The Inference Report

Mixture-of-Experts (MoE) is a popular class of large language models (LLMs), offering high efficiency and accuracy. However, in KV-cache-intensive serving scenarios, MoEs often exhibit a tension between the GPU memory requirements of the model weights and the growing KV cache. We propose PagedWeight, a novel management method for MoE LLM serving that dynamically quantizes MoE model's weights at runtime and balances expert-weight precision with the KV cache sizes. PagedWeight exposes and effectively navigates the complex tradeoff between the model's task accuracy, memory consumption, and throughput/latency. Across several memory-sensitive MoE serving scenarios, PagedWeight improves the quality-memory tradeoff over several existing quantization baselines. PagedWeight achieves FP16-equivalent accuracy with up to 72.0% GPU memory savings and 1.94$\times$ throughput improvement, and improves quality over quantization methods by up to 39.3% at a similar memory budget with at most 4.1% throughput loss.

To address the escalating energy and latency demands of machine-learning workloads, we introduce a blueprint for an energy-efficient and fast thermodynamic computing stack that leverages stochastic analog processes in physical hardware. In this work, we focus on energy-based thermodynamic computing where the stochastic process is well described by Langevin dynamics with tunable energy potentials. The implementation of such potentials in physical hardware enables us to generate and sample from basic parameterized energy-based models. We demonstrate how to construct and train popular classes of machine learning models based on these hardware-native energy-based models, using the framework of probabilistic graphical models. We analyze the runtime and energy consumption of different models in this thermodynamic paradigm based on theoretical considerations and numerical studies. As a preliminary experimental realization of such hardware, we present our stochastic analog superconducting circuits driven by thermal noise. Together, these results outline a path toward energy-efficient thermodynamic hardware for probabilistic machine learning.

In many applications of matching, the point clouds to be matched are not merely unstructured sets of points but rather samples from distributions with an intrinsic cluster structure. In such cases, as individual points are often interchangeable within a coherent region, finding a robust region-to-region alignment is more desirable than establishing a precise point-to-point correspondence. To this end, we propose a novel approach for cluster-aware matching based on Laplacian Optimal Transport (LapOT). The key idea is to regularize the optimal transport problem with quadratic Laplacian terms constructed from similarity graphs of the point clouds, which encourages the optimal coupling to respect the cluster structure of both point sets. We also introduce Refined Simultaneous Clustering (RSC), a method that leverages the cluster-aware coupling obtained from LapOT to produce consistent partitions across the point sets, which can overcome the limitations of independent clustering and yield more stable and interpretable results. We demonstrate the effectiveness of our approach through theoretical analysis and empirical experiments, showing that LapOT indeed produces cluster-aware matching that leads to more consistent and meaningful alignments between point clouds.

Reinforcement learning (RL) has recently emerged as a promising feedback control strategy for nonlinear and complex dynamical systems. However, RL algorithms are sample inefficient and require a large number of interaction with the environment to synthesize optimal control strategies. Consequently, applications of RL are typically limited to sparse sensors and actuators due to the curse of dimensionality entailed by the exploration-exploitation dilemma in high-dimensional spaces. In this work, we bridge RL and traditional optimal control for dynamical system with a novel Physics-EnhAnced Reinforcement Learning (PEARL) paradigm tailored to the control of high-dimensional and parametric dynamical systems, exploiting the differentibility of their dynamics. Specifically, PEARL employs an actor-adjoint algorithm that leverages automatic differentiation to compute policy gradients over short horizons and adjoint-based sensitivities of future returns approximated via neural networks, significantly reducing the number of environment interactions, while mitigating long-term gradient instabilities. Through two challenging parametric navigation problems in unsteady flows, we show that PEARL (i) effectively exploits differentiable environments to outperform state-of-the-art RL algorithms, (ii) is sample efficient, thanks to the physics-guided policy learning, (iii) generalizes across multiple scenarios, which is crucial when dealing with parametric systems, and (iv) enables scaling RL to high-dimensional state and action spaces, without requiring low-dimensional state representations or multi-agent strategies.

Connected and Autonomous Vehicles (CAVs) rely on interconnected software and hardware components, including sensors, Electronic Control Units, in-vehicle infotainment systems, and telematics units, where vulnerabilities can compromise assets, users, and vehicle operations. These vulnerabilities are commonly documented as plain text in the Common Vulnerabilities and Exposures (CVE) database; however, security practitioners require structured information about affected assets, types of weaknesses, and attack behaviors to effectively mitigate the risks from these vulnerabilities. To this end, we evaluate open-weight Large Language Models (LLMs) for generating Structured Threat Information Expression (STIX), a well-known structured format for representing threat information, for CAV-related CVEs. We construct a dataset called CAV-STIXGen that maps CAV vulnerability descriptions to STIX domain objects (SDO), STIX relationship objects (SRO), Common Weakness Enumeration (CWE), and MITRE ATT&CK techniques mappings. Using this dataset, we evaluated 11 open-weight LLMs (4B to 120B parameters) across various prompting strategies and temperatures. Single-model configurations achieve F1 scores of 0.94 for SDO, 0.63 for SRO, and 0.99 for CWE mapping, while complete MITRE ATT&CK mapping remains challenging. In a multi-agent setup, Gemma-4-31B and Codestral-22B achieve F1 scores of 0.91 for SDOs and 0.43 for SROs, respectively. Lastly, we analyze CWE and MITRE ATT&CK co-occurrences to identify recurring threat patterns in the CAV domain, demonstrating how AI-assisted vulnerability-to-STIX translation can automate threat intelligence and prioritize defense in transportation security.

Muon is competitive with AdamW in large-scale pre-training, but its value for reinforcement-learning (RL) post-training remains unclear. We study vanilla Muon in sparse-reward agentic RL through matched single-seed comparisons with AdamW on ALFWorld using Qwen2.5-0.5B-Instruct. Under Group-in-Group Policy Optimization (GiGPO), applying Muon only to hidden weight matrices raises final-window validation success from 0.290 to 0.546 (+88%); high-rate AdamW controls retain no post-update success. The effect depends on the advantage estimator and learning rate. At 3e-5, Muon improves GRPO from 0.161 to 0.268, whereas GraphGPO's late-window gap narrows near saturation. At 1e-5, GraphGPO Muon reaches 0.901, raises normalized validation AUC from 0.399 to 0.556, and reaches 0.5 and 0.75 success 30 and 60 updates earlier, respectively. These exploratory results show that Muon can benefit agentic RL and motivate studying the policy optimizer, advantage estimator, and learning rate jointly. Multi-seed and cross-task validation remain open.

Residential short-term load forecasting (STLF) is challenging because household demand is heterogeneous, temporally variable, and shaped by diverse behavioural routines. This work investigates whether inferred behavioural structure can be embedded within the forecasting mechanism of a Neural Process-based probabilistic model, rather than used only as an external grouping signal, for context-conditioned residential STLF. We propose a behaviour-conditioned Attentive Neural Process framework that treats each load profile as a forecasting task. Behavioural structure is represented by a discrete latent variable inferred from the available context and used for behaviour-conditioned decoder conditioning, while a continuous latent variable captures shared functional uncertainty across heterogeneous profiles. To enable conditioning without ground-truth behavioural labels, clustering-derived information provides weak supervision during training, whereas test-time conditioning relies only on context-inferred class distributions. Experiments on the Smart Grid, Smart City (SGSC) dataset use user-disjoint train/validation/test splits, variable context lengths, and multi-step forecast horizons, with comparisons against a label-agnostic ANP baseline and fixed-window deterministic STLF baselines. The proposed variants improve MAE and CRPS over ANP across horizons and context settings, with the largest gains under limited context. The best-performing variant achieves average reductions of 7.9% in MAE and 6.9% in CRPS relative to ANP. Compared with fixed-window baselines, this variant achieves lower RMSE across all evaluated horizons while maintaining competitive MAE, suggesting fewer large prediction deviations under heterogeneous consumption patterns. These results support single-model, uncertainty-aware forecasting across heterogeneous households, contexts, and horizons.

Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued that this active observation is essential for a wide range of tasks. Whether today's multimodal large language models (MLLMs) exercise active observation is an empirical question that current vision-language benchmarks do not answer. We introduce ActiveVision, a benchmark that makes active observation measurable for MLLMs, comprising 17 tasks across 3 categories. Tasks are designed to force repeated visual perception rather than a single static description. Frontier MLLMs collapse on ActiveVision: the highest-scoring model we evaluate, GPT-5.5 at the highest exposed reasoning-effort tier, solves only 10.6% of items and scores zero on 11 of the 17 tasks, and even Claude Fable 5, despite topping most reasoning and coding leaderboards, solves just 3.5%, far behind three human participants who average 96.1%. Furthermore, much of the gap persists even when models write and run their own vision code: such code is unreliable on realistic imagery, and catching its failures itself requires the active perception the models lack. Together, these results indicate that current MLLMs lack robust active visual observation, motivating architectures and training objectives that close the perception-reasoning loop.

Urban intersections are among the most hazardous locations in road networks, posing significant risks to vehicles and vulnerable road users (VRUs) such as pedestrians and cyclists. The complexity of multi-agent interactions demands continuous, real-time monitoring systems capable of anticipating conflicts before they escalate into crashes. We present PRISA, a modular infrastructure LiDAR framework leveraging privacy-preserving, low-light-robust roadside sensors for long-term traffic observation and real-time risk detection at the edge. The framework comprises two core components: a sensing and perception layer and a plug-and-play risk assessment module. The latter automatically curates site-specific training data from accumulated perception outputs to train a trajectory prediction model without manual annotation. It then deploys the trained model for continuous motion forecasting and dual surrogate safety evaluation, using Time-to-Collision (TTC) for longitudinal conflicts and Predicted Post-Encroachment Time (PPET) for crossing and VRU-involved interactions. PRISA is evaluated on the public R-LiViT dataset and deployed on an NVIDIA Jetson AGX Thor at a live signalized intersection in Chattanooga, Tennessee. PPET-based assessment operates at 194~ms end-to-end latency over a 2.4-second predictive horizon, with TTC-based detection and perception remaining within real-time constraints, demonstrating practical feasibility for proactive multi-agent intersection safety monitoring.

In this work we demonstrate that a single transformer-based generative model can capture Standard Model structure spanning five decades of invariant mass, from the sub-GeV regime to the TeV continuum, a range that no single Monte Carlo sample covers. To achieve this we design \textsc{ShellFlow}, a Riemannian conditional flow matching model that, given the recorded event composition, generates each particle on its on-shell manifold. Its only physics priors are the on-shell condition and the invariant-mass formula. The model is trained on $\sim 10^{9}$ real $pp$ collision events from the ATLAS Open Data 13~TeV release and told nothing else. From a single training run, the model learns to reproduce all of the following: intra-particle kinematics, the dilepton resonances ($J/ψ$, $Υ$, $Z$) at their PDG positions, the leptonic Weinberg angle, the $W$ and top-quark masses, and inter-particle correlations that enter no training objective. A substantial fraction of the Standard Model is thus learnable directly from recorded collision data.

Improved Kernel Partial Least Squares (IKPLS) algorithms 1 and 2 are among the fastest PLS calibration algorithms. This article focuses on two shared steps, the computation of the $\mathbf{X}$ rotations, $\mathbf{R}$, and the $\mathbf{Y}$ loadings, $\mathbf{Q}$, and accelerates both. For $\mathbf{R}$, term-by-term accumulation is replaced by a direct evaluation strategy that requires the same number of multiplications but parallelizes better on modern hardware. For $\mathbf{Q}$, I identify - to the best of my knowledge, for the first time - equivalences showing that each $\mathbf{Y}$ loading is obtainable, up to explicitly derived constants, from quantities already computed earlier in the same iteration, and I exploit them in IKPLS to reduce the cost of each loading from $Θ\left(KM\right)$ to $Θ\left(M\right)$ operations whenever $M = 1$ or $2 \leq M < K$, with $K$ predictor variables (number of columns in $\mathbf{X}$) and $M$ response variables (number of columns in $\mathbf{Y}$). Both improvements provably yield exactly the same $\mathbf{W}$, $\mathbf{P}$, $\mathbf{Q}$, $\mathbf{R}$, and $\mathbf{T}$ as the original algorithms. Benchmarks with NumPy (CPU) and JAX (GPU) show speedups of up to two orders of magnitude for the isolated steps and of approximately $2\times$ (CPU) and $6\times$ (GPU) for entire fits. Both improvements are implemented in the free, open-source Python package \texttt{ikpls}.

LLM powered multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, their advantages over single-agent systems (SAS) remain unclear, with performance varying inconsistently across settings. Here, we provide an information bottleneck perspective on elucidating the differences between MAS and SAS. Specifically, our key observation is that a SAS accumulates its full reasoning trace in one shared context, while a MAS uses isolated local contexts connected by bounded relay messages. We show that, under infinite relay bandwidth, any SAS can be simulated by a MAS that transmits the full upstream context. Thus, the nontrivial advantage of MAS arises under bounded relays, where compression introduces a fundamental trade-off: reducing redundant context can improve efficiency, but may also incur loss of task-relevant information. We formalize this trade-off as an information bottleneck controlled by an effective parameter $β$, which captures how the balance shifts with model capability, and shows that MAS gains arise when context reduction outweighs relay information loss. We conduct 18 controlled experiments across five benchmarks and three model scales to validate our theoretical studies. We observe that MAS consistently helps when relays are near-sufficient, especially for weaker models. In contrast, MAS gains shrink or reverse when relays incur information loss, especially for stronger models that can already extract useful information from redundant context and thus gain little from compression. Our study shows that multi-agent design is fundamentally an information-bottleneck optimization problem. This perspective explains when bounded inter-agent communication helps or hurts.

Multimodal Scientific Claim Verification (MSCV) requires models to verify scientific claims using visually grounded evidence from papers, including figures, tables, charts, and textual context. However, existing methods often fail because they struggle to locate decisive visual evidence, accurately read structured scientific visuals, and integrate multimodal observations into reliable reasoning. We introduce ToolSciVer, the first tool-augmented framework for MSCV to our knowledge. ToolSciVer equips a VLM with three type-aware visual tools, table row/column focus, chart-to-structure parsing, and high-resolution region zoom, which convert dense scientific visuals into explicit, claim-facing evidence, and trains the policy with Group Relative Policy Optimization (GRPO) under a composite reward of answer correctness, format validity, length control, tool-use efficiency, and tool-validity penalties. Experiments on SciVer and MuSciClaims datasets on five VLMs from three model families (Qwen, InternVL, Gemma) demonstrate that our method achieves superior performance compared to four competitive baselines including prompting-based and RL-based tool-use methods, highlighting the effectiveness of learned, type-aware tool use for scientific claim verification.

AI governance increasingly requires judgments about whether an AI system remains adequately trustworthy over time, whether observed changes are tolerable, and how such judgments should be documented in a transparent and contestable way. Yet existing work on AI trustworthiness remains either too high-level to support lifecycle monitoring and reassessment or too narrowly metric-driven to connect with governance needs. We therefore propose a lightweight methodology for auditable trustworthiness levels in AI governance. The methodology has two components: a formal framework for representing and learning trustworthiness levels, and a lightweight AI lifecycle governance procedure for documenting, monitoring, and reassessing them over time. The formal framework models governance-relative trustworthiness through a context-sensitive protocol of measurable dimensions and learns trustworthiness levels as interpretable rules over trustworthiness profiles. Using decision trees as an interpretable proof-of-concept model class, the methodology yields explicit trustworthiness plateaus, readable level transitions, and two simple lifecycle diagnostics: boundary margins and profile drift. The governance procedure embeds these formal objects in a conformity-oriented workflow for design-time labeling, post-deployment monitoring, reassessment, and reporting. It also assigns human responsibilities and control gates for protocol design, validation, monitoring, and reassessment. We illustrate the methodology on synthetic AI lifecycle traces involving degradation, shocks, updates, heterogeneous monitoring cadences, and system comparison. Our methodology does not replace legal or other expert judgment: it supports conformity documentation and lifecycle monitoring by providing an evidential basis for documenting and tracking AI governance-relevant changes over time.

Autonomous discovery systems couple a resource that answers queries (a simulator, instrument, or analytic model) to an algorithm that selects what to query next. Most software frameworks for this loop inherit the control structure of numerical optimization: campaigns run for a fixed number of iterations, query costs are absent from the programming interface, and decision-making is treated as free. In practice, queries may differ in cost by orders of magnitude, and planners built on large language models or expensive surrogates consume resources of their own. Here we present CADAQUES, an open-source Python framework built on one architectural principle: cost is a first-class primitive of the discovery loop. CADAQUES separates the loop into two structural protocols, an Oracle that answers queries and a Driver that proposes them, and charges both evaluations and decisions against a common vector-valued budget spanning wall time, CPU hours, monetary cost, and language model tokens. An append-only ledger records, for each transaction, the cost declared before execution and the cost settled afterwards, making their discrepancy an observable property of the campaign. We evaluate the architecture by locating the critical temperature of the two-dimensional Ising model from noisy finite-size estimates against the exact thermodynamic-limit reference. In this noisy setting, strategies that concentrate around the best observed result can be misled by noise-induced peaks, whereas a schedule that explores with cheap low-fidelity queries and refines with higher-fidelity ones yields lower and less variable errors than high fidelity throughout, at the studied budget scale. Metering adds tens of microseconds per iteration, three orders of magnitude below the cheapest oracle query. The framework is MIT-licensed and archived at Zenodo (doi:10.5281/zenodo.21293589).

Evaluations should do more than measure a models current performance. They should tell us what to fix for the next model iteration and provide a way to generate targeted post training data. Most evaluation pipelines identify weak examples, topics, or categories, but they leave the underlying capability failure implicit: they say where a model fails, not why. We introduce CRAFT, a method that converts any rubric based evaluation dataset into a model specific diagnosis of weak capabilities. CRAFT treats each grading criterion as a capability probe: it extracts a capability description from every prompt rubric pair, clusters these descriptions into a hierarchical capability tree, scores the target model at every node, and selects low performing nodes dynamically across tree levels, at the granularity where each failure is clearest. The selected weak capabilities then direct the generation of targeted supervised finetuning data. Holding the data generation, finetuning, and evaluation setup fixed, we compare CRAFT against prompt level EvalTree clustering and untargeted random generation on four open source models, two professional domains (finance and legal), and 13 held out benchmarks disjoint from the diagnostic data. CRAFT achieves the strongest finance domain average for all four models under repeated temperature decoding; on legal domain, it is strongest for three of four models and remains within the decoding variance bands of the best baseline on the fourth. Diagnosing weaknesses at the level of rubric criteria, rather than prompts or categories, thus yields both a sharper picture of what a model cannot do and measurably better models after finetuning on that diagnosis.

Optimizing energy systems is a crucial step toward achieving a carbon-neutral future, with software tools playing a major role in the process. However, selecting the most suitable tool for specific optimization challenges can be complex, given the diverse objectives and requirements of various energy systems. In this study, we aim to address this issue by evaluating five preselected software tools-REMix, MTRESS, COMANDO, OEMOF, and HOMER PRO-to identify the scenarios for which they are most suitable. To achieve this, we conducted an extensive review of literature, documentation, tutorials, and example models, and developed a set of comparison criteria that were subsequently used to evaluate these tools. Our analysis suggests that REMix is particularly effective for scenarios where investment path optimization is required. COMANDO excels in systems with atypical components. OEMOF is the best-suited open-source tool for standard optimization problems. HOMER PRO is recommended for users seeking rapid synthesis optimization, especially those with limited programming experience. Due to difficulties in obtaining sufficient information on MTRESS, we were unable to complete the analysis for this tool.

Language models encode text as subword tokens, raw bytes, or rendered pixels, but these encodings are usually compared under modeling constraints that expose different amounts of linguistic content to models across different languages. We instead ask what each encoding preserves when both the content and the downstream capacity are controlled. Using verified parallel sentences across thirteen languages and five scripts, we compare tokens, bytes, and pixels through a shared bottleneck whose width is swept to trace rate-utility frontiers. This separates three quantities that are often conflated: the number of input positions an encoding creates, the latent capacity available after encoding, and the task-relevant information that survives compression. We evaluate three utilities: surface form preservation, cross-lingual sentence alignment, and topic classification. No encoding dominates across tasks or capacity regimes. Pixels preserve surface form best, bytes preserve cross-lingual alignment best, especially in same-script multilingual settings, and tokens support topic prediction best. These performances are not explained by sequence length alone. Short inputs can discard useful meaning, while long inputs can preserve information that compresses well. Choosing an encoding is therefore not a fixed preference for tokens, bytes, or pixels, but a rate-utility tradeoff that depends on the task, language mix, capacity regime, and compute budget.

Frontier AI companies have published capability thresholds that differ substantially, making it difficult for third parties to verify whether a threshold has been crossed or to compare requirements across companies. Moreover, without common minimum thresholds, risk mitigation may be inconsistent, creating a potential race to the bottom in safety standards. We develop a methodology for deriving harmonized thresholds across three risk domains. For misuse risks (cyber and biological), we take expected harm as the key primitive and use an explicit risk-modeling approach that accounts for risk channels and model release conditions. For automated AI R&D, we base our proposed threshold on the observed rate of AI progress rather than expected harm. Our analysis expands upon prior work and highlights existing empirical gaps and limitations.

State machine replication (SMR) and Byzantine fault-tolerant (BFT) consensus guarantee agreement despite a bounded number of arbitrary, colluding faulty participants. However, these guarantees rely on participants outside this set correctly executing the protocol's transition semantics. Agentic validators expose a weaker boundary: an authenticated, responsive, non-equivocating, and protocol-compliant reasoning participant may still endorse a semantically invalid transition due to reasoning errors. We call this failure mode an epistemic fault, and the collective phenomenon the Honest Quorum Problem (where "honest" means protocol-compliant, not semantically correct). Such a quorum can satisfy ordinary checks while forming a certificate for an invalid transition. Thus, agreement alone does not guarantee semantic validity or execution safety. Furthermore, because agentic validators often share model weights, training distributions, prompts, or toolchains, they are highly susceptible to correlated epistemic faults. We define Epistemic Byzantine Fault Tolerance (EBFT), a fault-tolerance model for agentic infrastructure and post-deterministic distributed systems. EBFT augments the conventional Byzantine fault bound with two separate, confidence-indexed quantities: $e_δ$ bounds coherent invalid endorsements outside the Byzantine set, and $u_ε$ bounds unusable validator support that degrades liveness. These quantities characterize semantic safety risk and liveness degradation independently. We derive quorum-threshold conditions for semantic validity, consensus agreement, liveness, and feasible threshold selection, and outline a calibration methodology for estimating these budgets. We show that adding nominally distinct agents improves fault tolerance only when it measurably reduces the upper-tail concentration of invalid endorsements or unusable support.

Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the pretraining that precedes it. As a result, two basic questions remain open: (1) how do pretraining choices (model size, data) shape the returns to RL compute, and (2) what does RL actually do to the model? These questions are difficult to study in the standard LLM setting: pretraining corpora are vast and uncontrolled, making it hard to attribute behaviors to pretraining versus RL, and systematic compute sweeps across both stages are prohibitively expensive. To address these challenges, we use chess as a controlled testbed for studying reasoning across the full pretraining-to-post-training pipeline. We follow the standard LLM training pipeline by pretraining language models from 5M to 1B parameters on human chess games, supervised fine-tuning on synthetic reasoning traces, and running RL on chess puzzles with verifiable rewards. Using this framework, we find that the post-RL performance at given RL compute level is well-predicted from the pretraining loss, and slope of the RL reward curves improves approximately linearly with the pretraining tokens. Beyond scaling, we find that RL does not simply sharpen the SFT policy: on easy puzzles it amplifies correct moves the SFT policy already preferred, while on hard puzzles it surfaces correct moves that were nearly absent under SFT. We further test whether our findings transfer beyond chess by training a 1B language model on math-domain text, where the same predictive pattern emerges: longer-pretrained checkpoints reach higher post-RL performance and improve faster under RL. In sum, we provide a quantitative account of the pretraining-to-RL interface and a controlled testbed for studying the science of reasoning across the full pretraining-to-post-training pipeline.

Transferring policies across domains poses a vital challenge in reinforcement learning, due to the dynamics mismatch between the source and target domains. In this paper, we consider the setting of online dynamics adaptation, where policies are trained in the source domain with sufficient data, while only limited interactions with the target domain are allowed. There are a few existing works that address the dynamics mismatch by employing domain classifiers, value-guided data filtering, or representation learning. Instead, we study the domain adaptation problem from a generative modeling perspective. Specifically, we introduce DADiff, a diffusion-based framework that leverages the discrepancy between source and target domain generative trajectories in the generation process of the next state to estimate the dynamics mismatch. Both reward modification and data selection variants are developed to adapt the policy to the target domain. We also provide a theoretical analysis to show that the performance difference of a given policy between the two domains is bounded by the generative trajectory deviation. More discussions on the applicability of the variants and the connection between our theoretical analysis and the prior work are further provided. We conduct extensive experiments in environments with various shifts to validate the effectiveness of our method. The results demonstrate that our method provides superior performance compared to existing approaches, effectively addressing the dynamics mismatch. We provide the code of our method at https://github.com/hanyang-chen/DADiff-release

AlphaFold2's 93 million parameters, shaped by the evolutionary record of protein structure encoded in the Protein Data Bank and in sequence alignments, are conventionally treated only as machinery for converting sequence to structure. We propose they are also a scientific object that can be analyzed directly: a learned encoding of protein conformational organization that can be probed and characterized. By smoothing the Evoformer's weight tensors with a Gaussian convolution and scaling the result, we show that the trained model produces physically structured conformational landscapes. Under perturbation, ubiquitin's native contacts break in the order established by decades of folding experiments. For KaiB, five independently trained models agree that the alternative fold is not recovered under perturbation. For alpha-synuclein, five models produce five different but coherent landscapes, mapping where the training signal has determined the representation and where it has not. Matched-power noise controls confirm that random corruption of equal magnitude produces debris, not conformations. The model learned to predict static structures; the conformational organization visible under perturbation was not an explicit training target, suggesting it emerged as a byproduct of that objective. AlphaFold2's weights appear to encode structural constraints, shaped by evolutionary and structural training data, that extend beyond what unperturbed inference reveals. We call the approach of reading them neural spectroscopy, and Scaled Gaussian Convolution one such protocol.

Increasingly, speech and language processing tasks take either audio or text directly rather than extracting features from these as the input to the classifier or regressor. Often these systems make use of complex, for example transformer-based, processes that have the ability to derive highly non-linear mappings between the input and the output. Unfortunately these systems can also learn ''shortcuts'' where the classifier is overly reliant on particular aspects of the input to yield the output. For the task of language proficiency assessment, this over-reliance can enable learners to increase their score by exploiting the shortcut rather than improving their ability. This paper introduces a novel training criterion that is able to reduce the classifier's reliance on shortcuts, thus for example limiting this option for malpractice in language assessment. This process is illustrated on two forms of assessment system, one based on the audio the other on the speech recognition text. The results show that, for both systems, there is higher correlations with features that could be exploited for malpractice than expected from the human reference, indicating an over-reliance on these features. By introducing the modified training criterion, this correlation can be reduced to be closer to the reference correlation.

This paper illustrates the Pick-to-Learn methodology applied to the calibration of a Model Predictive Control policy. While developed around a specific example, the presentation is meant to highlight a methodology of broad applicability. The example concerns an aircraft traveling from an origin point to a destination point in the presence of uncertain crosswinds and a low-connectivity zone that should be avoided. The MPC policy is parameterized by two hyperparameters, which are selected from data by the P2L procedure. Starting from a dataset of 400 wind realizations, also called scenarios, P2L identifies a final compression set containing only two informative scenarios. The resulting MPC policy avoids the low-connectivity zone on all available scenarios and, according to the P2L theory, satisfies a probabilistic risk bound of $4.8\%$ at confidence level $1-10^{-5}$, where the risk is the probability of entering the low-connectivity zone in a future flight under a new wind realization not included in the sample.

The growing adoption of Large Language Models in scientific research has created a need to understand what competencies researchers and graduate students require to use these tools critically and responsibly. This rapid review analyzed 194 articles retrieved from Elicit and Google Scholar (2022 to 2025), from which 40 were selected for competency extraction and thematic analysis following independent dual screening (Gwet AC1: 0.76 to 0.83). Eight competencies were identified. The most prevalent was domain expertise and oversight of AI outputs (n = 123), encompassing subject matter mastery, systematic skepticism, source verification, and researcher accountability. Other key competencies include metacognition and decision making about AI use (n = 55), ethics and academic integrity (n = 53), prompt engineering for research (n = 38), and reproducibility of AI use (n = 29). AI literacy and technical knowledge (n = 16) was explicitly identified as a risk factor when absent, with domain expertise treated as a prerequisite for meaningful critical evaluation. The findings suggest that preparing researchers to use LLMs goes beyond technical instruction, requiring an integrated set of epistemic, ethical, and methodological competencies centered on human accountability for the knowledge produced. These results have direct implications for the design of graduate programs and AI literacy initiatives.

Precipitation nowcasting over the immediate 10-90 min period is important for flood management and real-time decision-making in urban regions. Conventional short-range forecasting with high-resolution numerical weather prediction requires frequent data assimilation, model initialization, and spin-up, introducing computational latency. Machine learning provides an alternative by learning storm evolution directly from high-frequency observations and producing forecasts quickly after training. This is particularly relevant for Mumbai, India, where monsoon convection, land-sea interactions, and localized intense rainfall make short-term prediction difficult. Here, we develop a compact radar-only nowcasting framework that combines multi-elevation reflectivity, Doppler radial velocity, and radial-velocity-gradient proxy features within an encoder-decoder U-Net. Using the most recent radar volume scan, the model predicts 12 future composite reflectivity fields at 7.5-min intervals up to 90 min lead time. The derived velocity magnitude, divergence-like, directional-shear, and vorticity-like channels represent kinematic signatures associated with convergence and boundary interactions without requiring full wind-field retrieval. A high-reflectivity attention module improves sensitivity to convective cores, and physics-guided attribution examines whether the learned sensitivities are meteorologically meaningful. The model is trained using Mumbai Doppler radar observations from May to August 2023 and evaluated on temporally independent events. At 90 min lead time, Critical Success Index values are 0.437, 0.332, and 0.193 for $\geq$10, $\geq$20, and $\geq$30 dBZ thresholds, respectively. Compared with persistence, the model gives lower RMSE and higher spatial correlation at longer lead times. Once trained, it runs on a standard computer, generating nowcasts within seconds for real-time use.

Multimodal sarcasm and cyberbullying detection remain challenging because the intended meaning often emerges from incongruity between textual and visual information rather than from either modality alone. Existing multimodal approaches primarily rely on feature fusion or cross-modal attention, which may not effectively capture hierarchical semantic inconsistencies across different levels of representation. To address this limitation, this paper proposes HCIG (Hierarchical Cross-modal Incongruity Graph Network), a novel framework that models cross-modal incongruity at token, phrase, and global levels using graph attention networks and adaptively integrates these representations through a learned hierarchical attention mechanism. As a complementary architecture, we also introduce GCCN (Graph-based Cross-modal Contradiction Network), which performs graph-based reasoning using contradiction-aware pooling for efficient multimodal interaction learning. The proposed models are evaluated on the MMSD sarcasm benchmark and the MultiBully cyberbullying dataset, together with comprehensive ablation studies and cross-task transfer experiments. Experimental results demonstrate that HCIG achieves the best performance on MMSD with 85.74% accuracy and 85.29% macro-F1, while GCCN attains the highest macro-F1 (68.66%) on MultiBully and HCIG achieves the highest accuracy (69.62%) and bullying-class F1 (74.90%). The findings demonstrate that hierarchical multi-granularity incongruity modeling provides more effective multimodal reasoning than conventional fusion strategies, offering a robust framework for sarcasm and cyberbullying detection in social media.

The post-training of Vision-Language-Action (VLA) models is essential due to the diversity of simulators, robot embodiments, and task objectives. Existing compute services, whether offered as direct accelerator rental or batch-workload submission, typically allocate an exclusive set of GPU and CPU resources to a single tenant. While this paradigm maximizes client flexibility, it burdens users with infrastructure adaptation, and the fixed card-hour accounting model renders short or bursty workloads both expensive for tenants and inefficient for the service provider. To address these challenges, we present JoyNexus, a unified service for multi-tenant VLA supervised fine-tuning, reinforcement learning, and evaluation. JoyNexus decouples the Training Model Service, Inference Model Service, and Environment Service, each accessed through APIs and backed by resident shared base models with tenant-specific slots. Tenants can directly invoke high-level semantic APIs for training, rollout, and evaluation, or compose custom algorithms using lower-level APIs and their assigned endpoints. Multiple tenants submit workloads concurrently; their action modules, optimizers, rollout records, and policy versions remain isolated, and the service is scheduled by the global Training Queue and Inference Queue. To further improve multi-tenant training efficiency, JoyNexus introduces group batching for heterogeneous VLA data schemas that share a compatible model-facing prefix, enabling a single shared backbone forward pass over grouped samples. Finally, we evaluate JoyNexus through workload simulation and a group-batching pipeline in a realistic embodied scenario. Results show that, compared with isolated single-tenant execution, JoyNexus reduces aggregate GPU time and improves service utilization via cross-tenant scheduling on shared resources.

While large language models (LLMs) can solve advanced reasoning problems in seconds, we show that even frontier models fail to perform a much simpler operation: exactly copying an input string that lies well within their context windows. We attribute this failure to positional encodings in Transformer architectures, whose inductive bias favors copying through a shortcut based on matching local contexts rather than carefully locating the corresponding input positions. To address this issue, we introduce 2D-RoPE, which organizes text into a 2D grid rather than a 1D sequence and assigns each token a row ID and a column ID. Under this view, copying becomes simply retrieving input tokens at a fixed column offset, which makes the task easy to learn. In synthetic copy experiments, shallow Transformers with 2D-RoPE achieve perfect copying at input lengths hundreds of times longer than those seen during training, whereas standard positional encodings fall far behind. We further show that the advantage of 2D-RoPE language models on copy tasks consistently holds in large-scale pretraining on DCLM with model sizes up to 1.4B parameters. Overall, our results suggest that viewing text in 2D can benefit language modeling, and we hope this encourages future work to further explore the potential of 2D positional encodings.

Agentic Artificial Intelligence (AI), enabled by Large Language Models, marks a shift from rule-based automation toward autonomous, goal-driven control of Next-Generation Networks (NGNs). Existing surveys treat the two domains in isolation, leaving protocol integration, evaluation, and standardization alignment underexplored. To address this gap, a two-part tutorial-and-survey is presented. Part I formalises the control, management, and AI-native planes of 5G and 6G. It then covers the foundations of agentic systems: reasoning, planning, tool use, multi-agent coordination, and evaluation. Part II maps agentic capabilities onto 5G/6G control surfaces, standardization, and major 6G initiatives. Finally, it identifies open challenges shaping autonomous telecommunications.

Retinal layer segmentation in Optical Coherence Tomography (OCT) is a fundamental step for extracting quantitative biomarkers of retinal structure. Indeed, there is a growing interest in the analysis of OCTs in the context of neurodegenerative diseases. However, segmentation remains challenging due to speckle noise, shadowing artifacts, low contrast between adjacent layers, anatomical variability across subjects, and domain shifts arising from different acquisition protocols and clinical populations. While deep learning methods have achieved remarkable performance, their robustness and generalization across heterogeneous datasets remain limited. In this work, we investigate the role of spatial normalization as a preprocessing strategy to mitigate geometric domain shifts and improve the consistency of retinal layer segmentation. Inspired by standard practices in neuroimaging, we introduce a fovea-centered normalization framework that aligns OCT volumes into a common anatomical reference. We perform a comprehensive evaluation of state-of-the-art deep learning architectures. To provide a comprehensive assessment of segmentation quality, we combine conventional overlap-based metrics at B-scan level with topology-aware metrics at A-scan level and thickness-based measures at the en-face level. In cases where a ground truth is not available, we propose topology violation quantitative metrics that do not require ground truth annotations and a thickness-based qualitative assessment that captures structural consistency and clinically relevant patterns at the en-face level. The results demonstrate the importance of spatial normalization in OCT segmentation pipelines toward the development of robust and clinically meaningful retinal analysis tools, enabling reliable biomarker extraction and downstream computational analysis in neurodegenerative research.

Model merging is promoted as a substitute for joint multi-task training, yet in the reinforcement-learning setting this substitution is essentially never tested against the baseline it claims to replace: methods merge independently released agents precisely because a joint model is unavailable. We build the missing comparison. Training difficulty-1 and difficulty-2 Qwen3-8B specialists on the AppWorld agent benchmark with LOOP, we merge them (TIES, RAM+) and pit the result against a jointly trained model on the same data. On task-goal completion, merging matches joint RL -- and every merge variant is statistically indistinguishable. To explain why merge method does not matter here, we measure the geometry of the specialists' task vectors, which carries no task-sampling noise: they are near-orthogonal (cosine 0.06 - 0.10) despite ~65% support overlap, a small, shared direction that grows over training and that we calibrate against a random-init floor and a same-run ceiling to confirm it reflects learning, not the low-rank parameterization. Because direction and support are decoupled, support and sign-based merging (RAM, TIES) collapse to near-uniform averaging. We release all code and statistics.

Large language models (LLMs) are improving rapidly as reflected in benchmark scores, yet these AI benchmarks largely test capabilities such as factual recall, narrow question answering, mathematical problem-solving, and coding and agentic tool-use. What remains poorly measured is AI progress on the analytical knowledge work white-collar professionals perform daily, including synthesizing complex information, exercising judgment under uncertainty and incomplete information, applying strategic and adversarial thinking in multi-stakeholder settings, weighing trade-offs, and producing defensible, structured analyses. This gap is even more pronounced for subjective components of such work, where success can be challenging to define. The "case method" form of education practiced by top business schools provides a natural foundation for addressing this measurement gap, and we construct BusinessCaseBench, a benchmark spanning hundreds of questions drawn from business cases across eighteen disciplines, each paired with a grading rubric derived from the expert-written instructor case solution. On BusinessCaseBench, frontier AI models already score highly against instructor rubrics, and capability within one model family improves substantially over two years. These results provide strong evidence that AI performance on this class of work is already high and rapidly improving, with implications for business schools, where case pedagogy trains undergraduates and MBAs in this kind of analytical reasoning, and for entry-level professional roles, where such skills have historically anchored early-career work.

Gene regulatory networks (GRNs) link transcription factor (TF) proteins to their target genes, yet reconstructing these networks from genome-wide data remains challenging under practical and methodological constraints. Many methods couple modeling assumptions to a specific inference procedure and rely on heuristic model selection, while evaluation is constrained by incomplete reference networks and point-estimate outputs that lack uncertainty. GRN reconstruction also depends on prior knowledge to constrain TF-gene interactions, yet available priors are often assay-dependent and difficult to transfer across species and less-characterized systems. In this thesis, we develop two complementary frameworks that address these limitations. In the first, PMF-GRN casts GRN inference as a probabilistic graphical model optimized by variational inference, enabling principled model selection and uncertainty-aware edge estimates. In the second, GLM-Prior addresses the prior bottleneck by fine-tuning the pretrained Nucleotide Transformer to predict TF-target gene interactions directly from nucleotide sequence, while generalizing across yeast, mouse, and human settings. Together, PMF-GRN and GLM-Prior motivate a dual-stage view of GRN reconstruction in which sequence-derived priors provide a transferable starting scaffold and probabilistic inference refines regulatory estimates with quantified uncertainty under incomplete evaluation resources.

We present Loopie, the most powerful looped Transformer to date. The Loopie series consists of two Mixture-of-Experts (MoE) models: a 20B-parameter model with 2B active parameters and a 6Bparameter model with 0.6B active parameters. Looped Transformers have long faced a challenge: given an N-fold increase in pre-training compute, increasing the parameter count by a factor of N usually outperforms looping a model N times. Loopie addresses this challenge. Extensive ablation studies, including comparisons with a vanilla 30B-A3B model, show that Loopie substantially outperforms vanilla Transformer baselines trained with the same compute budget. Our novel post-training pipeline equips Loopie with strong reasoning abilities. At the 2025 IMO and IPhO, Loopie achieves gold-medal performance without tools.

Pluvial (rainfall-driven) flooding accounts for 45% of National Flood Insurance Program (NFIP) claims in the United States and is harder to predict than its riverine and coastal counterparts, with existing approaches limited to coarse resolution, regional domains, or computationally intensive process-based models unsuitable for daily continental-scale use. We present DELUGE, a multimodal deep learning framework for daily pluvial flood damage prediction at ~1 km resolution and national scale, trained on spatially and temporally corrected NFIP claims (2017-2022) and structured around the hazard, exposure, and vulnerability components of disaster risk. Rather than blanket coverage of the Conterminous United States (CONUS), we model the top 100 highest-claim 75 km cells, distributed nationwide and accounting for ~81% of total pluvial flood claims. Our architectural novelty is a pair of parametric modules in the hydrometeorology branch, a Value Modulator and a Temporal Modulator, conditioned on terrain descriptors and AlphaEarth foundation-model embeddings, that expose directly inspectable hydrological response parameters and provide architecture-level interpretability-by-design. Under a spatial block holdout, DELUGE outperforms tuned Random Forest, XGBoost, and LightGBM baselines by 9% to 30% on a dollar-weighted area under the precision-recall curve (PR-AUC), a metric that emphasizes the rare, high-cost claims of greatest operational interest. Beyond DELUGE, we argue this interpretable conditioning scheme is a transferable pattern for integrating foundation-model embeddings into other geospatial prediction tasks.

Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research state. We present SciForge, a multimodal research-native AI workbench that reserves the graphical interface for human judgment while search, parsing, model routing, workflow execution, plotting, writing, and presentation generation run as modular agent-accessible services. SciForge is built around five pillars: (i) \emph{goal-scoped scientific decision governance} for \textbf{goal-oriented} research, with review gates and shared review surfaces; (ii) \emph{translate-then-reason} for \textbf{multimodal} input, routing scientific objects through domain translators before the agent reasons; (iii) \emph{evidence governance} for \textbf{auditable} traceability, linking claims to provenance chains and audit findings; (iv) \emph{collaborative team science} for \textbf{collaborative} research, enabling multi-role decision governance, with shared team workspaces planned for future releases; and (v) \emph{real-world application scenarios} for \textbf{practical} impact, demonstrated through eight end-to-end user cases, with flagship demonstrations including multi-day agentic research sprints for gene discovery, AI-guided de novo protein design, molecular optimization, and genome-to-BGC discovery. The system combines a thin interaction layer, contextual research capability patterns, an Agent Runtime and Workflow Engine, an Evidence-DAG audit sidecar and a Scientific Model Router. SciForge currently runs as a desktop application, with mobile supervision support; future releases will deepen team collaboration. The system is open-source and available at https://github.com/AGI4Sci/SciForge

Data-driven pre-fault dynamic security assessment (DSA) rapidly evaluates the dynamic risk of credible contingencies on a power system using machine learning. Existing approaches face two limitations. First, they require a large labelled database for training, with a separate model trained, tuned, and maintained for each contingency in a potentially long list of credible contingencies. Second, the trained models generalize poorly to unseen contingencies. This work addresses the limitations by using a tabular foundation model (TFM) that assesses stability through in-context learning, requiring no retraining or hyperparameter optimization. A single TFM can assess many contingencies at once, removing the need for one model per classifier. We also characterize when the use of electrical distance coordinates (EDC) as continuous features enables generalization of TFM to unseen contingencies and when they do not, demonstrating how a few labelled samples can reliably improve generalization. Through comprehensive case studies on the IEEE 68-bus system, we show that a single TFM attains an average Macro F1 score of about 90% with only 120 labelled samples per contingency, roughly two orders of magnitude fewer than conventionally assumed, without any model retraining or hyperparameter tuning. For new/unseen contingencies, we show that using just 10 labelled samples of the new contingency with EDC encoding matches the best achievable transfer learning oracle model, which requires fully labelled data and is not deployable in practice. Overall, this initial study paves the way towards developing and deploying foundation models for power system operations, with possible applications across multiple operational tasks.

Quantum continual learning aims to train quantum models on sequential tasks without losing previously learned knowledge. However, variational quantum classifiers (VQCs) are prone to catastrophic forgetting under nonstationary task distributions. We propose quantum elastic weight consolidation (QEWC), a quantum Fisher information (QFI)-informed regularization method for mitigating forgetting. Unlike conventional elastic weight consolidation based on classical Fisher information (CFI), which measures parameter importance through measurement-dependent output statistics, QEWC uses QFI to quantify the intrinsic sensitivity of the parameterized quantum state. This gives an information-geometric view in which important parameters are identified by the local response of the quantum state manifold. We evaluate QEWC on VQCs trained on sequential binary classification tasks, including classical image-classification and quantum phase-classification tasks. Simulations show that sequential training without regularization causes severe forgetting, while both CFI-based EWC and QFI-based QEWC improve retention of previous tasks. Mechanistic analyses further show that the two methods impose different regularization geometries: CFI acts selectively on measurement-sensitive directions, whereas QFI imposes a denser state-geometric constraint over parameter space. Under depolarizing noise, CFI values are strongly suppressed by degraded measurement statistics, while QFI preserves a more stable sensitivity structure of the noisy parameterized quantum state. These results establish QEWC as a physically motivated approach for studying and mitigating forgetting in quantum continual learning through quantum-state geometry.

This paper presents our system for Task 3 of the CLEF 2026 FinMMEval Lab, which requires daily long, flat, or short trading decisions for Bitcoin (BTC) and Tesla (TSLA) using news and historical market data. We formulate the problem as a discrete-action Markov Decision Process and compare four deep reinforcement learning algorithms: Policy Gradient (PG), Proximal Policy Optimization (PPO), Deep Q-Learning (DQL), and Deep Deterministic Policy Gradient (DDPG). The agents use technical indicators, cyclical calendar encodings, and daily news sentiment scores produced by LLaMA 3.2 1B. To reduce overfitting and align training with the objective of outperforming buy-and-hold, we introduce an alpha reward based on excess market return and randomize episode start dates. Hyperparameters are optimized with Ray Tune over 180 trials per algorithm-asset pair, with early stopping and model selection based on validation Sharpe ratio. On the CLEF Task 3 test set, DDPG achieves the strongest overall performance. DQL was selected a priori for the live endpoint because it obtained the highest validation Sharpe ratio, with selection performed without access to the test period. For TSLA, DDPG and DQL achieve cumulative returns of 54.96% and 52.62%, respectively, compared with 16.45% for buy-and-hold. For BTC, DDPG achieves a positive return of 1.58% while buy-and-hold declines by -34.27%. The results also reveal a substantial validation-to-test generalization gap, highlighting the difficulty of transferring policies selected in bull-market conditions to a bear-market regime.

Introduction: Biological systems face anatomical and metabolic constraints, including costly synaptic maintenance and limited connectivity. These constraints favor neural codes that compress behaviorally relevant information into low-redundancy patterns. We test whether an excitatory competitive Hebbian rule can support synaptic resource allocation under such constraints and whether the resulting representations occupy a more favorable cost-performance regime than reference learning rules. Methods: Representational cost is quantified using mutual-information-based measures derived from the Variational Information Bottleneck. Experiments use fixed audiovisual embeddings from three audiovisual benchmarks (AVE, Kinetics-Sounds, VGGSound100) to isolate downstream associative plasticity. Hebbian learning is compared with Dense Difference Target Propagation (DDTP) and backpropagation (BP) under matched sparsity and architectural constraints. Results: Hebbian learning achieves lower task-information cost (CTI) than sparse BP and DDTP in the main compressed comparisons, while reaching CTI values comparable to shallow BP with nonnegative weights. Rather than uniformly improving classification performance, Hebbian learning shifts the trade-off between task-relevant information and representational cost, yielding lower CTI at comparable functional performance in several settings. Discussion: The results indicate a cost-performance trade-off rather than uniform accuracy gains. For a given level of task-relevant information, Hebbian representations retain less input information while preserving functional performance, although accuracy is slightly reduced on some datasets. These findings support interpreting Hebbian learning as a mechanism for synaptic resource allocation rather than as a general strategy for maximizing audiovisual classification accuracy.

As software evolves over time, it is important to ensure that any behavioral changes occur as intended by developers. A promising approach for this goal is to generate tests that expose behavioral differences between the old and new versions of a program. However, current approaches fail to trigger behavioral differences for many code changes. This paper presents~DiffTestGen, a novel change-directed, LLM-based differential testing approach specifically designed to expose behavioral differences introduced by a code change. The approach is enabled by two key contributions: First, DiffTestGen leverages static call graph analysis and project documentation to identify valid entry points for test generation and to guide the LLM toward reaching the changed code. Second, DiffTestGen iteratively improves our newly introduced union coverage metric, which combines coverage of modified code in the old and the new version, by providing targeted coverage feedback to the LLM. We evaluate DiffTestGen on two datasets comprising a total of 463 PRs. DiffTestGen exposes behavioral differences in 78.2% of the PRs while achieving an average union coverage of 90.7%. Compared with the baselines, DiffTestGen exposes 99 more PRs overall and increases code coverage by 12.5% and 15.6% percentage points, respectively. By integrating DiffTestGen with the Testora regression detector, we show that the identified behavioral differences can be used to detect regression bugs missed by the best existing approaches.

Dialogue state tracking (DST) is one of the core components in task-oriented dialogue systems. At each turn in a conversation, DST estimates the user belief or dialogue state, which is used as input for downstream modules to predict system actions and generate responses. The increasingly popular dialogue system applications like Google Assistant, Siri and Alexa need to support a large number of services and APIs, resulting in growing attention to the scalability of such systems. Especially for some domains with little or no training data, the capability of transferring existing knowledge of other domains is highly desired. In this paper, we present a novel scalable framework for multi-domain dialogue state tracking. The proposed system leverages the pretrained BERT model to achieve zero-shot generalization, making it easy to quickly adapt to new domains without additional training. The performance of our model is evaluated on recently released schema-based dialogue (SGD) dataset, showing significant improvement compared to previous baseline.

AI systems increasingly retrieve from records that revise themselves: issue threads, encyclopedic histories, policy logs, and long conversations. The challenge is not only finding relevant evidence, but deciding which claims remain in force, which were superseded, and when to abstain. Structured memories promise to solve this with typed edges, temporal updates, and conflict status, yet evaluations often change mechanism and prompt presentation together. We study this as Evidence-State Revision, comparing flat retrieval, coarse edge invalidation, and fine-grained RevisionLedger on 2,907 high-agreement questions from GitHub, multi-repo issue histories, Wikipedia, and DyKnow-style temporal streams. A render-matched control (same layout, deprecation disabled) reveals the central confound: when a value is changed and later restored, RevisionLedger appears to beat a flat baseline by +0.182, but almost all the gain comes from easier presentation; the fine-grained mechanism residual is indistinguishable from zero (+0.021 to +0.025 across two judge families). After presentation is controlled, coarse invalidation is the only mechanism that pays for current-state queries, beating the fine ledger by 0.084; the same query-sufficiency principle says provenance mainly needs retained invalidated evidence, not richer typing. Memory evaluations should hold render fixed, and deprecation-aware systems should deploy the coarsest retained state that covers their queries.

Multi-Task Learning (MTL) in robotics perception systems supports comprehensive 3D spatial scene understanding by integrating semantic segmentation and depth estimation. While Vision Foundation Models (VFMs) are increasingly adopted as robust feature encoders, existing decoding strategies present a critical bottleneck. To address this, we propose DPNeXt, a streamlined multi-scale feature fusion decoder and efficient alternative to the standard Dense Prediction Transformer (DPT). DPNeXt uses dual depthwise separable inverted bottlenecks to improve frozen VFM utilization through fusion-centric decoding and independent task modularization. To further mitigate negative inductive transfer between tasks, we introduce the Multi-Task Boundary Guidance (MTBG) strategy. Unlike prior boundary-aware methods that add fusion modules or gating, MTBG applies symmetric boundary-focused supervision to encourage geometric consistency without extra annotation or inference cost. Experiments on Cityscapes show that DPNeXt-S outperforms prior state-of-the-art (SOTA) MTL models, while DPNeXt-B further improves the overall performance and achieves the best results among the compared methods. On NYUv2, DPNeXt-B also achieves the best semantic segmentation and depth estimation results among the compared methods while requiring substantially fewer trainable parameters than prior large-scale MTL models. Compared with the standard DPT, DPNeXt-S reduces trainable parameters by 78.6% and achieves the fastest inference speed among the compared models on resource-constrained laptop hardware. The source code, model checkpoints, and a demo video will be made available at https://github.com/kangjehun/DPNeXt.

Governments are increasingly mandating that LLM-generated content carry watermarks. The EU AI Act calls for markings that are "sufficiently reliable and robust." California's SB 942 requires disclosure that is "permanent or extraordinarily difficult to remove." Both mandates rest on an untested assumption: that watermark detection yields evidence reliable enough for courts. This paper tests that assumption directly. We evaluate three representative LLM watermarking methods -- KGW, Unigram, and the MarkLLM implementation of SynthID-Text -- against the Daubert admissibility criteria and the NIST SP 800-86 digital forensic process. To structure this evaluation, we propose a Forensic Readiness Score (FRS) framework with 12 criteria, three mandatory gates, and a 60-point scoring system. We focus on meaning-preserving paraphrase as the attack vector, since it is both legally realistic and difficult to dismiss as evidence tampering. The results raise serious evidentiary concerns. Out of 846 valid paraphrase runs across 15 diverse prompts per method, every single initially-detected KGW and Unigram text lost its watermark after paraphrasing -- 100% conditional removal. SynthID fared only slightly better at 98.3%. Even before any attack, false-negative rates were already high: 70% for KGW, 83% for Unigram, 80% for SynthID. The SynthID configuration also flagged 5.4% of paraphrased human-written controls as AI-generated and showed an 18.6% paradox rate, with 80% of its own pristine watermarked output landing in the uncertainty deadband. None of the three methods satisfy more than two of five Daubert factors. We also find that the FRS point-based scoring system, despite working as designed, cannot fully capture forensic uselessness -- a limitation worth noting for future framework design. These configurations, as tested, do not meet the evidentiary bar that courts require.

Increases in photovoltaic generation, charging of electric vehicles and heat-pump demand challenge operating limits in low-voltage distribution grids. This requires curative curtailment methods that can operate under sparse observability, noisy measurements, and imperfect grid models. Unlike prior end-to-end reinforcement-learning approaches for partially observable curtailment, this work decouples congestion detection and control by combining a random-forest violation pre-classifier with an actor-critic controller, and evaluates its robustness to measurement noise and grid-parameter mismatch. The framework is tested on a real low-voltage grid using synthetic future operating scenarios with low observability and controllability. With accurate grid parameters, the controller reduces total violation magnitude by 98.9%, and this performance remains nearly unchanged under the tested measurement-noise settings. Grid-model mismatch proves to be more challenging, but the controller still mitigates most violations under the tested mismatch assumptions.

Prompt optimization adapts large language models (LLMs) without updating model parameters, but many automatic prompt optimizers remain heuristic search procedures over candidate instructions. This paper studies prompt optimization as Bayesian posterior sampling over discrete prompt tokens. We define a posterior distribution by combining a task likelihood term, which rewards prompts that explain input-output examples, with a language-model prior, which favors fluent instructions. This converts prompt optimization into an energy-based posterior sampling problem, for which gradients can be used to guide discrete Markov chain Monte Carlo (MCMC) proposals over vocabulary tokens. We refer to our framework as BayesPO, short for Bayesian Prompt Optimization. In this paper, BayesPO is instantiated with Markov chain Monte Carlo: it uses a Metropolis-Hastings corrected Gibbs-with-Langevin (GwL) proposal and integrates parallel tempering for global exploration of rugged LLM-induced energy landscapes. The concrete sampler further adapts the GwL sampler to the practical constraints of non-weight-tied LLM embeddings. Experiments with Qwen2.5 models show that the sampler discovers semantically meaningful prompts on diagnostic tasks, that parallel tempering helps escape a local optimum in a poetry completion task, and that post-optimizing APE prompts on 24 instruction-induction subtasks improves average accuracy from 60.04% to 63.23%. The study also reveals two main limitations: energy minimization may overfit small optimization sets, and the current sampler remains computationally expensive. These findings position Bayesian prompt sampling as a principled post-optimization tool and point to a promising direction for probabilistic prompt optimization.

Deep remote photoplethysmography (rPPG) attains sub-bpm heart-rate error on frontal, stationary faces yet degrades sharply under head pose: on MMPD, the state-of-the-art FactorizePhys backbone's MAE grows $1.60\times$ from frontal ($|\text{yaw}|{<}15^\circ$) to large-yaw ($|\text{yaw}|{\geq}45^\circ$) frames. We argue that pose is a \emph{coordinate-structural} nuisance rather than a data-augmentation problem: in image coordinates the same pixel maps to different anatomy at different poses, blocking three priors otherwise natural for rPPG, namely the dichromatic reflection model, pulse-phase invariance across skin regions, and the POS/CHROM chromaticity projection, each of which presumes a stable anatomy-to-pixel mapping. We introduce \textbf{CanonicalPhys}, which prepends a differentiable four-point homography that fixes four facial anchors at canonical positions; in this canonical frame the three priors become expressible as a per-pixel Lambertian weight, a cross-ROI temporal consistency loss, and knowledge distillation from windowed POS, none of which adds trainable parameters over the backbone. At an identical parameter count, CanonicalPhys reduces MMPD's frontal-to-large-yaw MAE degradation from $1.60\times$ to $1.33\times$ and flattens the mild-yaw bin from $1.32\times$ to $1.07\times$ (across CanonicalPhys variants), with matched cross-dataset MAE reductions of up to $32\%$ on pose-rich targets. Code: https://github.com/infraface/CanonicalPhys

Over the past decade, responsible AI (RAI) has produced a substantial body of practice for identifying and mitigating the risks AI poses in high-stakes settings. Yet this work has not produced a market that rewards trustworthiness. Firms that invest seriously in safety, fairness, and oversight cannot consistently prove to consumers, regulators, and shareholders that their systems go beyond the bare minimum of compliance. What is missing is a way for society to recognize or compare the difference. The result is a trust gap: a structural condition in which responsible development efforts happen inside organizations but produce no external, independently recognized and verifiable signal of trustworthy outcomes. We argue this gap is sustained in part because of a focus on responsible AI (a matter of internal process) as opposed to trustworthy AI (a matter of independently verifiable real-world outcomes), and that it persists because of three compounding failures: (1) the market cannot distinguish trustworthy systems from their imitations; (2) evaluation targets models and outputs rather than deployed sociotechnical systems and their outcomes; (3) the measurement ecosystem is oriented toward avoiding harm rather than demonstrating benefit. Reviewing existing AI governance instruments and comparing them to certification regimes in healthcare, sustainability, and security, we show that none integrate a governance baseline, independently verified positive-outcome evidence, and market signaling in a single framework. We propose independent, outcome-oriented certification as the connective layer that can close the trust gap, complementing regulation and internal governance by making trustworthiness measurable, comparable, and commercially rewarded.

The ODRL policy language is emerging as the de-facto standard for policy modelling data access and usage preferences, AI governance policies and data workflows in European dataspaces. The current standard has no mathematical formal semantics to describe how a system should implement policy evaluation. This has resulted in a variety of systems and tools that implement their own interpretation of the language, which limits interoperability and cannot guarantee consistent results. Based on an existing semantic model of ODRL, we formalise the problems of ODRL evaluation for the access control and monitoring scenarios, in both static and streaming settings, and we provide a novel, efficient algorithm and implementation. We present the first ODRL Evaluator with transparent formal semantics and supporting all rule types. We experimentally measure its performance, analysing different scalability dimensions related to policy complexity and size of the data on which a policy is evaluated. We compare our system with the state-of-the-art by providing a comparative review of existing ODRL evaluators, which highlights the differences in supported ODRL features and evaluation modes.

This application paper presents DebrisTracer, a framework for the reliable tracking of debris in hypervelocity impact fast imaging. These noisy and highly specific datasets capture the ejection of a large number of debris fragments after the impact of a projectile launched at hypervelocity into a target material. The reliable estimation of debris mass and speed distributions is of major importance in aerospace applications. We document how to extend an off-the-shelf topology tracking framework based on critical point extraction and matching, in order to incorporate domain knowledge and physical assumptions. Our approach automatically produces an accurate and reliable debris tracking, enabling an interpretable visual analysis of this complex space-time phenomenon. Extensive experiments demonstrate the accuracy improvements provided by our approach over established tools used by domain experts in terms of physical validation, specifically via the prediction of the experimental ejected mass and crater depth profiles. We illustrate the utility of our approach across several use cases (with varying impact angles and physics). We show that our statistical summaries enable the visual identification of distinct regimes within the debris population, corroborating and refining prior expectations of domain experts. Our database and our C++ implementation are available at this address: https://github.com/tloloum/DebrisTracer.

Accurate hand gesture recognition using surface electromyography (sEMG) typically relies on multichannel sensor arrays and computationally intensive models. This limits practical deployment in low-power and embedded systems. This study investigates the feasibility of classifying ten hand gestures using a single sEMG channel combined with lightweight machine learning architectures. Raw sEMG signals were transformed into a comprehensive feature-based representation, including time-domain, frequency-domain, higher-order-crossing, and relative-intensity features. Feature redundancy was reduced using Pearson correlation filtering and the removal of highly correlated features, while dimensionality-reduction techniques (LDA and PCA) were applied selectively. Three classifiers, a feed-forward neural network (NN), k-nearest neighbors (KNN), and a support vector machine (SVM), were systematically evaluated across four experiments. Results demonstrate that combining time and frequency features with Pearson filtering and a compact NN can achieve up to 90 percent accuracy, even with limited temporal and spatial information. These findings highlight the potential of single-channel sEMG systems for cost-effective, low-power gesture-recognition applications.

The flourishing code hosting platforms and coding agents enable even beginners with private data to build tailored Machine Learning (ML) models using available code quickly. The training data for ML models, often regarded as private property (e.g., clinical records, transaction information), is at significant risk of information leakage. Property Inference Attacks (PIAs), as a significant type of privacy attack, aim to expose global property information of the training set. In this paper, we present Code-Poisoning Property Inference Attack (CPPIA), the first code-level PIA, which overcomes four limitations of existing works: insufficient attack performance, severe degradation of model accuracy, high computational overhead, and failure under defenses. We consider malicious code providers from code hosting platforms (GitHub) and coding agents (Codex). Upon downloading the poisoned code, data holders train models with their private data without professional auditing, subsequently releasing label-only APIs to the public. The adversary embeds the properties into secret samples during training and queries the trained model on these samples later to leak privacy. CPPIA offers 100\% attack accuracy without degrading model accuracy. It is also computationally lightweight and requires no shadow models. We evaluate the attack performance across four datasets, eight model architectures, eighteen properties, and under three defense mechanisms, demonstrating the universality and effectiveness of CPPIA.

We study a society of agents belonging to a number of occupational or cultural groups that form opinions about others' situation in the same or different group. Opinions develop either by observation within own group or by directly interacting with members of other groups, therefore by word of mouth (WoM). Additionally, global mass media (MM) may be available that inform indirectly about the situation of the various groups. The sociocultural interplay of these processes and the degrees of relative exposure to each of the sources has diversified effects on final opinion and social attitude formation. In large and complex societies and groups where not everyone can physically interact by WoM with everyone about everything, these processes show potential for mass control and social automation engineering. Our model can also represent and be generally informative about segmented societies that consist of groups with different occupational and cultural characteristics and it can offer insights into social issues such as the generation gap, social cleavages and so on.

Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations.Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior.However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and faithfulness. Moreover, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization capabilities that support informed decision-making and appropriate action across diverse stakeholders.

Code comprehension is one of the most time-consuming tasks in software engineering, yet most LLM-based assistants produce explanations that ignore who is asking and force developers into a disruptive copy-paste workflow. We present TARS, an LLM-powered agent integrated into Visual Studio Code that supports program comprehension through autonomous explanations anchored directly to the code under analysis. Built around a lightweight Theory of Mind paradigm, TARS profiles a developer's expertise, role, and stylistic preferences, then adapts the depth and tone of its explanations accordingly, grounding them in project documentation via Retrieval-Augmented Generation. To evaluate TARS, we conducted a controlled experiment with 18 participants on non-trivial Java snippets. Participants using TARS completed tasks 26\% faster, reported lower cognitive load, and found the explanations meaningfully adapted to their profiles.

Standard automation ROI misses four categories of systemic risk -- tacit knowledge erosion, resilience reduction, regulatory exposure, and socio-institutional capital degradation -- that affect long-term organizational performance. PHP-AIO (Protocol for Human Preservation in AI-Optimized Organizations) is a five-gate sequential decision protocol with a final composite check that quantifies these unpriced systemic risks at the role level and produces auditable automation decisions. A closed-form automation-debt measure ($ρ(P)$) formalises how role-level decisions accumulate across multi-step processes; its warning is neutralised only by a regulator-mandated human-in-the-loop anchor. Applied to stylised profiles of representative internal roles, PHP-AIO produces distinct outcomes -- automate, augment, hybrid, and preserve -- for candidates that standard cost-benefit analysis would uniformly automate. Threshold sensitivity analysis confirms the gate decisions are robust to upward perturbations of at least 14% in three of four representative cases. Keywords: AI governance, automation decision, human oversight, tacit knowledge, organizational resilience, financial services

Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks. Most recent progress in this area has been driven by remote-sensing-specific architectural designs, often introducing new encoders, alignment modules, or task-specific fusion mechanisms. In this work, we challenge the necessity of such architectural specialization. We show that a generally capable vision-language model can achieve competitive or state-of-the-art performance at challenging remote sensing benchmarks, provided that it is trained at sufficient scale across diverse data and tasks. Our model uses a single language policy that can either answer directly in text or invoke a localization tool for segmentation and grounding. To train this heterogeneous behaviour, we employ a multi-task reinforcement learning framework with adaptive task rewards covering multiple-choice VQA, free-form VQA, captioning, detection, and segmentation across a large variety of input types. Our approach achieves competitive results across a broad set of benchmarks, including high-resolution, multi-temporal, multi-modal and multi-view tasks. Further, as training data scales, our experiments show consistent improvements across most tasks both in and out of distribution, which correlate with per-task data diversity. These findings suggest that, for remote sensing VLMs, data scale is more important than architectural novelty.

Large Language Models (LLMs) are increasingly used for source code generation despite their outputs often exhibiting security vulnerabilities. Prior work shows that prompt engineering can mitigate such risks, yet (1) they focused on high-level prompting strategies, neglecting recent evidence that fine-grained syntactic variations can substantially alter model behavior; and (2) predominantly evaluate proprietary LLMs, limiting the applicability of their findings in industrial settings where self-hosted, open models are preferred for privacy, compliance, and deployment control. In this paper, we study how fine-grained syntactic constituents of prompts influence the security of open LLM-generated code. Using a parser-driven approach, we systematically generate syntactic variants of security-relevant code generation prompts and evaluate their impact on code security across multiple open LLMs and programming languages. Our results show that specific syntactic elements, such as constraints, guards, conditions, and concept bindings, and their position within the prompt consistently affect the likelihood of generating insecure code. These findings identify prompt syntax as a concrete security control surface and provide actionable guidance for reducing vulnerability risk in LLM-assisted development.

Deep reinforcement learning (DRL) has a longstanding tradition in addressing the reach-avoid task problem, especially for controlling robotic arms. While this task serves as a baseline environment within the research community, the ability of DRL to effectively learn the each-avoid task in complex and realistic scenarios beyond simplified and restricted tabletop settings remains uncertain. In this paper, we present, for the first time, a comprehensive benchmark for the reachavoid task that accurately captures real-world complexities without simplifications. We demonstrate a diverse range of settings for robotic arm reach-avoid task, which can be used for evaluating DRL research. We achieved this by utilizing the MuJoCo MJX physics engine and parallelizing both the simulation environment and DRL algorithms using the Brax library. We achieved state-of-the-art results with success rates of 96.1% (UR5e) and 98.8% (Franka Emika Robot) for the reach task and 86.8% (UR5e) and 95.2% (Franka) for the static reachavoid task. Our results indicate that while in previous works DRL agents could solve, for example, a reach task in a simplified setting perfectly, their agents performance collapses when evaluated in realistic scenarios. Overall, this work identifies that additional research is still required to claim the successful resolution of the robotic arm reach-avoid task using DRL. The environment and benchmarking code is available as open source at the following link

Advanced static program analysis requires reasoning on the semantics of non-trivial program behaviors (e.g., pointers and complex data structures such as lists and sets, functions, and objects) and how they affect the memory. In most programming languages, static and dynamic allocations are typically managed by the stack and the heap, respectively. However, how allocations behave and how the memory is managed at runtime can vary significantly depending on the programming language being analyzed. Proper handling of these aspects is essential, as an accurate memory model enables the detection of critical issues such as buffer overflows and underflows, use-after-free errors, and null pointer exceptions prior to execution, that is, before such erroneous behaviors occur. In this paper, we propose and formalize a generic memory framework to handle stack and heap memory during the analysis, that is able to support various behaviors from different programming languages (e.g., C, C++, Java, and Python), while remaining parametric, allowing different memory and value analyses to be independently chosen and combined. It relies on the Abstract Interpretation theory and enables sound approximation of different memory models and program behaviors. We introduce a split state abstraction that separates value and memory analyses into two modular abstract domains. These domains interact through a set of memory identifiers, along with a set of operations defined by the domains to manipulate them, allowing the framework to capture both value information and structural memory relationships.

Adult and pediatric electrocardiogram (ECG) interpretation relies on age-sensitive criteria, and models pretrained mainly on adult ECGs often transfer poorly to pediatric populations when pediatric labels are scarce. Existing multimodal ECG--text methods typically align waveforms and text at the global sample level, entangling evidence from co-occurring diagnoses and limiting transfer under this gap. We propose Pediatric-Adult ECG Alignment via Cross-modal Enhancement (PEACE), a knowledge-guided framework pretrained on the largely adult MIMIC-IV ECG corpus. PEACE describes each diagnosis along rhythm, morphology, and ST--T axes and, per recording, composes only positive-label descriptors into three axis tokens and a fused embedding. A label query network (LQN) uses diagnostic labels as queries to cross-attend over ECG tokens and axis tokens, while label set aware bidirectional contrastive learning (LSBC) aligns pooled ECG features with the fused embedding when recordings share diagnoses. Curriculum adaptive fusion (CAF) gates alignment strength according to smoothed classification loss and training progress, limiting disruption during early optimization. The knowledge branch is used only for training supervision; inference uses ECG signals alone. On ZZU-pECG, PEACE reaches macro average AUCs of 59.39%, 81.74%, and 91.56% under zero-shot, 50-shot, and full fine-tuning, with the clearest gains over foundation and knowledge-pretraining baselines under limited supervision; versus domain adaptation initializations, zero-shot improves substantially while 50-shot AUC is comparable to DANN. After fine-tuning on PTB-XL, PEACE reaches 96.90% macro average AUC over nine harmonized labels. Ablations confirm that label-conditioned knowledge alignment, rather than global text fusion, is the key driver of pediatric transfer gains.

Data-free knowledge distillation transfers the knowledge encoded in a teacher model to a student model without access to the original training data. Prior work such as Contrastive Abductive Knowledge Extraction (CAKE) achieves this for classifiers by synthesizing samples near the teacher's decision boundary. In this work, we investigate whether this boundary-seeking principle extends to autoencoder distillation through experiments on the MNIST dataset . To enable a direct comparison, we reformulate continuous reconstruction as a dense, per-feature classification task, allowing the decoder to output categorical logits. We show that boundary-seeking objectives are fundamentally ill-posed in bottlenecked generative architectures. CAKE operates on a single, instance-level objective, but a decoder acts as an array of tightly coupled, feature-level classifiers constrained by a shared low-dimensional bottleneck. Independently sampling contrastive targets for these coupled outputs violates the geometry of the learned latent manifold and produces severe gradient conflicts instead of informative boundary samples. Manifold-aware synthesis bypasses these conflicts entirely and establishes an effective baseline for data-free generative distillation.

Central to machine learning and signal processing is the ability to perform universal function approximation and learn complex input-output relationships from limited numbers of observations. Multivariate polynomial models offer a natural way to express such relationships through multiplicative feature interactions, but their coefficient tensors grow exponentially in size with the polynomial degree. Existing tensorized polynomial models reduce this cost, yet canonical polyadic decompositions have rank-limited expressivity, and tensor train formulations are feature order dependent. We introduce Multivariate Polynomial Optimization based on Matrix Product Operators (MPO)$^2$, a framework that combines learned MPO feature embeddings with compact polynomial weight tensors. This yields feature order independent polynomial representations that can incorporate structured operators such as projections, convolutions, and masks for weight tensor symmetries. Across regression and classification benchmarks, (MPO)$^2$ improves over existing tensor decomposition based polynomial models and provides a flexible alternative for efficient polynomial function approximation.

Complex systems comprise heterogeneous domains whose states, uncertainties, risks, and control consequences can cross domain boundaries. Existing cross-domain digital twin approaches broadly focus on comparison, reuse, semantic mapping, standardization, and interoperability, but do not inherently require operational connections among domain states, errors, objectives, constraints, decisions, and controls. This article proposes the trans-domain digital twin as an operational formulation along the continuum of Composite/Federated Digital Twin Systems. This approach connects heterogeneous domain twins through an aligned shared state, explicit coupling of data, models, states, errors, objectives, and controls, heterogeneous temporal coordination, joint decision-making, and feedback-based adaptation. The proposed framework presents a seven-layer conceptual architecture, a trans-domain orchestration core, minimum compliance conditions, a general operational formalism, progressive fast-meso-slow loops, and a single-episode offline training mechanism linked to bounded online adaptation. It also describes conceptual validation and evaluation criteria, a maturity model, a reference deployment architecture, and requirements for runtime safety, provenance, versioning, and model lifecycle management. The framework is conceptually mappable to standards for digital twins, model exchange, distributed simulation, and smart transducers; however, its formal compliance and operational effectiveness must be examined through independent benchmarks, uncertainty quantification, ablation testing, and field validation.

The stochastic fundamental diagram (SFD) provides a probabilistic description of the relationship between traffic density and flow or speed, enabling uncertainty-aware traffic modeling. However, existing stochastic models frequently struggle to accommodate rigorous physical constraints while retaining sufficient flexibility to capture complex nonlinear patterns. To address this, we propose a novel semiparametric SFD modeling framework by leveraging specially designed functional forms. These functions intrinsically satisfy physical constraints defined on the moments of the conditional flow distribution given traffic density while incorporating neural-network-based structures to capture complex empirical patterns. We derive a system of moment-matching equations to convert physical constraints into the parameterization of the conditional distribution, proving that a unique solution exists for the location-scale family of distributions, thereby guaranteeing model well-posedness. Furthermore, we demonstrate that the framework can be extended to non-location-scale distributions, including those requiring additional boundary constraints. Empirical evaluations on a real-world dataset reveal that our approach consistently outperforms representative baselines, delivering superior probabilistic accuracy and robust uncertainty quantification, particularly in congested regimes. Overall, the proposed framework provides a theoretically grounded and flexible foundation for stochastic traffic flow modeling.

Despite strong capabilities in data understanding and decision-making, autonomous data science agents still heavily rely on trial-and-error workflows that involve expensive computation. This bottleneck motivates models that can anticipate the effects of data science operations before real execution. In this paper, we introduce the concept of Data Science World Model, which model the data science execution environment by predicting environment state transitions conditioned on current workflow states and candidate operations. We further propose DSWorld, a practical framework that combines structured state construction, cost-aware routing, lightweight real execution, and an LLM-based simulator for expensive operations. To support training, we construct an 8K-scale transition trajectory dataset and introduce Reflective World Model Optimization, an error-aware reinforcement learning strategy for improving transition prediction. Experiments show that DSWorld accelerates RL-based agent training by approximately $14\times$ and search-based inference by approximately $3$-$6\times$ while maintaining competitive performance, and outperforms the strongest LLM baseline by 35.6% on transition prediction tasks. The code is available at https://anonymous.4open.science/r/DSWorld.

In production large language model (LLM) deployments, high API availability guarantees do not equate to conversational continuity. When a primary provider experiences an outage or strict rate-limiting, naive stateless failover mechanisms successfully maintain uptime but silently discard conversation history, severely disrupting the user experience. To rigorously quantify and resolve this failure mode, we introduce two novel metrics: Continuity Preservation Rate (CPR) and Continuity Latency Overhead (CLO). We propose a stateful, multi-provider proxy architecture utilizing a History-Forwarding strategy to seamlessly reconstruct conversational state across heterogeneous LLM endpoints during failover events. Furthermore, we release continuity-bench, https://github.com/Vishal-sys-code/continuity-bench, an open evaluation harness designed to stress-test context preservation under high-concurrency provider failure conditions. Our empirical evaluation ($N=750$ failover events) demonstrates that our stateful proxy achieves a 99.20\% CPR [95\% CI: 98.27\%, 99.63\%], cleanly transferring deep conversational context to fallback providers, compared to a near-0\% preservation rate for standard stateless architectures. Finally, we characterize failover latency distributions, identifying the critical necessity of asynchronous exponential backoff with jitter to prevent cascading retry storms against strict-limit fallback APIs. Our results provide a principled foundation for building robust, state-preserving multi-model inference systems.

Current world models operate at a single level of abstraction, with most prioritizing perceptual fidelity while lacking the spatial reasoning and semantic understanding required for real-world downstream tasks. We present a hierarchical driving world model that factorizes future prediction across two levels operating at distinct temporal and abstraction scales: a high-level predictor that forecasts coarse scene structure over extended temporal horizons, and a low-level generator that produces detailed predictions conditioned on the high-level output. This decomposition yields high perceptual fidelity while also capturing strong spatial and semantic representations. We further show that pretraining with a diffusion forcing objective yields substantially richer internal representations than the standard teacher forcing objective, while teacher forcing -- predicting only the next frame from clean context -- produces more stable autoregressive rollouts. We therefore introduce a generic two-stage training paradigm that pretrains the model with diffusion forcing and fine-tunes with teacher forcing, combining the representational benefits of the former with the rollout stability of the latter. Our approach achieves state-of-the-art results across the standard suite of driving world model evaluations on established benchmarks, including long-horizon generation fidelity, steering responsiveness evaluated on counterfactual scenarios, and internal representation quality. Project page with code, demo, checkpoints and qualitative results: https://lmb-freiburg.github.io/orbis2.github.io/

While the internal mechanisms of autoregressive (AR) transformers have been studied extensively, much less is known about diffusion language models (DLMs), an emerging alternative that generates text by iterative denoising. In this work, we study how DLMs implement induction, a mechanism behind in-context learning in which the model finds a repeated context and copies the token that followed it. Our analysis compares attention-only AR models and absorbing-mask DLMs with matched architectures. We find that DLMs learn a bidirectional induction circuit, where previous-token and next-token heads write local context into the residual stream and later induction heads use it to find and copy the answer from the matching source position. The circuit is direction-symmetric, working whether the source appears in the past or in the future. When only left context is visible, matching what an AR model sees, the DLM does not outperform its AR counterpart in induction capabilities. However, we observe it has stronger induction when both sides of the masked token are visible, pointing to bidirectional context access rather than a stronger one-sided mechanism. Beyond induction, we provide causal evidence that DLMs compute the global fraction of masked tokens and use it as an implicit timestep, even though they are given no explicit timestep embedding.

This work presents a game-theoretic framework for interpretable hyperparameter-objective interaction analysis rather than proposing a new optimization algorithm. In the proposed framework, Shapley Effects are employed for global sensitivity analysis, while Pareto front sets are utilized to identify effective hyperparameter configurations and support early-stage model evaluation. The resulting analysis reveals which players (hyperparameters) are most influential with respect to different objectives in a given game (application). Consequently, the proposed framework provides interpretable insights into objective-aware hyperparameter interactions, enabling practitioners to guide subsequent optimization, reduce the search space, and perform early-stage model evaluation. The effectiveness of the proposed framework is demonstrated using three distinct neural network architectures across different problem domains under multi-objective settings.

Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind. We hypothesize that a central missing ingredient is not more capability but dimensional completeness. We propose that the believability of an artificial interlocutor -- the degree to which a user attributes an inner life to it, which we call perceived mind -- is governed by whether the agent expresses a small set of first-person stances that humans use as evidence of mind, and that this is separable from task intelligence. We name four such dimensions -- time, truth, entropy, and love -- each defined as a behavioral stance rather than a benchmark competency, each with a human analog and a concrete emulation path; the time dimension already has an author-reported prototype. We identify an observable behavior layer -- initiative (unprompted action) and cadence (the shape and timing of turns) -- through which the stances surface in conversation, both partially realized as deployed features in a production companion application. We state six falsifiable predictions that a later pre-registered study will test, separating those that are pre-registrable now from those that remain conjectures pending operationalization. This is a conceptual framework: it reports no human-subjects data, and its central comparative claims are predictions, not findings. Throughout we hold a firm boundary -- the object is inferrable interiority, not interiority; this is perception engineering, not a theory of machine consciousness -- and we treat the resulting attachment and manipulation risks as load-bearing rather than incidental.

Imitation Learning aims to learn skills from extensive observations and demonstrations for robots, so it suffers from data scarcity and environment generalization. The existing methods predominantly focus on imitation from in-domain tasks and consequently struggle with generalization to unseen tasks. To bridge this generalization gap, we propose the \textbf{D}ynamics-\textbf{A}ware \textbf{M}eta-\textbf{I}mitation (DAMI) framework. By integrating meta-learning to construct a shared skill space, DAMI equips agents for rapid adaptation to novel tasks. We introduce the Visual-Motor Trajectory (VMT) module to capture complex spatio-temporal dynamics within the task latent space. Furthermore, we propose the Unpaired Unified Task (U2T) block to fuse unstructured multimodal observations. To coordinate these representations, we integrate a Task-Conditioned Feature Modulation (TCFM) mechanism customized for modulating low-level 3D features. By capturing intrinsic dynamics from a random complete reference demonstration, our framework learns the underlying task logic rather than memorizing static cues, ensuring effective generalization. Extensive experiments in both simulation and real-world settings demonstrate that our approach outperforms state-of-the-art baselines regarding direct inference on seen tasks and adaptation to unseen tasks via few-shot fine-tuning.

Much empirical legal research depends on translating unstructured text into structured variables. In corporate governance research as elsewhere, this translation has traditionally relied on human coding of documents such as charters and bylaws, a process that is costly, difficult to scale, and often opaque. This paper introduces DECODEM, a set of benchmark datasets for evaluating the automated extraction of corporate governance variables from organizational documents. The benchmarks pair randomly sampled corporate charters and bylaws with high-quality human annotations covering a range of governance provisions commonly studied in empirical work. Using these datasets, the paper evaluates several large-language-model extraction pipelines that vary in prompt design, task decomposition, and document handling. The underlying task consists of a set of document-level binary classification problems, one for each governance variable. The results show that automated extraction is feasible at a high level of accuracy for many provisions, with median performance near the upper bound across approaches. At the same time, performance varies systematically across variables, with a small number of provisions accounting for most of the remaining errors. More elaborate prompting strategies and cascading pipelines do not consistently improve performance for frontier models, but substantially narrow the gap between frontier and efficiency-oriented models in some settings, suggesting that pipeline design can partly substitute for model capability. By providing a standardized benchmark and a systematic evaluation of extraction methods, the paper demonstrates that current frontier models can extract legally meaningful information from complex corporate documents with high accuracy and suggests an important future role for automated feature extraction in constructing corporate governance datasets.

Human label variation in natural language inference is increasingly treated as signal rather than noise, but how much of it formal semantic structure explains has not been measured directly. We measure it on the 3,113 SNLI and MNLI items of ChaosNLI, using a rule-based operator and monotonicity tagger validated against MED (0.883 agreement at the edit site, 0.807 on the sentence-level summary our analyses consume), three preregistered analysis blocks, and full reporting of negative results. Three bounds emerge. First, a group-level boundary: hypotheses that are not purely upward monotone show reliably higher label entropy (Cliff's delta = -0.284), and rank-based tests defend the effect against operator-presence and length reductions, though a bounded-outcome sensitivity check weakens the regression form of the length defense. Second, an item-level ceiling: the same formal profiles explain only 3.3 to 3.6 percent of entropy variance and reach a median-split AUC of 0.606, too weak to identify high-disagreement items. Third, composition invariance: across the boundary, three high-powered preregistered contrasts on validated error shares and explanation-type shares (VariErr, LiTEx) all return null results. In this sample, formal semantic structure shifts how much annotators disagree by a small amount and does not detectably change what they disagree about. ChaosNLI-S/M consists of items selected for low original agreement, and every claim is conditioned on that scope. All analyses were preregistered in a version-controlled research log, whose audit trail, including one corrected interpretation rule, the paper discloses.

Human motion capture from head-mounted devices (HMDs) offers a scalable way to acquire real-world human motion and interaction data, which is crucial for applications in embodied AI and VR/AR. Existing approaches focus on either egocentric body tracking, estimating the motion of the subject wearing the device, or exocentric tracking, capturing the movements of people in the wearer's surroundings. So far, these two paradigms have largely been explored in isolation. In this paper, we propose a novel distributed framework that jointly leverages ego- and exocentric multi-modal signals for human motion estimation from HMDs. Unlike traditional motion capture systems requiring bulky multi-camera setups or obtrusive mocap suits, our approach, EgoExoMoCap, is as simple as two (or more) people, each wearing a pair of smart glasses. The method leverages head (plus potentially wrist) tracking signals for accurate estimation of global motion in the 3D world and combines context-aware image features based on DINOv3 to achieve robustness in the presence of noise and occlusions. Extensive experiments on two in-the-wild datasets show that our approach can robustly reconstruct motion even in challenging scenarios.

Large Language Models (LLMs) have become the dominant workload on modern AI accelerators, yet deploying them on specialized hardware still faces two core challenges: how to import a trained model into a compiler-friendly intermediate representation, and how to efficiently schedule the autoregressive inference loop under limited on-chip memory. This paper presents an MLIR (Multi-Level Intermediate Representation) based compilation method for large language models, illustrated using two dialects of operators, TopOp and TpuOp. TopOp serves as a high-level graph dialect that is independent of both the source framework and the target chip, and is responsible for expressing model semantics; TpuOp serves as the target hardware dialect, carrying chip-related decisions such as quantization, layer groups, and memory layout. A model is first represented as TopOp, then lowered layer by layer to TpuOp, and finally a deployable binary is generated. In addition, each Transformer layer is split into three stages for static compilation: prefill, prefill_kv (prefill with historical key-value cache), and decode, so as to accommodate the different computational characteristics of prompt-parallel processing and per-token generation. The method has been implemented in the TPU-MLIR compiler{https://github.com/sophgo/tpu-mlir} and the LLM-TPU deployment project\footnote{https://github.com/sophgo/LLM-TPU}, supporting a variety of generative models including the Qwen, Llama, InternVL, and MiniCPM-V series, as well as multiple quantization and deployment forms such as GPTQ, AWQ, and AutoRound.

Moderation systems increasingly rely on external toxicity tools, but those tools are unreliable under code-mixing, transliteration, slang, and language mismatch. We study the \emph{conditional reliability} of toxicity priors in Indian multilingual and code-mixed short text: English toxicity, Indic abuse, and rule-based severity cues can be useful evidence, but only in some linguistic and abuse-severity contexts. We propose ToxGate, a trust-fusion head that conditions each auxiliary signal on the encoder representation before adding it to the prediction state. Across three short-text abuse datasets, four transformer encoders, and five seeds per setting, ToxGate improves over matched plain encoders in 10 of 12 in-domain settings and 7 of 8 transfer settings. The largest and most interpretable gains occur in high-risk moderation slices, including explicit slurs, violent threats, and cross-dataset transfer. The broader lesson is that moderation systems should treat external toxicity tools and priors as conditional evidence rather than fixed features or ground truth, in focused ablations, source-specific gating gives the strongest results in transfer, severe-abuse slices, and high-risk triage.

Naturalistic language comprehension requires listeners to process both local probabilistic expectations and contextual semantic relations. Surprisal has been widely used to quantify local word unexpectedness, but evidence that it robustly predicts fMRI BOLD responses during continuous comprehension has been mixed. This study investigates whether contextual semantic relevance, defined as how strongly an incoming word relates to its recent semantic context, predicts BOLD responses during naturalistic speech comprehension. We analyzed two public fMRI datasets, the Alice dataset and the Moth dataset, treating them as complementary rather than identical replications. Transformed BOLD responses were modeled with generalized additive mixed models (GAMMs) and original continuous BOLD time series were tested with FIR/deconvolution analyses. In Alice, semantic relevance was significant across all 12 ROIs (region of interest), whereas surprisal was not significant after FDR correction. In Moth, semantic relevance showed consistent negative effects across all 30 ROIs, while surprisal showed no comparable pattern. These findings suggest that semantic relevance is a promising BOLD-sensitive metric of contextual semantic fit. More broadly, our findings support the view that slow hemodynamic responses during naturalistic speech comprehension may be especially sensitive to contextual semantic integration, whereas local probabilistic prediction error may be more difficult to detect reliably with fMRI. In this sense, semantic relevance extends computational models of language comprehension from prediction alone toward context-sensitive semantic integration.

Coding agents can fix a failing example without preserving the domain rule that made it fail, so later generations can repeat the same plausible mistake. We present agentic synthesis against counterexample-supplemented sketches, a repository-native method for systems whose governing policy is discovered during implementation. A human starts with a partial, code-shaped sketch, and a coding agent generates the first implementation. When a concrete failure exposes missing or mistaken policy, an operator explicitly approves the corrected behavior and rule. The agent then revises the sketch and repairs or regenerates code and prompt surfaces for that one counterexample. The full archive preserves provenance; a selected regression set gates each revision before the next candidate is revealed; and periodic clean regeneration tests whether the evolved sketch, rather than prompt history or accumulated examples, carries the learned policy. We demonstrate the method with CatSynth, a synthetic browser application and captured coding-agent experiment. In one open-world run with GPT-5.4-mini, 8 of 14 frozen candidate cases became counterexamples. The rebuild controls inherited that promotion schedule, and all three paths passed the 8 accepted cases. Rebuilding from the evolved sketch passed 19 of 21 withheld cases, compared with 15 of 21 when rebuilding from the initial sketch and replaying all accepted examples. Retaining code across counterexamples required 9 Developer calls and 719 lines of cumulative artifact churn, versus 15 calls and 2,394 lines for replay-all, and passed 18 of 21 withheld cases. These results provide inspectable evidence that the evolved sketch carried reviewed policy and that retaining code reduced rework in this run; with one model and one reveal order, they do not establish general superiority or correctness beyond the encoded checks.

A range of methods aim to enhance the performance of vision-language models (VLMs) at test time. Among them, transduction has emerged as a promising paradigm due to its strong compatibility and efficiency. However, realistic evaluations often involve highly imbalanced class distributions, which cause performance degradation or even collapse. In this work, we systematically revisit transduction from the perspective of penalized likelihood estimation (PLE), showing that PLE with a KL-divergence anchor term naturally yields an adaptive shrinkage behavior between prior anchors and empirical estimates. From this viewpoint, the brittleness of transductive methods can be attributed to the absence of anchoring mechanism and static modeling of the shrinkage strength. Therefore, we propose Mixture of Von Mises-Fisher Models with Dynamic Shrinkage (MOON). MOON is built upon a mixture of von Mises-Fisher distributions to model feature representations on the unit hypersphere. To handle imbalance, MOON dynamically adjusts the shrinkage strength using zero-shot priors at both instance and class levels. Thus, it suppresses unreliable assignments and prevents harmful updates from outlier classes, thereby mitigating negative transfer. MOON is model-agnostic, training-free, and requires no task-specific hyperparameter tuning. Extensive experiments further validate the advantage of MOON in both performance and efficiency. Our code is available at https://github.com/walawalagoose/MOON

Autoregressive video diffusion models have enabled the generation of arbitrarily long videos by removing conditioning on future frames, thus greatly improving computational efficiency. Yet, they suffer from error accumulation over time, as the denoised sequence gradually drifts away from the conditioning distribution seen during training. Recent advances attempt to reduce this error by anchoring each generated frame to the learned manifold of real ones. However, even when all generated individual frames lie close to the real manifold, there are trajectories which the model lacks sufficient knowledge to continue without exiting it, thus reaching a terminal point. To prevent the model from being trapped in terminal points, we start from the hypothesis that for well-modeled future trajectories the distribution of the predicted noise should match the one of the forward noising process. To enforce such a prior at test time, we introduce Terminal points Avoidance through Noise Guided Optimization (TANGO), which uses the diffusion model as a critic of its own outputs, by predicting one step forward and requiring an isotropic Gaussian noise prediction. We use the deviation from this expected noise distribution to search for an alternative trajectory that does not lead to a terminal point. Our approach achieves a $3.1\%$ absolute improvement on VBench over state-of-the-art, while reducing Fréchet Video Distance by $28.3\%$ on average across $15$s videos. Our code is available on https://mever-team.github.io/tango.

Metaphor in Arabic is a culturally grounded mechanism for constructing meaning, encoding cultural knowledge that shapes interpretation. Yet current Arabic language models typically collapse lexical, cultural, and metaphorical information into a single representational space, a phenomenon we term "semantic smearing". We introduce CAMMAR (Culture-Aware Matryoshka for Metaphorical Arabic Representations), a representation learning framework that organizes meaning into nested lexical, cultural, and metaphorical embedding subspaces through a staged semantic curriculum. The design implements compositional principles of Al-Jurjani's theory of nazum, modeling figurative meaning as compositionally grounded in prior semantic relations, and yields a training-free geometric measure of metaphoricity based on the distance between lexical and metaphorical representations. Evaluated on a new span-annotated Arabic metaphor set as word-matched figurative/literal pairs, the geometric readout detects metaphor well above chance when the inter-layer geometry is shaped by paired supervision (AUC up to 0.84; figurative outscores its literal counterpart for the same word in 82.6\% of pairs), but sits at chance under an unsupervised domain contrast alone, a clean separation between a legible-under-supervision regime and a non-emergent one. A controlled ablation shows that grounding the lexical layer in morphological roots gives a small but consistent gain, an effect absent from direct probing that reflects the layer's quality as a measurement anchor. We will release the datasets, cultural concept inventory, and code upon acceptance.

Workflow generation in visual creation systems such as ComfyUI demands not only syntactic accuracy but also expert-level reasoning over modular compositions. Existing large language model (LLM) approaches often treat this as a direct text-to-JSON generation task, struggling with structural brittleness and lacking the experiential knowledge required for effective design. We argue that successful workflow generation requires modeling knowledge itself, including its structure, hierarchy, and reasoning dynamics. To this end, we propose a knowledge-centric framework that learns to invert, inject, and infer with knowledge across multiple abstraction levels. We first perform knowledge inversion to distill hierarchical representations, ranging from full pseudo-codes and skeletons to high-level strategies, from large collections of real-world workflows. We then conduct knowledge injection through supervised fine-tuning, teaching the model to reason from task descriptions to strategies and from strategies to executable structures. During inference, the model performs reversible reasoning to synthesize executable workflows, augmented by self-refinement for structural coherence. Extensive experiments demonstrate that our method produces workflows with richer node diversity, more coherent structures, and higher execution success rates than existing systems, establishing a new foundation for knowledge-driven, agentic workflow generation.

Big data clustering remains challenging: the Minimum Sum-of-Squares Clustering (MSSC) problem underlying K-means is NP-hard, and existing methods either reach poor local minima or require prohibitive metaheuristic hybrids. We target arbitrarily tall data: a fixed feature space may contain arbitrarily many, possibly infinitely many, observations, while the algorithm accesses only finite random samples. We propose Big-means++, an algorithm achieving scalability and global-search quality by curating inputs to MSSC optimization on big data. It orchestrates local K-means refinements into a data-native global search for big data clustering. Rather than optimizing the full-data MSSC objective, Big-means++ traverses sample-induced surrogate landscapes. Each sample defines a distinct empirical MSSC approximation with a perturbed local-optimum structure, turning sample-to-sample variation into a global-search mechanism. Unlike Big-means, a flowing-incumbent strategy propagates centroid state across empirical landscapes through K-means refinements on fresh samples without rollback to a best-so-far solution. This increases mobility and favors stable, high-quality configurations across approximations of the full-data structure. A new shaking mechanism varies sample size geometrically, broadening the surrogate landscapes explored across resolution scales, accounting for cluster imbalance, and improving solution quality. A competitive multi-agent system asynchronously explores independent sampled landscapes, transforming diverse stochastic trajectories into collective search intelligence. Automatic convergence detection stops each agent after attaining a high-quality solution but before further search risks degrading it, while providing a universal speed-quality control. Experiments on 22 datasets against 11 competing algorithms demonstrate the effectiveness, efficiency, and robustness of Big-means++.

Can a model be identified from one experiment? We study analytic systems that are linearly parameterized by a combination of prescribed dictionary terms, such as partial differential operators and dynamical systems. For a single input-response pair, recovery is possible exactly when the evaluated dictionary terms are linearly independent. We prove a sharp zero-one law: either no input uniquely determines the coefficients, or almost every random input sampled from a nondegenerate Gaussian measure does. This dichotomy reduces one-shot system identification to a question about degenerate inputs and provides an a posteriori certificate for any recovered model. Numerical examples recover dynamical systems, nonlinear partial differential equations, and structured matrix families from single trajectory data, while also detecting when an extra probe is necessary.

Accurate timing prediction at the register-transfer level (RTL) is a longstanding challenge in design automation. Existing graph-based methods struggle with limited receptive fields, high complexity, and a lack of signal directionality. We present RTL-Sequencer, a novel sequence-based paradigm that enables scalable RTL timing prediction via linearizing logic cones by breadth-first traversal and applying modern linear sequence models. Furthermore, sequence models are customized by four synergistic techniques, including sequence shuffling, bidirectional modeling, differentiable modeling, and a hybrid graph-sequence architecture. Extensive experiments demonstrate significant improvements of RTL-Sequencer over state-of-the-art baselines, advancing early-stage timing optimization.

Automated essay scoring (AES) enables scalable assessment and timely feedback but remains challenged by transformer input-length limitations, which can cause information loss when processing long essays. This study proposes a generative AI-assisted summarization framework to improve long-form essay representation while maintaining scoring reliability. Using the ASAP 2.0 dataset, we generate controlled-length summaries with three GPT-5 variants (GPT-5, GPT-5 mini, and GPT-5 nano) and use them as inputs for downstream AES models. To preserve original writing signals, handcrafted linguistic features extracted from full essays are integrated with summary representations to form a hybrid framework. The approach is evaluated in terms of scoring performance, summarization quality, and computational cost. Scoring reliability is measured using quadratic weighted kappa (QWK), while summary quality is assessed through lexical overlap, semantic similarity, information retention, and redundancy metrics. Results show that GPT-5 mini achieves the highest agreement with human ratings, whereas GPT-5 produces the strongest summarization quality. Summary quality decreases for higher-scoring essays, indicating that more complex writing is more difficult to compress without information loss. These findings reveal trade-offs among model capacity, summary fidelity, cost efficiency, and preservation of educational constructs. This study provides an initial controlled evaluation of GPT-based summarization for AES and identifies important baselines and ablation studies required for future generalization. Overall, generative AI summarization offers a promising approach for scalable writing assessment while requiring careful validation of information preservation and fairness.

We study aggregation of statistical evidence under unknown and potentially complex dependence using group-invariance. Building on permutation-based constructions that treat transformed datasets as exchangeable units, we aggregate evidence across statistics for each transformed dataset and calibrate the resulting aggregates across transformations. We develop a finite-sample power and adaptivity theory for this framework, together with extensions to sequential and data-dependent aggregation that preserve validity. For single-batch aggregation, which uses one collection of transformed datasets for both standardization and calibration, we show that the critical values uniformly improve on deterministic calibrations valid under arbitrary dependence, including Bonferroni correction, while adapting to the unknown dependence structure. We also introduce a sequential alpha-spending version that permits early rejection when evidence is strong, and a two-batch extension that separates standardization from calibration to accommodate learned aggregation rules and reduce computation. Applications to adaptive nonparametric testing and conformal prediction illustrate how these results sharpen existing aggregation methods.

Autonomous driving systems (ADS) are rapidly advancing and increasingly deployed in real-world applications. This creates growing demands for effective testing to ensure system functionality and safety. However, ADS testing remains complex and lacks well-established standards for scenario selection, performance evaluation, and acceptance criteria. To better understand current ADS testing practices and challenges, we conducted an interview study with experts working on ADS development and testing in nine companies from six different countries. Through thematic analysis, we synthesized industrial testing practices, challenges, potential solutions, future trends, and proposed an evidence-centered closed-loop testing framework for ADS testing. Our findings show that current practices primarily focus on scenario-based and X-in-the-loop testing approaches, supported by diverse tools, metrics, benchmarks, and testing strategies. The participants highlighted major challenges related to scenario realism, scenario coverage, simulation fidelity, and acceptance criteria, while also discussing potential solutions such as the use of AI, world models, and end-to-end approaches. Furthermore, participants envisioned future ADS testing to become more automated, data-driven, and transparent across the industry. Overall, this study provides a comprehensive industry-grounded overview of ADS testing, proposes an evidence-centered closed-loop testing framework to provide actionable guidance for ADS testing, and outlines important directions for future research and practice.

In-context learning is a remarkable property of transformers and has recently received a lot of interest. In many studies of in-context learning, it has been shown that transformers are capable of implementing solver for linear and non-linear regression problems, in which the most of them implement gradient descent algorithm. However, it is still unclear whether those implementations have actually been acquired through training. In this paper, we construct a transformer with linear self-attention, which in-context learns the least squares estimate in a simple regression task. The point here is that the closed form (analytical) solution is approximately obtained by using layer normalization rather than an approximate solution based on gradient descent algorithm. Then, we show an experimental example, in which our implementation is mainly used in the transformer trained with l1 regularization when the target output is the least squares estimate.

Oscillatory Neural Networks (ONNs) present an attractive physics-based computing paradigm rooted in the dynamics of a network of typically fully coupled oscillators aiming to minimize an underlying energy function. In this paper, we propose an ONN-based solver for one well-known constrained combinatorial optimization problem, namely a Sudoku, by formulating the problem as a Graph Coloring problem. By modifying the already existing Graph Coloring solver to a computationally cheaper version and introducing an additional term ensuring the fulfillment of the Sudoku constraints, our solver is shown to significantly outperform the existing HNN- and ONN solvers in terms of accuracy. In particular, we are able to achieve nearly flawless accuracies on $4 \times 4$ as well as rather high accuracies on $9 \times 9$ Sudoku puzzles for different numbers of unknown digits.

Rollout generation is a major bottleneck in Reinforcement Learning (RL) for Mixture-of-Experts (MoE) Large Language Models, motivating low-precision rollout acceleration such as FP8. As an emerging low-precision format, NVFP4 combines fine-grained scaling for accuracy preservation with native W4A4 FP4 GEMMs for higher throughput than FP8. However, we find that directly applying NVFP4 to MoE RL rollout is impractical. NVFP4 rollout with BF16 training collapses after roughly 150 steps, accompanied by rapidly growing rollout-trainer log-probability gaps. Through training-inference error analysis and controlled ablations, we identify activation error, rather than weight error, as the dominant source of FP4 RL instability: weights can be synchronized and aligned by a shared quantization-dequantization path, whereas activations are recomputed online and error is amplified by the coarse E2M1 grid. Therefore, to stabilize NVFP4 RL for MoE, we propose QUantization-error Alignment across Dual Sides (QUADS). On the trainer side, we introduce Asymmetric Quantization-Aware Training fake-quantizing weights while keeping activations unquantized for better alignment. On the rollout side, Residual Activation Compensation corrects high-error activation channels while preserving native W4A4 GEMMs. In our MoE RL experiments on several benchmarks, QUADS achieves BF16-level accuracy, improves average pass@1 by 21.49 points over naive NVFP4 RL, and delivers ~16% higher rollout throughput than FP8.

Industrial processes often generate complex, interdependent time-series data from multiple sensors across multiple stages, forming complex dependencies among variables and process stages. Effective monitoring and timely anomaly detection of these time series through multivariate time series anomaly detection (MTAD) is crucial for preventing failures and ensuring the reliability of automated systems. Graph neural networks (GNNs) have advanced MTAD by leveraging data-driven graphs to model complex dependencies among variables, effectively capturing relational structures within multivariate time series to enhance anomaly detection performance. However, existing GNN-based approaches often overlook critical process knowledge, and even when this knowledge is considered, seamlessly incorporating it into existing models remains inherently challenging, leading to suboptimal performance. To address this limitation, we propose a knowledge-assisted multi-graph framework for modeling sensor dependencies in multi-stage industrial processes for MTAD, which explicitly incorporates process knowledge into graph learning to enhance dependency modeling and improve anomaly detection performance. Our method constructs three complementary graphs: one purely data-driven and two refined by integrating structural constraints derived from process knowledge. To effectively leverage these graphs for anomaly detection, we employ a multi-graph attention network, enabling a more accurate and robust representation of complex dependencies. Comprehensive experiments on two real-world, multi-stage industrial datasets demonstrate that incorporating process knowledge substantially enhances anomaly detection performance.

Classical approaches to event-based egomotion estimation, including those adopted by the top-performing teams of the ELOPE challenge, rely on geometric optimization frameworks such as contrast maximization, homography estimation, or dense optical flow combined with analytic motion inversion. This work investigates the geometric structure that emerges inside a multi-modal network for egomotion estimation. Event tensors, inertial measurements, and range signals are fused through a cross-modal attention architecture and trained in a batch setting. We analyze the latent space geometry and attention dynamics, showing that (i) embeddings lie on low-dimensional manifolds aligned with motion variables, (ii) attention weights adapt with angular excitation and visual reliability, and (iii) the fused representation recovers classical observability cues. These results bridge analytical estimation theory and modern data-driven fusion.

Geospatial datasets support applications from urban planning to climate modeling, yet consistent assessment of FAIR compliance is difficult. Existing evaluators use different rubrics and evidence sources and may fail on JavaScript-rendered pages or repository-specific identifiers. For 50 datasets from 10 repositories, the standard deviation of normalized scores across available tools averages 15.0 percentage points and reaches 30.3 for one dataset. Because these outputs are not equivalent measurements, we use them to characterize disagreement and failure modes, not comparative accuracy. We present AgentFAIR, a multi-agent framework combining structured metadata extraction with 13 sub-principle-specific LLM evaluators. Each produces a 0-3 maturity score, cited evidence, and recommendations; a critic checks evidence and consistency and can request targeted re-evaluation. Mean Findability, Accessibility, Interoperability, and Reusability scores are 79.7%, 70.4%, 45.3%, and 72.0%. Rank correlations with four baseline tools range from 0.31 to 0.61; the FAIR-enough comparison is not statistically significant. On a 10-dataset repeated-run subset, sub-principle agreement averages 89% (standard deviation: 3 percentage points), versus 71% without the critic. A preliminary 15-dataset expert study yields Fleiss' kappa of 0.71 and 82% alignment with expert consensus. API cost is approximately USD 0.054 per dataset. These results support auditability and feasibility, while the limited benchmark, incomplete ablations, and single-model-family validation constrain claims about accuracy and generalization.

Repository-level documentation, such as READMEs, is often the first point of contact between users and a repository. When this documentation is incorrect, users may encounter runtime errors or waste their time debugging. We call such mistakes in repository-level documentation README bugs. Addressing README bugs is challenging because documentation mixes prose with code, its connection to the source of truth is loose, and finding a bug still leaves developers to craft a repair. This paper presents READU, an inconsistency-driven technique for just-in-time detection and repair of README bugs. The key insight behind READU is that README bugs often manifest as inconsistencies between documentation and another source of truth: either repository-internal facts, such as source code, or repository-external facts, such as external dependencies. READU applies a high-recall commit filter, runs internal and external consistency checkers in parallel, uses an alert judge to remove false positives, and automatically synthesizes documentation patches. On 6,000 recent commits from six popular repositories including Linux and Spring Boot, READU detects 244 true positives with 75% precision, while consuming less than $0.01 and less than one minute per commit, on average. Of these true positives, READU correctly repairs 217. We report 66 found README bugs, of which (so far) 44 are confirmed and 26 are fixed.

Video Large Language Models (Video LLMs) have made significant advancements in various video understanding tasks. However, long-video scenarios remain challenging due to the tension between limited visual token budgets and the need to capture multiple key events. Existing approaches typically process long videos in two stages, i.e., i) select keyframes and ii) perform detailed perception, which exhibit limitations: they lack a modular mechanism for adaptive capacity allocation and self-correction, resulting in unreliable modeling. To tackle these challenges, we propose MoD-VLLM, a novel Modularized Dynamic-Granularity Video LLM framework for multi-event long video understanding, which unifies temporal grounding and semantic understanding iteratively and self-reflectively. Specifically, we propose a Positive-Negative Video Segments Grounding module and a Modularized Dynamic-Granularity Reflection module, which form a closed loop to progressively localize the question-related video segments. The grounding module instructs a Video LLM to distinguish relevant from irrelevant video segments based on the video question. The reflection module employs a modularized scheduler that dynamically selects fine-grained encoding for relevant positive segments to capture detailed perception and coarse-grained encoding for negative segments to maintain global context. We further propose a dynamic-granularity reinforcement learning strategy, allowing MoD-VLLM to learn optimal grounding policies and dynamic granularity visual representation jointly. Moreover, we propose MEventBench, a challenging Multi-Event Long Video Benchmark for complex long video reasoning. Extensive experiments on several long video understanding benchmarks and our MEventBench demonstrate that MoD-VLLM significantly outperforms state-of-the-art baselines.

OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such as healthcare and bioinformatics. In practice, however, real-world ontologies are often incomplete, which pose challenges for reasoning. In this work, we focus on a fundamental subsumption reasoning problem: given an incomplete ontology and a candidate (non-entailed) subsumption, determine whether the subsumption is semantically plausible and, if so, providing a logically sound explanation containing potential missing axioms. This task unifies subsumption verification with ontology abduction, and generalizes the latter by removing the need for a predefined candidate set of missing axioms. To address this subsumption reasoning problem, we propose NeurOWL, an end-to-end neuro-symbolic framework that jointly performs verification and abduction, leveraging both formally defined semantics and textual semantics through Large Language Models and ontology embeddings. We evaluate NeurOWL on real-world ontologies across multiple domains, demonstrating strong and robust performance across different domains.

Access to potable water is crucial for health, economic development, and sustainability. However, accurately classifying water quality remains a significant challenge due to the complexity and variability of water source data. This paper addresses the challenge of predicting water potability through machine learning and deep learning algorithms. It introduces a novel feature augmentation algorithm, AquaAugmentor, to enhance the predictive performance of these models for low-dimensional datasets. Utilizing a dataset that includes chemical attributes of water, such as pH, hardness, solids, chloramines, sulfate, and others. This study evaluates the performance of the models with and without AquaAugmentor. Each model applied to classify water as potable or non-potable and its performance is then evaluated and compared based on test accuracy and AUC score. The results highlight the strengths and limitations of our proposed algorithm, providing insights into the most effective techniques for improving the predictive performance of water quality classification. This study contributes to the broader efforts of ensuring safe water access and serves as a framework for employing machine learning in environmental quality assessments. The findings aim to assist researchers, policymakers, and public health officials in making informed decisions based on reliable machine learning predictions.

Explainable AI (XAI) for time series has seen significant algorithmic growth, but its utility in providing measurable performance gains for downstream tasks remains under-explored. This paper bridges this gap by introducing drXAI, a novel methodology that repurposes XAI attribution methods for effective data reduction in Time Series Classification (TSC). The core challenge in modern TSC is scalability; state-of-the-art models, such as Transformers, exhibit quadratic complexity relative to sequence length and linear complexity relative to the number of channels. This renders them computationally prohibitive for massive datasets. drXAI addresses this by using a fast, GPU-accelerated classifier (Hydra) to generate local attributions. We aggregate these into global feature importance scores and employ an automated elbow-cut heuristic to select the most salient features without requiring manual thresholds. We evaluate our approach on both synthetic and real-world univariate and multivariate datasets. On synthetic benchmarks, drXAI successfully recovers ground-truth features where traditional baselines fail. On real-world data, drXAI achieves between 80% and 90% data reduction while maintaining classification accuracy comparable to models trained on the full dataset. Most importantly, we show that drXAI allows resource-intensive models like ConvTran to scale to datasets that were previously inaccessible due to memory constraints. Our results show the benefits of using XAI not just for interpretability, but as a robust tool for feature selection and scalability in time series analysis. All our code and data are openly available.

Higher-order couplings enhance the expressive power of hypergraph neural networks (HGNNs), but they also intensify representation collapse in deep propagation due to strong multi-way feature mixing. This work investigates hypergraph oversmoothing from a dynamical-systems perspective and develops a reaction--diffusion framework for depth-resistant hypergraph learning. By defining hypergraph gradient and divergence operators, we interpret message passing as an incidence-level diffusion process. The analysis of pure diffusion shows that its continuous semiflow exponentially contracts the null-mode-free component of node representations and drives the Dirichlet energy to zero, revealing hypergraph oversmoothing as an intrinsic transverse-energy dissipation phenomenon. Motivated by this analysis, we propose Hypergraph Neural Reaction--Diffusion (HNRD), which introduces a reaction mechanism acting on the transverse component to compensate diffusion-induced dissipation and stabilize discriminative variations. We establish global well-posedness of the proposed dynamics and prove that the null-mode-free Dirichlet energy remains bounded away from zero. A forward-Euler discretization provides a practical HNRD layer with a stability condition for deep propagation. Experiments on benchmark and synthetic heterophilic hypergraphs demonstrate that HNRD consistently improves over representative hypergraph baselines. Depth, robustness, and efficiency analyses further show that HNRD preserves stable performance and nonzero Dirichlet energy under deep propagation and perturbations. These results provide a principled dynamical framework for designing deep hypergraph architectures that maintain higher-order expressiveness without representation collapse.