# Research Papers — 2026-05 · bundle page 238 of 326 > Full-text markdown of papers #11851–11900 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/238 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/237.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/239.md) ### Strategic commitments shape collective cybersecurity under AI inequality Authors: Adeela Bashir, Zia Ush Shamszaman, Zhao Song, Matjaz Perc, The Anh Han Published: 2026-05-10 Categories: cs.AI, physics.soc-ph arXiv: https://arxiv.org/abs/2605.09415v2 The growing integration of AI into cybersecurity is reshaping the balance between attackers and defenders. When access to advanced AI-enabled defence tools is uneven, resource-limited defenders may be unable to adopt effective protection, creating persistent system vulnerabilities. We study the impact of differential AI access using an evolutionary game-theoretic model in a finite population. We first show that when high-capability defence is costly, the population is driven toward low-cost, weak-defence behaviour, sustaining attacks and weakening long-run security. To address this problem, we introduce differential access to AI defence tools by allowing defenders to choose between low- and high-capability protection based on their resources. We then examine the role of a small group of committed defenders who always adopt strong defence and influence others through social learning. Although commitment increases the prevalence of strong defence, it alone cannot stabilise secure outcomes due to high defence costs. We therefore incorporate a targeted subsidy to remove the cost disadvantage from committed defenders. Our analysis shows that subsidised commitment significantly increases strong defence adoption, suppresses successful attacks, and improves overall system resilience. Simulations across a broad parameter space confirm that subsidies consistently outperform commitment alone. In addition, social-welfare analysis shows improved defender outcomes while keeping attacker gains low. These findings suggest that targeted support for key defenders can be an effective mechanism for stabilising cybersecurity in AI-driven environments and provide a theoretical bridge between cybersecurity policy, AI governance, and strategic allocation of defensive AI capabilities. --- ### Cross-Cultural Transfer of Emoji Semantics and Sentiment in Financial Social Media Authors: Ahmed Mahrous, Roberto Di Pietro Published: 2026-05-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.09414v1 Emojis are widely used in online financial communication, but it is unclear whether they provide transferable sentiment signals across languages, platforms, and asset communities. This study examines the extent to which emoji usage, semantics, and sentiment polarity remain stable across financial communities, and how these layers influence zero-shot sentiment transfer. Using large corpora of Twitter and StockTwits posts in four languages, we measure cross-community divergence and evaluate sentiment models trained under emoji-only, text-only, and text+emoji inputs. We find that emoji frequencies differ across communities, especially across languages, but their semantics and sentiment polarity are largely stable. Cross-asset transferability shows minimal degradation, while cross-language transfer remains the most challenging. Including emojis consistently reduces transfer gaps relative to text-only models. These results indicate that financial communication exhibits a partially shared ``emoji code,'' and that emojis provide compact, language-independent sentiment cues that improve model generalization across markets and platforms. --- ### RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models Authors: Weijia Liufu, Xiaoyu Guo, Ruiyi Chen, Jingzhi Liu, Kaidong Zhang, Xiwen Liang, Jianqi Lin, Dawei Sun, Yuze Wang, Rongtao Xu, Bingqian Lin, Bowen Yang et al. Published: 2026-05-10 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.09410v1 Vision-Language-Action (VLA) models remain brittle in long-horizon, contact-rich manipulation because success-only imitation provides little supervision for execution drift, while failed rollouts are often discarded. We introduce RePO-VLA, a recovery-driven policy optimization framework that assigns distinct roles to success, recovery, and failure trajectories. RePO-VLA first applies Recovery-Aware Initialization (RAI), slicing recovery segments and resetting history so corrective actions depend on the current adverse state rather than the preceding failure. It then learns a Progress-Aware Semantic Value Function (PAS-VF), aligning spatiotemporal trajectory features with instructions and successful references. The resulting labels salvage useful failure prefixes via reliability decay, while low-value labels mark drift and terminal breakdowns, teaching differences among nominal, failed, and corrective actions. The data engine turns adverse states into planner-generated or human-collected corrective rollouts, teaching recovery to the success manifold. Value-Conditioned Refinement (VCR) trains the policy to prefer high-progress actions. At deployment, a fixed high value ($v=1.0$) biases actions toward the learned success manifold without online failure detectors or heuristic retries. We introduce FRBench, with standardized error injection and recovery-focused evaluation. Across simulated and real-world bimanual tasks, RePO-VLA improves robustness, raising adversarial success from 20% to 75% on average and up to 80% in scaled real-world trials. --- ### GravityGraphSAGE: Link Prediction in Directed Attributed Graphs Authors: Riccardo Porcedda, Francesca Chiaromonte, Fabrizio Lillo, Andrea Vandin Published: 2026-05-10 Categories: cs.LG, cs.SI, stat.ML arXiv: https://arxiv.org/abs/2605.09408v1 Link prediction (inferring missing or future connections between nodes in a graph) is a fundamental problem in network science with widespread applications in, e.g., biological systems, recommender systems, finance and cybersecurity. The ability to accurately predict links has significant real-world applications, such as detecting fraudulent financial transactions or identifying drug-target interactions in biomedicine. Despite a rich literature, link prediction is still challenging, especially for graphs enriched with information on edges (direction) and nodes (attributes). In fact, research on link prediction, especially the one based on Graph Deep Learning (GDL), has mostly focused on undirected graphs, without fully leveraging node attributes. Here, we fill this gap by proposing Gravity-GraphSAGE (GG-SAGE), a modified version of GraphSAGE, a GDL model for node embeddings, composed of a gravity-inspired decoder. This implementation is the first example in the literature of a GraphSAGE backbone adopted for directed link prediction. Using the benchmark datasets Cora, Citeseer, PubMed and 16 real-world graphs from the online Netzschleuder repository, we show that our proposed model outperforms state-of-the-art GDL link prediction techniques. Using further experimental evidence, we relate the quality of the output of our model with various characteristics of the graph, suggesting that our framework scales well when applied to data of increasing complexity. --- ### AnyDepth-DETR/-YOLO: Any-depth object detection with a single network Authors: Woochul Kang, Hyungseop Lee, Jiho Lee Published: 2026-05-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.09407v1 Modern object detectors are static, fixed-depth networks optimized for a single operating point, requiring separate models for different deployment scenarios. We present an any-depth detection framework that enables a single network to span a continuous range of accuracy--efficiency trade-offs by controlling depth at inference time without retraining. Each backbone and neck stage is divided into an essential path, which always executes, and a skippable refinement path; this decomposition preserves the full multi-scale feature hierarchy at every depth configuration, unlike conventional early exiting that discards entire stages. To train such a network, jointly optimizing many sub-networks of varying depth introduces conflicting gradient signals. We address this via self-distillation between only the two extremes, with prediction-level and feature-level alignment losses that enforce stage-wise modularity, ensuring the outputs of each stage remain compatible regardless of the paths taken. Instantiated on RT-DETR and YOLOv12, our full-depth configurations match or surpass their respective SOTA baselines with negligible parameter overhead, while the most efficient configurations achieve up to $1.82\times$ speedup at a cost of only 2.0 AP, all from a single set of weights. --- ### Let the Target Select for Itself: Data Selection via Target-Aligned Paths Authors: Huitao Yang, Hengzhi He, Tung Sum Thomas Kwok, Guang Cheng Published: 2026-05-10 Categories: cs.LG, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2605.09404v2 Targeted data selection seeks training examples from a candidate pool that improve downstream task performance. While trajectory-based selectors effectively guide this process, existing approaches typically construct reference states by warming up on the candidate pool itself, thereby inheriting pool-dependent distributional biases. To address this coupling, we introduce Target-Aligned Candidate Selection (TACS), which constructs a short, capacity-constrained reference path using a compact target-validation proxy. Candidates are ranked by their normalized loss reduction along this trajectory, requiring only forward passes and allowing the path to be reused across distinct pools for a fixed model-target pair. Empirically, TACS achieves competitive downstream performance across controlled logistic, vision, and NLP benchmarks, while slashing selection compute by up to 69% and candidate storage to less than 10 MB in large-scale instruction tuning. --- ### Let the Target Select for Itself: Data Selection via Target-Aligned Paths Authors: Huitao Yang, Hengzhi He, Guang Cheng Published: 2026-05-10 Categories: cs.LG, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2605.09404v1 Targeted data selection aims to identify training samples from a large candidate pool that improve performance on a specific downstream task. Many recent methods estimate candidate utility by aggregating local attribution scores along a trajectory induced by the candidate pool. When the pool is heterogeneous, however, this reference trajectory may be misaligned with the dynamics of a target-aligned selected subset, creating what we call reference path bias. We propose an alternative reference path: a validation-induced flow obtained from a short, capacity-limited warmup on the available target validation proxy. Along this path, candidates are scored by a normalized endpoint loss drop, yielding a simple zero-order selection rule that requires no candidate gradients or Hessian approximations. Across controlled logistic, vision, and instruction-tuning experiments, this score is competitive with strong dynamic attribution baselines while substantially reducing warmup and storage cost. Moreover, since the reference trajectory is decoupled from any specific candidate pool, the same compact warmup can be reused across additional pools without recomputing the trajectory. --- ### Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers Authors: Gabriel Smithline, Chris Mascioli Published: 2026-05-10 Categories: cs.LG, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2605.09403v2 Architectural choices inside the Transformer feedforward network (FFN) block do not merely affect the block itself; they reshape the computations learned by the rest of the model. We study this effect in one-layer Transformers trained on digit addition with carry, modular arithmetic, and histogram counting. Comparing dense FFNs, gated linear units (GLUs), mixture-of-experts (MoE), and MoE-GLUs, we find that sparse MoE routing can shift computation from FFN to attention, with the strongest ablation-visible effect on carry-based addition. We decompose this redistribution into reduced per-token FFN capacity and sparse partitioning across experts. Critically, frozen random routing nearly matches learned routing, suggesting that redistribution is driven largely by architectural sparsity rather than router-learned specialization. As a secondary finding, GLU-style multiplicative gating rotates task-relevant Fourier structure out of the per-neuron basis and into distributed subspaces, making neuron-level interpretability less informative while preserving structured computation. We validate these conclusions with random-routing, narrow-FFN, and top-2 MoE controls, plus parameter-matching, activation-function, and width-scaling analyses. Together, these results show that local FFN design choices can have nonlocal consequences for Transformer computation. --- ### D2ACE: Multi-Label Batch Selection Guided by Dual Dynamics and Adaptive Correlation Enhancement Authors: Bin Liu, Haoyu Peng, Zhijia Wei, Jiajing Zhang, Grigorios Tsoumakas Published: 2026-05-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.09400v1 Batch selection is crucial for improving both training efficiency and predictive performance in deep multi-label classification (MLC). Existing batch selection methods typically rely on a single metric to assess instance importance and use static label weights to distinguish label significance, neglecting the dynamic evolution of metric utility and label significance during training. In addition, the method that explicitly exploits label correlations is largely affected by abundant irrelevant labels and insensitive to local label distributions. To address these issues, we propose D2ACE, a novel multi-label batch selection method guided by Dual Dynamics and Adaptive Correlation Enhancement. D2ACE explicitly captures metric and label-level training dynamics by combining stage-wise Bernoulli mixture sampling, which balances uncertainty and noise-resistant hardness, with dynamic label weighting to recalibrate label priorities at each epoch based on current metric statistics. Furthermore, D2ACE introduces a local context-aware correlation enhancement to focus on relevant labels with instance-adaptive dependencies. Extensive experiments on tabular and image benchmarks demonstrate that D2ACE outperforms existing batch selection approaches across various deep MLC models, achieving stronger predictive performance and more efficient correlation modeling. --- ### Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions Authors: Dier Tang, Guangyue Han Published: 2026-05-10 Categories: cs.IT, cs.LG, math.ST, stat.ML arXiv: https://arxiv.org/abs/2605.09396v2 This paper relaxes the restrictive symmetry conditions adopted in (4), (5) and extends their universal feature selection framework to accommodate noisy observations as well as attribute structures that may exhibit directional preferences. We introduce the notion of weak spherical symmetry, quantified by second-moment distances, which allows controlled deviations from rotational invariance. Under this relaxed condition, we develop a universal feature selection framework based on the singular value decomposition of the canonical dependence matrix computed from noisy data. Our main result shows that the selected features achieve asymptotically optimal error exponents up to a residual term that depends on the symmetry deviation $δ$ and the noise levels $η_1, η_2$. When $δ, η_1, η_2$ are relatively small, our result recovers that of (5), thereby demonstrating that exact spherical symmetry is unnecessary. Overall, our findings highlight the robustness of the selection framework against second-moment deviations and observation noise, thereby broadening its applicability across diverse inference tasks and providing a theoretically grounded tool for universal feature selection in practical scenarios. --- ### Universal Feature Selection with Noisy Observations and Weak Symmetry Conditions Authors: Dier Tang, Guangyue Han Published: 2026-05-10 Categories: cs.IT, cs.LG, math.ST, stat.ML arXiv: https://arxiv.org/abs/2605.09396v1 This paper relaxes the restrictive symmetry conditions adopted in (4), (5) and extends their universal feature selection framework to accommodate noisy observations as well as attribute structures that may exhibit directional preferences. We introduce the notion of weak spherical symmetry, quantified by second-moment distances, which allows controlled deviations from rotational invariance. Under this relaxed condition, we develop a universal feature selection framework based on the singular value decomposition of the canonical dependence matrix computed from noisy data. Our main result shows that the selected features achieve asymptotically optimal error exponents up to a residual term that depends on the symmetry deviation $δ$ and the noise levels $η_1, η_2$. When $δ, η_1, η_2$ are relatively small, our result recovers that of (5), thereby demonstrating that exact spherical symmetry is unnecessary. Overall, our findings highlight the robustness of the selection framework against second-moment deviations and observation noise, thereby broadening its applicability across diverse inference tasks and providing a theoretically grounded tool for universal feature selection in practical scenarios. --- ### Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning Authors: Lin Li, Jiawei Huang, Qihao Quan, Dan Li, Boxin Li, Xiao Zhang, Erli Meng, Wenjie Feng, Jian Lou, See-Kiong Ng Published: 2026-05-10 Categories: cs.AI, cs.LG, cs.MA, cs.MM arXiv: https://arxiv.org/abs/2605.09395v3 In this paper, we propose the first VL\underline{\textbf{M}} \underline{\textbf{a}}gentic \underline{\textbf{r}}easoning framework for few-\underline{\textbf{s}}hot multimodal \underline{\textbf{T}}ime \underline{\textbf{S}}eries \underline{\textbf{C}}lassification (\textsc{MarsTSC}), which introduces a self-evolving knowledge bank as a dynamic context iteratively refined via reflective agentic reasoning. The framework comprises three collaborative roles: i) Generator conducts reliable classification via reasoning; ii) Reflector diagnoses the root causes of reasoning errors to yield discriminative insights targeting the temporal features overlooked by Generator; iii) Modifier applies verified updates to the knowledge bank to prevent context collapse. We further introduce a test-time update strategy to enable cautious, continuous knowledge bank refinement to mitigate few-shot bias and distribution shift. Extensive experiments across 12 mainstream time series benchmark datasets demonstrate that \method{} delivers substantial and consistent performance gains across 5 VLM backbones, outperforming both classical and foundation model-based time series baselines under few-shot conditions, while producing interpretable rationales that ground each classification decision in human-readable feature evidence. Code is available at https://github.com/HuangJW0821/MarsTSC. --- ### Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning Authors: Lin Li, Jiawei Huang, Qihao Quan, Dan Li, Boxin Li, Xiao Zhang, Erli Meng, Wenjie Feng, Jian Lou, See-Kiong Ng Published: 2026-05-10 Categories: cs.AI, cs.LG, cs.MA, cs.MM arXiv: https://arxiv.org/abs/2605.09395v2 In this paper, we propose the first VL$\underline{\textbf{M}}$ $\underline{\textbf{a}}$gentic $\underline{\textbf{r}}$easoning framework for few-$\underline{\textbf{s}}$hot multimodal $\underline{\textbf{T}}$ime $\underline{\textbf{S}}$eries $\underline{\textbf{C}}$lassification ($\textbf{MarsTSC}$), which introduces a self-evolving knowledge bank as a dynamic context iteratively refined via reflective agentic reasoning. The framework comprises three collaborative roles: i) Generator conducts reliable classification via reasoning; ii) Reflector diagnoses the root causes of reasoning errors to yield discriminative insights targeting the temporal features overlooked by Generator; iii) Modifier applies verified updates to the knowledge bank to prevent context collapse. We further introduce a test-time update strategy to enable cautious, continuous knowledge bank refinement to mitigate few-shot bias and distribution shift. Extensive experiments across 12 mainstream time series benchmarks demonstrate that $\textbf{MarsTSC}$ delivers substantial and consistent performance gains across 6 VLM backbones, outperforming both classical and foundation model-based time series baselines under few-shot conditions, while producing interpretable rationales that ground each classification decision in human-readable feature evidence. --- ### HyNeuralMap: Hyperbolic Mapping of Visual Semantics to Neural Hierarchies Authors: Zihan Ma, Tian Xia, Kexin Wang, Xiao Li, Xiaowei He, Yudan Ren Published: 2026-05-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.09392v1 Understanding the intricate mappings between visual stimuli and neural responses is a fundamental challenge in cognitive neuroscience. While current approaches predominantly align images and functional magnetic resonance imaging (fMRI) responses in Euclidean space, this geometry often struggles to preserve fine-grained semantic relationships and latent hierarchical structures across visual and neural modalities. To overcome this, we propose HyNeuralMap, a framework that employ hyperbolic Lorentz model to map visual semantics into a shared, cross-subject neural hierarchy. By leveraging the negative curvature of hyperbolic space as an inductive bias, the proposed framework better captures hierarchical semantic organization and cross-subject neural similarities. Specifically, visual and neural embeddings are jointly optimized through hyperbolic geometric alignment, where geodesic distances preserve semantic proximity and hierarchical relationships more effectively than Euclidean embeddings. Experiments demonstrate that HyNeuralMap consistently outperforms state-of-the-art Euclidean baselines in both multi-label semantic prediction and cross-modal retrieval tasks. This confirms hyperbolic geometry's superiority for cross-modal semantic alignment and hierarchical modeling, providing a new avenue for vision-neural representation learning. --- ### Do Linear Probes Generalize Better in Persona Coordinates? Authors: Prasad Mahadik, Adrians Skapars Published: 2026-05-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.09391v2 It is becoming increasingly necessary to have monitors check for harmful behaviors during language model interactions, but text-only monitoring has not been sufficient. This is because models sometimes exhibit strategic deception and sandbagging, changing their behavior during evaluation. This motivates the use of white-box monitors like linear probes, which can read the model internals directly. Currently, such probes can fail under distribution shift, limiting their usefulness in real settings. We study whether there exists a low-dimensional subspace of the model internals that captures harmful behaviors more robustly, while leaving out spuriously correlative features. Inspired by the Assistant Axis and Persona Selection Model, we construct persona axes for deception and sycophancy using contrastive persona prompts. The first principal components, obtained by unsupervised PCA of the persona-specific vectors, cleanly separate harmful and harmless personas. Across 10 evaluation datasets, we show that persona-derived directions transfer non-trivially and probes trained on persona-PC projections generalize better than probes trained on raw activations. We also find that a unified axis consisting of multiple harmful and harmless behaviors improves generalization across behaviors and datasets. Overall, persona vectors provide a useful inductive bias for building more transferable behavior probes. --- ### NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning Authors: Tiehan Cui, Peipei Liu, Yanxu Mao, Congying Liu, Mingzhe Xing, Datao You Published: 2026-05-10 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2605.09387v1 While Large Language Models (LLMs) have catalyzed progress in embodied intelligence, a fundamental gap between their inherent probabilistic uncertainty and the strict determinism and verifiable safety required in the physical world. To mitigate this gap, this paper introduces NEXUS, a modular framework designed for continual learning in embodied agents. Different from prior works that treat symbolic artifacts merely as static interfaces, NEXUS leverages them for symbolic grounding and knowledge evolution. The framework explicitly decouples physical feasibility from safety specifications: capability of agents is improved through closed-loop execution feedback, while probabilistic risk assessments are grounded into deterministic hard constraints to establish a rigorous pre-action defense. Experiments on SafeAgentBench demonstrate that NEXUS achieves superior task success rates while effectively refusing unsafe instructions, exhibiting robust defense against adversarial attacks, and progressively improving planning efficiency through knowledge accumulation. --- ### Kinetic-Optimal Scheduling with Moment Correction for Metric-Induced Discrete Flow Matching in Zero-Shot Text-to-Speech Authors: Dong Yang, Yiyi Cai, Haoyu Zhang, Yuki Saito, Hiroshi Saruwatari Published: 2026-05-10 Categories: eess.AS, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.09386v1 Metric-induced discrete flow matching (MI-DFM) exploits token-latent geometry for discrete generation, but its practical use is limited by two issues: heuristic schedulers requiring hyperparameter search, and finite-step path-tracking error from its first-order continuous-time Markov chain (CTMC) solver. We address both issues. First, we derive a kinetic-optimal scheduler for prescribed scalar-parameterized probability paths, and instantiate it for MI-DFM as a training-free numerical schedule that traverses the path at constant Fisher-Rao speed. Second, we introduce a finite-step moment correction that adjusts the jump probability while preserving the CTMC jump destination distribution. We validate the resulting method, GibbsTTS, on codec-based zero-shot text-to-speech (TTS). Under controlled comparisons with a unified architecture and large-scale dataset, GibbsTTS achieves the best objective naturalness and is preferred in subjective evaluations over masked discrete generative baselines. Additionally, in comparison with the evaluated state-of-the-art TTS systems, GibbsTTS shows strong speaker similarity, achieving the highest similarity on three of four test sets and ranking second on the fourth. Project page: https://ydqmkkx.github.io/GibbsTTSProject --- ### LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering Authors: Runze Ma, Shunbo Jia, Haonan Lyu, Guo Liu, Caizhi Liao Published: 2026-05-10 Categories: cs.CV, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2605.09384v2 The reasoning gap between large and compact vision-language models (VLMs) limits the deployment of medical AI on portable clinical devices. Compact VLMs of 2-4B parameters can run on resource-constrained hardware but lack the multi-step reasoning capacity needed for interpretable clinical decision support. Existing knowledge distillation methods transfer answers without the reasoning process behind them. Medical visual question answering (VQA) serves as a testbed for this problem, as it requires models to integrate visual evidence with clinical knowledge through structured reasoning chains. We introduce LiteMedCoT-VL, a pipeline that transfers chain-of-thought reasoning from a 235B teacher model to 2B student models through LoRA-based fine-tuning on explanation-enriched training data. All inference is conducted without image captions by default, simulating the clinical scenario in which a physician interprets a medical image directly without an accompanying radiology report. On the PMC-VQA benchmark, LiteMedCoT-VL achieves 64.9% accuracy, exceeding the zero-shot Qwen3-VL-4B baseline of 53.9% by 11.0 percentage points and outperforming all published baselines. This result indicates that a 2B model with reasoning distillation can match or exceed models with twice the parameters. Visual grounding analysis shows that the model relies on image content rather than exploiting textual priors. Our code is publicly available at https://github.com/R4nzer/LiteMedCoT-VL. --- ### LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering Authors: Runze Ma, Shunbo Jia, Haonan Lyu, Guo Liu, Caizhi Liao Published: 2026-05-10 Categories: cs.CV, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2605.09384v1 The reasoning gap between large and compact vision-language models (VLMs) limits the deployment of medical AI on portable clinical devices. Compact VLMs of 2--4B parameters can run on resource-constrained hardware but lack the multi-step reasoning capacity needed for interpretable clinical decision support. Existing knowledge distillation methods transfer answers without the reasoning process behind them. Medical visual question answering (VQA) serves as a testbed for this problem, as it requires models to integrate visual evidence with clinical knowledge through structured reasoning chains. We introduce LiteMedCoT-VL, a pipeline that transfers chain-of-thought reasoning from a 235B teacher model to 2B student models through LoRA-based fine-tuning on explanation-enriched training data. All inference is conducted without image captions by default, simulating the clinical scenario in which a physician interprets a medical image directly without an accompanying radiology report. On the PMC-VQA benchmark, LiteMedCoT-VL achieves 64.9% accuracy, exceeding the zero-shot Qwen3-VL-4B baseline of 53.9% by 11.0 percentage points and outperforming all published baselines. This result indicates that a 2B model with reasoning distillation can match or exceed models with twice the parameters. Visual grounding analysis shows that the model relies on image content rather than exploiting textual priors. Our code is publicly available at https://anonymous.4open.science/r/LiteMedCoT-VL. --- ### Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts Authors: Ilay Yavlovich, Jad Agbaria, Muhamed Mhamed, Nir Weinberger, Jose Yallouz Published: 2026-05-10 Categories: cs.LG, cs.CV, cs.DS, math.OC arXiv: https://arxiv.org/abs/2605.09382v2 The Linear Assignment Problem is a fundamental combinatorial optimization task where classical exact solvers ensure optimality but suffer from an $\mathcal{O}(N^{3})$ bottleneck, while recent neural approximations struggle with scalability and exactness. We propose a learning-augmented framework that accelerates exact solvers by predicting dual variables to warm-start the search, backed by a fallback mechanism to preserve worst-case guarantees. Central to our approach is RowDualNet, a lightweight, row-independent architecture that avoids the $\mathcal{O}(N^{2})$ memory bottleneck of graph models, enabling scalable neural warm-starting up to $N=16{,}384$. Feasibility is guaranteed by construction via the Min-Trick mechanism, completely eliminating the need for costly iterative projections. Empirically, our method drastically reduces the search effort of the Jonker-Volgenant (LAPJV) algorithm, yielding robust zero-shot generalization with strict optimality and end-to-end speedups of over 2x on complex synthetic data, 1.25x on real-world tracking, and 1.5x on transportation networks. --- ### EduStory: A Unified Framework for Pedagogically-Consistent Multi-Shot STEM Instructional Video Generation Authors: Xinyi Wu, Jayant Teotia, Shuai Zhao, Erik Cambria Published: 2026-05-10 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.09378v1 Long-horizon video generation has advanced in visual quality, yet existing methods still struggle to maintain knowledge consistency and coherent pedagogical narratives across multi-shot instructional videos, especially in STEM domains. To address these challenges, we propose EduStory, a unified framework for reliable instructional video generation. EduStory integrates pedagogical state modeling to track persistent knowledge states, script-guided structured control to organize multi-shot narratives, and learning-oriented evaluation metrics to assess knowledge fidelity and constraint satisfaction. To support rigorous evaluation, we further introduce EduVideoBench, a diagnostic benchmark with multi-granularity annotations, including pedagogical storyboards, shot-level semantics, and knowledge state transitions, together with baseline tasks for controllable instructional video generation. Extensive experiments demonstrate that domain-aware state modeling and structured control substantially reduce narrative breakdown and improve alignment with instructional intent. These results highlight the significance of domain-specific structural constraints and tailored benchmarks for advancing reliable, controllable, and also trustworthy long-horizon video generation. --- ### From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs Authors: Daemyung Kang, Eunjin Hwang, Hanjeong Lee, HyeokJin Kim, Hyunhoi Koo, Jeongkyu Shin, Jeongseok Kang, Jihyun Kang, Jinho Heo, Joongi Kim, Junbum Lee, Jungseung Yang et al. Published: 2026-05-10 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2605.09370v5 Large-scale AI training is fundamentally a distributed systems problem, where hardware failures are routine operating conditions rather than rare exceptions, yet public operational evidence from production training clusters remains limited. This report presents an empirical analysis of a 63-node NVIDIA B200 production cluster (504 GPUs), using 55 days of Prometheus time-series data and 73 days of operational logs covering 224 multi-node training sessions. The environment is cross-organizational: five parties (SKT, Upstage, Lablup, NVIDIA Korea, VAST Data) share a unified monitoring pipeline. This enabled joint diagnosis of a 60-node-scale storage I/O bottleneck absent in 2-4-node tests, a production-scale phenomenon no single team could isolate alone. We perform three quantitative analyses yielding four findings. First, over 751 Prometheus metrics and 10 XID-identified GPU failures, no single metric is consistently dominant across failure types, motivating multi-signal detection. Second, 523 checkpoint events trace the save/load path from GPU VRAM to the NFS server: restart loading reaches 21.5% of maximum read bandwidth (700 GB/s) and save bursts 16.0% of maximum write bandwidth (250 GB/s), with NFS/RPC queueing and transport-layer backlog rising together. Third, across 224 sessions over 73 days, node exclusions concentrate so the top 3 of 63 nodes account for over 50%. Fourth, auto-retry chain analysis shows a 33.3% success rate over 12 chains (73 attempts), 2.7x the 12.5% manual rate, with a median retry interval of 11 minutes (IQR 10-11). All analyses are grounded in production infrastructure providing session-level workload management, GPU-centric scheduling, and unified observability. --- ### Explainable Knowledge Tracing via Probabilistic Embeddings and Pattern-based Reasoning Authors: Siyu Wu, Cong Xu, Wei Zhang Published: 2026-05-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.09369v1 Knowledge Tracing (KT) models students' knowledge states based on learning interactions to predict performance. While deep learning-based KT models have boosted predictive accuracy, most models rely on deterministic vector embeddings and opaque latent state transitions, limiting interpretability regarding how specific past behaviors influence predictions. To address this limitation, we propose Probabilistic Logical Knowledge Tracing (PLKT), an interpretable KT framework that formulates prediction as a goal-conditioned evidence reasoning process over historical learning behaviors. Instead of representing knowledge states as deterministic vector embeddings, PLKT employs robust Beta-distributed probabilistic embeddings to represent student knowledge states. This probabilistic foundation allows us to model the uncertainty of historical behaviors and perform explicit logical operations (e.g., conjunction), constructing transparent reasoning paths that reveal how specific past interactions contribute to the prediction. Extensive experiments show that PLKT outperforms state-of-the-art KT methods while achieving superior interpretability. Our code is available at https://anonymous.4open.science/r/PLKT-D3CE/. --- ### Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration Authors: Keqi Han, Songlin Zhao, Yao Su, Xiang Li, Yixuan Yuan, Lifang He, Carl Yang Published: 2026-05-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.09366v3 Transforming neuroimaging data into clinically actionable biomarkers is a knowledge-intensive and labor-intensive process. Standardized workflows such as fMRIPrep have improved robustness and efficiency, but they are statically configured and cannot reason about downstream objectives, deliberate over alternative strategies, or close the loop between intermediate evidence and subsequent decisions in the way a human researcher would. This lack of closed-loop adaptation often leaves domain experts trapped in a cycle of manual trial-and-error to tune parameters and remediate pipeline failures, severely constraining the scalability of clinical biomarker development. To bridge this gap, we introduce NEXUS, an autonomous multi-agent framework that integrates neuroimaging workflow execution with scientific-objective understanding. Unlike conventional flat toolcalling agents, NEXUS adopts a code-centric execution paradigm where specialist agents collaboratively synthesize and optimize executable programs over composable domain-specific primitives. This design enables robust, long-horizon workflow construction that adapts dynamically to runtime observations. Furthermore, we propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection to drive evidence-grounded workflow remediation. Experiments on ADHD-200 and ADNI demonstrate that NEXUS outperforms standard workflow-based baselines in predictive performance while exhibiting sophisticated agentic behaviors, including strategy exploration and adaptive refinement. The code is available at https://github.com/LearningKeqi/Virtual-Neuroscientist-NEXUS. --- ### Position: Avoid Overstretching LLMs for every Enterprise Task Authors: Kuldeep Singh, Anson Bastos, Isaiah Onando Mulang' Published: 2026-05-10 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.09365v1 Enterprise workloads are dominated by deterministic, structured, and knowledge-dependent tasks operating under strict cost, latency, and reliability constraints. While these are often addressed through large language model (LLM) deployment or distillation into smaller models, we argue this is inefficient, unreliable, and misaligned with enterprise task structures. Instead, AI systems should treat language models as interfaces rather than monolithic engines, externalizing knowledge and computation into dedicated components for greater reliability, scalability, and transparency. Our theoretical evidences show that finite-capacity models cannot fully capture the breadth of knowledge required for enterprise tasks, creating inherent limits to efficiency and interpretability. Building on this, we take the position that language models should primarily be used for structured extraction in deterministic enterprise workflows, while computation and storage are delegated to knowledge bases and symbolic procedures. We formally demonstrate that such modular architectures are more reliable and maintainable than monolithic frameworks, offering a sustainable foundation for enterprise tasks. --- ### Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning Authors: Valliappan Chidambaram Adaikkappan, David Meger, Sai Rajeswar, Pietro Mazzaglia Published: 2026-05-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.09364v1 This paper investigates robust representation learning in offline goal-conditioned reinforcement learning (GCRL). Particularly in sparse reward scenarios, learning representations that align state and goal latents is a challenge that frequently culminates in representation divergence where the encoder drifts toward a low-dimensional, goal-agnostic subspace that destabilizes policy learning. We address this issue by showing that an agent must acquire a fundamental understanding of its environment across multiple scales, from local physical dynamics to long-horizon goal-directed structure. Building on this insight, we propose Ms.PR, a framework that leverages multi-scale predictive supervision to enforce goal-directed alignment within the latent space. We demonstrate that Ms.PR leads to improved representation quality and strong performance on both vision and state-based tasks. Furthermore, we show that our approach is exceptionally resilient under realistic, challenging data regimes, maintaining state-of-the-art performance across a wide variety of tasks, trajectory stitching scenarios, and extreme noise conditions. --- ### Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions Authors: Soumita Hait, Ping Li, Haipeng Luo, Mengxiao Zhang Published: 2026-05-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.09363v1 Last-iterate convergence of learning dynamics in games has attracted significant recent attention. In two-player zero-sum games with bandit feedback, where only the loss of the selected action pair is observed, Fiegel et al. (2025) show a separation between average-iterate and last-iterate convergence in duality gap: while the optimal t^(-1/2) rate after t rounds is achievable for the former via standard no-regret algorithms, the latter cannot converge faster than t^(-1/3) in expectation or t^(-1/4) with high probability. However, in many practical settings, such as preference learning, the players observe not only their loss but also the opponent's action. This raises a natural question: can such additional information enable faster last-iterate convergence? We answer this question affirmatively, showing that t^(-1/2) last-iterate convergence is achievable with high probability in this setting, via an efficient algorithm that updates its strategy infrequently by solving an estimated log-barrier-regularized game. We identify fundamental obstacles preventing standard analysis for multi-armed bandits, the single-player case, from generalizing to games, and develop a novel analysis to overcome them. Experiments confirm that our algorithm indeed converges faster than naive baselines and prior methods that do not exploit opponent-action feedback. Finally, we note that our results also improve those for dueling bandits, a special case with skew-symmetric game matrices. --- ### FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printing Authors: Wenting Wang, Zhuo Huang, Kun Qian, Neelotpal Dutta, Yuhu Guo, Yingjun Tian, Yeung Yam, Charlie C. L. Wang Published: 2026-05-10 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2605.09362v2 We present FrameTwin, a curve-anchored Gaussian alignment framework that uses sparse-view images to close the control loop for adaptive wireframe 3D printing. Our key idea is to capture the deformation of thin wireframe structures from sparse-view images using Gaussian kernels anchored to parametric curves, yielding a compact and geometry-aware encoding that explicitly captures strut topology. Driven by a differentiable rendering pipeline, FrameTwin estimates a neural deformation field that aligns the partially printed target model with the deformed structure observed during fabrication, where the optimized curve-Gaussian representation serves as a digital twin of the evolving wireframe. Unlike general Gaussian-splatting approaches, our formulation constrains kernel placement along parametric curves, substantially reducing the ambiguity inherent in sparse-view observations of thin structures. The resultant deformation-field alignment enforces global consistency across all struts. By using the estimated deformation field to blend the distorted printed geometry with the remaining unprinted geometry, FrameTwin enables adaptive updates to future printing trajectories. We demonstrate that FrameTwin can robustly capture and compensate for deformation in wireframe models fabricated using a robotized 3D printing system. --- ### FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printing Authors: Wenting Wang, Zhuo Huang, Kun Qian, Neelotpal Dutta, Yuhu Guo, Yingjun Tian, Yeung Yam, Charlie C. L. Wang Published: 2026-05-10 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2605.09362v1 We present FrameTwin, a curve-anchored Gaussian alignment framework that uses sparse-view images to close the control loop for adaptive wireframe 3D printing. Our key idea is to capture the deformation of thin wireframe structures from sparse-view images using Gaussian kernels anchored to parametric curves, yielding a compact and geometry-aware encoding that explicitly captures strut topology. Driven by a differentiable rendering pipeline, FrameTwin estimates a neural deformation field that aligns the partially printed target model with the deformed structure observed during fabrication, where the optimized curve-Gaussian representation serves as a digital twin of the evolving wireframe. Unlike general Gaussian-splatting approaches, our formulation constrains kernel placement along parametric curves, substantially reducing the ambiguity inherent in sparse-view observations of thin structures. The resultant deformation-field alignment enforces global consistency across all struts. By using the estimated deformation field to blend the distorted printed geometry with the remaining unprinted geometry, FrameTwin enables adaptive updates to future printing trajectories. We demonstrate that FrameTwin can robustly capture and compensate for deformation in wireframe models fabricated using a robotized 3D printing system. --- ### Your Simulation Runs but Solves the Wrong Physics: PDE-Grounded Intent Verification for LLM-Generated Multiphysics Simulation Code Authors: Zhenghan Song, Yulong Liu, Cheng Wan, Chenjun Li, Lingfu Liu, Yunyi Li, Congcong Yuan Published: 2026-05-10 Categories: cs.LG, cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2605.09360v1 Execution-based evaluation of LLM-generated code implicitly treats successful execution as a proxy for correctness. In scientific simulation, this proxy is insufficient: a generated input file can run, mesh, and converge while encoding governing equations that differ from the user's intent. We call this mismatch between intended physics and generated code the comprehension-generation gap. We instantiate this in MOOSE, where Kernel and BC objects map compositionally to weak-form residual terms, enabling deterministic reconstruction of the encoded PDE and comparison against an intended contract. We formalize this comparison as the Intent Fidelity Score (IFS), a structural metric covering governing terms, BCs, ICs, coefficients, and time scheme. Building on IFS, we develop a PDE-grounded refinement loop that uses deterministic violation reports to correct generated code iteratively. We evaluate on MooseBench, a 220-case multiphysics benchmark with PDE-level ground truth released with this work. On this benchmark, our method consistently improves mean IFS over direct generation, with gains concentrated on hard cases. On the subset where direct generation falls below IFS 0.7, refinement adds +0.22 to +0.41 absolute IFS. In the deployment audit, execution-only repair improves execution success while leaving 39-40% of all 220 cases runnable but still solving the wrong physics across the three main deployment-audit models, exposing executability and intent fidelity as separable failure modes. Static proof-of-concept experiments on four PDE-oriented DSLs (UFL/FEniCS, FreeFEM, FiPy, and Devito) suggest that the reconstruction-and-comparison pattern extends beyond MOOSE. These findings reinforce that executable simulation code should be verified against the mathematical structure it is intended to encode, not accepted on execution alone. --- ### Skill-R1: Agent Skill Evolution via Reinforcement Learning Authors: Yash Vishe, Rohan Surana, Xunyi Jiang, Zihan Huang, Xintong Li, Nikki Lijing Kuang, Tong Yu, Ryan A. Rossi, Jingbo Shang, Julian McAuley, Junda Wu Published: 2026-05-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.09359v1 Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself, which is costly, model-specific, and often infeasible for closed-source models. Skill optimization is not a one-step problem but a recurrent process with two coupled levels of credit assignment: a useful skill must improve rollout quality under current conditioning, while a useful revision must turn observed outcomes into a better skill for the next round. We propose Skill-R1, a reinforcement learning framework for instance-level recurrent skill optimization from verifiable rewards. Rather than updating the task LLM, Skill-R1 trains a lightweight skill generator that conditions on the task context, prior rollouts, and their verified outcomes to produce skills that steer a frozen task LLM. This preserves black-box compatibility with both open- and closed-source models while making adaptation substantially cheaper than model-level updates. Skill-R1 proceeds over multiple generations: at each step, the current skill induces rollouts whose verified outcomes are fed back to produce the next revision. To optimize this recurrent process, we introduce a bi-level group-relative policy optimization objective combining intra-generation and inter-generation advantages. The intra-generation term compares rollouts under shared skill conditioning, while the inter-generation term rewards revisions that improve behavior across successive generations. Together, these provide a principled objective for directional skill evolution rather than one-shot self-refinement. Empirically, Skill-R1 achieves consistent gains over no-skill baselines and standard GRPO across benchmarks with verifiable rewards, with particularly strong improvements on complex, multi-step tasks. --- ### Split CNN Inference on Networked Microcontrollers Authors: Junyu Lu, Shashwath Suresh, Hao Liu, Qi Hong, Qing Wang Published: 2026-05-10 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2605.09357v1 Running deep neural networks on microcontroller units (MCUs) is severely constrained by limited memory resources. While TinyML techniques reduce model size and computation, they often fail in practice due to excessive peak Random Access Memory (RAM) usage during inference, dominated by intermediate activations. As a result, many models remain infeasible on standalone MCUs. In this work, we present a fine-grained split inference system for networked MCUs that enables collaborative inference of Convolutional Neural Networks (CNN) models across multiple devices. Our key insight is that breaking the memory bottleneck requires splitting inference at sub-layer granularity rather than at layer boundaries. We reinterpret pre-trained models to enable kernel-wise and neuron-wise partitioning, and distribute both model parameters and intermediate activations across multiple MCUs. A lightweight, resource-aware coordinator orchestrates the inference across MCU devices with heterogeneous resources. We implement the proposed system on a real testbed and evaluate it on up to 8 MCUs using MobileNetV2, a representative CNN model. Our experimental results show that CNN models infeasible on a single MCU can be executed across networked MCUs, reducing the per-MCU peak RAM usage while maintaining the practical end-to-end inference latency. All the source code of this work can be found here: https://github.com/shashsuresh/split-inference-on-MCUs. --- ### Function-Space ADMM for Decentralized Federated Learning: A Control Theoretic Perspective Authors: Akihito Taya, Yuuki Nishiyama, Kaoru Sezaki Published: 2026-05-10 Categories: cs.LG, cs.NI arXiv: https://arxiv.org/abs/2605.09356v1 Decentralized federated learning (FL) is a promising approach for training machine learning models on sensor networks, Internet of Things (IoT) devices, and other edge systems where no central server exists. While federated learning offers advantages such as preserving data privacy, it often suffers from non-independent and identically distributed (IID) data distributions across devices, which cause significant performance degradation. This issue is particularly severe when directly optimizing model parameters, because neural network training is inherently non-convex and standard convergence guarantees for convex optimization do not apply. Unlike existing decentralized FL methods that primarily operate in parameter space, we propose federated function-space alternating direction method of multipliers (FedF-ADMM). FedF-ADMM exploits the convexity of loss functionals within function space to derive alternating direction method of multipliers (ADMM)-based update directions, which are subsequently projected onto the parameter space via knowledge distillation. We further introduce a stabilization coefficient to enhance robustness under severe non-IID settings and analyze its behavior from a control-theoretic perspective by interpreting it as a proportional-integral (PI) term. Experiments under challenging non-IID scenarios, including settings where each device has data from only a single label, demonstrate that FedF-ADMM achieves faster and more stable convergence than existing decentralized FL methods, while attaining higher accuracy and better consensus among devices. --- ### FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning Authors: Xing Han, Shravan Chaudhari, Tanvi Ranade, Rama Chellappa, Suchi Saria Published: 2026-05-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.09355v2 Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, tasks are co-available at design time where related tasks could borrow representational strength from one another, (2) continual adaptation, in which new tasks emerge after deployment with previously unseen modality combinations. However, neither regime alone suffices: the pretraining task set is never exhaustive, while bypassing joint training forfeits the transfer gains and efficiency among co-trainable tasks. Sparse Mixture-of-Experts (MoE) is a natural fit for this dual requirement: sparse activation enables modular capacity expansion as new tasks arrive, while routing decouples modality-level computation from task-level composition. In this work, we propose a scalable MoE framework for multitask pretraining and continual learning across flexible modality combinations. The framework is designed to support training on multimodal tasks with diverse modality configurations by leveraging modality-specific routers that process tokens from each modality across tasks. Furthermore, it enables continual learning over sequential multimodal tasks within a fixed-capacity MoE by compressing accumulated expert knowledge into low-rank memory subspaces, while expanding only the lightweight routers. We validate the effectiveness of our method on multiple healthcare multimodal benchmarks. It demonstrates competitive multitask pretraining performance while alleviating catastrophic forgetting and improving parameter efficiency. --- ### FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning Authors: Xing Han, Shravan Chaudhari, Tanvi Ranade, Rama Chellappa, Suchi Saria Published: 2026-05-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.09355v1 Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, tasks are co-available at design time where related tasks could borrow representational strength from one another, (2) continual adaptation, in which new tasks emerge after deployment with previously unseen modality combinations. However, neither regime alone suffices: the pretraining task set is never exhaustive, while bypassing joint training forfeits the transfer gains and efficiency among co-trainable tasks. Sparse Mixture-of-Experts (MoE) is a natural fit for this dual requirement: sparse activation enables modular capacity expansion as new tasks arrive, while routing decouples modality-level computation from task-level composition. In this work, we propose a scalable MoE framework for multitask pretraining and continual learning across flexible modality combinations. The framework is designed to support training on multimodal tasks with diverse modality configurations by leveraging modality-specific routers that process tokens from each modality across tasks. Furthermore, it enables continual learning over sequential multimodal tasks within a fixed-capacity MoE by compressing accumulated expert knowledge into low-rank memory subspaces, while expanding only the lightweight routers. We validate the effectiveness of our method on multiple healthcare multimodal benchmarks. It demonstrates competitive multitask pretraining performance while alleviating catastrophic forgetting and improving parameter efficiency. --- ### The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence? Authors: Zhaoyang Zhang, Run Shao, Dongyue Wu, Jiajie Teng, Chao Tao, Jingdong Chen, Haifeng Li Published: 2026-05-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.09352v1 Understanding why independently trained neural networks from different modalities converge toward shared representations, and where this convergence leads, remains an open question in representation learning. All existing evidence relies on symmetric similarity measures, which can detect convergence but are structurally blind to its direction. We introduce directional convergence analysis using cycle-kNN, an asymmetric alignment measure, applied across dozens of independently trained unimodal models spanning point clouds, vision, and language. We uncover a consistent directional asymmetry: non-language modalities move toward the neighborhood structure of language significantly more than the reverse, and this pattern holds across all model families and scales--yet is entirely invisible to symmetric measures. Mechanistic analysis traces the directionality to feature density asymmetry, whereby language representations occupy the most compact regions of representational space. The Information Bottleneck framework provides a principled interpretation: optimization under compression drives representations toward discrete, compositional structures characteristic of language. We formalize this as the Wittgensteinian Representation Hypothesis: the semantic structure of language is the asymptotic attractor of multimodal representation convergence. --- ### CHAINTRIX: A multi-pipeline LLM-augmented framework for automated smart-contract security auditing Authors: Gabriela Dobrita, Simona-Vasilica Oprea, Adela Bara Published: 2026-05-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.09350v1 Smart-contract exploits have caused billions of USD in cumulative losses, yet audits remain expensive and slow. Automated tools have emerged to close this gap, but each class has a characteristic failure mode. Static analyzers report findings that frequently fail manual triage at high rates, while large language models (LLMs) hallucinate findings that contradict the source code. Thus, we propose Chaintrix, an end-to-end auditing framework whose central architectural commitment is that every LLM-generated claim must be discharged against a deterministic structural contract representation. We introduce a Cross-Contract Interaction Model (CCIM) that parses Solidity into a structured map of function-level reads, writes, modifiers and resolved cross-contract calls. CCIM serves as the substrate against which all 12 of Chaintrix's deterministic signal engines and the parallel LLM audit pipelines operate. A staged false-positive-reduction pipeline, terminating in a Structural Verdict Engine (SVE) that applies deterministic structural checks against parsed code, filters the merged finding set, with selected high-confidence findings further validated through symbolic execution and fuzz testing. We evaluate Chaintrix on EVMbench, the smart-contract security benchmark by OpenAI, Paradigm, OtterSec. Chaintrix detects 86 of 120 high-severity vulnerabilities (71.7% recall), with 25 audits scoring 100% recall, placing Chaintrix 26 percentage points above the strongest frontier-model baseline. --- ### Mutual Information Optimal Density Control of Linear Systems and Generalized Schrödinger Bridges with Reference Refinement Authors: Shoju Enami, Kenji Kashima Published: 2026-05-10 Categories: math.OC, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2605.09349v1 We consider a mutual information (MI) regularized version of optimal density control of a discrete-time linear system. MI optimal control has been proposed as an extension of maximum entropy optimal control to trade off between control performance and benefits provided by stochastic inputs. MI regularization induces stochasticity in the policy, which poses challenges for applications of MI optimal control in safety-critical scenarios. To remedy this situation, we impose Gaussian density constraints at specified times to directly control state uncertainty. For this MI optimal density control problem, we propose an alternating optimization algorithm and derive the closed form of each step in the algorithm. In addition, we reveal that the alternating optimization of the MI optimal density control problem coincides with that of the so-called generalized Schrödinger bridge problem associated with the discrete-time linear system. --- ### HOME-KGQA: A Benchmark Dataset for Multimodal Knowledge Graph Question Answering on Household Daily Activities Authors: Shusaku Egami, Aoi Ohta, Tomoki Tsujimura, Masaki Asada, Tatsuya Ishigaki, Ken Fukuda, Masahiro Hamasaki, Hiroya Takamura Published: 2026-05-10 Categories: cs.CL, cs.AI, cs.DB, cs.MM arXiv: https://arxiv.org/abs/2605.09348v1 Large Language Models (LLMs) provide flexible natural language processing capabilities, while knowledge graphs (KGs) offer explicit and structured knowledge. Integrating these two in a complementary manner enables the development of reliable and verifiable AI systems. In particular, knowledge graph question answering (KGQA) has attracted attention as a means to reduce LLM hallucinations and to leverage knowledge beyond the training data. However, existing KGQA benchmark datasets are biased toward encyclopedic knowledge, limited to a single modality, and lack fine-grained spatiotemporal data, which limits their applicability to real-world scenarios targeted by Embodied AI. We introduce HOME-KGQA, a novel KGQA benchmark dataset built on a multimodal KG of daily household activities. HOME-KGQA consists of complex, multi-hop natural language questions paired with graph database query languages. Compared to existing benchmarks, it includes more challenging questions that involve multi-level spatiotemporal reasoning, multimodal grounding, and aggregate functions. Experimental results show that the LLM-based KGQA methods fail to achieve performance comparable to that on existing datasets when evaluated on HOME-KGQA. This highlights significant challenges that should be addressed for the real-world deployment of KGQA systems. Our dataset is available at https://github.com/aistairc/home-kgqa --- ### Dsat: A Native SAT Solver for Discrete Logic Authors: Yaofang Zhang, Ken Zhou, Adnan Darwiche Published: 2026-05-10 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2605.09347v1 Discrete variables are common in many applications, such as probabilistic reasoning, planning and explainable AI. When symbolic reasoning techniques are brought in to bear on these applications, a standard technique for handling discrete variables is to binarize them into Boolean variables to allow the use of Boolean computational machinery such as SAT solvers. This technique can face both computational and semantical challenges though. In this work, we develop a native SAT solver for discrete logic, which is a direct extension of Boolean logic in which variables can take arbitrary values. Our proposed solver has a similar design to Boolean SAT solvers, with ingredients such as unit resolution and clause learning but ones that operate natively on discrete variables. We illustrate the merits of the developed SAT solver by comparing it empirically to CSP solvers applied to discrete CNFs, to Boolean SAT solver applied to binarized CNFs, and to some hybrid solvers. --- ### RuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step Authors: Xiaocheng Luo, Kang Wang, Zaifu Zhan, Yuechi Zhou, Xiangyu Duan Published: 2026-05-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.09346v1 The Chain-of-Thought (CoT) paradigm, while enhancing the interpretability of Large Language Models (LLMs), is constrained by the inefficiencies and expressive limits of natural language. Latent Chain-of-Thought (latent CoT) reasoning, which operates in a continuous latent space, offers a promising alternative but faces challenges from structural complexities in existing multi-step or multi-model paradigms, such as error propagation and coordination overhead. In this paper, we introduce One-Model One-Step, a novel compression framework for Latent Reasoning with Rule-Based Priors(RuPLaR) to address this challenge. Our method trains an LLM to autonomously generate latent reasoning tokens in a single training stage, guided by rule-based prior probability distributions, thereby eliminating cascaded processes and inter-model dependencies. To ensure reasoning quality, we design a joint training objective that enforces answer consistency via cross-entropy, aligns soft tokens with rule-based priors via KL divergence (the Soft Thinking constraint), and adds a problem-thought semantic alignment constraint in the representation space. Extensive experiments show that our compression framework not only improves accuracy by 11.1% over existing latent CoT methods but also achieves this with minimal token usage, underscoring its effectiveness and extensibility. Code: https://github.com/xiaocen-luo/RuPLaR. --- ### Selection Plateau and a Sparsity-Dependent Hierarchy of Pruning Features Authors: Guangqi Li, Yongxin Li Published: 2026-05-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.09345v1 We identify a Selection Plateau phenomenon in one-shot neural network pruning: all rank-monotone weight scorers converge to identical accuracy at fixed sparsity, independent of functional form. We propose the Sparsity-Information-Complexity Spectrum (SICS) hypothesis: a sparsity-dependent minimum feature complexity kappa(S) governs plateau escape, with kappa=0 sufficient at low sparsity (S<0.65), kappa=1 dominant at critical sparsity (S~0.7), and kappa=2 necessary at extreme sparsity (S>0.75). On ViT-Small/CIFAR-10, testing nine feature classes across four sparsities, smooth non-monotone features provide +6.6% escape at S=0.7, while only raw features with high-frequency wiggle escape at S=0.8 (+2.6%). A fake non-monotone scorer underperforms the gradient baseline, indicating the requirement is magnitude-independent non-monotonicity. A handcrafted Gaussian bump achieves only +0.006 escape vs. chaos-derived +0.046, indicating rank-alignment is necessary but insufficient. SICS provides a unifying explanation for the performance clustering of diverse pruning methods and suggests that future selection algorithms should adapt feature complexity to target sparsity. --- ### SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making Authors: Zeyu Li, Lei Li Published: 2026-05-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.09343v1 Decision making in large-scale complaint handling systems increasingly relies on heterogeneous evidence, including complaint narratives, screenshots, order metadata, historical interactions, and platform policies. Existing complaint understanding systems mainly perform shallow classification or template matching over isolated modalities, while underutilizing explicit scene structure, rule knowledge, and cross-evidence dependencies. To address this limitation, we present SKG-VLA for multimodal complaint decision making. The core idea is to model each case as a structured complaint scene and represent its decision-relevant semantics with a \emph{Scene Knowledge Graph} (SKG), which organizes complaint entities, evidence items, policy clauses, temporal events, transactional states, and action-relevant relations into a unified graph. Based on SKG, we build a data synthesis pipeline that generates complaint scene descriptions, rule-consistent graph generalizations, question-answer supervision, and decision recommendations. We further construct a large-scale complaint scene dataset with both text-only and multimodal in-domain benchmarks. Finally, we adopt a three-stage training strategy -- domain-adaptive pre-training, task-oriented instruction fine-tuning, and end-to-end multimodal alignment -- to inject structured scene priors into a multimodal decision model. Experiments show that SKG-VLA consistently improves policy-grounded reasoning, complaint decision accuracy, long-tail generalization, and robustness under incomplete evidence. --- ### A Cross-Layered Multi-Drone Coordination for Medical Supply Delivery during Disaster Response Management Authors: Aneesh Calyam, Subrahmanya Chandra Bhamidipati, Zack Murry, Sharan Srinivas Published: 2026-05-10 Categories: cs.MA, cs.LG arXiv: https://arxiv.org/abs/2605.09342v1 Autonomous drone fleets have immense potential in medical supply delivery during disaster incident response. However, coordinating multiple drones in such settings introduces compounding challenges: dynamic environmental hazards such as wind, obstacles, and intermittent network connectivity, constrained energy budgets, and the need to serve patient locations fairly under deadlines and triage-based priority while optimizing schedule utilization. In this paper, we present CEDA, a novel CTDE Deep Q-Network algorithm for cooperative multi-drone medical delivery, designed to jointly optimize triage-priority-aware routing, multi-agent coordination, and energy-efficient navigation under dynamic uncertainty. CEDA introduces a Priority-Preserving Fair Scheduling strategy, in which a structured reward function encodes both triage weights and complementary fairness mechanisms ensuring no patient class is starved of service. We evaluate CEDA in a simulated grid environment featuring dynamic hazard zones, stochastic action failures, and dynamically spawning patients across three triage priority levels, as well as in a PX4 SITL validation using two X500 quadrotors controlled via MAVSDK in offboard position mode. Simulation results demonstrate that CEDA achieves a delivery completion rate above 85%, reduces obstacle collisions by over 90% across training, and delivers an average of 6 patients per episode with a triage efficiency of 0.82. CEDA preserves clinical priority ordering, Critical patients are served first, while achieving near-zero mortality across lower-triage classes, confirming that priority-weighted routing does not condemn Stable or Urgent patients to neglect. PX4 SITL validation further demonstrates that the learned policy remains executable and triage-coherent under practical communication constraints and realistic multi-drone coordination in disaster response settings. --- ### SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System Authors: Shuai Pan, Yixiang Liu, Jiaye Gao, Te Gao, Weiwen Liu, Jianghao Lin, Zhihui Fu, Jun Wang, Weinan Zhang, Yong Yu Published: 2026-05-10 Categories: cs.MA, cs.CL arXiv: https://arxiv.org/abs/2605.09341v2 Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targets: skill evolution and multi-agent system (MAS) restructuring. This separation can create organization bottlenecks, context pressure, and mis-specialization. We present SkillMAS, a non-parametric framework for adaptive specialization in multi-agent systems that couples skill evolution with MAS restructuring. SkillMAS uses Utility Learning to assign credit from verified execution traces, bounded skill evolution to refine reusable procedures without unfiltered library growth, and evidence-gated MAS restructuring when retained failures and Executor Utility indicate a structural mismatch. Across embodied manipulation, command-line execution, and retail workflows, SkillMAS is competitive under the reported harnesses while clarifying how post-deployment specialization is attributed, updated, and applied. --- ### Perceptual Asymmetry Between Hue Categories: Evidence from Human Color Categorization Authors: Elnara Kadyrgali, Nuray Toganas, Muragul Muratbekova, Pakizar Shamoi Published: 2026-05-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.09339v1 Human color categories are not uniformly distributed in perceptual space, yet most computational color models still assume fixed and evenly structured representations. In this paper, we present a focused analytical extension of the COLIBRI fuzzy color model by investigating perceptual asymmetry between hue categories. Using previously collected large-scale human color categorization data, we introduce quantitative measures of category extent and boundary uncertainty, namely Wideness and Boundary Width, derived from fuzzy membership functions at the α = 0.5 level. The analysis reveals a strong imbalance between the two categories: yellow occupies a compact and sharply constrained region of the hue space, whereas green spans a substantially broader interval and exhibits a more extended transition structure. The results show that perceptual color categories are not only fuzzy, but also highly non-uniform in their geometric organization. This asymmetry suggests that some categories behave as narrow, highly specific perceptual labels, while others function as broad, tolerant regions of human color naming. These findings provide a new perspective on linguistic color categorization and extend the interpretability of the COLIBRI framework for perceptually grounded color modeling. --- ### Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates Authors: Anik Kumar Paul, Nibedita Roy, Nagesh Talagani, Swetha Ganesh, Gugan Thoppe, Alexandre Reiffers-Masson Published: 2026-05-10 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2605.09337v1 We propose FAR-SIGN (Fully Asynchronous Robust optimization via SIGNed directional projections) for adversary-resilient learning in parameter-server--worker systems. FAR-SIGN achieves robustness through sign-based updates along carefully designed directions and mitigates the resulting bias via a two-timescale mechanism. It admits both first-order and zeroth-order implementations and enables fully asynchronous execution without requiring a private reference dataset at the server. We establish almost-sure convergence of FAR-SIGN to the set of stationary points for smooth, nonconvex objectives. Moreover, we prove the near-optimal rate of $O(n^{-1/4+ε})$ in the first-order setting and the standard $O(n^{-1/6+ε})$ in the zeroth-order setting, where $n$ is the iteration count and $ε>0$ can be chosen arbitrarily small. Experiments on MNIST show that FAR-SIGN outperforms robust aggregation-based methods in both accuracy and wall-clock time. --- ### Functional Graphs for Predicting and Explaining Goal Failure in Sparse Goal-Conditioned RL Authors: Shalley Dash Published: 2026-05-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.09335v1 Sparse goal-conditioned reinforcement learning can produce policies whose failures are hidden by aggregate success rates. We analyze trained goal-conditioned value policies through the deterministic functional graphs induced by greedy evaluation: for each goal, every state maps to a single successor, decomposing behavior into attractors and basins. This reveals a local-to-global structure in learned policies. We define local goal support (LGS), a one-step statistic measuring the fraction of valid neighboring states whose greedy successor is the goal. In deterministic sparse GridWorlds, zero LGS exactly precludes goal entry from non-goal starts. Empirically, weak LGS is a strong diagnostic of goal-level failure across update rules, curricula, larger grids, and bottleneck geometries: the fixed rule LGS <= 0.5 identifies low-success goals with precision 0.921, recall 0.929, and F1 0.925 in the main 8x8 TD setting, with similar performance across variants. However, local support is not sufficient for global success: some supported goals still fail because distant states are captured by competing attractors or fragmented basin structure. We therefore introduce a compact post-hoc taxonomy of policy-induced graphs -- goal-dominant, competitor-dominated, partial/contested, and fragmented -- to characterize residual failure modes beyond local support. These results show that sparse GCRL failures can be understood as structured policy-induced dynamics, and that local one-step policy structure provides a cheap post-training diagnostic for goal-level failure. --- ### Dimension-Free Saddle-Point Escape in Muon Authors: Yanlin Long, Yufei Gu, Zeke Xie Published: 2026-05-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.09331v1 Modern Large Language Model (LLM) training is fundamentally bottlenecked by pathologically flat saddle points in extreme high-dimensional landscapes. Motivated by this challenge, we analyze the saddle-point escape dynamics of the emerging Muon optimizer, demonstrating its resilience against the $\mathcal{O}(D)$ dimensional curse that severely traps element-wise adaptive optimizers like AdamW. By extending generalized matrix perturbation theory, we develop a theoretical framework to capture Muon's non-equilibrium optimization trajectories. This theoretical machinery mathematically proves that Muon elegantly bypasses the dimensional curse via a non-linear spectral shaping mechanism. By leveraging resolvent functional calculus and macroscopic Cauchy contour integration, we avoid isotropic noise assumptions and Tracy-Widom edge singularities. We establish that structural incoherence securely shields the trajectory from orthogonal drift, enabling a dimension-free saddle-point escape, and triggering a deterministic $\mathcal{O}(1)$ discrete ballistic ejection under sufficient spectral gap. Consequently, we provide an algebraically dimension-free escape bound for Muon, formalizing the underlying mechanics of its non-convex optimization dynamics. --- ### The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory Authors: Luoxi Tang, Rupali Rajendra Vaje, Yuqiao Meng, Sakshi Sunil Narkar, Weicheng Ma, Zeyu Ding, Dazheng Zhang, Zhaohan Xi Published: 2026-05-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.09330v1 Agentic memory enables LLMs to persist information beyond a single context window and reuse it in later decisions, but it also introduces a new vulnerability: spurious correlations, where retrieved memory carries miscorrelated evidence and propagates erroneous reasoning into downstream decisions. Despite the widespread use of agentic memory, this risk remains largely underexplored. We address it from two aspects. First, we benchmark several canonical types of spurious patterns identified through causal structure and record them across trajectory-level memory. Diagnosing agentic memory systems on this benchmark reveals that memory improves reasoning on clean inputs but amplifies reliance on spurious patterns when they are present. Second, we propose CAMEL, a plug-and-play calibration method that operates across diverse memory architectures at both write and retrieval time. CAMEL consistently reduces reliance on spurious patterns across all three types while preserving or improving performance on clean inputs and staying robust under adaptive attacks targeting the calibration. Overall, CAMEL offers a principled and lightweight solution toward more reliable agentic memory deployment. ---