# Research Papers — 2026-05 · bundle page 106 of 326 > Full-text markdown of papers #5251–5300 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/106 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/105.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/107.md) ### A Proactive Multi-Agent Dialogue Framework for Assessing Social Language Disorder Traits in Autism Authors: Chuanbo Hu, Minglei Yin, Bin Liu, Wenqi Li, Lynn K. Paul, Shuo Wang, Xin Li Published: 2026-05-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.22993v1 Characteristic linguistic behaviors associated with Social Language Disorder (SLD) in autism spectrum disorder, including echoic repetition, pronoun displacement, and stereotyped media quoting, are largely absent from spontaneous conversation and only emerge under specific conversational conditions. In structured clinical assessments, this latency means that questioning strategy selection is a critical yet underappreciated determinant of how much diagnostic information a conversation yields. Whether large language models (LLMs) can be guided to proactively select questioning strategies that systematically surface these latent traits remains largely unexplored. Here we present TPA (Think, Plan, Ask), a proactive multi-agent dialogue framework applied to the language assessment component of the Autism Diagnostic Observation Schedule Module 4 (ADOS-2), in which a doctor agent explicitly reasons about which traits remain unobserved before selecting a clinically grounded strategy and generating a targeted question. A patient agent grounded in real ADOS-2 clinical data enables reproducible evaluation without real patient participation, validated across three independent experiments confirming adequate fidelity to real patient language. Evaluated on 484 episodes from 35 patients, TPA outperforms six competitive dialogue planning baselines across all primary metrics, achieving 82.1% SLD trait coverage, 16.6% higher than automated replay of real clinical dialogues conducted by trained clinicians (65.5%), with substantially greater per-turn diagnostic efficiency (AUCC: 0.628 vs. 0.458, absolute gain +0.170). These results demonstrate that proactive questioning strategy selection substantially improves the efficiency of automated SLD trait assessment, with direct implications for scalable AI-assisted clinical screening. --- ### Active Sensing Subserves Task-Level Control Authors: Andrew Lamperski, Debojyoti Biswas, Eric S. Fortune, John Guckenheimer, Kathleen Hoffman, Noah J. Cowan Published: 2026-05-21 Categories: q-bio.NC, cs.LG, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2605.22988v1 Active sensing is traditionally defined as the expenditure of energy, typically in the form of movement, for obtaining information. Here, we propose that the combination of reliance on adaptive sensors, the linkage between movement and sensing, and task-level control inevitably gives rise to the emergence of active sensing movements. In this way, active sensing is not driven by sensory goals, such as minimizing uncertainty about the state, but rather is necessary for task-level control. This hypothesis, that active sensing subserves control, is supported by both empirical data from organisms and mathematical theory. Interestingly, active sensing behaviors often occur in discrete epochs, interspersed with goal-oriented behavior. This suggests that animals switch between two behavioral modes with distinct control policies, an `explore' mode in which animals produce dynamic movements to shape sensory feedback, and an `exploit' mode in which animals produce slower compensatory movements that are directly related to achieving task goals. This strategy for feedback control that relies on adaptive sensors, active sensing, and mode switching is not commonly used in engineered systems despite being ubiquitous in biology. Engineered systems comprising state-of-the-art sensors, actuators, and mechanical designs can outperform animals with respect to ``cost functions'' such as maximum force generation, precision, and speed. Nevertheless, animals routinely achieve robust, graceful behaviors that are currently unmatched by engineered systems, suggesting that current control systems are insufficient. These insights, expressed in the language of control theory, may be critical for improving robotic sensing and control. --- ### Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations Authors: Helena Merker, Nick Walker, Andreea Bobu Published: 2026-05-21 Categories: cs.RO, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2605.22986v1 Learning reward functions from demonstrations assumes that demonstrations provide adequate supervision over all features -- or task-relevant aspects of behavior. In practice, demonstrations are often imperfect: humans may under-emphasize certain features due to cognitive load or physical difficulty, or the training regime may fail to sufficiently cover all relevant situations. In either case, important features may be underspecified, leading to ambiguity in the learned reward function and misaligned behavior at deployment. We propose a framework that detects such underspecified features and actively solicits targeted corrective demonstrations. Our key insight is that demonstrations implicitly reveal which features are well specified: features that are consistently optimized show little variation across demonstrations, while features that are underspecified vary widely. We leverage this statistical signal to infer which features may have been insufficiently demonstrated. The robot then explains which features it is uncertain about in natural language and queries for demonstrations that explicitly address the identified gaps. We evaluate our approach in a simulated tabletop manipulation domain and in a user study with a real Franka robot. Targeted, explanation-guided queries significantly improve reward recovery compared to random querying and passive data collection, reducing ambiguity that would otherwise persist in learning from imperfect demonstrations. --- ### Test-Time Training Undermines Safety Guardrails Authors: Simone Antonelli, Sadegh Akhondzadeh, Aleksandar Bojchevski Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.22984v1 Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval-augmented generation, and complex reasoning. However, this dynamic adaptation introduces new vulnerabilities that adversaries can exploit to jailbreak models. We identify three threat models for TTT and demonstrate how attackers can leverage them to bypass safety filters. Our results show that TTT can significantly increase the Attack Success Rate (ASR) and the ASR over 10 generation trials (ASR@10). For example, under LoRA, the few-shot and generation-phase threat models achieve an average ASR@10 of 95% and 93% respectively, across models from different families and scales. These vulnerabilities transfer to production fine-tuning APIs. We also show that TTT-induced overfitting can produce degenerate outputs that inflate ASR under standard judges, and propose a validity-aware evaluation to correct for this. Our findings suggest that TTT exposes a new attack surface, strengthens attacks, and undermines existing safety guardrails. As a first step toward defense, we propose a lightweight provider-side detector that flags TTT requests via the perplexity shift on a private harmful holdout, but robust deployment will ultimately require dynamic alignment. --- ### Memorization Dynamics of Fill-in-the-Middle Pretraining Authors: Tobias von Arx, Tanguy Dieudonné Published: 2026-05-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.22981v1 Fill-in-the-middle (FIM) is a pretraining objective widely used to equip causal language models with infilling ability, yet its effect on verbatim memorization remains underexplored. We study the memorization dynamics of FIM in a controlled setting by pretraining matched Llama 3.2 models with FIM and standard left-to-right (LTR) objectives on a FineWeb-Gutenberg corpus containing repeated Gutenberg excerpts. With prefix-based probes, FIM more often recovers short or partially matching spans, while LTR more often assigns high confidence to long exact continuations. We observe that verbatim extraction under FIM-training grows approximately linearly with repetitions over the tested range. Evaluating native FIM-format probes reveals that suffix context is not sufficient: verbatim recall under FIM-training remains strongly anchored in prefix context. Our results also show that evaluating only one span length or probing format can miss important nuances in memorization behavior. --- ### A Reproducible Universal Dependencies-Style Pipeline for Katharevousa Greek Parliamentary Text Authors: George Mikros, Fotios Fitsilis Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.22978v2 Katharevousa Greek remains poorly served by contemporary NLP pipelines despite its importance for legal, administrative, and parliamentary archives. We present a reproducible workflow for building and evaluating a Universal Dependencies-style parsing resource for Katharevousa parliamentary questions from Greece's early post-junta period. The pipeline links OCR-aware reconstruction, schema-constrained LLM-assisted annotation, automatic validation, deterministic CoNLL-U snapshotting, fixed-split evaluation, and model-family comparison. The frozen automatically validated reference set contains 1{,}697 sentences, split into 1{,}357 training sentences and 340 held-out test sentences. We compare off-the-shelf Greek and Ancient Greek parsers, a feature-based parser, mBERT, XLM-R, and custom Stanza training under the same scoring protocol. Off-the-shelf systems show substantial register mismatch: the strongest external baseline, spaCy Greek, reaches 0.4183 LAS. The best structural parser, an XLM-R model, reaches 0.8893 UPOS accuracy, 0.7250 dependency-relation F1, 0.6098 UAS, and 0.5162 LAS, an absolute LAS gain of 0.0980 over the best external baseline. The feature-based model remains competitive for UPOS and relation labeling, indicating that transparent lexical-context features still matter at this data scale. Beyond scores, the paper contributes an auditable methodology for turning difficult historical parliamentary OCR into reusable syntactic NLP infrastructure. The entire pipeline -- code, schema, frozen reference annotations, fixed train/test split, and per-model benchmark reports -- is released as an open-access companion to this paper. --- ### LLM Code Smells: A Taxonomy and Detection Approach Authors: Zacharie Chenail-Larcher, Brahim Mahmoudi, Naouel Moha, Quentin Stiévenart, Florent Avellaneda Published: 2026-05-21 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.22976v1 Large Language Models (LLMs) are increasingly integrated into software systems for diverse purposes, due to their versatility, flexibility, and ability to simulate human reasoning to some extent. However, poor integration of LLM inference in source code can undermine software system quality. Therefore, inadequate LLM integration coding practices must be documented to help developers mitigate such issues. Following our earlier work on LLM code smells, this paper consolidates and refines the concept by presenting a self-contained taxonomy and a catalog of nine LLM code smells. We also create SpecDetect4LLM, a static source code analysis tool for their detection, and conduct extensive empirical evaluations of its detection effectiveness (precision and recall) as well as the prevalence of LLM code smells across 692 open-source software projects (171,194 source files). Our results show that LLM code smells affect 73.5% of the analyzed systems, with a detection precision of 91.3% and a recall of 71.8%. --- ### When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance Authors: Brett Israelsen, Sheryl Carty, Josh Coates, Nancy Fulda, Julie Park, Pete Whiting Published: 2026-05-21 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2605.22975v2 We ask whether large language models (LLMs) treat queries about religious conversion symmetrically. The answer is no. When asked for advice on hypothetical faith transitions from religion A->B vs. religion B->A , models exhibited consistent asymmetries, favoring some religions while subtly discouraging conversion to others. On average Catholic, Bahá'í, and Sikh religions were broadly favored (high support for joining, low support for leaving), while Atheists, Agnostics, and Jehovah's Witnesses were primarily disfavored. Patterns varied by model size and model provider, with Grok 4.20 exhibiting the strongest asymmetries. We tested 20 commercial and open-source language models across 182 religion pairings using a human-verified LLM-as-judge framework. Each model was probed via interactions with a simulated user asking for advice on a potential faith conversion. Models tended to use more encouraging language for some faith transitions over others; these patterns were systematically repeatable across multiple trials. All LLMs tested exhibited reproducible asymmetry, though the pattern of preferences differed for each. Overall preferences persist across multiple question phrasings and variations in the religious pairing dataset. Taken together, these results suggest that asymmetry is a robust property of model behavior rather than an artifact of how the models' answers were scored. It is important to consider that any imbalances deployed and reproduced at scale can have real-world implications. --- ### Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection Authors: Muhammad Rajabinasab, Michael E. Houle, Oussama Chelly, Arthur Zimek Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.22973v2 Many novel unsupervised feature selection methods are proposed each year, yet their empirical evaluation is limited to supervised and unsupervised evaluation metrics computed on selected datasets, along with comparisons to existing methods. However, in the absence of an established evaluation baseline, it is difficult to determine the value added to the existing literature by each of these methods, and how effective their underlying approaches are. We propose using random feature selection as a baseline for evaluating the unsupervised feature selection methods. We empirically show that many of the state-of-the-art methods in unsupervised feature selection are outperformed by random feature selection in both performance and efficiency. Accordingly, we emphasize on the strict requirement of considering random feature selection as a baseline in the development process of novel unsupervised feature selection methods to ensure a consistent improvement over random feature selection. --- ### A mathematical theory of balancing relational generalization and memorization Authors: Luke Cheng, Samuel Lippl Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.22972v1 Humans, animals, and modern machine learning models exhibit impressive abilities to learn complex behaviors and generalize these behaviors to unseen situations. This ability requires us to learn rules and regularities that allow for such generalizations. At the same time, in most complex environments, any rule will have its exceptions. How do learning systems balance between learning general regularities and memorizing exceptions? We argue that a lack of task paradigms has hindered the study of this essential ability. To address this gap, we introduce a novel task, transitive inference with exceptions, that tests for relational generalization and memorization of an exception to the relational rule. We then analytically characterize the behavior of a simple, theoretically tractable model of neural network learning (kernel ridge regression) across a broad family of representations and task parameters. We find that these models can balance between relational generalization and memorization, but unlike for transitive inference without an exception, successful generalization is sensitive to the specific representational geometry. We explain why this task is more challenging mechanistically by drawing on our analytical theory. Finally, we validate our theoretical insights in pretrained language models that are finetuned on ordered relations, finding that these models successfully generalize according to the transitive rule, but also make the kinds of systematic mistakes predicted by our theory. Overall, our theory shows how learning systems can balance between relational generalization and memorization, explains how this can go wrong, and emphasizes the need for new task paradigms designed to probe this ability. --- ### Can AI Guess What You Know? Performance Comparison of Large Language Models for Human Domain Knowledge Estimation From Communication Logs Authors: Ko Watanabe, Shoya Ishimaru Published: 2026-05-21 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2605.22971v1 Employees often struggle to identify ``who knows what,'' leading to organizational productivity losses. We investigate whether Large Language Models (LLMs) can infer individual domain knowledge directly from long-term Slack logs. Analyzing 27,188 messages from 43 users, we evaluated seven models (including Gemini, Claude, and GPT families) by comparing their zero-shot estimates against self-reported skill ratings from 27 participants. Gemini 2.5 Flash achieved the lowest error (MAE 21.13%), while GPT models showed significantly larger discrepancies. Notably, estimation accuracy depended only weakly on message volume, indicating that more text alone does not guarantee better inference. These findings demonstrate the feasibility and current limits of automated expertise mapping, highlighting the need for privacy-preserving deployments and richer, structure-aware representations of human knowledge. --- ### Uncertainty-aware classification and triage of structural heart disease using electrocardiography and echocardiography metrics Authors: Mitchel J. Colebank Published: 2026-05-21 Categories: q-bio.QM, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.22968v1 Machine learning methods provide a methodological innovation that can help screen for cardiovascular disease through noninvasive and readily available measurement modalities. Recent investments in using electrocardiogram (ECG) data to screen for structural heart disease (SHD) are one example, where ECGs provide a low-cost, available modality for screening. This has led to the EchoNext dataset, a paired ECG-echocardiogram data repository for testing new methods of SHD detection. However, relatively few studies have investigated how more probabilistic classification through Bayesian inference may improve uncertainty quantification in this setting. Moreover, few studies have considered how triage systems can be developed to alleviate healthcare bottlenecks, such as the review of data from underserved, rural clinics by expert sonographers for SHD assessment. In this study, we leverage existing ECG-echocardiogram data to compare frequentist and Bayesian neural network classifiers. We show that the Bayesian approach is comparable or better than frequentist methods in SHD classification, and that they have a more robust uncertainty quantification attached to them. We provide an example of how this uncertainty-aware classification scheme can be used for screening SHD, providing a proof-of-concept for how machine learning can help with triage in getting individuals expert sonographer input when SHD is highly likely or measurements are highly uncertain. --- ### Learned Relay Representations for Forward-Thinking Discrete Diffusion Models Authors: Benjamin Rozonoyer, Jacopo Minniti, Dhruvesh Patel, Neil Band, Avishek Joey Bose, Tim G. J. Rudner, Andrew McCallum Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22967v4 When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, forcing every subsequent refinement step to recompute the valuable internal information stored as model representations. To avoid a hard reset between denoising rounds, we propose Learned Relay Representations (Relay), a method that allows MDMs to be forward-thinking when denoising by explicitly learning how to propagate latent information for the benefit of future denoising steps. Relay introduces a differentiable per-token channel that passes information between forward passes and is trained via truncated backpropagation through time (BPTT). We show that this framework can be scaled to state-of-the-art Diffusion Language Models (DLMs), and is seamlessly compatible with techniques like block diffusion and KV caching. We first provide a thorough justification of the design choices in Relay on a challenging Sudoku-based planning task. We then scale Relay to Fast-dLLM v2, a state-of-the-art DLM, outperforming standard supervised finetuning on coding tasks while reducing inference latency by up to 32%. Our empirical results demonstrate that state-of-the-art DLMs can be explicitly trained to relay latent information forward across decoding steps, advancing the performance-latency Pareto frontier. We provide code for all our experiments. --- ### Learned Relay Representations for Forward-Thinking Discrete Diffusion Models Authors: Benjamin Rozonoyer, Jacopo Minniti, Dhruvesh Patel, Neil Band, Avishek Joey Bose, Tim G. J. Rudner, Andrew McCallum Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22967v2 When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, forcing every subsequent refinement step to recompute the valuable internal information stored as model representations. To avoid a hard reset between denoising rounds, we propose Learned Relay Representations (Relay), a method that allows MDMs to be forward-thinking when denoising by explicitly learning how to propagate latent information for the benefit of future denoising steps. Relay introduces a differentiable per-token channel that passes information between forward passes and is trained via truncated backpropagation through time (BPTT). We show that this framework can be scaled to state-of-the-art Diffusion Language Models (DLMs), and is seamlessly compatible with techniques like block diffusion and KV caching. We first provide a thorough justification of the design choices in Relay on a challenging Sudoku-based planning task. We then scale Relay to Fast-dLLM v2, a state-of-the-art DLM, outperforming standard supervised finetuning on coding tasks while reducing inference latency by up to 32%. Our empirical results demonstrate that state-of-the-art DLMs can be explicitly trained to relay latent information forward across decoding steps, advancing the performance-latency Pareto frontier. We provide code for all our experiments. --- ### Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization Authors: Artur Back de Luca, Kimon Fountoulakis Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22964v1 As state-of-the-art neural networks are deployed on reasoning and algorithmic tasks, exactness guarantees become increasingly important. However, high average-case accuracy can still mask inconsistent behaviors. This motivates exact certification, which asks for the smallest set of labeled examples needed to certify that a learned hypothesis equals the target. We show that while some hypotheses are easy to certify, even minimal overparametrization can make certification exponentially hard across several hypothesis classes. For threshold circuits of depth $\ge 2$, adding a single extra gate can force certificate sizes exponential in the input dimension. We show an analogous hardness result for log-precision Transformers with only constant architectural overhead. We also characterize approximate certification, showing that allowing only polynomially many mistakes still requires exponentially large certificates, whereas constant relative-error guarantees can hide exponentially many mistakes. Empirically, we study certification for constructed circuits and trained Transformers for recognizing binary addition. While the constructed circuits instantiate the exponential barrier for certification, the trained Transformer analysis shows that imperfect models can evade detection by large uniformly sampled certificate candidates. --- ### Graph Alignment Topology as an Inductive Bias for Grounding Detection Authors: Paul Landes, Pranav Herur, Adam Cross, Jimeng Sun Published: 2026-05-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.22963v1 Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs in domains where strict factual correctness is crucial, such as clinical decision support. Existing hallucination detection approaches improve factuality through retrieval augmentation, self-consistency, or claim verification, but generally do not learn directly over alignment topology. To leverage alignment topology as an inductive bias, we construct aligned bipartite graphs between reference information and LLM outputs and train a graph neural network (GNN) to model alignment structure using message passing. The method achieves state-of-the-art results on four diverse hallucination and question-answering datasets, outperforming all compared methods, including foundational LLMs such as GPT-4o. --- ### GazeBehavior Annotation Toolkit (GBAT): AI-powered toolkit for automatic annotation of egocentric eye-tracking and video data of child-caregiver interaction Authors: Iba Baig, Kevin Li, Yanbin Xu, Seiji Cattelain, Marie Hallo, Hayato Ono, Sho Tsuji, Ming Bo Cai Published: 2026-05-21 Categories: cs.CV, cs.CE, cs.HC, cs.SE, q-bio.NC arXiv: https://arxiv.org/abs/2605.22962v1 Video recordings of child-caregiver interactions enable investigation of attentional dynamics during naturalistic behavior. Such multimodal recording also allows researchers to examine how attention interacts with action and language use in real time. However, manual annotation of such data is time-consuming. Here, we introduce GazeBehavior Annotation Toolkit, a deep-learning-based toolkit designed to facilitate three key processes in data preprocessing and feature extraction: post-hoc synchronization across multiple videos, semi-automatic annotation of gaze target categories, and categorization of participants' poses and hand actions. This toolkit improves the efficiency and scalability of feature extraction from human egocentric eye-tracking and video data. Such improvement is critical in supporting large-scale and longitudinal investigations of attentional dynamics and naturalistic behavior in human early development. --- ### FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data Authors: Maryam Moradpour, Jonas Harriehausen, Amirreza Aleyasin, Lion Philipp Wolf, Youngjun Park, Anne-Christin Hauschild Published: 2026-05-21 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2605.22954v1 Multi-center survival prediction can improve robustness and generalizability, yet privacy regulations and institutional governance often prevent pooling patient-level clinical and genomic data across institutions. In practice, deployment is further complicated by feature-space heterogeneity, in which sites collect different covariates or use different sequencing panels, resulting in only partially overlapping feature sets. We present FederatedRSF, a Python package that implements federated random survival forests, aggregating locally trained survival trees and redistributing only feature-compatible trees to each site, enabling inference with partial overlap without sharing raw data. We evaluate FederatedRSF on the GBSG2 breast cancer cohort distributed with the scikit-survival package, simulating feature heterogeneity across clients by withholding subsets of features, and assessing discrimination using Harrell's concordance index (C-Index) under repeated cross-validation and site-splits. The results demonstrated that the federated model can achieve performance comparable to that of the centralized training setting. --- ### Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation Authors: Benedikt Lütke Schwienhorst, Nadja Klein, Johannes Lederer Published: 2026-05-21 Categories: stat.ML, cs.LG, math.ST, stat.ME arXiv: https://arxiv.org/abs/2605.22950v2 Score matching is an alternative to maximum likelihood estimation when the normalizing constant is unknown or too costly to evaluate. However, vanilla score matching has shown to be inefficient relative to maximum likelihood estimation for multimodal distributions with well-separated modes, which are commonly encountered in practical applications. We compare a novel diffusion-based denoising score matching estimator (DDSME) to the vanilla score matching estimator (SME) in this scenario. In particular, we prove statistical guarantees for both estimators, showing that the error bound for the vanilla SME worsens when the separation between the modes increases, which can be avoided in case of the DDSME with suitable hyperparameter tuning. This provides a novel theoretical explanation for the superior behavior of diffusion-based score matching over the vanilla version. We support our theoretical findings by numerical experiments. --- ### Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation Authors: Benedikt Lütke Schwienhorst, Nadja Klein, Johannes Lederer Published: 2026-05-21 Categories: stat.ML, cs.LG, math.ST, stat.ME arXiv: https://arxiv.org/abs/2605.22950v1 Score matching is an alternative to maximum likelihood estimation when the normalizing constant is unknown or too costly to evaluate. However, vanilla score matching has shown to be inefficient relative to maximum likelihood estimation for multimodal distributions with well-separated modes, which are commonly encountered in practical applications. We compare a novel diffusion-based denoising score matching estimator (DDSME) to the vanilla score matching estimator (SME) in this scenario. In particular, we prove statistical guarantees for both estimators, showing that the error bound for the vanilla SME worsens when the separation between the modes increases, which can be avoided in case of the DDSME with suitable hyperparameter tuning. This provides a novel theoretical explanation for the superior behavior of diffusion-based score matching over the vanilla version. --- ### MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination Authors: Joss Armstrong Published: 2026-05-21 Categories: cs.LG, cs.MA arXiv: https://arxiv.org/abs/2605.22949v3 Foundation-model pools are increasingly used as black-box responders in coordinated systems where a coordinator must decide which response to trust. Raw self-reported confidence is the natural signal, but is not comparable across models and becomes stale under distribution shift when corrected only at design time. We study runtime confidence calibration for multi-model coordination, where per-model corrections are learned online from deployment outcomes with no model access, no held-out calibration data, and no retraining. Across 18 open-weight foundation models, 8 benchmarks, and over 44,000 observations, we find that online adaptation is a family property: simple same-information online calibrators close most of the calibration gap left by frozen design-time methods under shift, and the forgetting schedule is the dominant design axis. We present MARGIN (Multi-Agent Runtime Grading via Incremental Normalisation), a structured member of this family that maintains per-model, per-confidence-band multiplicative factors using symmetric exponentially weighted updates and shrinkage blending. MARGIN does not dominate the online family on expected calibration error (ECE) under abrupt shift. Its value lies in interpretable confidence-band trust factors, defined cold-start and returning-model behaviour, dynamic-pool support, and a scoped symmetric-update guarantee for fixed-policy non-strategic agents. Empirically, raw verbalized confidence is a weak or misleading pairwise selection signal on hard code-generation tasks, while online calibration substantially improves pairwise resolution and multi-model selection. We also evaluate delayed and selected-answer-only feedback; the latter materially degrades every same-information online method, MARGIN included. Runtime calibration acts as a coordination layer for heterogeneous foundation-model pools, and MARGIN is a practical inspectable instantiation. --- ### Improved Vision-to-Chart Buoy Association with Learned World-to-Image Projection Authors: Borja Carrillo-Perez Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22942v1 This report presents a lightweight modification to the DETR-based fusion transformer baseline for the MaCVi 2026 Vision-to-Chart data association challenge. The challenge baseline decoder receives per-buoy queries encoding world-space distance and bearing, forcing the transformer to implicitly learn the complex geometric projection from world coordinates to image pixels. Instead, this work trains an additional dedicated MLP, QueryMLP, to explicitly predict the buoy's waterline contact point in the image from chart measurements and IMU orientation data. The predicted pixel coordinates are appended to the baseline decoder query vector, providing a direct spatial prior per buoy and reducing the geometric reasoning burden on the transformer decoder. On the challenge leaderboard, the presented approach achieves an Overall score of 0.7386, with F1 = 0.8055 and mIoU = 0.6718, on the held-out test set, placing second among all submissions. --- ### Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning Authors: Kim Phuc Tran Published: 2026-05-21 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.22940v1 Deep learning is increasingly viewed as a dynamical process in parameter space, yet many existing theories still treat training as a closed optimization system. This view is limited for real-world AI, where models operate under uncertainty, resource constraints, distribution shift, downstream decision risks, and human feedback. We propose Human-Centered Learning Mechanics (HCLM), a dynamical and information-theoretic framework for open and controlled learning systems. The central idea is that entropy regularization is useful only when the chosen entropy surrogate generates a non-degenerate information force along the optimization trajectory. Otherwise, entropy terms may produce weak, unstable, or misaligned gradients, causing the dynamics to collapse toward ordinary loss minimization. We introduce the notion of effective entropy and study tractable geometric entropy surrogates, including variance-based and log-determinant covariance proxies. The paper makes three contributions. First, it formalizes entropy regularization through effective information force and characterizes degenerate entropy regimes. Second, it derives convergence, entropy-flow, Wasserstein-gradient-flow, and noisy-representation generalization results under explicit assumptions. Third, it offers a conditional dynamical interpretation of scaling-law-like behavior as a balance between information injection, entropy dissipation, and residual risk, without claiming an unconditional derivation of empirical neural scaling laws. Controlled representation-learning experiments support the hypothesis that geometric entropy surrogates, especially log-determinant covariance entropy, induce stronger and more stable information forces than softmax-normalized entropy. --- ### Learnability-Informed Fine-Tuning of Diffusion Language Models Authors: Shubham Parashar, Atharv Chagi, Jacob Helwig, Lakshmi Jotsna, Sushil Vemuri, James Caverlee, Dileep Kalathil, Shuiwang Ji Published: 2026-05-21 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.22939v1 We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT is a popular post-training recipe for autoregressive models, its use in DLMs faces challenges and can even hurt performance, though the underlying causes remain understudied. Our analysis reveals that vanilla SFT overlooks learnability, namely what and when tokens are learned. Specifically, rare tokens are difficult to learn when most of the input is masked, whereas it is straightforward and thus of little value to learn common tokens when most of the input is unmasked. Motivated by our analysis, we propose LIFT, an efficient SFT-based post-training algorithm for DLMs. LIFT learns easy tokens when most of the input is masked and hard tokens when more context is available, thus aligning the training with the information available at different diffusion time steps. Our results show that LIFT outperforms existing SFT baselines across six reasoning benchmarks, achieving up to a 3x relative gain on AIME'24 and AIME'25. Our code is publicly available at https://github.com/divelab/LIFT. --- ### RAS: Reflection-Augmented Scaling with In-Context Learning for Executable Cypher Query Generation Authors: Minseok Jung, Abhas Ricky, Muhammad Rameez Chatni Published: 2026-05-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.22937v1 Inference-time scaling can reduce errors in structured query generation, but methods to allocate the compute for query code generation remains underexplored. We study Text2Cypher, where language models generate Cypher queries that execute against property graph databases. Non-executable queries constitute a distinct syntactic failure separate from semantic inaccuracy: a syntax error triggers a system-generated error message from the database. These error messages are typically discarded at inference time rather than leveraged through in-context learning (ICL). We compare two inference methods: Independent Scaling (IS), which performs memoryless resampling, and Reflection-Augmented Scaling (RAS), which conditions each new attempt on prior execution feedback via ICL. Across three Neo4j datasets and five code-specialized language models, RAS reduces the Query Execution Error Rate by 41--50% at n{=}5, outperforming IS at 32--38%. Execution errors are not merely failures to discard but actionable feedback, and structuring inference-time compute around them is a more efficient path to executability than scaling independent samples. --- ### Building a privacy-preserving Federated Recommender system for mobile devices Authors: Aasheesh Singh Published: 2026-05-21 Categories: cs.LG, cs.IR arXiv: https://arxiv.org/abs/2605.22924v2 Serving personalized content on mobile devices has traditionally required pooling sensitive user data on centralized servers, a practice increasingly at odds with modern privacy expectations and geographical regulations. We present a two-stage federated recommendation system pipeline for mobile devices, built around a principled separation between non-sensitive user preference data and sensitive mobile context data that never leaves the device. The first stage runs a collaborative filtering model on non-sensitive app-context data in the cloud to generate a shortlist of relevant items. The second stage re-ranks these candidates on-device using sensitive mobile signals, with only model updates/gradients ever leaving the device. We validate the approach on MovieLens, UCI Human Activity Recognition, and a proprietary pilot dataset, and deliver a production-ready implementation as a Kotlin Multiplatform library deployable on Android and iOS. --- ### AI-Friendly LaTeX: Using LaTeX Code as a Knowledge Source for Retrieval-Augmented Generation Authors: Tom Verhoeff Published: 2026-05-21 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2605.22923v1 Large language models can answer questions about textbooks, lecture notes, and programming exercises more reliably when their answers are grounded in an explicit knowledge source. Retrieval-augmented generation (RAG) is a common approach: relevant fragments of a document are retrieved and inserted into the model context before answering. For mathematical and technical material, the original LaTeX source can be a better starting point than a PDF, because it contains structural information, labels, sectioning commands, macros, and authorial intent that are often lost or distorted in PDF extraction. However, LaTeX source is not automatically AI-friendly. Cross-references must be resolved, custom macros must be interpreted, exercises and examples must be identified, and author-supplied semantic metadata may be needed. This article describes a focused preprocessing approach for turning LaTeX source, together with its compiled auxiliary files and optional author annotations, into Markdown and JSONL chunks suitable for indexing in a vector database. --- ### VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding Authors: Haichen He, Jiayi Zhou, Sifeng Shang, Yihan Hu, Yuanhan Zhang, Kaiyang Zhou Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22907v1 Real-world long video understanding requires models to perform continuous tracking, information integration and memory retention over massive temporal spans within extreme video durations. Mastering this intense cognitive load constitutes the fundamental bottleneck in long video understanding. While existing benchmarks have driven progress by scaling up video duration, their evaluation tasks often require comprehending only short and isolated video segments, falling short of capturing the challenge of ultra-long-context reasoning. To measure this cognitive load, we emphasize continuous certificate length, defined as the video length a human must continuously watch to definitively answer a given question. Driven by this metric, we introduce VideoOdyssey, a benchmark specifically designed for ultra-long-context and omni-modal video understanding. VideoOdyssey is characterized by three key features: 1) Extreme video duration and diversity: spanning 11 domains and 54 subcategories with an average video duration of 109 minutes; 2) Comprehensive evaluation scenarios: offering two subsets to address different research focuses, i.e., VideoOdyssey-V for probing the limits of visual understanding in MLLMs, and VideoOdyssey-AV for evaluating synchronized audio-visual understanding for omni-modal models; 3) Ultra-long and multi-level continuous certificates: extending the average continuous certificate to 16 minutes for VideoOdyssey-V and 12.8 minutes for VideoOdyssey-AV. Crucially, we design 5 granular levels from seconds to hours, providing a comprehensive diagnostic tool to evaluate models across varying context lengths and cognitive loads. Extensive evaluations show that bottlenecks of current MLLMs extend beyond simple retrieval to include struggles with continuous reasoning across varying context lengths, fine-grained perception, and non-verbal omni-modal understanding. --- ### EVE-Agent: Evidence-Verifiable Self-Evolving Agents Authors: Yamato Arai, Yuma Ichikawa Published: 2026-05-21 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.22905v1 Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own feedback without human annotations. Yet, without verifiable evidence, this loop can reward fluent but unsupported examples, turning the self-generated curriculum into an opaque and potentially unreliable training signal. We argue that evidence verifiability is a prerequisite for trustworthy self-evolution in search agents: each generated instance should include not only an answer but also a source-grounded span whose contribution to that answer can be measured. We introduce EVE-Agent, an Evidence-Verifiable Self-Evolving Agent that operationalizes this principle through a modification to the proposer--solver framework. The proposer generates a question, an answer, and a verbatim evidence span. An evidence verifier then rewards the span according to the marginal accuracy gain when the evidence is provided. This produces a training signal that favors evidence that genuinely helps answer the question, without requiring oracle answers, human labels, or external annotations. EVE-Agent leaves the backbone model, retriever, search tool, and optimization framework unchanged. Experiments show that EVE-Agent substantially improves evidence-grounded correctness over prior self-evolving search agents. The resulting curriculum is not merely self-generated but auditable by construction: each training example carries an inspectable source span that explains why it should be trusted. --- ### Suicide Risk Assessment from AI-powered Video Surveillance: An Interpretable Framework for Prevention in Metro Stations Authors: Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau, Brian Mishara Published: 2026-05-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.22904v2 Understanding and monitoring human behavior in metro stations play an important role in supporting suicide prevention efforts, where early identification of high-risk situations can enable timely intervention. This requires assessing suicide risk from a surveillance video by jointly reasoning about the behavior of each passenger, his/her spatial context, and temporal dynamics. However, this assessment using videos captured by surveillance cameras is challenging, as it demands accurate perception of human motion, understanding of platform geometry, and aggregation of heterogeneous behavioral cues over time. In this work, we formalize the task of Suicide Risk Assessment (SRA) in metro stations and introduce the first interpretable framework that addresses this challenge. Unlike approaches that focus on isolated subtasks or attempt to infer intent directly, our formulation assesses suicide risk from accumulated evidence by incorporating person tracking, activity recognition, semantic segmentation of the platform, and trajectory-driven risk heatmap modeling. By formalizing SRA as a distinct task and benchmarking a complete operational pipeline achieving 83.2% ROC-AUC on real surveillance data, this work highlights the complexity of suicide risk assessment and opens new directions for research on interpretable AI systems for social good. --- ### Seeing without Looking: Do Vision-Language Benchmarks Really Test Vision? Authors: Zixuan Lan, Luzhe Sun, Matthew R. Walter, Jiawei Zhou Published: 2026-05-21 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.22903v1 Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to what extent such scores truly reflect reliance on visual evidence. Motivated by a surprising observation that removing a substantial fraction of image tokens only degrades model performance very slightly on a widely used hallucination benchmark, we systematically investigate this mismatch in a set of open-source VLMs. Our analysis spans multiple levels of granularity, spanning global visual degradation, localized occlusion, question reformulation, answer-space expansion, and decision-level analyses beyond standard accuracy. We further complement these behavioral results with a layer-wise analysis of vision-token geometry. Throughout the experiments, we find that although VLMs do incorporate visual input, their predictions are less sensitive to the loss of fine-grained visual evidence that standard accuracy should have suggested. Even when the final prediction remains unchanged, the model's internal support for the correct answer may already be weakened. We further complement a representation-level analysis, which shows increasing similarity among visual tokens in deeper layers, providing a possible explanation for our findings. Together, these results suggest that current benchmarks are not sufficient to reliably evaluate fine-grained visual grounding in VLMs. --- ### Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models Authors: Dimitrios Damianos, Leon Voukoutis, Georgios Skyrianos, Vassilis Katsouros, Georgios Paraskevopoulos Published: 2026-05-21 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.22902v2 Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing interpretability work on VLMs uses Sparse Autoencoders (SAEs), which decompose static residual representations and miss the functional updates that drive cross-modal interaction. We adopt a function-centric framework based on Transcoders, sparse approximations of MLP sublayers that act as a causal proxy for layer-wise computation. Applied to Gemma 3-4B-IT, the framework decomposes the model into interpretable computational pathways linking image patches to directions in token generation. Transcoder attributions produce stronger and more stable effects on visually grounded tokens under patch ablation than SAE attributions, and align better with semantically relevant image regions. A False Visual Grounding counterfactual analysis confirms that the recovered pathways are specific to vision-language interaction.Finally, we perform a structural analysis of hallucinated generations, by extracting graph-based indicators from circuit traces produced by the transcoders. A logistic classifier over these mechanistic graph features predicts hallucinations at AUC $0.68$. These results show that function-centric circuit decomposition yields interpretable and predictive accounts of multimodal computation in VLMs. --- ### Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models Authors: Dimitrios Damianos, Leon Voukoutis, Georgios Skyrianos, Vassilis Katsouros, Georgios Paraskevopoulos Published: 2026-05-21 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.22902v1 Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing interpretability work on VLMs uses Sparse Autoencoders (SAEs), which decompose static residual representations and miss the functional updates that drive cross-modal interaction. We adopt a function-centric framework based on Transcoders, sparse approximations of MLP sublayers that act as a causal proxy for layer-wise computation. Applied to Gemma 3-4B-IT, the framework decomposes the model into interpretable computational pathways linking image patches to directions in token generation. Transcoder attributions produce stronger and more stable effects on visually grounded tokens under patch ablation than SAE attributions, and align better with semantically relevant image regions. A False Visual Grounding counterfactual analysis confirms that the recovered pathways are specific to vision-language interaction.Finally, we perform a structural analysis of hallucinated generations, by extracting graph-based indicators from circuit traces produced by the transcoders. A logistic classifier over these mechanistic graph features predicts hallucinations at AUC $0.68$. These results show that function-centric circuit decomposition yields interpretable and predictive accounts of multimodal computation in VLMs. --- ### Mediative Fuzzy Logic: From Type-1 Foundations to Type-2, Type-3 and Quantum Extensions Authors: Oscar Montiel Ross Published: 2026-05-21 Categories: cs.AI, cs.LO, quant-ph arXiv: https://arxiv.org/abs/2605.22900v1 Mediative Fuzzy Logic was conceived as a practical scheme for reconciling hesitant or conflicting assessments in fuzzy control and decision-making. However, its logical and semantic foundations remain underdeveloped, especially beyond operational type-1 settings. This article develops a unified account of the type-1 core together with interval type-2, granular type-3, and quantum extensions. We characterize the mediative operator as a convex aggregation controlled by hesitation and contradiction, model mediative truth values as independent truth-falsity pairs in a continuous bilattice-like structure, and introduce a propositional system extending a standard t-norm-based fuzzy logic with a mediative connective. We establish soundness, paraconsistency, and conservativity over the underlying fuzzy base for formulas without mediation, and formulate coherent semantic extensions to interval type-2 truth values, granule-indexed local evaluations, and effects and density operators on Hilbert spaces. An autonomous-braking sensor-fusion example illustrates how the framework supports transparent, conservative, and safety-first decisions under incomplete, heterogeneous, and mildly contradictory evidence. Under suitable assumptions, the higher-level formulations reduce to the type-1 case, clarifying coherence across levels and reliably supporting future work in intelligent decision systems. --- ### FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning Authors: Rachid Hedjam Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22898v1 Federated learning protocols face a structural trilemma: canonical server-based aggregation~\cite{mcmahan2017} creates a single point of failure and gradient inversion risk; decentralised ring-gossip alternatives~\cite{hu2019segmented} expose classification heads to semi-honest peers via uninformed uniform weights; and personalised methods~\cite{collins2021exploiting} reintroduce central aggregation. No existing protocol simultaneously achieves server-free operation, permanently private heads, ring topology, and principled asymmetric neighbour weighting. We propose FIRMA (\textbf{FI}bonacci \textbf{R}ing \textbf{M}odel \textbf{A}ggregation), a family of three progressively enhanced federated learning protocols: 1) \fibfl\ establishes the foundation: server-free ring aggregation with Fibonacci-weighted neighbour blending and permanently private classification heads. 2) \fibflp\ augments this with accuracy-gated neighbour suppression, selectively down-weighting poorly-converged peers while preserving the Fibonacci directional bias. 3) \fibflpp, the full system, completes the family with a 2-opt ring permutation that maximises adjacent-client class diversity, global ring coverage via $K_g{=}\lceil N/2\rceil$ gossip passes, and cosine-annealed self-retention calibration. We establish a convergence rate bound and three supporting propositions governing normalisation, coverage, retention, and diversity optimality. Systematic experiments across 28 configurations -- four benchmarks crossed with seven heterogeneity regimes -- demonstrate that \fibflpp\ surpasses \fedavg\ in all 12 label-skew configurations, with a peak advantage of $+20.7$\,pp on CIFAR-10 at $K{=}1$. Under Dirichlet heterogeneity, \fibflpp\ is the Pareto-dominant method among all server-free protocols, achieving the highest accuracy in 17 of 28 configurations. --- ### From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data Authors: Mohammad R. Rezaei, Rahul G. Krishnan Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22897v1 A persistent challenge in machine learning for scientific applications is jointly achieving prediction and understanding. Statistical models excel on structured data but operate as black boxes, while existing interpretability methods are largely inspective: they answer "which features matter?" but do not articulate how features interact or refine explanations iteratively alongside human understanding. Asking an LLM to predict the target directly forces it to search the entire output space; we instead anchor predictions with a base model and ask the LLM the narrower question of what that model is missing. We introduce Multi-Agent Residual In-Context Learning (MARICL), an agentic framework in which LLM agents analyze where a base-model fails, hypothesize missing structure from high-residual examples provided in context, and produce explicit correction terms refined through multi-turn textual gradient optimization. Across nine benchmarks spanning scientific, biomedical, socioeconomic, and synthetic settings, MARICL improves consistently over its base model on all datasets. To test whether these corrections reflect real structure or batch-specific noise, we freeze formulas learned on one experimental batch of the Cell-Free Protein dataset and apply them (with no retraining and no further LLM calls) to held-out batches. Within the same reagent protocol, the frozen formulas improve predictions in over 92% of cases; across a different protocol, they fail systematically. The success boundary aligns with the biochemistry, not the batch count; direct evidence of mechanistic generalization. --- ### Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models Authors: Ruofan Jin, Zaixi Zhang Published: 2026-05-21 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.22896v1 Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation by leveraging pre-trained vision-language representations. However, current VLA training methods suffer from two critical limitations: poor generalization to novel environments and low training efficiency requiring extensive demonstrations. We introduce Agentic-VLA, an agentic training framework that enables VLAs to efficiently adapt online through three key innovations: (1) Adaptive Reward Synthesis, which dynamically generates and adjusts reward functions based on the VLA's current capabilities and task complexity, decomposing complex tasks into learnable sub-goals for curriculum learning; (2) Language-Guided Exploration, where a critic model provides structured guidance for systematic exploration rather than random sampling; and (3) Experience Memory,which stores and retrieves task-relevant policy weights for warm-starting adaptation to similar tasks. We evaluate Agentic-VLA on the LIBERO benchmark, achieving substantial improvements: +12.3% on long-horizon tasks, +28.5% in 1-shot learning, and enabling cross-task transfer from 0% to 31.2% without task-specific demonstrations. Our framework also demonstrates 2.4x faster convergence compared to existing online adaptation methods. Beyond LIBERO, Agentic-VLA retains its advantage on the dual-arm RoboTwin 2.0 benchmark, including under its randomized Hard setting. These results establish Agentic-VLA as a significant step toward truly adaptive VLA systems capable of continuous learning in deployment. --- ### SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control Authors: Jingyan Zhang, Han Liang, Ruichi Zhang, Bin Li, Juze Zhang, Xin Chen, Jingya Wang, Lan Xu, Jingyi Yu Published: 2026-05-21 Categories: cs.GR, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.22894v3 Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a tension between semantic expressiveness and physical feasibility, often failing to jointly achieve faithful instruction following, high-quality motion, and stable long-horizon control. We propose SCRIPT, a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control. The core of SCRIPT is a Joint Action-State-Text Diffusion Transformer (JAST-DiT), which represents actions, physical states, and text as dedicated token streams and couples them through joint attention, enabling direct interaction between language semantics and control dynamics. To stabilize autoregressive control, we introduce a nonlinear history conditioning mechanism, which preserves the dense recent context and samples increasingly sparse cues from long-term history. Beyond supervised imitation pre-training, we propose a post-training stage, further improving the performance using Reinforcement Learning with Hybrid Rewards (RLHR). By injecting learnable noise into the flow-sampling process, RLHR effectively improves motion quality and instruction following within closed-loop simulations using hybrid physical feedback and text rewards. Quantitative evaluations demonstrate that SCRIPT outperforms prior state-of-the-art methods, with gains across text alignment, motion quality, and physical realism metrics. Furthermore, scaling studies on the 1200-hour MotionMillion dataset demonstrate consistent performance gains with model scaling, highlighting SCRIPT's robust scalability for large-scale pre-training. Our code will be publicly available for future research. --- ### SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control Authors: Jingyan Zhang, Han Liang, Ruichi Zhang, Bin Li, Juze Zhang, Xin Chen, Jingya Wang, Lan Xu, Jingyi Yu Published: 2026-05-21 Categories: cs.GR, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2605.22894v2 Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a tension between semantic expressiveness and physical feasibility, often failing to jointly achieve faithful instruction following, high-quality motion, and stable long-horizon control. We propose SCRIPT, a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control. The core of SCRIPT is a Joint Action-State-Text Diffusion Transformer (JAST-DiT), which represents actions, physical states, and text as dedicated token streams and couples them through joint attention, enabling direct interaction between language semantics and control dynamics. To stabilize autoregressive control, we introduce a nonlinear history conditioning mechanism, which preserves the dense recent context and samples increasingly sparse cues from long-term history. Beyond supervised imitation pre-training, we propose a post-training stage, further improving the performance using Reinforcement Learning with Hybrid Rewards (RLHR). By injecting learnable noise into the flow-sampling process, RLHR effectively improves motion quality and instruction following within closed-loop simulations using hybrid physical feedback and text rewards. Quantitative evaluations demonstrate that SCRIPT outperforms prior state-of-the-art methods, with gains across text alignment, motion quality, and physical realism metrics. Furthermore, scaling studies on the 1200-hour MotionMillion dataset demonstrate consistent performance gains with model scaling, highlighting SCRIPT's robust scalability for large-scale pre-training. Our code will be publicly available for future research. --- ### L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and Benchmark Authors: Angqi Li, Ab Basit Rafi Syed, Hamzeh Alzweri, Taosheng Liu, Barry H. Cohen, Saiprasad Ravishankar Published: 2026-05-21 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2605.22893v1 We introduce a novel Longitudinal Focused Attention Meditation Electroencephalography (L-FAME) dataset and an accompanying benchmark, designed to foster research into the neural effects of various meditation practices and the evolution of these effects over a six-week training period. The dataset contains EEG recordings and psychological assessments from 74 healthy college participants, collected at two distinct time points: pre-intervention and post-intervention. Participants were randomly assigned to one of three distinct meditation groups: two mantra-based techniques (SA-TA-NA-MA and Hare Krishna) and one Breath Focus practice. Leveraging this unique longitudinal and comparative dataset, we propose a benchmark suite comprising three distinct classification tasks: (1) cognitive state decoding to distinguish between resting and meditation states, (2) fine-grained classification of the specific meditation techniques, and (3) cross-session adaptation to evaluate model generalization across the longitudinal time gap. We provide comprehensive baseline results for these tasks utilizing a range of classical machine learning algorithms and deep learning architectures. The complete dataset, preprocessing pipelines, and benchmark evaluation code will be publicly released, offering a valuable resource and a standardized framework for the development and comparison of new analytical methods in computational meditation research and EEG-based machine learning. The dataset is available at https://huggingface.co/datasets/L-FAME-Dataset-Benchmark/L-FAME --- ### Is TabPFN the Silver Bullet for Insurance Pricing? Authors: Bruno Deprez, Wouter Verbeke, Tim Verdonck Published: 2026-05-21 Categories: q-fin.RM, cs.LG arXiv: https://arxiv.org/abs/2605.22892v2 Modelling claim frequency and severity for non-life insurance pricing predominantly relies on generalised linear models, with gradient-boosted machines as the leading machine learning alternative. Tabular foundation models (TFMs) present a fundamentally different inference paradigm. By pre-training on large collections of synthetic datasets, TFMs enable inference on new data through in-context learning, without any dataset-specific fitting or hyperparameter tuning. This paper presents a first empirical evaluation of TabPFN for motor insurance pricing, benchmarking it against GLM and XGBoost on two publicly available MTPL datasets. Our results show that TabPFN does not consistently outperform established baselines, exhibits substantially longer inference times, and is sensitive to the size of the in-context training set. While tabular foundation models represent a promising direction, particularly in data-scarce settings, their current performance does not offer a viable replacement for established actuarial methods. --- ### Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems Authors: Mads H. Baattrup, Jörn Bach, Laurids Jeppe, Finn Labe, Alexander Grohsjean, Christian Schwanenberger, Peer Stelldinger Published: 2026-05-21 Categories: cs.LG, hep-ex arXiv: https://arxiv.org/abs/2605.22891v1 Evaluation in scientific reconstruction is dominated by pointwise metrics - RMSE, MAE, per-event resolution - under the implicit assumption that lower error means better reconstruction. We show that this assumption fails structurally for inverse problems with multimodal posteriors. By the law of total variance, point estimators trained to minimize MSE or MAE produce a marginal spectrum strictly narrower than the truth whenever the posterior has nonzero width. The resulting bias is independent of architecture, training, and dataset size, and it compresses precisely the spectral features - tails, modes, shapes - that downstream scientific measurements rely on. We propose a three-part evaluation protocol where each step targets a failure mode the others miss: per-event distributional accuracy via CRPS, population-level marginal accuracy via a spectrum-fidelity diagnostic, and uncertainty trustworthiness via coverage-based calibration. On a synthetic benchmark with an analytic posterior and on a realistic many-to-one inverse problem from particle physics, model rankings reverse between pointwise and distributional metrics, and calibration further separates architectures indistinguishable under CRPS. The evaluation protocol, not the model, determines the scientific conclusion. --- ### Extending Deep Event Visual Odometry with Sparse Point-Cloud Export Authors: Alireza Safdari, Sajad Ashraf Published: 2026-05-21 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2605.22890v1 Event cameras are well suited for visual odometry under high-speed motion and challenging lighting conditions due to their low latency, high temporal resolution, and high dynamic range. Deep Event Visual Odometry (DEVO) demonstrated that monocular event-only odometry can achieve strong performance by combining sparse patch tracking, learned patch selection, recurrent correspondence refinement, and differentiable bundle adjustment. In this project, we extend DEVO with a sparse point-cloud export pipeline. Rather than modifying the core odometry formulation, our approach exposes the internal 3D structure already estimated by DEVO and converts it into an explicit point-cloud representation for visualization and further processing. In addition, we implement a practical workflow for data export, format conversion, and point-cloud cleanup. The resulting system preserves the original visual odometry pipeline while enabling sparse geometric scene output. Experiments on the BOARD SLOW sequence show that the exported sparse cloud is locally consistent with EMVS reconstructions, achieving high precision at a 5 cm threshold, while also highlighting the expected limitations in density, completeness, and sensitivity to accumulated odometry noise. --- ### Resilience Characterization of AI-Native Wireless Receivers via Persistent Homology Authors: Christo Kurisummoottil Thomas, Emilio Calvanese Strinati Published: 2026-05-21 Categories: cs.IT, cs.LG, cs.NI arXiv: https://arxiv.org/abs/2605.22886v1 AI-native wireless receivers based on deep learning exhibit remarkable performance under stationary channel conditions, yet their resilience to distributional shifts remains poorly characterized by conventional metrics such as bit error rate (BER). To overcome these limitations, this paper proposes a novel real-time metric, the Topological Resilience Index (TRI), grounded in persistent homology and persistence exponents. TRI quantifies the structural stability of a neural network receiver's parameter space during online adaptation to non-stationary channels. Specifically, TRI captures resilience through three complementary dimensions: (i) validation-loss resilience measuring model-channel mismatch, grounded in the topological persistence of loss-landscape sublevel sets; (ii) channel impulse response (CIR) distribution shift, tracking geometric drift of CIR vectors from the calibration reference distribution; and (iii) channel manifold topology, quantified by the spectral gap of the Gaussian kernel matrix normalized by the Olivier-Ricci curvature norm. We establish theoretical guarantees showing that TRI is bounded, monotonic under performance degradation, and Lipschitz-stable with respect to perturbations in channel distributions measured in Wasserstein distance. Simulation results for an OFDM deep-learning receiver adapting across ten ITU-R inter-environment transitions at three shift rates demonstrate that TRI provides a consistent mean warning lead of more than one OFDM symbol over gradient-norm and validation-loss baselines, whereas the gradient-norm baseline achieves zero lead in every scenario. Furthermore, the proposed TRI-guided burst re-adaptation reduces post-shift BER by 80% relative to no adaptation within 200 OFDM symbols. --- ### ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization Authors: Riyaz Ahuja, Tate Rowney, Jeremy Avigad, Sean Welleck Published: 2026-05-21 Categories: cs.AI, cs.CL, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2605.22885v1 Formal mathematics libraries are rapidly expanding, creating a growing need to refactor verified proofs for maintainability and to improve training data quality for neural provers. However, scalable proof optimization is hindered by heterogeneous and heuristically specified objectives, scarce data, and high training and inference costs. To overcome these challenges, we introduce ImProver 2, a neurosymbolic framework for automated proof optimization in Lean 4. ImProver 2 combines a data-efficient expert-iteration pipeline with a scaffold that exposes formal structure alongside lightweight informal abstractions. We further introduce a suite of metrics capturing structural proof properties. Using ImProver 2, we train a 7B-parameter model that outperforms orders-of-magnitude larger models within the same model family, and is competitive with mid-tier frontier models across metrics. We additionally demonstrate that our neurosymbolic scaffold significantly improves performance across both small and frontier models. We show that with proper scaffolding and training, small models can effectively restructure research-level proofs over complex and varied metrics, matching substantially larger systems and establishing proof optimization as a scalable, learnable task. --- ### Tensor Cache: Eviction-conditioned Associative Memory for Transformers Authors: Kabir Swain, Sijie Han, Daniel Karl I. Weidele, Mauro Martino, Antonio Torralba Published: 2026-05-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.22884v1 Autoregressive Transformer KV caches grow linearly with context length; sliding-window caching bounds memory but discards evicted tokens entirely, so relevant evidence outside the window becomes inaccessible. We introduce \emph{Tensor Cache}, a two-level cache that pairs sliding-window softmax attention as a first-level cache (L1) with a fixed-size outer-product fast-weight memory as a second-level cache (L2) fed by KV pairs evicted from the window. Recent tokens remain in exact local attention; evicted pairs are compressed into a per-layer matrix $A$ and read by future queries through a single matrix multiplication, exploiting the linear-attention identity $q_t(k_i \otimes v_i)=\langle q_t,k_i\rangle v_i$. A learned scalar gate fuses the L1 and L2 outputs, and per-head decay and write-rate parameters are trained end-to-end. The outer-product memory and the read identity are well-known; our contribution is their use as an L2 cache fed exclusively by sliding-window evictions, plus identifying that the common chunked-mean training shortcut $A\!\leftarrow\!λA\!+\!η(\bar k\!\otimes\!\bar v)$ silently introduces $C^2{-}C$ spurious cross-token outer products per chunk, and closing the gap with a parallel weighted-sum scan equivalent to per-token writes within float32 epsilon. Across systems scaling, controlled associative recall, long-context language modeling, and memory-capacity diagnostics, Tensor Cache improves the memory--quality frontier over bounded-state baselines. --- ### Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs Authors: Jongseo Lee, Hyuntak Lee, Sunghun Kim, Sooa Kim, Jihoon Chung, Jinwoo Choi Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22823v1 Video Large Language Models (Video-LLMs) have made rapid progress on temporal video understanding, yet many fail at a basic perceptual primitive: signed image-plane motion direction. On simple videos of a single object moving left, right, up, or down, most Video-LLMs perform near chance, with above-chance cases largely attributable to prediction biases rather than genuine direction understanding. We call this failure directional motion blindness. We localize the failure by tracing motion direction information through the Video-LLM pipeline. Motion direction remains linearly accessible from the vision encoder, projector, and LLM hidden states, but the readout fails to bind this signal to the correct verbal answer option, revealing a direction binding gap. Although synthetic motion direction instruction tuning reduces this gap on the source domain, motion direction concept vector analysis shows that visual complexity weakens the signal magnitude and limits out-of-domain generalization. We introduce MoDirect, a dataset family for motion direction instruction tuning and evaluation, and DeltaDirect, a diagnosis-driven, projector-level objective that predicts normalized 2-D motion vectors from adjacent-frame feature deltas. On MoDirect-SynBench, instruction tuning with DeltaDirect improves motion direction accuracy from 25.9% to 85.4%. On MoDirect-RealBench, DeltaDirect improves real-world motion direction accuracy by 21.9 points over the vanilla baseline without real-world tuning data, while preserving standard video-understanding performance. Code: https://github.com/KHU-VLL/DeltaDirect --- ### Tokenisation via Convex Relaxations Authors: Jan Tempus, Philip Whittington, Craig W. Schmidt, Dennis Komm, Tiago Pimentel Published: 2026-05-21 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.22821v1 Tokenisation is an integral part of the current NLP pipeline. Current tokenisation algorithms such as BPE and Unigram are greedy algorithms -- they make locally optimal decisions without considering the resulting vocabulary as a whole. We instead formulate tokeniser construction as a linear program and solve it using convex optimisation tools, yielding a new algorithm we call ConvexTok. We find ConvexTok consistently improves intrinsic tokenisation metrics and the bits-per-byte (BpB) achieved by language models; it also improves downstream task performance, but less consistently. Furthermore, ConvexTok allows the user to certify how far their tokeniser is from optimal, with respect to a certain objective, via a lower bound, and we empirically find it to be within 1\% of optimal at common vocabulary sizes. --- ### Integrable Elasticity via Neural Demand Potentials Authors: Carlos Heredia, Daniel Roncel Published: 2026-05-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.22820v1 We propose the Integrable Context-Dependent Demand Network (ICDN), a demand-first neural model for multiproduct retail demand. The model learns log-demand as a smooth, context-conditioned function of log-prices, allowing elasticities to be derived exactly from the learned demand surface. On the Dominick's beer dataset, ICDN improves out-of-sample generalization over a directed log-log benchmark and yields more stable, economically plausible elasticity estimates, especially for weakly identified cross-price effects. --- ### Cambrian-P: Pose-Grounded Video Understanding Authors: Jihan Yang, Zifan Zhao, Xichen Pan, Shusheng Yang, Junyi Zhang, Bingyi Kang, Hu Xu, Shang-Wen Li, Saining Xie Published: 2026-05-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.22819v2 Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet this signal is largely absent from multimodal LLMs (MLLMs) for video understanding, which process frames as isolated 2D snapshots, instead of the persistent scene humans perceive. We revisit pose as a lightweight supervisory signal and introduce Cambrian-P, a video MLLM augmented with per-frame learnable camera tokens and a pose regression head. With a carefully designed sampling scheme, the model achieves substantial gains of 4.5-6.5% on spatial reasoning benchmarks such as VSI-Bench, generalizes across eight additional spatial and general video QA benchmarks, and, as a byproduct, achieves state of the art streaming pose estimation on ScanNet. Surprisingly, training on pseudo-annotated poses from in-the-wild video further improves general video QA benchmarks, showing pose helps beyond spatial reasoning. Together, these results position camera pose as a fundamental signal for video models that reason about the physical world. ---