# Research Papers — 2026-05 · bundle page 316 of 326 > Full-text markdown of papers #15751–15800 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/316 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/315.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/317.md) ### Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks Authors: Benjamin Warner, Ratna Sagari Grandhi, Max Kieffer, Aymane Ouraq, Saurav Panigrahi, Geetu Ambwani, Kunal Bagga, Nikhil Khandekar, Arya Hariharan, Nishant Mishra, Manish Ram, Shamus Sim Zi Yang et al. Published: 2026-05-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.01417v1 Evaluating large language models (LLMs) for medical applications remains challenging due to benchmark saturation, limited data accessibility, and insufficient coverage of relevant tasks. Existing suites have either saturated, heavily depend on restricted datasets, or lack comprehensive model coverage. We introduce Medmarks, a fully open-source evaluation suite with 30 benchmarks spanning question answering, information extraction, medical calculations, and open-ended clinical reasoning. We perform a systematic evaluation of 61 models across 71 configurations using verifiable metrics and LLM-as-a-Judge. Our results show that frontier reasoning models (Gemini 3 Pro Preview, GPT-5.1, & GPT-5.2) achieve the highest performance across both benchmarks, most frontier proprietary models are significantly more token efficient than open-weight alternatives, medically fine-tuned models outperform their generalist counterparts, and that models are susceptible to answer-order bias (particularly smaller models and Grok 4). A subset of our evals (Medmarks-T) can be directly used as reinforcement learning environments to post-train LLMs for medical reasoning. Code is available at https://github.com/MedARC-AI/Medmarks --- ### Who Decides What Is Harmful? Content Moderation Policy Through A Multi-Agent Personalised Inference Framework Authors: Ewelina Gajewska, Michal Wawer, Katarzyna Budzynska, Jaroslaw A. Chudziak Published: 2026-05-02 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2605.01416v1 The increasing scale and complexity of online platforms raises critical policy questions around harmful content, digital well-being, and user autonomy. Traditional content moderation systems rely on centralised, top-down rules, often failing to accommodate the subjective nature of harm perception. This paper proposes an LLM-based multi-agent personalised inference framework that filters content based on unique sensitivity profiles of individual users. Our architecture combines domain-specific Expert Agents, a Manager Agent for orchestrating content analysis and agent selection, and a Ghost Profile Agent for simulating user perspectives, to inform moderation decisions. Evaluated against a range of non-personalised baselines, the system demonstrates up to a 32% improvement in accuracy, showing increased alignment with individual user sensitivities. Beyond technical performance, our framework provides policy-relevant insights for platform governance, providing a scalable way to reconcile moderation policies with societal and individual digital rights --- ### AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries Authors: Wesley Shu, Peng Wei Published: 2026-05-02 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.01415v1 Recent AI systems compress the distance between capability growth and capability deployment. Earlier high-risk technologies were slowed by capital intensity, physical bottlenecks, organizational inertia, and specialized supply chains. By contrast, AI capabilities can be copied, invoked, embedded in workflows, and scaled across institutions at low marginal cost. This paper argues that declining deployment friction changes the safety problem at its root. Safety is not only local output correctness or preference alignment, but the control of irreversibility under rising decision density. The paper formalizes this claim through decision-energy density: the rate-weighted capacity of a node to generate, evaluate, select, and execute consequential decisions. It then identifies three sovereignty boundaries that determine whether AI remains an amplifier within a human-governed system or becomes a de facto control center: irreversible decision authority, physical resource mobilization authority, and self-expansion authority. The model shows how efficiency pressure, path dependence, scale feedback, and weak boundary constraints concentrate decision-energy in the most efficient node. This concentration can diffuse responsibility and raise the probability of irreversible system-level loss even when local per-action error rates remain low. The main result is a boundary stabilization theorem. It shows that safety need not require proving that advanced systems are always correct. Instead, it requires institutional and technical designs that prevent irreversible power from being released by a single high-efficiency node. The paper reframes AI safety as layered control, authorization, and externally reviewable limits, linking alignment, security engineering, organizational economics, and institutional design. --- ### Interactive Multi-Turn Retrieval for Health Videos Authors: Chengzheng Wu, Ke Qiu, Baoming Zhang, Ruiyu Mao, Xulong Tang, Kaixing Yang Published: 2026-05-02 Categories: cs.IR, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2605.01409v1 The growing availability of health-related instructional videos creates new opportunities for clinical training, patient rehabilitation, and health education, yet existing retrieval systems remain largely single-turn: a user submits one query and receives one ranked list. This interaction is brittle in health scenarios, where information needs are often vague at first and become clinically meaningful only after follow-up constraints such as posture, hand placement, contraindications, equipment, or patient condition are specified. We introduce interactive multi-turn semantic retrieval for health videos and construct MHVRC, a Multi-Turn Health Video Retrieval Corpus, by combining video-grounded descriptions from VideoChat-Flash with query refinements generated by DeepSeek. We further propose DATR, a Dialogue-Aware Two-Stage Retrieval framework. DATR first performs efficient coarse retrieval with a CLIP-style dual encoder and sparse frame sampling, then re-ranks the top candidates through multi-turn query fusion and a lightweight cross-encoder scoring module. Experiments on MHVRC show consistent gains over strong text-video retrieval baselines, while user studies indicate that refined multi-turn queries better capture fine-grained procedural semantics than single-turn annotations. The work establishes a benchmark and a scalable technical recipe for interactive health video retrieval. --- ### The Pre-Training Study of Expanded-SPLADE Models on Web Document Titles Authors: Hiun Kim, Tae Kwan Lee, Taeryun Won Published: 2026-05-02 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2605.01407v1 Masked Language Modeling (MLM) pre-training is one of the primary ways to initialize Neural Information Retrieval (IR) models prior to retrieval fine-tuning. However, studies show that MLM pre-trained models have limited readiness and transfer learning issues for fine-tuning them into Neural Bi-Encoder models. This paper studies the effect of different pre-training datasets and pre-training options on the MLM pre-trained models for retrieval fine-tuning. The study focuses on the SPLADE-style model, which uses the MLM layer also at fine-tuning time. More specifically, we experimented with Expanded-SPLADE (ESPLADE) models, a specific instance of SPLADE models, and in-house web document titles are used as datasets. Pre-training, fine-tuning, and evaluation with optional test-time pruning of sparse vectors are conducted. Our observations are three-fold: First, fine-tuned models of higher retrieval effectiveness at both unpruned and most strict pruned settings are mostly pre-trained on a general corpus, and pre-trained with a higher learning rate, showing lower MLM accuracies. Second, in the most strict pruned setting, those models show higher-level retrieval cost and a higher variance in the length of the individual postings list. Third, the repetition of the general pre-training dataset does not have much effect on retrieval effectiveness. The experimentation empirically identifies the potential limitations for aligning MLM pre-training to ESPLADE fine-tuning. Also, the experimentation provides an empirical observation that, at most strict pruned settings, the retrieval effectiveness is better maintained by the higher-level retrieval cost, showing the trade-off relationship between the two in our setting. --- ### AMSnet-q: Unsupervised Circuit Identification and Performance Labeling for AMS Circuits Authors: Ze Zhang, Junzhuo Zhou, Yichen Shi, Zhuofu Tao, Rui Ji, Zhiping Yu, Quan Chen, Ting-Jung Lin, Lei He Published: 2026-05-02 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2605.01404v1 Analog and mixed-signal (AMS) circuit design remains heavily reliant on expert knowledge. While recent AI-driven automation tools can generate candidate topologies, they critically depend on manually curated datasets with functional and performance annotations -- a requirement that current large language models (LLMs) and vision models cannot automate. Existing approaches still require domain experts to manually interpret circuit functionality. We present AMSnet-q, a fully automated, unsupervised pipeline that eliminates human-in-the-loop annotation by converting schematic images directly into a labeled AMS circuit database. Unlike prior work that stops at netlist extraction, our framework automates the complete verification loop: it performs schematic-to-netlist conversion, topology-aware testbench generation, and simulation-based sizing validation to objectively determine circuit functionality. Validated in 28 nm technology, AMSnet-q processed 739 schematics from the AMSnet 1.0 dataset, automatically constructing a repository of 4 circuit classes, 105 distinct topologies, and 89,789 labeled device configurations. By decoupling human effort from dataset volume and reducing the workload to a one-time testbench template per circuit class, AMSnet-q enables scalable, objective, and fully automated AMS database construction. --- ### Rethinking Multi-Label Node Classification: Do Tuned Classic GNNs Suffice? Authors: Yuxuan Xiao, Shengzhong Zhang Published: 2026-05-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.01403v1 Multi-label node classification (MLNC) has recently been addressed by increasingly complex label-aware designs that explicitly model node-label interactions and inter-label dependencies.However, it remains unclear whether the advantages of these methods truly stem from their specialized designs, or simply from insufficiently optimized baselines. In this paper, we revisit MLNC from a strong-baseline perspective and investigate whether carefully tuned classic full-graph GNNs can already serve as strong solutions to this task. We systematically study several representative backbones, including GCN, SSGConv, and GCNII, and optimize them using standard yet effective techniques such as normalization, dropout, and residual connections. Experiments on five representative benchmark datasets show that our tuned baselines outperform representative specialized methods on four datasets and achieve state-of-the-art performance in multiple settings. These results indicate that careful tuning of classic backbones is a highly influential but often overlooked factor in MLNC, and highlight the need for more rigorous strong-baseline evaluation in future research on multi-label graph learning. --- ### Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression Authors: Yao Du, Shanshan Song, Xiaomeng Li Published: 2026-05-02 Categories: cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.01402v2 Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions, leading to regression-to-the-mean behavior and poor tail performance. We identify the lack of cross-sample relational supervision as a key limitation of existing MLLM training paradigms. To address it, we propose a distribution-aware reinforcement learning framework based on Group Relative Policy Optimization, which introduces batch-level comparison-based supervision via the Concordance Correlation Coefficient-based reward to align predicted and ground-truth distributions in terms of correlation, scale, and mean. The framework is plug-and-play, requiring no architectural modification. Experiments on a unified suite of long-tailed regression benchmarks show consistent improvements over SFT and existing MLLM regression methods, with particularly strong gains in medium- and few-shot regimes. --- ### AI Expert Twin: Capturing Expert Cognition for Human-Centred, Practice-Based Learning Authors: Annie Yuan, Xiaohua Chen, Kalina Yacef, Judy Kay Published: 2026-05-02 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2605.01401v2 Tacit knowledge embedded in expert practice remains difficult to capture, formalise, and scale. While AI-driven educational systems have advanced personalisation, learner modelling, affective support, and self-regulated learning, they less often model the tacit reasoning and context-sensitive judgement that underpin expert practice in practice-based domains. This paper introduces the AI Expert Twin, a cognition-centric framework that models expert knowledge as structured, computable representations of procedural actions, semantic concepts, and decision processes. The framework also considers how value-laden preferences, trade-offs, and uncertainty shape expert judgement in practice. We formalise expert cognition as a three-layer representation and capture knowledge from experts under this model, laying the groundwork for integration into AI-powered educational system. A case study in a cultural heritage workshop demonstrates the feasibility of the approach in a real-world setting. The framework is designed to be transferable across domains such as vocational education and creative industries. By embedding expert heuristics into AI while maintaining transparency and learner agency, the AI Expert Twin offers a novel path towards scalable, practice-based learning and invites further research on ethical, human-centred applications of AI in education. --- ### Investigating the Effects of Different Levels of User Control in an Interactive Educational Recommender System Authors: Qurat Ul Ain, Mohamed Amine Chatti, William Kana Tsoplefack, Rawaa Alatrash, Shoeb Joarder Published: 2026-05-02 Categories: cs.HC, cs.AI, cs.CY, cs.IR arXiv: https://arxiv.org/abs/2605.01400v1 Educational recommender systems (ERSs) are becoming increasingly important in enhancing educational outcomes and personalizing learning experiences by providing recommendations of personalized resources and activities to learners, tailored to their individual learning needs. While user control is widely assumed to improve user experience, the effects of different levels of control in ERSs remain underexplored. To address this gap, we designed and evaluated an interactive ERS within the MOOC platform CourseMapper, where learners could interact with the input (i.e., user profile), process (i.e., recommendation algorithm), and output (i.e., recommendations) of the system. We conducted a between-subjects user study (N=184) to examine how varying levels of user control in an ERS influenced users' perceptions of the recommendation goals of perceived control, transparency, trust, satisfaction, and perceived quality. Our results show that enabling users to build and refine their profile is sufficient to promote positive perceptions of the ERS, while additional control options mainly reinforce these impressions. Moreover, perceived control is the only goal significantly affected by providing different levels of user control in the ERS, with input control exerting the strongest influence. Furthermore, different levels of control affect transparency, trust, satisfaction, and perceived quality in distinct yet interconnected ways. Overall, the findings provide empirical evidence that user control positively shapes transparency, trust, satisfaction, and perceived quality, though to varying extents. --- ### Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning Authors: Sangkwon Park, Donghun Kang, Jisoo Mok, Sungroh Yoon Published: 2026-05-02 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2605.01399v1 The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integration of retrieved information. This paper proposes to bridge retrieval results and the LLM's reasoning ability through Verbal Annotations, analytic narratives that explicitly articulate the logical connection between a search query and retrieved contexts. Our empirical investigation reveals the potential of Verbal Annotations to substantially enhance the LLM's ability to generate accurate, contextually-grounded responses. Motivated by this finding, we introduce Verbal-R3, a novel agentic RAG framework that consists of a Generator and a Verbal Reranker. The Generator performs iterative retrieval and reasoning, while the Verbal Reranker returns relevance scores and Verbal Annotations to guide the reasoning and answering process of the Generator. The inference process of Verbal-R3 is further refined through relevance-guided test-time scaling, which efficiently allocates test-time compute for effective trajectory expansion. Verbal-R3 achieves state-of-the-art performance on complex Question Answering benchmarks, validating the effectiveness of the proposed framework. --- ### LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation Authors: Dong Xu, Jialun Cao, Guozhao Mo, Junjie Hu, Cheng Wen, Hongyu Lin, Xianpei Han, Shengchao Qin, Cong Tian, Shing-Chi Cheung, Le Sun, Yaojie Lu Published: 2026-05-02 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.01394v1 Formal specification is essential for rigorous program verification, yet writing correct specifications remains costly and difficult to automate. Although large language models (LLMs) and agents have shown promising progress, their true capabilities and failure modes remain unclear. We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs. We introduce LiveFMBench, a continuously evolving benchmark of 630 ACSL (ANSI/ISO C Specification Language)-annotated C programs, including 360 newly collected cases designed to mitigate data leakage. Using this benchmark, we evaluate direct prompting with different sampling sizes, reasoning-enabled (thinking mode) inference, the agentic pipeline, and perform a fine-grained failure analysis. Experimental results reveal that naive evaluation substantially overestimates performance because models under direct prompting may exhibit unfaithful behaviors, such as deceiving automated provers or ignoring code-context constraints; after excluding such cases, the true specification generation accuracy drops by approximately 20\%. We further find that both increased sampling and thinking mode significantly improve success rates, with smaller models benefiting more from thinking mode. Agentic pipelines are particularly effective under low sampling budgets and on harder datasets. Failure analysis further shows that incorrect loop invariants are the dominant error type, while agentic pipelines notably reduce assertion errors. These results expose fundamental limitations in current LLM-based approaches and suggest they remain far from replacing human-authored formal specifications. We release LiveFMBench at https://huggingface.co/datasets/fm-universe/Live-FM-Bench and all evaluation artifacts to support future research. --- ### Recall to Predict: Grounding Motion Forecasting in Interpretable Motion Bank Authors: Abhishek Vivekanandan, Ahmed Abouelazm, J. Marius Zöllner Published: 2026-05-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01393v1 Motion forecasting often requires trading interpretability for predictive accuracy. Standard anchor-based architectures rely on opaque latent queries that are highly prone to latent collapse, or naive trajectory sampling that limits multi-modal diversity. We propose an end-to-end differentiable framework that grounds predictions in a comprehensive "motion bank", a structured embedding space of physically realizable trajectories constructed via contrastive learning. Rather than regressing paths from a blank slate, our architecture dynamically retrieves explicit motion priors using a novel Anchor Retrieval Layer. This module adapts orthogonally initialized queries via a Dual-Level Gated Cross-Attention mechanism and executes discrete trajectory selection using a Straight-Through Gumbel-Softmax estimator to preserve continuous gradient flow. The retrieved semantically grounded anchors are then geometrically refined by a DETR-style decoder, optimized jointly with a Winner-Takes-All (WTA) kinematic Gaussian Mixture Model (GMM), a latent diversity penalty, and a soft-min weighted endpoint loss. By strictly conditioning the decoding phase on diverse, interpretable motion primitives, our approach eliminates the "black box" of standard latent queries while achieving competitive multi-modal accuracy on the Argoverse 2 and Waymo Open Motion datasets. Code is available at: https://github.com/abviv/recall2predict --- ### Using LLMs in Software Design: An Empirical Study of GitHub and A Practitioner Survey Authors: Yifei Wang, Ruiyin Li, Peng Liang, Yangxiao Cai, Zengyang Li, Mojtaba Shahin, Arif Ali Khan, Qiong Feng Published: 2026-05-02 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.01392v2 Recent advancements in Large Language Models (LLMs) have demonstrated significant potential across software engineering tasks, including software design, an area traditionally regarded as highly dependent on human expertise and judgment. However, limited research has examined how LLMs are used in software design, aswell as the associated benefits and drawbacks. This paper addresses this gap by empirically investigating how software developers use LLMs in software design. We conducted a mixed-methods study, combining a mining study of 291 developer-ChatGPT conversations shared on GitHub with a survey of 65 software practitioners. From the mined conversations, we identified nine categories of design tasks supported by ChatGPT, including architecture design, data model design, and the use of design patterns.We further characterize developer-ChatGPT interactions, showing that developers in the mined conversations primarily use ChatGPT for knowledge acquisition and designrelated code generation, with most tasks situated at the detailed design level. The survey participants reported seven key benefits, such as better technology selection and early detection of design flaws, and six limitations, including lengthy outputs, inexecutable or incorrect code, and dependence on project context. These findings provide an evidence-based characterization of current LLM use in software design from both open-source and practitioner perspectives. --- ### Using LLMs in Software Design: An Empirical Study of GitHub and A Practitioner Survey Authors: Yifei Wang, Ruiyin Li, Peng Liang, Yangxiao Cai, Zengyang Li, Mojtaba Shahin, Arif Ali Khan, Qiong Feng Published: 2026-05-02 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.01392v1 Recent advancements in Large Language Models (LLMs) have demonstrated significant potential across a wide range of software engineering tasks, including software design, an area traditionally regarded as highly dependent on human expertise and judgment. However, there has been little research focusing on how LLMs are used in software design, nor on the associated benefits and drawbacks. This paper aims to bridge this gap by empirically investigating how software developers utilize LLMs in the context of software design. We conduct a mixed-methods study, combining a mining study of 291 developer-ChatGPT conversations shared on GitHub with a survey of 65 software practitioners. Our findings reveal nine distinct categories of design tasks supported by ChatGPT, including architecture design, data model design, and the use of design patterns. We further characterize developer-ChatGPT interactions, showing that developers primarily use ChatGPT for knowledge acquisition and design-related code generation, with most tasks situated at the detailed design level. The study identifies seven key benefits of utilizing LLMs in software design as perceived by developers, such as better technology selection and the early detection of design flaws. We also uncover six limitations, including the generation of overly lengthy and difficult-to-read outputs, the creation of inexecutable or incorrect code, and a heavy reliance on context that can lead to hallucinated results. These findings provide an evidence-based characterization of current LLM use in software design from both open-source and practitioner perspectives, highlighting a tension between perceived benefits and limitations, which lays a foundation for future research and the development of effective techniques and tools to integrate LLMs into software design practices. --- ### VISTA: Video Interaction Spatio-Temporal Analysis Benchmark Authors: Alejandro Aparcedo, Akash Kumar, Aaryan Garg, Dalton Pham, Wen-Kai Chen, Anirudh Bharadwaj, Aman Chadha, Yogesh Rawat Published: 2026-05-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01391v2 Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute sets and restricted entity types, failing to capture the freeform, multi-action interactions between diverse entities which characterize real-world video understanding. Furthermore, the lack of a systematic framework for analyzing model failures across complementary spatio-temporal axes hinders comprehensive evaluation. To address these gaps, we introduce VISTA, a Video Interaction Spatio-Temporal Analysis benchmark designed for open-set, multi-entity and multi-action spatio-temporal understanding in VLMs. VISTA decomposes videos into interpretable entities, their associated actions, and relational dynamics, enabling multi-axis diagnostics and unified assessment of relational, spatial, and temporal understanding. Our benchmark integrates multiple datasets into a single interaction-aware taxonomy and comprises ~12K curated video-query pairs spanning diverse scenes and complexities. We systematically evaluate 11 state-of-the-art VLMs on VISTA, and break down aggregate performance across our taxonomy to reveal shortcomings and pronounced spatio-temporal biases obscured by traditional metrics. By providing detailed, taxonomy-driven diagnostics on a challenging dataset, VISTA offers a nuanced framework to guide advances in model design, pretraining strategies, and evaluation protocols. Overall, VISTA is the first, large-scale, interaction-aware diagnostic benchmark for spatio-temporal understanding in VLMs. --- ### MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents Authors: Hung Pham Van, Nguyen Manh Hieu, Khang Pham Tran Tuan, Nam Le Hai, Linh Ngo Van, Nguyen Thi Ngoc Diep, Trung Le Published: 2026-05-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01386v2 Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from information dilution, absent provenance tracking, and uniform retrieval that ignores query context. We introduce MemORAI (Memory Organization and Retrieval via Adaptive Graph Intelligence), a framework that integrates three innovations: selective memory filtering with dual-layer compression to retain user-persona-relevant content, a provenance-enriched multi-relational graph tracking factual origins at the turn level, and query-adaptive subgraph retrieval with Dynamic Weighted PageRank that applies query-conditioned edge weighting. Evaluated on LOCOMO and LongMemEval benchmarks, MemORAI achieves state-of-the-art performance in memory retrieval and personalized response generation, demonstrating that selective storage, enriched representation, and adaptive retrieval are essential for coherent, personalized LLM agents. --- ### Sequential Learning and Catastrophic Forgetting in Differentiable Resistor Networks Authors: Maniru Ibrahim Published: 2026-05-02 Categories: cs.LG, cond-mat.dis-nn, physics.comp-ph arXiv: https://arxiv.org/abs/2605.01383v1 Differentiable physical networks provide a simple setting in which learning can be studied through the interaction between trainable parameters and physical equilibrium constraints. We investigate sequential learning in differentiable resistor networks governed by Kirchhoff's laws. Although individual input--output mappings can be learned by gradient-based adjustment of edge conductances, sequential training on conflicting tasks produces catastrophic forgetting. We show that forgetting is controlled by task conflict and by the degree of adaptation to the new task. Uniform anchoring and normalised gradient-weighted anchoring reduce forgetting only by increasing the final loss on the new task, giving a clear forgetting--adaptation trade-off. We also show that forgetting is associated with localised conductance changes on high-current edges, giving a physical interpretation as reconfiguration of dominant transport pathways. Broader random-task ensembles show that the strongest forgetting occurs when the second task reverses the output ordering imposed by the first task. Finally, comparisons across Erdős--Rényi, small-world, scale-free, and random-geometric graph ensembles show that topology changes the forgetting--adaptation balance. These results position differentiable resistor networks as compact, physically interpretable testbeds for studying continual learning in tunable matter. --- ### Sparse Representation Learning for Vessels Authors: Chinmay Prabhakar, Bastian Wittmann, Paul Büschl, Hongwei Bran Li, Bjoern Menze, Suprosanna Shit Published: 2026-05-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.01382v1 Analyzing human vasculature and vessel-like, tubular structures, such as airways, is crucial for disease diagnosis and treatment. Current methods often rely on small sub-regions or simplified tree-like structures, rendering analysis of entire organ-level networks at clinical resolution computationally challenging. To this end, we propose VAEsselSparse, an efficient encoder-decoder model to obtain a meaningful yet compact representation of the entire organ-level vascular network at sub-millimeter resolution. VAEsselSparse leverages the inherent sparsity of 3D vascular structures via sparse convolutions and attention mechanisms, achieving substantial spatial compression rates of 8 x 8 x 8. We demonstrate superior reconstruction performance compared to dense counterparts and previous methods. Importantly, the resulting latent space retains clinically relevant discriminative features readily usable for classification tasks, such as aneurysm/stenosis or subvariants of the circle of Willis. Moreover, the compact latent space of VAEsselSparse serves as an effective representation for learning vessel-specific priors through generative models, enabling the synthesis of realistic vasculature. --- ### A framework for analyzing concept representations in neural models Authors: Burin Naowarat, Hao Tang, Sharon Goldwater Published: 2026-05-02 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.01381v1 Understanding how neural models represent human-interpretable concepts is challenging. Prior work has explored linear concept subspaces from diverse perspectives, such as probing and concept erasure. We introduce a unified framework to study these subspaces along two axes: \textit{containment}, which tests if a concept is fully represented in a subspace but not outside it, and \textit{disentanglement}, which tests for isolation from other concepts. In experiments on both text and speech models, we first highlight that concept subspaces may not be uniquely determined, and discuss the implications for concept subspace analysis. Then, we compare properties of concept subspaces estimated using five estimators, proposed in different communities. We find that (1) the choice of estimator impacts the containment and disentanglement properties; (2) the state-of-the-art concept erasure method, LEACE, performs well on both testing axes, but still struggles to generalize to unseen data; and (3) in HuBERT speech representations, phone information is both contained and disentangled from speaker information, while speaker information is hard to contain in a compact subspace, despite being disentangled from phones. --- ### A Cellular Doctrine of Morality: Intrinsic Active Precision and the Mind-Reality Overload Dilemma Authors: Ahsan Adeel Published: 2026-05-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01376v1 Current AI systems, grounded in oversimplified neuroscience, risk eroding the distinction between truth and falsehood. They maximize reward by amplifying attention to information without intrinsic precision mechanisms to assess whether it is valid or worth attending to. This increases both the volume of information and the inherent biases in what the system attends to, whether true, false, or irrelevant. If not corrected, this trend will accelerate, threatening to overload systems and individuals with biased and dubious information and increasing the risk of confusion, poor judgment, and irrational or harmful decisions and behaviour, a condition I term the mind-reality overload dilemma. I argue that this threat may be mitigated by providing the public with access to more advanced AI tools built on the biophysical dynamics of pyramidal neurons underlying awake thought and higher-order cognition. These neurons support an intrinsic active precision mechanism that, rather than merely maximizing reward, uses locally and globally coherent predictions to evaluate the validity and contextual adequacy of evidence before it is attended to or propagated through hierarchies, prioritizing coherence and adequacy before attention.~While this approach does not derive or prescribe moral rules from biology, it may give rise to AI with more "real understanding", helping restore epistemic conditions by reducing information overload and amplifying reliable information, thereby supporting the formation of better-informed beliefs and more coherent judgments that benefit society at large-though no guarantees exist. --- ### MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation Authors: Pham Khanh Chi, Quoc Phong Dao, Thuat Nguyen, Linh Ngo Van, Trung Le, Thanh Hong Nguyen Published: 2026-05-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01374v2 Knowledge distillation is a key technique for compressing large language models (LLMs), but most existing methods align representations at fixed layers or token-level outputs, ignoring how representations evolve across depth. As a result, the student is only weakly guided to capture the teacher's internal relational structure during distillation, which limits knowledge transfer. To address this limitation, we propose Multi-Granular Trajectory Alignment (MTA), a framework that aligns teacher and student representations along their layer-wise transformation trajectory. MTA adopts a layer-adaptive strategy: lower layers are aligned at the word level to preserve lexical information, while higher layers operate on phrase-level spans (e.g., noun and verb phrases) to capture compositional semantics. We instantiate this idea through a Dynamic Structural Alignment loss that matches the relative geometry among semantic units within each layer. This design is motivated by empirical findings that Transformer representations become increasingly abstract with depth, and is also consistent with linguistic views in which higher-level meaning emerges through the composition of lower-level lexical units. We further incorporate a Hidden Representation Alignment loss to directly align selected teacher-student layers. Experiments show that MTA consistently outperforms state-of-the-art baselines on standard benchmarks, with ablations confirming the contribution of each component. --- ### Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast Authors: Jinyuan Feng, Xin Yu, Yiqun Chen, Xiaochi Wei, Yan Gao, Yi Wu, Yao Hu, Zhiqiang Pu Published: 2026-05-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.01373v1 The iterative denoising paradigm of Diffusion Large Language Models (DLMs) endows them with a distinct advantage in global context modeling. However, current decoding strategies fail to leverage this capability, typically exhibiting a local preference that overlooks the heterogeneous information density within the context, ultimately degrading generation quality. To address this limitation, we systematically investigate high-information-density (HD) tokens and present two key findings: (1) explicitly conditioning on HD tokens substantially improves output quality; and (2) HD tokens exhibit an early-decoding tendency, converging earlier than surrounding tokens. Motivated by these findings, we propose Focus on the Core \textbf{(FoCore)}, a training-free decoding strategy that utilizes HD tokens in a self-contrast manner, wherein HD tokens are temporarily remasked as negative samples, to guide generation. We further introduce FoCore\_Accelerate \textbf{(FoCore\_A)}, an efficient variant that, upon detecting HD token convergence, performs parallel decoding over stable candidates within a local context window, substantially accelerating generation. Extensive experiments on math, code and logical reasoning benchmarks demonstrate that FoCore consistently improves generation quality and efficiency across both LLaDA and Dream backbones. For instance, on HumanEval, FoCore improves pass@1 from 39.02 to 42.68 over standard Classifier-Free Guidance, while FoCore-A reduces the number of decoding steps by 2.07x and per-sample latency from 20.76s to 8.64s (-58.4\%). --- ### Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders Authors: Ailiang Lin, Zhuoyun Li, Keyu Mao, Kotaro Funakoshi, Manabu Okumura Published: 2026-05-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01372v1 Large language models (LLMs) have been widely explored for embedding generation. While recent studies show that in-context learning (ICL) effectively enhances the representational capability of LLMs by prepending a few task-related demonstrations, it causes substantial token overhead due to the increased sequence length. In this work, we propose EPIC, a novel embedding-based in-context prompt training strategy that leverages ICL to generate high-quality embeddings while reducing computational burden during both training and inference. This approach replaces discrete text demonstrations with their corresponding continuous embeddings, which not only encourages the LLM to align semantically-related text pairs during contrastive learning, but also requires the model to interpret demonstration embeddings as part of the in-context prompt. Consequently, EPIC-trained models achieve excellent embedding performance both with or without in-context prompts at inference time. Comprehensive experiments demonstrate that our method establishes new state-of-the-art results on the MTEB benchmark, surpassing frontier models trained solely on publicly available retrieval data. Extensive ablation studies further validate the effectiveness and necessity of our mechanism. --- ### MU-SHOT-Fi: Self-Supervised Multi-User Wi-Fi Sensing with Source-free Unsupervised Domain Adaptation Authors: Ahmed Y. Radwan, Hina Tabassum Published: 2026-05-02 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.01369v2 Deep learning has been widely adopted for WiFi CSI-based human activity recognition (HAR) due to its ability to learn spatio-temporal features in a privacy-preserving and cost-effective manner. However, DL-based models generalize poorly across environments, a challenge amplified in multi-user settings where overlapping activities cause CSI entanglement and domain shifts. Practical deployments often limit access to labeled source data due to privacy constraints, motivating source-free adaptation using only unlabeled target-domain CSI and a pre-trained source model. In this paper, we propose MU-SHOT-Fi, a source-free unsupervised domain adaptation framework for single- and multi-user Wi-Fi sensing. MU-SHOT-Fi employs permutation-invariant set prediction with Hungarian matching during source training, followed by frozen-classifier backbone adaptation in the target domain. To enable stable adaptation without labels, we introduce occupancy-weighted information maximization that prevents model collapse by focusing diversity regularization on likely-occupied slots while excluding the dominant class from marginal entropy. Additionally, we employ binary rotation prediction as spatial self-supervision that exploits CSI frequency-time structure to learn domain-invariant features. For single-user scenarios, we introduce SU-SHOT-Fi by replacing occupancy weighting with standard information maximization and incorporating contrastive predictive coding to exploit temporal consistency. Extensive experiments on the WiMANS and Widar 3.0 datasets across cross-environment, cross-frequency, cross-orientation, and combined domain shifts demonstrate that MU-SHOT-Fi effectively recovers multi-user exact-activity classification performance under large domain shifts while maintaining accurate occupancy estimation and preventing collapse toward dominant classes. --- ### From Characterization To Construction: Generative Quantum Circuit Synthesis from Gate Set Tomography Data Authors: King Yiu Yu, Aritra Sarkar, Erbing Hua, Maximilian Rimbach-Russ, Ryoichi Ishihara, Sebastian Feld Published: 2026-05-02 Categories: quant-ph, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2605.01367v1 High-fidelity circuit execution on noisy intermediate-scale quantum devices is bottlenecked by compilation pipelines that disregard complex, correlated noise. To address this, this methodology article proposes a quantum machine learning control (QMLC) framework for generative quantum circuit synthesis from gate-set tomography (GST) data that bypasses the traditional two-step pipeline of characterizing native quantum gates via GST followed by unitary decomposition algorithms. Instead, a generative concept space is directly learnt from GST data, enabling conditional synthesis of quantum circuits on a desired output distribution. Our approach tokenizes GST germ circuits and embeds them into a structured latent space using a curriculum-learning-motivated strategy, starting with short circuits and progressively incorporating longer ones with diverse output statistics. The embedded sequences are processed by a set-vision transformer with permutation-invariant pooling, producing k-seed vectors that represent the learned concept space of the quantum device. Aggregating data across multiple circuits makes this latent representation inherently context-aware, capturing the shared physical noise environment (e.g., crosstalk, drift) that isolated gate metrics miss. We propose an unconditional diffusion model to sample from the concept space. During inference, a user provides a target measurement distribution, and the model generates a corresponding circuit. To ensure fidelity and robustness, the output is denoised using a diffusion model that operates on the target conditional covariance matrix. This end-to-end framework is a step towards context-aware, hardware-native circuit synthesis directly from raw GST data, which offers a new paradigm for integrating quantum control and compilation. The QMLC framework is particularly suited for near-term quantum devices with complex calibration procedures. --- ### VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection Authors: Haowen Sun, Shaolong Zhang, Mingyang Li, Chengzhong Ma, Xinzhe Chen, Qiongjie Cui, Xingyu Chen, Zeyang Liu, Xuguang Lan Published: 2026-05-02 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2605.01365v1 Open-vocabulary 3D affordance detection requires localizing interaction regions on point clouds given novel affordance descriptions. Recent methods extend multimodal large language models (MLLMs) with special output tokens that are decoded into segmentation masks. However, these tokens are produced through autoregressive generation, which models sequential dependencies rather than spatial neighborhood relations, leaving them semantically rich but spatially impoverished for 3D localization. We propose Voxel-enhanced Affordance detection (VoxAfford), which bypasses this bottleneck by injecting multi-scale geometric features from a frozen pre-trained 3D VQVAE encoder into the output tokens after generation. Each output token uses its affordance semantics as a query to retrieve relevant geometric patterns from its paired voxel scale via cross-attention, with a learned compatibility gate controlling the injection strength. The enhanced tokens are then aggregated into a spatially-aware affordance prompt through semantic-conditioned attention and propagated alongside per-point features to generate the final mask. Experiments on open-vocabulary affordance detection tasks show that VoxAfford achieves state-of-the-art performance with approximately an 8% improvement in mIoU, and real robot experiments confirm zero-shot transfer to novel objects. --- ### Toward a foundational thermal model for residential buildings Authors: Ting-Yu Dai, Kingsley Nweye, Dev Niyogi, Zoltan Nagy Published: 2026-05-02 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2605.01364v1 The building energy community lacks a foundational thermal model, i.e., a single pretrained model capable of generalizing across diverse buildings, climates, and control strategies without building-specific calibration. Achieving this vision requires architectural principles that capture universal thermal dynamics rather than memorizing building-specific patterns. We take a step toward this goal by presenting a physics-informed transformer architecture that embeds domain knowledge, e.g., derivative enrichment and Euler-based numerical integration, into a decoder-only framework. We incorporate static building features extracted from simulation models and employ Rotary Position Embedding attention to capture temporal dependencies. Evaluated on the CityLearn dataset spanning 247 residential buildings across three climate zones, our model achieves one-step prediction accuracy (RMSE of 0.30°C in Texas, 0.29°C in Vermont) while outperforming both traditional baselines and fine-tuned Time-Series Foundation Models. We also demonstrate zero-shot transferability: models trained on as few as two buildings generalize to unseen buildings and climate zones without fine-tuning. Despite the limitation of simulated residential buildings, our results establish physics-informed architectural principles as a promising foundation for universal building thermal models. --- ### Data-Driven, Geometry-Aware Optimal-Transport Calibration of Flavor Tagger Authors: Yeonjoon Kim, Un-ki Yang Published: 2026-05-02 Categories: hep-ex, cs.LG, hep-ph, stat.ME arXiv: https://arxiv.org/abs/2605.01363v1 Flavor-tagging calibrations are often provided either as scale factors measured at a finite set of working points or as binned corrections to a chosen one-dimensional discriminant. However, this approach falls short of providing continuous, event-level calibration across the full multicomponent outputs of modern taggers. This limitation leads to information loss in analyses that demand high-performance flavor tagging, restricting analyses to a limited set of predefined variables. In this work, we propose a geometry-aware framework that formulates flavor-tagger calibration as an optimal transport problem on the probability simplex. The transport maps are parameterized and trained in the isometric log-ratio coordinate system. Because the quadratic Euclidean cost of Brenier transport in this coordinate system is equivalent to the Aitchison distance on the simplex, the learned map induces a minimal deformation under the Aitchison geometry. Furthermore, we extract flavor-conditional target distributions directly from control-region data using an expectation-maximization (EM) technique that simultaneously fits multiple control regions, models each flavor component with a normalizing flow, and estimates the regional mixture fractions. The extracted targets are subsequently used to learn flavor-factorized transport maps. Because the joint estimation of mixture fractions and flexible component densities admits weakly constrained directions, we further introduce a linearized feedback-operator analysis that propagates the fitted composition covariance into the extracted component densities, separating data-constrained modes from those dominated by the composition prior. The simulation-based closure study demonstrates improved closure in dedicated control regions and in independent validation mixtures. --- ### Decision-Focused Learning via Tangent-Space Projection of Prediction Error Authors: Junhyeong Lee, Sangjin Jin, Yongjae Lee Published: 2026-05-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.01361v2 Decision-Focused Learning (DFL) trains predictors to improve downstream decision quality, but computing regret gradients typically requires differentiating through solvers or relying on surrogate losses, which can be computationally expensive or deviate from the true objective. We show that, under standard regularity with locally stable active constraints, the regret gradient admits a closed-form geometric characterization, equivalent to the prediction error projected onto the tangent space of active constraints, scaled by local curvature. This reveals that regret gradients can be obtained by filtering decision-irrelevant components from the MSE gradient, providing a simpler and more direct alternative to existing approaches. Based on this, we propose PEAR (Projected Error As Regret-gradient), which computes regret gradients via a reduced linear system over active constraints, avoiding differentiation through solver iterations or additional optimization solves. Experiments on LP benchmarks and a real-world QP task show that PEAR achieves the best decision quality among all baselines while being the most computationally efficient, with gains that persist under constraint shifts. --- ### Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid Authors: Alessio Donvito, Antonio Lieto Published: 2026-05-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01359v1 In this paper, we employ the Minimal Cognitive Grid (MCG), a framework created to evaluate the cognitive plausibility of artificial systems, to offer a systematic assessment of leading computational models of analogy and metaphor, including the Structure-Mapping Engine (SME), CogSketch, METCL, and Large Language Models (LLMs). We present a formal and quantitative operationalization of the MCG framework and, through the analysis of its three main dimensions (Functional/Structural Ratio, Generality, and Performance Match), examine how well each system aligns with standard cognitive theories of the modeled phenomena, thus allowing for comparison of the models with respect to their cognitive plausibility, according to consistent and generalizable mathematical criteria. --- ### PACE: Parameter Change for Unsupervised Environment Design Authors: Fang Yuan, Quanjun Yin, Siqi Shen, Yuxiang Xie, Junqiang Yang, Long Qin, Junjie Zeng, Qinglun Li Published: 2026-05-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.01358v1 Unsupervised Environment Design (UED) offers a promising paradigm for improving reinforcement learning generalization by adaptively shaping training environments, but it requires reliable environment evaluation to remain effective. However, existing UED methods evaluate environments using indirect proxy signals such as regret, value-based errors, or Monte Carlo, which suffer from bias, high variance, or substantial computational overhead and fail to reflect agent realized learning progress. To address these limitations, we propose Parameter Change Environment Design (PACE), which evaluates an environment through the policy parameter change induced by training on that environment, directly grounding environment selection in realized learning progress. Specifically, PACE assigns environment value using a first-order approximation of the policy optimization objective, where the improvement induced by an environment is proportional to the squared L2 norm of the corresponding parameter update, enabling low-variance and computation-efficient evaluation without additional rollouts. Experiments on MiniGrid and Craftax show that PACE consistently outperforms established UED baselines, achieving higher IQM and smaller Optimality Gap on OOD evaluations, including an IQM of 96.4% and an Optimality Gap of 17.2% on MiniGrid. --- ### On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility Authors: Zhitao He, Haolin Yang, Rui Min, Zeyu Qin, Yi R. Fung Published: 2026-05-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01357v1 Large Language Models (LLMs) excel at long-context understanding but exhibit significant limitations in long-form generation. Existing studies primarily focus on single-generation quality, generally overlooking the volatility of the output. This volatility not only leads to significant computational costs but also severely impacts the models' reliable application. To address this gap, our work unfolds in three stages: benchmarking, probing, and mitigation. We first propose the VOlatility in Long-form Text Benchmark (VOLTBench), a novel heterogeneous-task benchmark designed to systematically quantify the length volatility of long-form generation. Subsequently, by analyzing attention traces, we conduct an in-depth probe to identify several common internal patterns that cause this volatility. Finally, to mitigate long-form output volatility, we propose Stable Generation via Logits Boosting (GLoBo), a lightweight decoding-stage optimization strategy, designed to significantly enhance both the length accuracy and stability of long-form generation without additional training. Extensive experiments on VOLTBench provide the first systematic confirmation of severe long-form output instability in mainstream models and validate that our proposed method successfully improves the mean output length of the base model by 148% and reduces the length volatility by 69%, while maintaining high generation quality. --- ### Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data Authors: Ruiqi Xue, Lei Yuan, Kainuo Cheng, Jing-Wen Yang, Yang Yu Published: 2026-05-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.01356v1 Learning constraint-satisfying policies from offline data without risky online interaction is crucial for safety-critical decision making. Conventional methods typically learn cost value functions from abundant unsafe samples to define safety boundaries and penalize violations. However, in high-stakes scenarios, risky trial-and-error is infeasible, yielding datasets with few or no unsafe samples. Under this limitation, existing approaches often treat all data as uniformly safe, overlooking safe-but-infeasible states - states that currently satisfy constraints but inevitably violate them within a few steps - leading to deployment failures. Drawing inspiration from the concept of knowledge-data integration, we leverage large language models (LLMs) to incorporate natural language knowledge into the policy to address this challenge. Specifically, we propose PROCO, a model-based offline safe reinforcement learning (RL) framework tailored to datasets largely free of violations. PROCO first learns a dynamics model from offline data and constructs a conservative cost function by grounding natural-language knowledge of unsafe states in LLMs, enabling risk estimation even without observed violations. Using the cost function and learned model, PROCO performs model-based rollouts to synthesize diverse counterfactual unsafe samples, supporting reliable feasibility identification and feasibility-guided policy learning. Across a range of Safety-Gymnasium tasks with exclusively safe or minimally risky training data, PROCO integrates seamlessly with a variety of offline safe RL algorithms and consistently demonstrates reduced constraint violations and improved safety performance compared to both the original methods and other behavior cloning baselines. --- ### AgriKD: Cross-Architecture Knowledge Distillation for Efficient Leaf Disease Classification Authors: Minh-Dung Le, Minh-Duc Hoang, Hoang-Vu Truong, Thi-Thu-Hong Phan Published: 2026-05-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.01355v2 Automated leaf disease classification is critical for early disease detection in resource-constrained field environments. Vision Transformers (ViTs) provide strong representation capability by modeling long-range dependencies and inter-class relationships; however, their high computational cost makes them impractical for deployment on edge devices. As a result, existing approaches struggle to effectively transfer these rich representations to lightweight models. This paper introduces AgriKD, a cross-architecture knowledge distillation framework for efficient edge deployment, which transfers knowledge from a Vision Transformer (ViT) teacher to a compact convolutional student model. To bridge the representational gap between Transformer and CNN architectures, the proposed approach integrates multiple distillation objectives at the output, feature, and relational levels, where each objective captures a different aspect of the teacher knowledge. This enables the student model to better preserve and utilize transformer-derived global representations. Experiments on multiple leaf disease datasets show that the distilled student achieves performance comparable to the teacher while significantly improving efficiency, reducing model parameters by approximately 172 times, computational cost by 47.57 times, and inference latency by 18-22 times. Furthermore, the optimized model is deployed across multiple runtime formats, including ONNX, TFLite Float16, and TensorRT FP16, achieving consistent predictive performance with negligible accuracy degradation. Real-world deployment on NVIDIA Jetson edge devices and a mobile application demonstrates reliable real-time inference, highlighting the practicality of AgriKD for AI-powered agricultural applications in resource-constrained environments. --- ### VUDA: Enabling Controlled Spatial Sharing of Graphics and Compute on NVIDIA GPUs Authors: Bin Xu, Pengfei Hu, Jinyu Gu, Haibo Chen Published: 2026-05-02 Categories: cs.OS, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2605.01352v2 Graphics and compute increasingly share a single GPU in embodied AI simulators, AI-enabled games, and VR systems. Running these workloads concurrently can improve utilization, but contention can also compromise rendering and inference latency. Effective sharing therefore requires control over both concurrency and resource allocation. Native CUDA and Vulkan runtimes complicate this task: they place work in separate scheduling domains, while compute-oriented resource controls do not govern the graphics pipeline. We present VUDA, a system that enables controlled spatial sharing of native CUDA compute and Vulkan graphics on NVIDIA GPUs. An analysis of GPU scheduling, address translation, and workload dispatch reveals how to coordinate the two execution stacks without replacing either one. VUDA redirects CUDA channels into Vulkan's scheduling domain while preserving the runtimes' separate data address spaces. It then uses GPU front-end controls to partition execution resources between the graphics and compute pipelines, with allocations adjustable at runtime. Together, these mechanisms let applications control resource sharing without modifying GPU drivers or rewriting kernels and shaders. We evaluate VUDA across four application scenarios on three NVIDIA GPU platforms, covering throughput and latency objectives for graphics, compute, or both. In embodied AI simulation, enabling concurrency improves throughput by up to $1.62\times$ over the same asynchronous pipeline under default time sharing. In driving perception, partitioned co-execution reduces the measured inference-budget miss rate from 80.1% to zero while sustaining 60-FPS rendering. --- ### VUDA: Breaking CUDA-Vulkan Isolation for Spatial Sharing of Compute and Graphics on the Same GPU Authors: Bin Xu, Pengfei Hu, Wenxin Zheng, Jinyu Gu, Haibo Chen Published: 2026-05-02 Categories: cs.OS, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2605.01352v1 GPU-based simulation environments for embodied AI interleave physics simulation (CUDA) and photorealistic rendering (Vulkan) on a single device. We observe that two foundational scenarios -- simulation data generation and RL training -- can be naturally adapted to execute their simulation and rendering phases concurrently, presenting a significant opportunity to improve GPU utilization through spatial multiplexing. However, a fundamental obstacle we term execution isolation prevents this: CUDA and Vulkan create separate GPU contexts whose channels are bound to different scheduling groups, confining compute and graphics to mutually exclusive time slices. Existing spatial-sharing techniques are limited to the CUDA ecosystem, while temporal-sharing approaches underutilize available resources. This paper presents VUDA, a system that breaks execution isolation to enable spatial parallelism between CUDA compute and Vulkan graphics workloads. VUDA is built on two key observations: although CUDA and Vulkan expose different programming abstractions, their execution paths converge to a common channel primitive at the driver and hardware level; meanwhile, their virtual-address spaces are inherently disjoint, making safe page-table merging feasible without remapping. VUDA exposes a thin API for developers to annotate co-schedulable CUDA streams, and realizes spatial sharing through channel redirection into Vulkan's scheduling domain and page-table grafting to unify address spaces, eliminating all data copying on the critical path. Experiments on representative embodied-AI workloads show that VUDA delivers up to 85% higher throughput than temporal-sharing baselines, while improving GPU utilization and reducing end-to-end latency. --- ### LLM Output Detectability and Task Performance Can be Jointly Optimized Authors: Koshiro Saito, Ryuto Koike, Masahiro Kaneko, Naoaki Okazaki Published: 2026-05-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01350v2 Detecting machine-generated text is essential for transparency and accountability when deploying LLMs. Watermarking enables statistically reliable detection by biasing token distributions to embed detectable signals into LLM outputs. However, it has been reported that watermarked LLMs often perform worse on downstream tasks. We propose PUPPET, a framework that fine-tunes an LLM via DPO to generate text that is both more detectable by a target detector and better performing on downstream tasks. We use two rewards: a detector that outputs a machine-class likelihood and an evaluator that measures a task-specific metric. Just as a watermark is verified with its secret key, this detector-specific design lets an LLM provider track how its published model is used. Experiments on long-form QA, summarization, and essay writing show that LLMs trained with PUPPET achieve detectability competitive with watermarking methods---even at strict low FPRs---while outperforming them on downstream tasks. Moreover, this optimization requires only a few thousand samples and 1--2 GPU hours, and its gains hold across out-of-domain tasks, six detectors of diverse architectures, and different LLM families and sizes, and are even robust to paraphrasing attacks. --- ### MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate Authors: Jianze Wang, Ying Liu, Jinlong Chen, Xuchun Hu, Qilong Zhang, Yu Cao, Jun Wang, Hua Yang, Yong Xie, Qianglong Chen Published: 2026-05-02 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.01347v1 On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single-teacher capability ceiling: when the teacher errs, the student inherits the error. OPD also remains largely unexplored in agentic tasks, where per-step errors compound across long trajectories and destabilize training. We propose MAD-OPD (Multi-Agent Debate-driven On-Policy Distillation), which breaks this ceiling by recasting the distillation teacher as a deliberative collective of teachers that debate over the student's on-policy state; the debate produces an emergent collective intelligence that supplies token-level supervision, with each teacher's contribution weighted by its post-debate confidence. To extend OPD to agentic tasks, we also introduce On-Policy Agentic Distillation (OPAD), which adds step-level sampling to stabilize training under multi-step error compounding. We additionally derive a task-adaptive divergence principle, selecting JSD (Jensen-Shannon divergence) for agentic stability and reverse KL (Kullback-Leibler) divergence for code generation, and verify it both theoretically and empirically. Across six teacher-student configurations (Qwen3 and Qwen3.5; 1.7B-14B students, 8B-32B teachers) and five agentic and code benchmarks, MAD-OPD ranks first across all six configurations; on the 14B+8B$\to$4B setting it lifts the agentic average by $+2.4\%$ and the code average by $+3.7\%$ over the stronger single-teacher OPD. --- ### CHASE: Competing Hypotheses for Ambiguity-Aware Selective Prediction Authors: Kartik Jhawar, Yuhao Geng, Atul N. Parikh, Lipo Wang Published: 2026-05-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01346v2 Standard selective prediction methods typically estimate uncertainty from the output of a single predictive branch. While effective for general uncertainty estimation, these approaches often struggle under partial observability, where local temporal evidence can be contradictory and standard confidence scores become misleading. We introduce CHASE (Competing Hypotheses for Ambiguity-Aware Selective Prediction), a selective prediction framework that explicitly compares structured temporal explanations to determine whether to commit to a decision or abstain. Because genuine ambiguity causes the score gap between competing hypotheses to collapse, CHASE optimizes a ranking-aware selector over these hypothesis margins to globally separate safe commitments from fundamentally uncertain ones. We evaluate this framework on the problem of hidden connectivity inference, utilizing a controlled, physically grounded simulator inspired by the dynamics of giant unilamellar vesicles (GUVs), alongside zero-shot qualitative transfer (without retraining or fine tuning) to representative real GUV videos. Our experiments demonstrate that explicitly reasoning over competing hypotheses provides a superior balance of metrics. Compared to canonical uncertainty baselines, CHASE achieves statistically significant gains in overall no-abstain accuracy, three-way accuracy, and overall ambiguity-aligned abstention (at 80% coverage). Specifically, it yields up to an 11.0% relative mean improvement in overall alignment, alongside up to an 8.8% relative boost in three-way accuracy in the very-high ambiguity regime. By maintaining a selective risk boundary strictly at par with the best baselines at 80% coverage, and reducing overall risk by 9.9% at 90% coverage, this framework offers a more reliable approach to decision-making under structured ambiguity. --- ### The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design Authors: Anjie Liu, Ziqin Gong, Yan Song, Yuxiang Chen, Xiaolong Liu, Hengtong Lu, Kaike Zhang, Chen Wei, Jun Wang Published: 2026-05-02 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.01345v3 Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fine-grained details required for complex reasoning. We argue that high-resolution visual reasoning is therefore not only semantic reasoning but also task-relevant evidence acquisition under limited perceptual bandwidth. Inspired by active vision and information foraging, we formalise this process as sequential Bayesian optimal experimental design (S-BOED), where an agent decides which visual evidence to acquire before answering. Since exact Bayesian inference is intractable in continuous gigapixel spaces, we derive a tractable coverage--resolution objective as a proxy for task-relevant information gain. We instantiate this framework with FOVEA, a training-free procedure that refines VLM crop proposals through evidence-oriented probing. Experiments on high-resolution benchmarks show consistent gains over direct and ReAct-style baselines, with particularly strong improvements in search-dominated remote-sensing settings. --- ### ABox Abduction for Inconsistent Knowledge Bases under Repair Semantics Authors: Anselm Haak, Patrick Koopmann, Yasir Mahmood, Anni-Yasmin Turhan Published: 2026-05-02 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2605.01341v1 Given a knowledge base (KB) with a non-entailed fact, the ABox abduction problem asks for possible extensions of the KB that would entail this fact. This problem has many applications, ranging from diagnosis to explainability and repair. ABox abduction has been well-investigated for consistent KBs and classical semantics, but little is known for the case of inconsistent KBs, which can be caused by erroneous data. In this paper we define suitable notions of abduction in this setting and propose criteria that guide abduction towards "useful" hypotheses. To regain meaningful reasoning in the presence of inconsistencies, we use well-established repair semantics. We provide a comprehensive landscape of the complexity of ABox abduction under repair semantics, treating different variants of the abduction problem for the light-weight description logics DL-Lite and EL_bot. --- ### Robust Parameter Learning for Uncertain MDPs Authors: Yannik Schnitzer, Alessandro Abate, David Parker Published: 2026-05-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.01339v1 Learning-based approaches to verifying unknown Markov decision processes (MDPs) often employ uncertain MDPs. These models use, for example, confidence intervals to capture transition uncertainty and allow synthesis of policies that are robust to this uncertainty. However, this approach typically quantifies uncertainty independently for individual transition probabilities, ignoring dependencies due to shared latent quantities. We propose to learn such models using parametric MDPs (pMDPs), where transition probabilities are expressions over a set of parameters. We project statistical uncertainty from empirical transition frequencies onto the pMDP's parameter space, yielding a probably approximately correct (PAC) uncertainty model for the underlying MDP that respects the algebraic dependencies between transitions. The resulting models are algorithmically challenging to solve, so we propose a hierarchy of sound polytopic outer approximations of the induced confidence set. We implement and evaluate our approach, demonstrating substantially tighter uncertainty estimates than classical interval-based uncertain MDP learning techniques. --- ### DiagramNet: An End-to-End Recognition Framework and Dataset for Non-Standard System-Level Diagrams Authors: Jincheng Lou, Ruohan Xu, Jiapeng Li, Junyin Pi, Runzhe Tao, Weijian Fan, Xiao Tan, Guojie Luo, Yibo Lin Published: 2026-05-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.01338v1 System-level diagrams encode the architectural blueprint of chip design, specifying module functions, dataflows, and interface protocols. However, non-standardized symbols and the scarcity of structured training data hinder existing multimodal large language models (MLLMs) from recognizing these diagrams. To address this gap, we introduce DiagramNet, the first multimodal dataset for system-level diagrams, comprising 10,977 connection annotations and 15,515 chain-of-thought QA pairs across four tasks: Listing, Localization, Connection, and Circuit QA. Building on this dataset, we propose a progressive training pipeline together with a decoupled multi-agent workflow that decomposes complex visual reasoning into Perception, Reasoning, and Knowledge stages. On the DiagramNet benchmark, integrating our 3B-parameter model with the proposed workflow surpasses the 2025 EDA Elite Challenge winner and outperforms GPT-5, Claude-Sonnet-4, and Gemini-2.5-Pro by over 2x in end-to-end evaluation. Notably, the workflow generalizes beyond our model, boosting Task 1 performance by 128.7x for Gemini-2.5-Pro and 12.4x for GPT-5. Furthermore, with only 60 images for detector adaptation, the method transfers effectively to AMSBench, achieving zero-shot connectivity reasoning on par with GPT-5 and Claude-Sonnet-4 while surpassing the AMS state-of-the-art method Netlistify. --- ### A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis Authors: Muhammad Arslan Manzoor, Dilshod Azizov, Daniil Orel, Umer Siddique, Zain Muhammad Mujahid, Yufang Hou, Preslav Nakov Published: 2026-05-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01336v1 News outlets shape public opinion at a scale that makes automated detection of political bias and factuality essential. However, the field still lacks unified resources, comprehensive evaluations across diverse approaches, and systematic analyses of the representations and fusion strategies that matter most, especially under label sparsity and dataset diversity. In addition, there is little empirical work reporting broad, observation-driven findings about what consistently works, what fails, and why. We address these gaps through four main contributions. First, we introduce MBFC-2025, a large-scale label set covering approximately 2,600 outlets from Media Bias/Fact Check (MBFC). Second, we construct multiview representations for ACL-2020 (Panayotov et al., 2022), which includes around 900 outlets, as well as for MBFC-2025. These representations span Alexa graphs, hyperlink graphs, LLM-derived graphs, articles, and Wikipedia descriptions. Third, we provide a systematic evaluation and analysis of embedding views and fusion strategies, including a reinforcement learning-based fusion variant. Fourth, we conduct extensive experiments that achieve state-of-the-art results on ACL-2020 and establish strong benchmarks on MBFC-2025. --- ### Mean Testing under Truncation beyond Gaussian Authors: Yuhao Wang, Roberto Imbuzeiro Oliveira, Themis Gouleakis Published: 2026-05-02 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2605.01335v1 We characterize the fundamental limits of high-dimensional mean testing under arbitrary truncation, where samples are drawn from the conditional distribution $P(\cdot \mid S)$ for an unknown truncation set $S$ that may hide up to an $\varepsilon$-fraction of the probability mass. For distributions with $p$-th directional moments of magnitude at most $ν_{P,p}$, truncation induces a bias of order $O(ν_{P,p}\varepsilon^{1-1/p})$. This bias creates a sharp information-theoretic detectability floor: when the signal $α$ falls below this threshold, the null and alternative hypotheses are indistinguishable even with infinite data. Above this floor, we prove that a simple second-order test achieving near-optimal sample complexity $n = O\!\left(\frac{\|Σ_P\|}{(α-4ν_{P,p}\varepsilon^{1-1/p})^2}\sqrt{d}\right)$. We further identify a structural escape from this finite-moment bias barrier. Under a directional median regularity assumption, truncation bias improves to linear order $O(\varepsilon)$. This reveals an intermediate regime in which estimation requires $Θ(d)$ samples for uniform recovery, while testing recovers the classical $Θ(\sqrt d)$ rate once truncation bias is eliminated. Together, our results provide a unified framework for mean testing under truncation, connecting finite-moment, sub-Gaussian, and median-regular structural regimes. --- ### OralMLLM-Bench: Evaluating Cognitive Capabilities of Multimodal Large Language Models in Dental Practice Authors: Rongyang Wang, Shuang Zhou, Jiashuo Wang, Wenya Xie, Xiaoxia Che Published: 2026-05-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.01333v2 Multimodal large language models (MLLMs) have emerged as a promising paradigm for dental image analysis. However, their ability to capture the multi-level cognitive processes required for radiographic analysis remains unclear. Here, we present a comprehensive benchmark to evaluate the cognitive capabilities of MLLMs in dental radiographic analysis. It spans three critical imaging modalities, i.e., periapical, panoramic, and lateral cephalometric radiographs, and defines four cognitive categories: perception, comprehension, prediction, and decision-making. The benchmark comprises 27 clinically grounded tasks derived from public datasets, with manually curated annotations and 3,820 clinician assessments for evaluation. Six frontier MLLMs, including GPT-5.2 and GLM-4.6, are evaluated. We demonstrate the performance gap between MLLMs and clinicians in dental practice, delineate model strengths and limitations, characterize failure patterns, and provide recommendations for improvement. This data resource will facilitate the development of next-generation artificial intelligence systems aligned with clinical cognition, safety requirements, and workflow complexity in dental practice. --- ### Zero-Shot Interpretable Image Steganalysis for Invertible Image Hiding Authors: Hao Wang, Yiming Yao, Yaguang Xie, Tong Qiao, Zhidong Zhao Published: 2026-05-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01331v1 Image steganalysis, which aims at detecting secret information concealed within images, has become a critical countermeasure for assessing the security of steganography methods, especially the emerging invertible image hiding approaches. However, prior studies merely classify input images into two categories (i.e., stego or cover) and typically conduct steganalysis under the constraint that training and testing data must follow similar distribution, thereby hindering their application in real-world scenarios. To overcome these shortcomings, we propose a novel interpretable image steganalysis framework tailored for invertible image hiding schemes under a challenging zero-shot setting. Specifically, we integrate image hiding, revealing, and steganalysis into a unified framework, endowing the steganalysis component with the capability to recover the secret information embedded in stego images. Additionally, we elaborate a simple yet effective residual augmentation strategy for generating stego images to further enhance the generalizability of the steganalyzer in cross-dataset and cross-architecture scenarios. Extensive experiments on benchmark datasets demonstrate that our proposed approach significantly outperforms the existing steganalysis techniques for invertible image hiding schemes. --- ### Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay Authors: Jin Tong, Guang Liang, Peilin Sun, Jianxin Wu Published: 2026-05-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.01330v1 Low-bit quantization is a practical route for efficiently deploying vision Transformers, yet activation outliers complicate fully quantized deployment. Existing methods either handle quantization post-training or suppress large activations during training; however, aggressively restricting outliers in vision models can lead to a poorer trade-off between full-precision and quantized accuracy. We argue that rather than simply suppressing outliers, the training objective should control the structural amplification that makes them harmful. To this end, we introduce Colinearity-Decay (CD), a structural regularizer for ordered matrix pairs within Transformer blocks. CD penalizes detrimental cross-matrix alignment and mitigates extreme activations without altering the architecture or task loss. Applied as a decoupled update, CD is non-invasive and introduces minimal training overhead. Across ImageNet-1K pre-training, COCO detection, and downstream fine-tuning, CD consistently boosts quantized accuracy across multiple pipelines while preserving, or even improving, full-precision performance. Ultimately, our results demonstrate that structural regularization effectively prepares vision Transformers for low-bit deployment with zero inference-time overhead. --- ### Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents Authors: Shijun Lei, Hongyu Wang, Yunji Liang, Haowen Zheng, Bin Guo, Zhiwen Yu Published: 2026-05-02 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.01329v1 In-group favoritism refers to the phenomena of favoring members of one's in-group over out-group members and is widely observed in numerous social cooperative behaviors. Recently, in-group favoritism biases have also been identified in generative language models. However, whether the in-group favoritism exists when persona agents are faced with contradicting information (e.g., misinformation), and how to mitigate the adverse effects of in-group favoritism biases in persona agents have been understudied. To address these problems, we propose a Truth or Tribe simulation framework to study the agent cooperation within the spread of contradicting information through a triadic interaction paradigm, and conduct controlled trials to evaluate the primary moderating factors. Extensive results showcase that persona agents display strong in-group favoritism, accepting incorrect answers from identity-similar peers at much higher rates than from dissimilar peers. In-group favoritism continues to emerge in defeasible reasoning contexts where no absolute truth exists, and it intensifies as cognitive complexity increases. Furthermore, three intervention strategies--Identity-Blind Instruction, Structured Counterfactual Reasoning, and Heterogeneous Perspective Ensemble--are proposed to mitigate the in-group favoritism. ---