps in 65% of such cases (a metric we term the snowball rate). Existing mitigations-sampling multiple chains, post-hoc self-verification, or full program synthesis-either lack symbolic grounding, catch errors too late, or sacrifice the flexibility of natural language reasoning. We propose Constraint-Anchored Reasoning Traces (CART), a neuro-symbolic framework that trains MLLMs to interleave natural language reasoning steps with symbolic constraint assertions: lightweight, machine-checkable statements about visual content (e.g., count(red_objects) = 3). A dual-pronged Constraint Propagation Module-combining a learned neural grounding head with Boolean Constraint Propagation-continuously verifies these anchors against extracted visual features and checks their mutual logical consistency. When a contradiction is detected, a backtrack controller halts generation and reverts to the last consistent checkpoint, preventing error propagation. A variable-frequency emission mechanism allows the model to adaptively control anchor density, avoiding trace bloat. We construct 218K training instances by augmenting GQA, CLEVR-CoGenT, and VCR with ground-truth constraint annotations derived from scene graphs, and fine-tune open-source MLLMs (LLaVA-NeXT, Qwen2-VL) via LoRA. On five benchmarks, CART reduces the snowball rate from 0.65 to 0.14, improves GQA accuracy by +4.6 percentage points over trainingonly baselines, and achieves 89.1 F1 on POPE-all with at most 18% inference overhead.

Conditional generative modeling remains a challenging problem in semi-supervised settings where labeled data is scarce but unlabeled samples are abundant. To effectively leverage structural information embedded within the unlabeled dataset and compensate for sparse conditioning signals, we propose a semi-supervised framework combining conditional stochastic interpolation with low-dimensional latent representations. RepG decomposes generation into two stages: label-dependent latent sampling and high-dimensional reconstruction. This isolates the supervised learning of conditional dependencies to a low-dimensional space, requiring few labels while utilizing the abundant unlabeled data purely for reconstruction. Theoretically, we establish an error decomposition showing that the Kullback-Leibler divergence of RepG comprises stage-wise estimation errors and a structural bias quantified by conditional mutual information. For deep neural network estimators, we derive non-asymptotic convergence rates proving that RepG significantly improves sample complexity. By confining the supervised estimation burden to the low intrinsic dimension of the latent representation, RepG achieves a strictly faster convergence rate. Complemented by a minimax lower bound, our theoretical results demonstrate that this method effectively mitigates the curse of dimensionality inherent in direct ambient-space generative modeling.

The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size comes from large pools of "expert" subnetworks, of which only a few act on any token. That pool is why these models do not fit on the machines most developers own, yet for a user who only wants coding help, most experts encode abilities that will never be invoked. We ask how many experts can be removed, and which, by pruning two recent open-weight MoE models from different families (Qwen3.6-35B-A3B and Gemma-4-26B-A4B) under five selection strategies, judged the way a user would: by whether the model still writes correct code. Half the experts can be removed from either model with no statistically detectable loss on the primary code benchmark, and the damage lands almost entirely on abilities outside coding, the intended trade. But the winning strategy flips between the two models, so a recipe validated on one family cannot be assumed to work on another. We further show that perplexity, the metric much of the pruning literature leans on, can rate a broken model above an intact one; that a lightweight fine-tune recovers about half of what aggressive pruning loses; and that against quantizing the full model to the same memory, pruning wins only where quantization would have to drop below 3 bits per weight. Five attempts to overturn that crossover, with failure criteria fixed in advance (better calibration, guarded selection, causal expert importance, failure attribution, and an agentic evaluation letting each model repair its failures from execution feedback), all leave it standing; the last shows single-shot benchmarks overstate compression penalties broadly, as one repair turn erases the 2-bit quantization penalty entirely. Expert pruning works, but it demands per-model validation on the task the model will actually serve.

Understanding deep neural networks remains a central challenge in machine learning. In particular, the theoretical properties of even two-layer ReLU networks, especially in the presence of weight decay, remain poorly understood. To this end, we derive a sufficient condition on the hyperparameter settings under which the global minima collapse to the zero solution. Interestingly, our experiments reveal that using AdamW as an optimizer prevents the collapse of the learned parameters, whereas using SGD does not, which may help explain the success of AdamW in deep learning training. In addition, when restricting the input dimension to one, we derive an analytical solution for the globally optimal parameter sets of two-layer ReLU networks and show that $\ell_2$-regularization has a width-invariant effect on connectivity, but its dimensionality-reducing effect becomes stronger as the network width increases. These results provide insight into how width-dependent hyperparameters influence the geometry of regularized loss landscapes.

This paper proposes a causal independence principle for value -- the value Causal Markov Condition (v-CMC) -- and develops the conceptual and mathematical foundations of a "causal value theory" linking causality and utility. After motivating a local formulation of the v-CMC, we introduce a probability-value duality that translates standard causal-inference results into the value setting. In particular, we formulate local, global, and decomposition versions of the v-CMC and prove their equivalence. We also define v-separation and show that it is sound and complete for conditional value independence. Furthermore, we derive a Bellman-type recursion as a special case of the v-CMC, thereby generalizing standard Bellman recursion from linear chains to causal DAGs. Finally, we show how the v-CMC supports modular transfer and updating of utility information across causal contexts and develop algorithms for causally structured utility elicitation and canonical influence-diagram construction.

Large language models and LLM-based agents are widely used as personal chat assistants, enterprise copilots, and autonomous workflow agents. In all these applications, memory (the ability to retain, access, and reason over information accumulated over long contexts and multiple interactions) plays a crucial role in determining the reliability of any agent. We introduce RECON (Reasoning over Extended Contexts with Obfuscated Narratives), a benchmark for evaluating compositional reasoning over long contexts. RECON spans 24 case files across three domains (criminal, medical, and financial), each ranging from 50k to 100k tokens, and tests agents on six memory intensive tasks: reconstructing multi-hop evidence chains, propagating cascading invalidations, resolving source conflicts, counterfactual reasoning, satisfying temporal constraints, and temporal fact retrieval. Recent memory benchmarks evaluate whether agents can retrieve scattered facts or detect if a fact has changed whereas RECON evaluates what happens after the change, whether agents can trace which downstream conclusions are affected, which survive through independent support, and how alternative timelines would have unfolded. Our evaluation reveals substantial limitations across current architectures: even the strongest non-Oracle system reaches only 22.4% Accuracy, with retrieval and reasoning each surfacing as challenges.

We study Controlled Query Evaluation (CQE), a declarative approach to confidentiality-preserving data access, in the context of Description Logic (DL) ontologies, and for confidentiality policies expressed through Epistemic Dependencies (EDs). We first address the problem of answering queries (specifically, Boolean unions of conjunctive queries) under known semantics for CQE (GA- and IGA-entailment). Our results show that if the TBox is expressed in $\text{DL-Lite}_{\mathcal{R}}$, CQE is computationally intractable in general. Moreover, in the presence of EDs, the IGA semantics has recently been proven not to satisfy an important confidentiality preservation property known as indistinguishability. With the goal of defining computationally easier and confidentiality-preserving forms of CQE, we introduce a new semantics for CQE, based on the notion of minimal policy violation (MPV). We show that the new semantics provides a sound approximation of the previous ones, while satisfying the indistinguishability property. We also prove that, in the case of $\text{DL-Lite}_{\mathcal{R}}$ ontologies, query entailment under the MPV semantics can be decided in polynomial time in data complexity. Finally, we present a software implementation of our framework that we used to evaluate the feasibility of this new approach using an existing benchmark for OWL 2 QL.

We describe DS@GT's submission to the eRisk 2026 Task 1 challenge on conversational depression screening, in which systems interview LLM personas that simulate individuals with varying depression profiles and produce a Beck Depression Inventory II (BDI-II) score plus four key symptoms per persona, without directly asking sensitive mental health questions. Our pipeline evolved through three stages: a monolithic single-model prototype to start off, a baseline multi-agent architecture that separates conversational interviewing from BDI-II scoring under a coordinating orchestration layer, and a final hybrid configuration that replaces the paid GPT-5-nano interviewer with the open-source Gemma 27B. To offset the model's weaker reasoning and instruction-following, the hybrid adds three algorithmic components: a precomputed dialogue tree that standardizes interview openers and follow-ups, a reliability-weighted consensus aggregation inspired by the Weaver framework, and a cluster-based imputation step for unprobed symptoms. We submitted three fully automated runs across all 20 personas, with Run 1 from the paid baseline and Runs 2 and 3 from the hybrid. Hybrid Run 3 achieved an ADODL of 0.9063, ranking 3rd among all complete-submission runs and placing DS@GT 2nd among the 21 teams overall, while outperforming our paid baseline Run 1 (0.8841) at roughly one-quarter of the per-persona API cost. These results support our central hypothesis that with sufficient algorithmic supervision, a weaker open-source model can compete with a stronger proprietary model in the conversational interviewer role. Our source code is available at https://github.com/dsgt-arc/erisk-task1-2026.