# Research Papers — 2026-05 · bundle page 50 of 326 > Full-text markdown of papers #2451–2500 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/50 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/49.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/51.md) ### Stability of Low-Rank Implicit Regularization in Perturbed Deep Matrix Factorization Authors: Jingzhe Wang, Hung-Hsu Chou Published: 2026-05-27 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.28613v2 This paper studies the stability of low-rank implicit regularization in deep matrix factorization, a tractable model for understanding how gradient-based training can favor low-complexity structure. We first revisit the noiseless setting and derive sufficient spectral conditions under which gradient descent exhibits a nonempty low-rank interval. These conditions clarify how the target spectrum, initialization, and step size jointly determine when a low-rank phase is observable along the optimization trajectory. We then analyze the perturbed problem, where the target matrix is subject to an additive perturbation. By studying the perturbed gradient descent dynamics at the eigenvalue level, we prove convergence guarantees and quantify how the perturbation size affects iteration complexity and eigenvalue recovery. Finally, we establish stability of the low-rank phase under perturbation: the effective rank of the iterates remains close to that of the rank-L approximation of the noiseless target over a perturbed low-rank interval, with explicit dependence on the perturbation size. Numerical illustrations support the theoretical predictions and illustrate the role of spectral structure in determining when this stability is observed. --- ### Learning High-Dimensional Parity Functions with Product Networks using Gradient Descent Authors: Guillaume Larue, Louis-Adrien Dufrène, Quentin Lampin, Hadi Ghauch, Ghaya Rekaya Published: 2026-05-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28612v1 Parity functions are fundamental Boolean operations with critical applications across machine learning, cryptography, and error correction. Yet, learning high-dimensional parity functions poses significant challenges: in a general setting, standard neural network architectures typically require exponential sample complexity, making gradient-based optimization intractable for large number of inputs $N$. We demonstrate that compact product-based neural architectures combined with stochastic data sparsity (Bernoulli inputs with $p_e \leq 1/N$) and appropriate hyperparameter choice enable efficient parity learning, with theoretical guarantees of convergence. Experiments validate our theory across dimensions up to $N = 100{,}000$, with empirical evidence showing optimal hyperparameter choices for $p_e$ and learning rate $α$, as well as polynomial complexity scaling laws. This work establishes fundamental connections between architectural inductive bias and data sparsity, opening new possibilities for neural arithmetic, structured reasoning, binary neural networks, and machine learning applied to automated protocol discovery. --- ### JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models Authors: Jiachen Qian Published: 2026-05-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.28609v1 Forensic vision-language models (VLMs) have recently been developed to detect image tampering and provide natural-language explanations. However, their robustness against adversarial manipulation remains underexplored. Existing adversarial attacks typically aim to flip the model's binary judgment, while the accompanying explanation may still reveal forensic cues and contradict the attacked judgment. In this paper, we study judgment-explanation consistent adversarial attacks against forensic VLMs and propose JECA^2, a controlled white-box red-team diagnostic that jointly redirects visual attribution and aligns textual explanations with the target judgment. On the visual side, JECA^2 uses Grad-CAM-guided perturbations to divert attribution from tampered regions toward benign regions. On the textual side, it optimizes prompt embeddings toward authenticity-affirming semantics under a token-proximity constraint. Experiments on forensic VLM benchmarks show that JECA^2 achieves higher attack success and automated judgment-explanation consistency than implemented baselines under white-box threat settings, while transfer to closed-source VLMs remains measurable but limited. Our results highlight a consistency failure mode in explanation-based forensic VLMs and motivate future robustness evaluation beyond binary detection accuracy. --- ### Adaptive Multimodal Agents-Based Framework for Automatic Workflow Execution Authors: Susanna Cifani, Mario Luca Bernardi, Marta Cimitile Published: 2026-05-27 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.28607v1 Modern information systems require autonomous agents capable of navigating complex workflows, yet current methodologies often struggle with the transition from structured metadata parsing to general environmental perception. While the integration of MLLMs has enabled agents to interact directly with GUIs, existing approaches typically treat task sequences as discrete, linear episodes. This fragmentation prevents agents from capturing the underlying transition topology, limiting their effectiveness in novel or non-stationary scenarios. To address this, we propose a novel multimodal multi-agent framework that achieves automatic workflow execution through a distinct two-phase pipeline. First, during an offline discovery phase, the architecture adaptively constructs a topological knowledge base from fragmented execution logs. During inference, agents leverage Adaptive Retrieval-Augmented Generation (RAG) over this fixed, pre-established graph, coupled with a closed-loop collaborative verification protocol to dynamically self-correct and navigate. This graph-based approach facilitates superior task decomposition and adaptive navigation performance. We validate our framework in a real-world context, demonstrating its ability to maintain high reliability and semantic awareness even with limited training data. --- ### Internally Referenced Low-Light Enhancement Authors: Peiyuan He, Hainuo Wang, Hengxing Liu, Mingjia Li, Xiaojie Guo Published: 2026-05-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.28605v1 Self-supervised low-light image enhancement (LLIE) is highly appealing as it eliminates the reliance on external paired data. However, the lack of external references causes networks to struggle with decoupling entangled illumination, delicate textures, and amplified noise. To resolve this challenge, we propose an Internally Referenced LLIE framework that extracts reliable physical and structural references from the degraded input image itself. First, we introduce a local exposure-simulated scheme to extract a low-frequency pseudo ground-truth. This serves as an internal physical reference to guide global illumination estimation and correct color casts. Second, we propose a dual-domain preservation strategy with spatial and spectral constraints to construct internal structural references. Specifically, an Illumination-Aligned Perceptual loss preserves global structures under illumination shifts, while a Shift-Invariant Spectral Correlation loss captures fine-grained local structures and suppresses high-frequency noise. Finally, we propose a Gain-Adaptive Feature Modulation (GAFM) mechanism to address highly spatially-variant residual noise. By transforming the self-estimated illumination map into an internal spatial gain prior, GAFM dynamically guides a blind-spot network for spatially-aware denoising. Extensive experiments demonstrate that our method achieves state-of-the-art performance, delivering superior noise suppression and textural fidelity. Code will be publicly released at https://visonj.github.io/IRLE/. --- ### Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification Authors: Xiao Wang, Minglei Yang, Bin Yang, Wenke Huang, Zheng Wang, Xin Xu, Mang Ye Published: 2026-05-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.28604v1 Identifying key individuals in video scenes is essential for applications such as automated video editing and intelligent surveillance. Current methods primarily focus on static images and immediate visual cues, overlooking the rich spatio-temporal information in videos. This leads to the phenomenon of Temporal Importance Shift (TIS), wherein individuals deemed significant in early frames may be demoted as the entire temporal context is considered. To address this, we introduce the Video Important Person (VIP) identification task, aimed at automatically identifying the most influential individuals in videos while providing textual rationales. We present Temporal-VIP, a large-scale rationale-annotated dataset consisting of 9,249 video segments across 11 categories with aligned importance rationales. To mitigate TIS, we develop the VIP-Net framework, which includes a Social Cue Encoder (SCE) for extracting multi-modal spatio-temporal cues, a Temporal Importance Rectifier (TIR) for hierarchical cue fusion and cross-modal alignment, and VIP Inference for ranking individuals. Experimental results show that VIP-Net achieves 67.3% accuracy, significantly outperforming state-of-the-art models (37.5%-53.9%) and yielding a mean rationale similarity of 0.63 to ground truth through feature-guided LLM refinement. The dataset and code are available at https://huggingface.co/datasets/yml2002/Temporal-VIP. --- ### Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert Calibration Authors: Haonan Wen, Hanyang Chen, Songhe Feng Published: 2026-05-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.28603v1 Irregular multivariate time series forecasting is critical in many real-world applications, where time series are irregularly sampled and exhibit dynamically evolving missingness patterns. Although existing methods perform well in offline settings, they often suffer from significant performance degradation when deployed online due to dynamic shifts in data distribution. Maintaining forecasting capability in such dynamic scenarios typically necessitates online adaptation techniques. Since irregular sampling fundamentally undermines temporal continuity and periodicity, we cannot leverage these widely studied characteristics from regular MTS for online learning. To this end, we study the problem of online IMTS forecasting and propose Under-Cali, an uncertainty-driven dual-expert calibration framework consisting of three core components: an uncertainty estimator, a dual-expert calibration module, and an adaptive routing module. We design an uncertainty estimator that serves as the core control signal to jointly manage inference and adaptation processes. In our framework, the uncertainty estimator first assesses uncertainty for each incoming batch. The adaptive routing module then directs samples with high uncertainty to the unreliable expert for calibration, while low uncertainty samples remain with the reliable expert. Subsequently, the system updates the reliable expert and the uncertainty estimator using well-calibrated reliable samples, and updates the unreliable expert with challenging samples, enabling stable and efficient online learning. Under-Cali keeps the source forecasting model frozen and performs adaptation only through a lightweight, model-agnostic calibration module, enabling efficient adaptation. Extensive experiments on IMTS benchmarks demonstrate consistent improvements with low computational cost. Our code is available at https://github.com/HaonanWen/Under-Cali. --- ### Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability Authors: Leizhen Zhang, Shuhan Chen, Sheng Chen Published: 2026-05-27 Categories: cs.AI, cs.CL, cs.LO arXiv: https://arxiv.org/abs/2605.28602v1 Large language models (LLMs) are increasingly used for tasks that implicitly reduce to Boolean satisfiability (SAT), yet their reasoning ability on SAT remains unclear. We present a systematic study of LLMs on 2-SAT and 3-SAT, together with two canonical reductions, Vertex Cover and discrete 3D packing, to probe representation-invariant reasoning. We first evaluate models using conventional metrics, including accuracy, precision, recall, and F1, as well as the SAT phase-transition setting. We find that these metrics can be misleading: many models obtain high scores by over-predicting satisfiable formulas, fail to reproduce the classical easy-hard-easy signature around the 3-SAT threshold, and degrade sharply as the number of variables grows. To address this problem, we introduce a paired-formula protocol based on minimally different satisfiable and unsatisfiable instances, together with Accurate Differentiation Rate (ADR), which requires both members of each pair to be classified correctly. ADR separates reasoning-oriented models from heuristic ones and correlates with witness validity. Beyond CNF, we test cross-representation consistency by converting CNF to Vertex Cover and 3-SAT to discrete 3D packing. Model decisions on CNF and on the corresponding graph or packing instances agree for most models on more than 80 percent of instances, suggesting stable decision rules across representations. Overall, our results show that SAT is a conservative probe for LLM reasoning, and that paired evaluation with ADR provides a more faithful and representation-robust assessment than conventional metrics. --- ### Transformers Provably Learn to Internalize Chain-of-Thought Authors: Yixiao Huang, Hanlin Zhu, Zixuan Wang, Jiantao Jiao, Stuart Russell, Somayeh Sojoudi, Song Mei Published: 2026-05-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28600v1 Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducing the complexity of tasks like parity learning from exponential to polynomial in the input length. However, generating explicit reasoning steps at inference is computationally expensive. Implicit Chain-of-Thought (ICoT) has emerged as a promising empirical remedy that trains models to internalize intermediate steps within their hidden states, but its theoretical foundations remain poorly understood. We give the first theoretical analysis of ICoT, proving that an $L$-layer transformer trained under our proposed Log-ICoT curriculum learns $k$-parity with $\mathsf{poly}(n)$ samples and $L = \log_2 k$ training stages. This matches the sample efficiency of explicit CoT while eliminating its inference overhead, and extends prior one-layer parity guarantees to multi-layer architectures. Compared to standard ICoT, which removes thinking tokens one at a time, Log-ICoT removes them in geometric chunks, reducing the number of stages from linear in $k$ to logarithmic. Experiments on multi-layer transformers confirm the theory and visualize how reasoning is progressively absorbed into deeper layers. --- ### Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News Authors: Alejandro Buitrago López, Alberto Ortega Pastor, Javier Pastor-Galindo, José A. Ruipérez-Valiente Published: 2026-05-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.28598v1 LLM-powered social agents are increasingly used to simulate online social behavior, yet their realism remains difficult to validate. Existing work has largely relied on general-purpose benchmarks, while less attention has been paid to short, reactive discourse such as audience replies to online news. In this paper, we evaluate whether LLM-generated reactions to Spanish online news reproduce measurable properties of real audience discourse. Using the Hatemedia dataset, we pair 5,631 news items with 58,555 real audience reactions, and generate a matched synthetic dataset using five LLMs under a shared experimental setting. We compare real and synthetic reactions across three dimensions: hate speech, sentiment, and semantic alignment, considering both off-the-shelf and fine-tuned generation. Results show that off-the-shelf models are poor proxies for real audience reactions: they strongly underproduce hate speech, introduce model-specific sentiment biases, and remain distributionally distant from human replies. Fine-tuning improves fidelity unevenly. Qwen3 provides the most balanced approximation, while Mistral7B achieves the strongest sentiment and semantic alignment but overshoots hate prevalence. Plausible synthetic replies do not necessarily reproduce the distributional properties of public discourse. --- ### Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation Authors: Jianwei Li, Jung-Eun Kim Published: 2026-05-27 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.28597v1 This position paper argues that the AI/ML community should stop overclaiming and retire the label "positive backdoor," and instead treat trigger-activated hidden behaviors as Secret Alignment. Crucially, protective claims based on Secret Alignment should be presumed not secure by default unless supported by rigorous, standardized evaluation. The Private AI era, enabled by open-weight LLMs and accessible training/inference stacks, turns language models into privately owned digital assets, creating security concerns around unauthorized access, model theft, and behavioral misuse. Recently, a line of work framed as "positive backdoors" has been proposed to address these challenges. To ground our position in evidence, we unify these proposals as covert trigger-behavior associations for access gating, ownership attribution, and safety enforcement, and evaluate three representative applications across six core properties: effectiveness, harmlessness, persistence, efficiency, robustness, and reliability. Our results reveal substantial brittleness - especially in the confidentiality, integrity, and availability (CIA) - of trigger-behavior mappings often underrepresented by existing claims. We further relate these outcomes to behavior density and decision complexity, offering a behavioral lens for understanding deployment-time risks and motivating community-wide evaluation that makes Secret Alignment claims provable. --- ### Dark Quest II: A Wide-Coverage Neural Network Emulator of the Nonlinear Matter Power Spectrum Across Extended Cosmologies Authors: Satoshi Tanaka, Takahiro Nishimichi, Yosuke Kobayashi Published: 2026-05-27 Categories: astro-ph.CO, cs.LG arXiv: https://arxiv.org/abs/2605.28596v1 \textsc{DarkEmulator2} is a neural network emulator of the nonlinear matter power spectrum in a nine-dimensional $w_0 w_a νo \mathrm{CDM}$ parameter space, developed as the emulator component of the \textsc{Dark Quest II} (DQ2) program. It is trained on simulations generated with the \textsc{Ginkaku} code, whose numerical implementation, accuracy tests, and post-processing pipeline are described in the companion paper. The design follows a unified strategy: in addition to the cosmological parameter vector, we supplement the neural network's inputs with three families of physically motivated auxiliary quantities -- the linear matter power spectrum, descriptors of the simulation resolution, and a low-dimensional summary of the initial Gaussian random field -- that are expected to improve generalization across the parameter space. Training a single network jointly across three simulation resolution tiers allows the emulator to exploit a small number of high-resolution simulations while retaining broad coverage from lower-resolution simulations. For a $L_{\mathrm{box}}=1\,\hiGpc$ box with $N=3000^{3}$ particles, the emulator reproduces the simulated matter power spectrum to subpercent accuracy up to the particle Nyquist scale, $k_{\mathrm{Ny}}\simeq 10\,\hMpci$. The emulator remains accurate over the calibrated wavenumber range, while its highest-$k$ predictions depend on the simulation resolution and shot noise. We validate the emulator on independent test suites and, through a cross-comparison with several public emulators and widely used fitting formulas, characterize the inter-model consistency and the parameter-dependent trends in their residuals. --- ### Thermodynamic properties of chemically disordered compounds via AI-driven estimation of partition function with the PULSE method Authors: Baptiste Bernard, Luca Messina, Eiji Kawasaki, Emeric Bourasseau Published: 2026-05-27 Categories: cond-mat.stat-mech, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2605.28594v1 In this article, we present an improved version of the PULSE method (Partition function Unsupervised Learning Sampling and Evaluation) for estimating the thermodynamic properties of chemically disordered compounds. The aim is to reduce the computational cost of Monte Carlo approaches for this type of material and to demonstrate that this generative tool can estimate thermodynamic properties by sampling and estimating the partition function of the system. To validate this innovative approach, we use the 2D Ising model as a benchmark. We demonstrate that our method accurately reproduces average properties with high precision and efficiency compared to traditional Monte Carlo sampling methods. Our results highlight the efficiency and adaptability of the PULSE method, making it a valuable tool for studying materials for which conventional methods are too inefficient to compute properties affected by chemical disorder at low cost. --- ### PLS in the Mirror of Self-Attention Authors: Jiangsheng, You Published: 2026-05-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28592v1 This note provides an interesting observation on casting partial least square (PLS) as a linearized self-attention so that PLS may be studied within the neural network paradigm. On the other hand, the dimensionality reduction and selection of predictors in PLS may indicate that self-attention includes certain degree of dimensionality normalization toward improved learning. --- ### Models That Know How Evaluations Are Designed Score Safer Authors: Katharina Deckenbach, Haritz Puerto, Jonas Geiping, Sahar Abdelnabi Published: 2026-05-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.28591v4 The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or harmful requests. Evaluating this fine-tuned model on five safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge. --- ### Models That Know How Evaluations Are Designed Score Safer Authors: Katharina Deckenbach, Haritz Puerto, Jonas Geiping, Sahar Abdelnabi Published: 2026-05-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.28591v3 The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or moral dilemmas. Evaluating this fine-tuned model on five safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge. --- ### Thinned Mean Field Langevin Dynamics Authors: Zonghao Chen, Heishiro Kanagawa, François-Xavier Briol, Chris J. Oates, Lester Mackey Published: 2026-05-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28589v1 Several important learning tasks can be formulated as minimizing an entropy-regularized objective over an appropriate space of probability distributions. Mean-field Langevin dynamics (MFLD) facilitate computation in this general context, casting the minimizer as the invariant distribution of a McKean--Vlasov process, which can be numerically discretized using $N$ particles and thus simulated. However, simulating this interacting particle system has computational complexity of order $N^2$. Motivated by recent research into \emph{kernel thinning}, we propose \texttt{KT-MFLD}, in which each particle interacts only with a thinned particle coreset of size $\mathcal{O}(N^{\frac{1}{2}})$. \texttt{KT-MFLD} thus reduces the computational complexity to order $N^{\frac{3}{2}}$ while, under mild regularity conditions, achieving the same convergence guarantees (up to logarithmic factors) as MFLD. Our theoretical analysis is empirically confirmed on tasks including the training of student-teacher neural networks, quantization with maximum mean discrepancy, and computation of predictively-oriented posteriors in a post-Bayesian framework. --- ### Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem Authors: Luca Beurer-Kellner, Aleksei Kudrinskii, Marco Milanta, Kristian Bonde Nielsen, Hemang Sarkar, Liran Tal Published: 2026-05-27 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2605.28588v1 We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4% of all skills contain at least one critical-level security issue and at least 8 manually confirmed malicious skills remain publicly available on clawhub.ai as of the date of publication. This report documents our methodology, presents a threat taxonomy based on real-world samples, and details the attack patterns we observed. As skill marketplaces grow rapidly and AI agents gain access to sensitive credentials and systems, automated security analysis is no longer optional. --- ### Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation Authors: Yang Gao, Wuyang Li, Po-Chien Luan, Alexandre Alahi Published: 2026-05-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.28587v1 Understanding dynamic 3D environments is essential for safe autonomous driving, particularly when reasoning about human-centric, nonrigid agents. However, existing weakly supervised occupancy prediction frameworks predominantly assume rigid-body motion and rely on simple frame-to-frame offsets, limiting their ability to capture fine-grained deformations and maintain temporal coherence. To address this issue, we propose DeGO, a deformable Gaussian occupancy framework that unifies decoupled Gaussian deformation with factorized 4D foundation-model distillation. DeGO disentangles rigid and nonrigid motion, enabling each Gaussian primitive to evolve through both deformation and offset-based updates. In parallel, a factorized 4D distillation strategy transfers cross-camera and cross-frame knowledge from the VGGT foundation model, producing foundation-aligned features that enhance temporal consistency. Experiments on the Occ3D-NuScenes benchmark demonstrate that our method achieves state-of-the-art performance under weak supervision, delivering 13.5% gains on human-centric instances and 10.9% overall improvements. These results highlight the effectiveness of deformation-aware and foundation-guided occupancy modeling for dynamic scene understanding. The code is publicly available: https://github.com/vita-epfl/DeGO --- ### Outer-Momentum Restarting in High-Dimensional Two-Phase Optimization Authors: Kristi Topollai, Allan Ma, Tolga Dimlioglu, Sui Jiet Tay, Anna Choromanska Published: 2026-05-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28585v1 Communication-efficient distributed optimizers such as DiLoCo reduce synchronization costs by letting workers perform many local updates before aggregating their progress with an outer momentum optimizer. Recent theory suggests that the outer optimizer acts on an effective spectrum induced by the inner optimization loop, and that the choice of outer momentum controls how progress from local updates is accumulated across communication rounds. We study periodic restarting of the outer momentum as a simple complementary mechanism for controlling this outer memory. In a linearized squared-loss model where prediction-space residuals evolve under the empirical NTK, we derive a mode-wise restart contraction showing that resets exploit phase cancellation by discarding stale momentum while preserving inner-loop progress. Toy experiments verify the predicted contraction behavior, and language-model pretraining experiments show that periodic restarts widen the stable range of outer learning rates and momentum values across communication periods. --- ### SARAD: LLM-Based Safety-Aware Hybrid Reinforcement Learning with Collision Prediction for Autonomous Driving Authors: Kangyu Wu, Peng Cui, Guoxi Chen, Ya Zhang Published: 2026-05-27 Categories: cs.RO, cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2605.28583v1 Ensuring both safety and efficiency in decision-making for autonomous driving systems remains a fundamental challenge. Traditional Deep Reinforcement Learning (DRL) suffers from unsafe random exploration and slow convergence, while Large Language Models (LLMs) demonstrate inherent latency in real-time inference operations. To address these limitations, this paper proposes SARAD, a novel safety-aware hybrid framework that synergizes LLMs and DRL for autonomous driving. SARAD substitutes the random exploration of DRL with Retrieval-Augmented Generation (RAG)-enhanced, LLM-guided decisions sourced from a dynamic expert knowledge repository. An attention discriminator is proposed to integrate the prior knowledge of LLMs into DRL policy optimization. A collision predictor module, fine-tuned with historical collision data, is further designed to improve vehicle safety. Extensive experiments show that SARAD achieves significant performance improvements in the Highway-Env simulator, validating the effectiveness of the proposed model in autonomous driving. --- ### MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation Authors: Xiaoyu Dong, Zhi Li, Xiao-Ming Wu Published: 2026-05-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.28579v2 Large language models (LLMs) have recently advanced text-driven 3D generation, yet Text-to-CAD remains far from supporting industrial product design. Existing benchmarks focus primarily on generating single-part CAD models and evaluate them using geometric similarity metrics that fail to capture functionality, manufacturability, and assemblability. To address this gap, we introduce MUSE, a Text-to-CAD benchmark focused on complex, editable boundary representation (B-Rep) assemblies. MUSE pairs practical design instances with structured Design Specifications and evaluates generated models through a three-stage protocol: code check, geometric check, and design-intent alignment. The final stage uses design-specific rubrics to assess functionality, manufacturability, and assemblability, moving beyond shape matching toward practical design quality. To enable scalable evaluation, we use a rubric-based visual language model (VLM) judge and validate its reliability through human annotation. Experiments on closed-source and open-source LLMs reveal a clear failure cascade from executable code to valid geometry and finally to engineering-ready design, with even the strongest models achieving limited success on fine-grained engineering criteria. Together, MUSE provides a realistic benchmark and evaluation framework for advancing Text-to-CAD from geometric generation toward true engineering design. Our project website, including the leaderboard, dataset, and code, is available at https://dong7313.github.io/muse-benchmark/. --- ### A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks Authors: Nicolas Tremblay, Benjamin Ricaud, Filippo Maria Bianchi Published: 2026-05-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28578v1 We propose the Tikhonov layer, a graph neural network layer that is interpretable by design: once trained, its learned parameters directly reveal which node features and which aspects of the graph topology were leveraged for prediction. In practice, the layer's propagation matrix takes the closed-form $R = (p(L)+Q)^{-1} Q$, where $L$ is the normalized graph Laplacian, $Q = diag(q_1,...,q_n)$ a learnable diagonal matrix of positive node-importance scores, and $p(\cdot)$ a learnable polynomial. For any input feature $x$, the layer output $Rx$ is the exact minimizer of a generalized graph Tikhonov problem that trades off node-level data fidelity against a topology-driven regularization penalty. The learned pair $\{\{q_i\},p\}$ constitutes a built-in explanation: large $q_i$ indicates that node $i$'s own features drive the prediction, while small $q_i$ signals reliance on the local graph topology; the shape of $p$ reveals whether homophily, heterophily, or a band-pass response is exploited. Expressivity is preserved by routing complexity through a dedicated, arbitrarily deep Q-network that produces the importance scores, while the Tikhonov layer itself remains transparent. We prove that distinct node-importance matrices yield distinct propagation operators, structurally coupling the explanation to the computation. Additionally, the Tikhonov layer provides, in a single layer, a global receptive field, mitigating both oversmoothing and oversquashing. Experiments on standard graph classification benchmarks confirm that the model matches (and sometimes outperforms) opaque baselines while producing interpretable and faithful explanations. --- ### Continual Model Routing in Evolving Model Hubs Authors: Jack Bell, Giacomo Carfì, Gerlando Gramaglia, Vincenzo Lomonaco Published: 2026-05-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.28577v1 AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. However, this rapid growth poses two fundamental challenges: scaling model selection across thousands of experts and continually updating routing mechanisms as new models and tasks are introduced. In this paper, we formalise this setting as Continual Model Routing (CMR) and propose CMRBench, a new large-scale benchmark simulating realistic hub expansion and including over 2,000 candidate models. Finally, we introduce CARvE, a contrastive embedding approach for efficient continual model routing via checkpoint-based anchoring and structured replay. Extensive empirical results and ablations show that CARvE significantly outperforms zero-shot retrieval, fine-tuning, and adapter-merging baselines in model, family, and domain-level accuracy. --- ### A Conflict-Aware Penalty and Statistical Loss Framework for Balancing Modalities and Enhancing Stability in Multimodal Sentiment Analysis Authors: Jianheng Dai, Jiazhang Liang, Sijie Mai Published: 2026-05-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.28575v1 Multimodal Sentiment Analysis (MSA) fuses text, acoustic, and visual streams to infer sentiment. Because pre-trained text encoders are far more expressive than their acoustic and visual counterparts, the text modality tends to dominate optimization, suppressing weaker modalities and inducing gradient norm conflicts that destabilize training. To address this, we propose a Conflict-aware Penalty (CP) that detects and penalizes gradient norm conflicts at each training step, and a Statistical Loss (SL) that aligns predicted distribution statistics with empirical input statistics. Crucially, CP prevents dominant modality gradients from interfering with the SL objective, enabling synergistic training within a unified framework incorporating adaptive modality encoding, gated cross-modal fusion, and unimodal auxiliary heads. Experiments on CMU-MOSI demonstrate state-of-the-art performance, with ablation studies confirming the effectiveness of each component. --- ### Efficient Pre-Training of LLMs through Truncated SVD Layers Authors: Kaivan Kamali, Kajetan Schweighofer, Hormoz Shahrzad, Olivier Francon, Babak Hodjat, Risto Miikkulainen Published: 2026-05-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.28573v1 The massive scaling of Large Language Models (LLMs) has made pretraining increasingly cost-prohibitive. While low-rank representation and orthonormal weight matrices could in principle reduce parameter counts and computational overhead, most existing methods rely on static rank selection and do not enforce weight orthonormality due to high computational cost. This paper introduces TSVD, a framework that maintains low rank and strict orthonormality throughout the training process. It utilizes a spectral energy-based heuristic for adaptive rank selection, and a caching mechanisms to maintain orthonormality. Theoretical analysis justifies the advantage of the approach in pretraining dynamics and experiments across various model scales demonstrate that it is effective empirically. TSVD matches or exceeds the performance of full-parameter baselines while significantly reducing compute requirements. The approach thus offers a well-founded, practical, and scalable path toward efficient high-performance LLM pretraining. --- ### Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression Authors: Tue M. Cao, Nguyen Do, My T. Thai Published: 2026-05-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.28567v1 Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing large feature circuits into interpretable supernodes. Although these have been treated as separate problems, we show that both are instances of a more fundamental challenge, which we frame as the estimation of semantic distances between SAE features that lie on different activation manifolds. We introduce a distributional framework for this problem, in which each feature is represented not by a single decoder vector like in the literature, but by an activation-weighted distribution over the hidden states that express it. By projecting these distributions into a shared reference space and comparing them with Wasserstein distance, our method provides a unified semantic metric for cross-layer feature comparison. We prove that our representation is invariant to activation rescaling, stable under perturbations, and recovers true matches under finite-sample margin conditions. Empirically, our method outperforms decoder-vector and LLM-based baselines and captures subtle functional distinctions between related features. Notably, our method compresses large feature circuits into interpretable supernodes automatically. --- ### Tree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design Patterns Authors: Guni Sharon Published: 2026-05-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.28566v2 Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, yet their standard generation process -- auto-regressive token prediction -- is inherently myopic and prone to cascading errors. To address this, the Tree-of-Thoughts (ToT) framework creates a search space over intermediate reasoning steps, allowing search models to explore, look ahead, and backtrack. However, current ToT research remains fragmented across Natural Language Processing and Automated Planning communities, often using inconsistent terminology and ad-hoc implementations. Consequently, we synthesize the ToT landscape through a unified taxonomy based on classical heuristic search terminology. We map LLM-based reasoning to classical search components: state representation (granularity of thoughts), successor generation (prompting operators), and heuristic evaluation (self-assessment of progress). We analyze existing work within the context of our taxonomy and identify emerging design patterns: systematic search (Best-First Search) for shallow, deterministic tasks and lookahead-heavy strategies (DFS, MCTS) for deep multi-step reasoning. We conclude by identifying open algorithmic challenges at the intersection of heuristic search and LLM reasoning, and call on the heuristic search community to engage with this emerging domain. --- ### Verified Misguidance: Measuring Structural Citation Failures in Search-Augmented LLMs Authors: Yongsik Seo, Wooseok Jeong, Eunyoung Kim, Hyeonseo Jang, Dongha Lee Published: 2026-05-27 Categories: cs.DL, cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2605.28565v1 Users of search-augmented LLMs rely on citations as evidence that responses are grounded in real sources, and rarely verify the cited pages themselves. Millions of queries per day now pass through these systems, making citation quality a silent determinant of whether users are informed or misled-yet existing benchmarks each address one facet in isolation, leaving the joint structure that determines citation trustworthiness unmeasured. We construct CITETRACE, a large-scale dataset that traces the full citation chain from user query through retrieved source to generated answer: 11,200 real-world queries from 28 communities paired with 112,000 responses from ten models across five providers, yielding 761,495 evaluable citation pairs. We design a three-dimension evaluation framework that scores each citation on intent-purpose alignment, source suitability, and answer-source fidelity, using expert-validated predefined matrices and a five-level fidelity rubric; the framework applies to any system that produces citation-bearing responses. Applying this framework at scale, we identify a systematic pattern we call VERIFIED MISGUIDANCE (VM): models cite real, accessible sources yet fail along one or more dimensions, producing a fidelity-suitability trade-off in which faithful models select inappropriate sources and vice versa. Across our pool, 30.6% of citations distort their sources and 27.1% originate from domain-inappropriate sources; at the response level, up to 96% of users encounter at least one structurally misleading citation. Provider-level differences explain 88-96% of citation-quality variance, suggesting that source selection is governed more by factors beyond individual model capability than by the LLMs themselves. Together, CITETRACE and its evaluation framework provide the first resource for diagnosing structural citation failures in deployed search-augmented systems. --- ### A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models Authors: Aditya Kommineni, Emily Zhou, Kleanthis Avramidis, Tiantian Feng, Shrikanth Narayanan Published: 2026-05-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.28563v1 Evaluating foundation models under appropriate adaptation settings is essential for understanding the quality and transferability of the learned representations. Recent EEG foundation models have demonstrated promising transfer capabilities across tasks and datasets, motivating their growing use in neurotechnology and clinical applications. However, these models are typically evaluated under full fine-tuning on well-curated downstream datasets, a setting that does not reflect biomedical domain constraints such as limited labeled data, reduced sensor coverage, or parameter-efficient adaptation. In this work, we propose a multi-dimensional evaluation framework for assessing EEG models under realistic low-resource conditions. Empirical analysis of both supervised EEG models and recent EEG foundation models, including LaBraM, CSBrain, and CBraMod, across 6 different datasets is performed under the proposed multi-dimensional evaluation framework. We find that EEG foundation models consistently provide performance gains on long-context tasks such as sleep stage prediction and mental health state classification. In contrast, for short-window Brain Computer Interface style tasks, supervised models achieve comparable despite having substantially fewer parameters. Additional analyses demonstrate that current foundation models provide limited robustness to short-window tasks and channel constrained settings. Together, these findings motivate the use of multi-dimensional evaluation protocols that characterize model behavior under realistic use constraints. --- ### Soft-SVeRL: Self-Verified Reinforcement Learning with Soft Rewards Authors: Saurabh Dash, Pierre Clavier, John Dang, Matthias Galle, Marzieh Fadaee, Ahmet Üstün, Beyza Ermis Published: 2026-05-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.28561v1 Reinforcement Learning from Verifiable Rewards (RLVR) has improved language models in domains such as mathematics and code, where correctness can be checked automatically. However, many important tasks are only partially verifiable: prompts contain multiple requirements, responses may satisfy some but not all of them, or no single reference answer might exist. We introduce Soft-RLVR, a framework for reinforcement learning from decomposed, learned verification signals. Soft-RLVR converts each prompt into a checklist of atomic requirements, scores candidate responses item by item with an LLM verifier, and trains on the resulting soft reward. Checklist-based rewards turn sparse pass/fail supervision into a denser partial-credit signal, but they also introduce a tradeoff: averaging item-level judgments can reduce verifier noise, while partial credit can reward incomplete responses. We formalize this tradeoff and identify conditions under which checklist-based verification gives a more reliable RL training signal than holistic verification. We further introduce Soft-SVeRL, a self-verifying variant of Soft-RLVR in which the policy also acts as the verifier. We show that self-verification is prone to reward inflation from overly permissive self-judgments, and that explicit stabilization is needed to prevent this collapse. In a controlled instruction-following setting with rule-based ground-truth evaluation, checklist-based Soft-RLVR improves IFEval by up to 11.1 points using only learned verifier rewards. Our experiments further show that verifier quality and checklist quality both affect downstream RL outcomes, and that explicit stabilization is essential for effective self-verification. --- ### Token Optimization Strategies for LLM-Based Oracle-to-PostgreSQL Migration Authors: Oleg Grynets, Dmytro Babarytskyi, Vasyl Lyashkevych Published: 2026-05-27 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2605.28557v1 LLMs are increasingly used for software modernization, code translation, and database migration. However, LLM-based Oracle2PostgreSQL migration remains constrained by high token consumption, long-context degradation, dialect-specific semantic differences, and the risk of semantic drift during query transformation. Direct inclusion of large Oracle SQL/PL-SQL artefacts, schema definitions, procedural logic, and migration instructions into the model context increases cost and may reduce generation quality. This paper shows token optimization as a constrained transformation problem in LLM-based Oracle2PostgreSQL migration. The study formalizes and evaluates twelve token optimization strategies: baseline representation, context pruning, minification, DSL-based semantic compression, metadata augmentation, context refactoring, schema distillation, adaptive routing, AST-based minification, identifier masking, output constraint enforcement, and hybrid optimization. The strategies are evaluated on samples of 10 and 100 Oracle SQL queries using Valid Syntax Rate, Exact Match, Semantic Match, CodeBLEU, and Token Efficiency. The results show that mild context pruning preserves semantic quality almost at the baseline level, achieving 89.75% Semantic Match on the 100-query sample compared with 89.80% for the unoptimized baseline. Adaptive routing provides the best practical trade-off, reducing input tokens by 8.72% and output tokens by 5.49% while maintaining 88.40% Semantic Match and increasing Token Efficiency by 6.67%. Aggressive schema distillation increases Token Efficiency by 132.22% but results in a 44.50-percentage-point decrease in Semantic Match. The findings demonstrate that token optimization cannot be treated as simple prompt shortening; it must be evaluated as a multi-objective migration problem balancing cost, syntactic validity, semantic preservation, and structural fidelity. --- ### A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks Authors: Tomer Keren, Nitay Calderon, Asaf Yehudai, Yotam Perlitz, Michal Shmueli-Scheuer, Roi Reichart Published: 2026-05-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.28556v2 As agent capabilities advance, existing benchmarks, such as $τ^2$-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remains complex, costly, and labor-intensive. Moreover, the standard approach, in which scenarios are first written in natural language and then mapped to tool sequences, captures only a narrow subset of the tool-use patterns agents exercise. In this paper, we address these problems by reversing the task construction process. We propose TASTE: Task Synthesis from Tool Sequence Evolution, an automatic method that generates challenging tasks with broader tool-use coverage. TASTE utilizes an Adaptive Contrastive $n$-gram model trained on LLM-judged validity signals. This enables sampling valid tool sequences that cover a vast range of tool combinations. TASTE then selects representative sequences from the pool via clustering, instantiates them into complete benchmark tasks, and refines them through iterative difficulty evolution. Using TASTE, we construct $τ^c$-Bench, a challenging extension of the three domains of $τ^2$-Bench. We evaluate $11$ agent/user LLM pairs and find that models nearly saturating $τ^2$-Bench suffer severe performance drops on our tasks (e.g., Gemini-3-Flash falls from $0.82\!-\!0.94$ to $0.28\!-\!0.61$). Beyond increasing difficulty, our generated tasks more than double the number of unique tool combinations agents must execute. Our results suggest high scores on existing benchmarks often reflect saturation rather than robust task-solving ability. By automating the generation of difficult, high-coverage benchmarks, TASTE enables continuous, scalable evaluation of future agents. --- ### High Performance, Low Reliability: Uncertainty Benchmarking for Tabular Foundation Models Authors: José Lucas De Melo Costa, Fabrice Popineau, Arpad Rimmel, Bich-Liên Doan Published: 2026-05-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28554v1 Recent Tabular Foundation Models (TFMs) have demonstrated state-of-the-art predictive performance, often surpassing Gradient-Boosted Decision Trees (GBDTs). However, the trustworthiness of these models, particularly their uncertainty quantification, has been largely overlooked. We investigate this gap through an extensive study comparing TFMs, GBDTs, and classical baselines on the 112 datasets of the TALENT benchmark. Our results reveal a performance-uncertainty trade-off: although TFMs achieve the highest predictive performance, measured by AUC, they exhibit lower conditional coverage under conformal prediction, measured by SSCS, compared to GBDTs. Complementary experiments on synthetic datasets further characterize the regimes in which this effect intensifies. We conclude that while TFMs advance predictive frontiers, achieving well-calibrated uncertainty remains a major open challenge for their reliable adoption. Code is available at: https://github.com/jose-melo/high-performance-low-reliability --- ### Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations Authors: Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta, Denis Kleyko, Mauro Conti, Matteo Zavatteri, Roberto Confalonieri Published: 2026-05-27 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.28553v2 In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly decodable well before the final layer, indicating that safety-relevant behavior is represented in intermediate activations before output generation. To test whether this signal is actionable, we introduce Mechanistic AutoDAN, a probe-guided variant of AutoDAN that replaces full-model fitness evaluation with partial forward passes and probe-based scoring inside a genetic prompt search loop. Across the evaluated models, our method achieves attack success rates competitive with vanilla AutoDAN while reducing per-iteration search time by up to 72%, and probe-guided prompts match or exceed AutoDAN's cross-model transfer in several configurations. We further find that the usefulness of probe guidance increases with model scale. Our results suggest that refusal-relevant information is decodable from intermediate activations and can serve as an effective search signal in an AutoDAN-style discrete jailbreak optimization loop, especially for larger and more robust models. --- ### Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations Authors: Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta, Denis Kleyko, Mauro Conti, Matteo Zavatteri, Roberto Confalonieri Published: 2026-05-27 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.28553v1 In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly decodable well before the final layer, indicating that safety-relevant behavior is represented in intermediate activations before output generation. To test whether this signal is actionable, we introduce Mechanistic AutoDAN, a probe-guided variant of AutoDAN that replaces full-model fitness evaluation with partial forward passes and probe-based scoring inside a genetic prompt search loop. Across the evaluated models, our method achieves attack success rates competitive with vanilla AutoDAN while reducing per-iteration search time by up to 72%, and probe-guided prompts match or exceed AutoDAN's cross-model transfer in several configurations. We further find that the usefulness of probe guidance increases with model scale. Our results show that refusal is not only observable at the output level, but is encoded as a structured and actionable signal in intermediate LLM activations. --- ### Modeling Vehicle-Type-Specific Pedestrian Crash Avoidance Behavior in Safety-Critical Interactions Using Smooth-Mamba Deep Reinforcement Learning Authors: Qingwen Pu, Kun Xie, Hong Yang, Di Yang, Junqing Wang Published: 2026-05-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.28552v1 As automated vehicles (AVs) increasingly share roadways with human-driven vehicles (HDVs), understanding how pedestrians respond to different vehicle types in safety-critical interactions is essential for the safe deployment of automated driving technologies. This study extracts safety-critical pedestrian-vehicle interactions from the Argoverse 2 dataset to capture real-world crash avoidance behaviors in encounters involving AVs and HDVs. To model vehicle-type-specific pedestrian crash avoidance behavior, we develop a Smooth-Mamba Deep Deterministic Policy Gradient framework, termed SMamba-DDPG, which integrates smooth action constraints with efficient temporal representation learning. To quantify pedestrian behavioral differences, the framework trains separate crash avoidance policies for pedestrian interactions with AVs and HDVs. Results show that SMamba-DDPG outperforms baseline reinforcement learning and supervised learning models in reproducing pedestrian crash avoidance behaviors. Reconstructed trajectories demonstrate strong behavioral realism, accurately reproducing crash avoidance kinematics in both AV and HDV scenarios. Reaction time analysis shows that the model captures human-like response delays and reveals that pedestrians respond more quickly to AVs than to HDVs. Counterfactual analysis further indicates that pedestrians adopt lower crossing speeds when interacting with AVs. Large-scale safety analysis of model-generated data revealed that pedestrian-AV interactions consistently yielded lower conflict rates and higher pedestrian yielding rates compared to pedestrian-HDV interactions. The findings highlight the importance of incorporating vehicle-type-specific pedestrian behavioral models for safer automated driving system design and more realistic traffic simulations in mixed-traffic environments. --- ### Resolution-free neural surrogates for geometric parameterization and mapping with spatially varying fields Authors: Yanwen Huang, Lok Ming Lui, Gary P. T. Choi Published: 2026-05-27 Categories: cs.CV, cs.GR, cs.LG arXiv: https://arxiv.org/abs/2605.28551v2 Many imaging problems require computing spatial transformations induced by spatially varying intensity, feature, or density fields. Canonical examples include distortion correction, deformable image registration, atlas-based segmentation, and deformation-driven image analysis. These tasks can be formulated as geometric mapping problems in which the transformation is constrained to preserve local structure, control boundary behavior, or regulate angular distortion. Such formulations typically lead to variational models, diffusion processes, or elliptic partial differential equations. However, repeatedly solving high-resolution systems becomes computationally expensive when the underlying parameter fields vary across instances. In this work, we propose a resolution-free neural surrogate for geometric parameterization and mapping problems. Given a spatially varying parameter field $p:Ω\to\mathbb{R}^m$ and query locations $\{x_i\}_{i=1}^N\subsetΩ$, the model predicts mapped locations $\{u(x_i)\}_{i=1}^N$ on arbitrary structured or unstructured point sets. To avoid dependence on a fixed grid, we use a multi-resolution geometric encoding strategy that conditions the network on coordinate-augmented samples of the parameter field. The model is trained without labeled solution data by enforcing geometry-aware constraints derived from variational energies, diffusion-based density equalization, and quasi-conformal theory. Experimental results on quasi-conformal mapping and density-equalizing mapping problems are presented to demonstrate the effectiveness of our proposed method. --- ### SPRINT: Efficient Spectral Priors for Humanoid Athletic Sprints Authors: Yantong Wei, Kaihong Huang, Hainan Pan, Jiawei Luo, Jiawei Zhou, Ziyan Mai, Zhiwen Zeng, Yaonan Wang, Huimin Lu Published: 2026-05-27 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2605.28549v1 The pursuit of humanoid athletic sprints is hindered by a scarcity of humanoid-viable kinematic reference data and the inability of existing frameworks to maintain stability during sprints. To overcome these limitations, we introduce SPRINT, a novel framework driven by efficient, frequency-adaptive spectral priors. By characterizing the fundamental periodicity of human locomotion in the frequency domain using a reference library of five discrete motion sequences, these priors generate kinematically feasible joint trajectories across a broad velocity spectrum, successfully extrapolating to speeds that exceed the reference distribution. Guided by these pretrained priors, the SPRINT policy achieves zero-shot sim-to-real transfer in field experiments on the Unitree G1 platform, reaching a peak sprinting velocity of 6 m/s and demonstrating seamless gait transitions while preserving biomimetic naturalness. Ultimately, this work establishes frequency-adaptive spectral priors as a highly data-efficient foundation for humanoid athletic sprints. The project page is available at https://anonymous.4open.science/w/SPRINT-138A/. --- ### GEM: Generative Supervision Helps Embodied Intelligence Authors: Ruowen Zhao, Bangguo Li, Zuyan Liu, Yinan Liang, Junliang Ye, Fangfu Liu, Diankun Wu, Zhengyi Wang, Xumin Yu, Yongming Rao, Han Hu, Jun Zhu Published: 2026-05-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.28548v1 Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a significant gap remains between the high-level semantic focus of standard text-guided pre-training paradigms and the low-level spatial and physical knowledge critical for execution in embodied environments. In this paper, we introduce GEM, a Generative-supervised Embodied vision-language Model designed to bridge this divide. We propose integrating a depth map generation task directly into the VLM pre-training phase. By training this generative objective jointly with the main model, we observe substantial improvements in embodied intelligence, significantly enhancing both semantic understanding and physical operation capabilities. To support this paradigm, we curate and release GEM-4M, a comprehensive large-scale dataset featuring a mixture of grounding, reasoning, and planning data paired with high-quality depth supervision. Extensive experiments demonstrate that GEM achieves state-of-the-art results across diverse embodied benchmarks. Furthermore, our deployed action model, GEM-VLA, exhibits vastly superior task execution abilities in both simulation environments and real-world evaluations. Code, models, and datasets are available at https://zhaorw02.github.io/GEM/ --- ### DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving Authors: Chen Shi, Jinrui Xu, Shaoshuai Shi, Kehua Sheng, Bo Zhang, Li Jiang Published: 2026-05-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.28544v1 Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primarily on static image-text pairs, video generative models capture temporal dynamics and motion priors that are naturally suited for driving. We present DriveWAM, a driving world-action model that adapts a pretrained video diffusion transformer into an autoregressive video-action policy. DriveWAM organizes video and action streams into a unified temporal token sequence and trains them under a joint flow-matching objective, preserving the pretrained video-generation architecture while adapting its large-scale video priors to action generation. To incorporate high-level scene understanding, we introduce scene-evolving driving guidance, where a frozen VLM produces chunk-specific semantic intent to guide video-action generation. To keep long-horizon rollout bounded, we further introduce selective KV memory, which maintains bounded modality-aware video and action memory pools through relevance-redundancy cache selection at inference time. Experiments on NAVSIM and the PhysicalAI-Autonomous-Vehicles benchmark show that DriveWAM achieves strong planning performance, and a data-scaling study from 4k to 100k driving clips further confirms the scaling potential of world-action modeling for end-to-end autonomous driving. --- ### Cultural Binding Heads in Language Models Authors: Avrile Floro, Luca Benedetto Published: 2026-05-27 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.28543v3 LLMs often default to equal treatment across cultural groups, even though context warrants differentiation: this is a lack of difference awareness. Using mechanistic interpretability and a factorial design on the N4 cultural appropriation benchmark from Wang et al. (2025), we identify 2-3 mid-layer attention heads per model that contribute causally to cultural binding across eight models (base and instruct versions of four architectures). Cultural binding is the process of associating a cultural item with its related identity. Knockout of the identity-to-item edges on these heads lowers the binding strength by 9-23%. The identified heads transfer from instruct to base models, suggesting that cultural binding is created during pre-training. An $α$-scaling shows a graded dose-response. Moderate amplification steering at generation ($α= 2-3$) increases cultural differentiation accuracy by 1-3 pp while leaving reasoning on culturally neutral questions mostly intact. A knowledge probing task shows that models know 3-6 times more than they act upon, indicating that the bottleneck lies in routing and not knowledge. --- ### Cultural Binding Heads in Language Models Authors: Avrile Floro, Luca Benedetto Published: 2026-05-27 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.28543v2 LLMs often default to equal treatment across cultural groups, even though context warrants differentiation: this is a lack of difference awareness. Using mechanistic interpretability and a factorial design on the N4 cultural appropriation benchmark from Wang et al. (2025), we identify 2-3 mid-layer attention heads per model that contribute causally to cultural binding across eight models (four architectures, base and instruct). Cultural binding is the process of associating cultural items with the appropriate identity. Knockout of the identity-to-item edges on these heads lowers the binding strength by 9-23%. The identified heads transfer from instruct to base models, suggesting that cultural binding is created at pre-training. An $α$-scaling shows a graded dose-response and moderate amplification steering at generation ($α= 2-3$) increases cultural differentiation accuracy by 1-3 pp while leaving neutral reasoning mostly intact. A knowledge probing task shows that models know 3-5 times more than they act upon it, indicating that the bottleneck lies in routing and not knowledge. --- ### GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection Authors: Zheng Wu, Chengcheng Han, Zhengxi Lu, Tianjie Ju, Yanyu Chen, Qi Gu, Xunliang Cai, Zhuosheng Zhang Published: 2026-05-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.28534v1 Despite the rapid progress of multimodal large language models in building Graphical User Interface (GUI) agents, their real-world task completion is fundamentally bottlenecked by a lack of world knowledge about GUI operations. Existing solutions typically rely on expensive multi-agent scaffolding or conventional post-training paradigms, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). However, post-training only allows agents to implicitly absorb world knowledge through action annotations or reward signals, leading to inefficient trajectory memorization rather than genuine comprehension. Therefore, an approach that enables explicit learning of this knowledge is imperative. To this end, we propose GUI-CIDER, a mid-training method that explicitly internalizes GUI world knowledge through Causal Internalization and Density-aware Exemplar Reselection. GUI-CIDER operates in three stages: (1) data synthesis, which distills static planning and dynamic causal knowledge from GUI trajectories into text; (2) exemplar reselection, which filters the corpus by rewarding causal structures and penalizing semantic redundancy; and (3) mid-training, where the refined data is used to embed the acquired knowledge. Extensive experiments on two GUI knowledge benchmarks and three task completion benchmarks demonstrate that GUI-CIDER consistently improves both the agent's understanding of GUI operations and its task success rates.The codes are available at https://github.com/Wuzheng02/GUI-CIDER. --- ### Semi-Supervised Hypothesis Testing by Betting on Predictions Authors: Yaniv Tenzer, Elad Tolochinsky, Yaniv Romano Published: 2026-05-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28533v1 We introduce a testing-by-betting framework that leverages predictions on unlabeled data to enhance the power of sequential hypothesis testing. Given limited samples from the joint distribution of $(X,Y)$, and additional unlabeled samples from the marginal of $X$, we ask how unlabeled data can be used to hypothesize about the distribution of $Y$, and the conditional distribution of $Y\mid X$. We introduce an e-statistic and use it to construct a sequential test. Under standard distributional assumptions -- label shift or concept shift -- we establish that the test is anytime valid. Furthermore, we show that for binary data, the e-statistic has non-trivial power. Crucially, our approach retains these properties even when the underlying predictions are inaccurate. Through simulations and applications to large language models evaluation, we demonstrate power gains over baseline approaches, including prediction-powered inference. These gains persist even with relatively limited unlabeled data and when predictions have low accuracy due to weak correlation between $X$ and $Y$. --- ### Do Agents Know What They Can't Do? Evaluating Feasibility Awareness in Tool-Using Agents Authors: Liang Cheng, Mingsheng Cai, Jiuming Jiang, Luo Mai Published: 2026-05-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.28532v1 Tool-using agents often incur substantial computational cost due to long reasoning chains and iterative tool usage. In practical scenarios, many tasks become infeasible under constrained tool environments, where the capabilities required for successful task completion are unavailable. Detecting infeasible tasks and stopping execution early can significantly reduce unnecessary execution cost. In this work, we propose FeasiGen, an automatic pipeline for constructing infeasible agent tasks by identifying the critical tools required for successful task completion. Our approach extracts tool-calling traces from successful executions across multiple agent systems, identifies critical tools consistently shared across diverse execution strategies, and masks these tools to automatically transform solvable tasks into infeasible ones. Human verification confirms that the infeasibility annotations for our constructed tasks achieve over 94% accuracy. We further introduce feasibility-aware evaluation metrics for measuring whether agents can recognize infeasible tasks and stop execution appropriately. Extensive evaluations across nine models reveal substantially weak infeasibility detection ability, with false continue rate reaching up to 73.9%. We further observe that multi-agent architectures significantly reduce erroneous execution under infeasible conditions. --- ### Stabilizing distribution-free probabilistic forecasts Authors: Jente Van Belle, Honglin Wen, Wouter Verbeke, Pierre Pinson Published: 2026-05-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.28531v1 Multi-step-ahead forecasts are often updated as new observations become available, since shorter forecast horizons typically improve forecast quality. However, such improvements come at the cost of forecast instability, i.e., variability in forecasts for the same target period. This instability can trigger costly changes to plans formulated based on the forecasts and may erode trust in the forecasting system. In this work, we integrate forecast stability alongside forecast quality into the training of distribution-free probabilistic time-series forecasting models, allowing us to control this trade-off. We propose a method for generating stabilized forecasted conditional quantile functions using regression splines parameterized by a neural network. This approach enables joint optimization of quality and stability, as it allows us to directly penalize dissimilarities arising from forecast updates. Furthermore, it allows assigning varying importance to stabilizing different parts of the forecast distributions (e.g., central parts vs. tails) to focus on the parts most relevant for the intended downstream use (e.g., the upper tail for inventory management). We empirically evaluate the proposed method on two datasets with different statistical properties and show that it can effectively reduce forecast instability without a substantial loss in forecast quality, and that it can target stabilization effort toward specific parts of the forecast distributions. --- ### Entropy-aware Masking for Masked Language Modeling Authors: Gokul Srinivasagan, Kai Hartung, Munir Georges Published: 2026-05-27 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.28526v1 Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the model learns to predict them using the surrounding context. This process enables the model to capture both syntactic and semantic properties of language. Conventionally, the tokens selected for masking are chosen at random, which may not always yield the most effective learning signals. In this work, we examine a token masking strategy based on entropy distribution. We use the model's entropy over token predictions to identify which tokens should be masked. This method aims to target tokens that are more informative and uncertain to improve the training efficacy. We also propose a novel self-masking approach that enhances training efficiency without relying on an external reference model. Experimental results demonstrate that our method achieves an average performance improvement of 5% in GLUE scores compared to the baseline. Further, we experiment with combining knowledge distillation with entropy masking, resulting in the best overall results. --- ### Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection Authors: Zhixing Zuo, Huilin He, Jiasheng Wu, Dawei Cheng Published: 2026-05-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.28524v1 In recent years, Large Language Models (LLMs) have shown great capability in processing graph tasks such as fraud detection. However, most existing methods rely heavily on rich text attributes, which poses difficulties for this domain due to the lack of textual data. Although some pioneering methods attempt to overcome it, their textualization of graph structures via hard prompts easily leads to feature distortion. Additionally, fraud detection often exhibits multi-relational complexity, where current methods struggle to capture this deep semantic information. To address these challenges, we propose LLM-GNN Soft Prompt Framework (LGSPF). Specifically, LGSPF bridges the graph structure and semantic space using soft prompt to eliminate reliance on text. We further introduce a parallel Graph Neural Network (GNN) encoder to translate multi-relational topologies into graph tokens for fine-grained LLM fraud comprehension. Through end-to-end optimization, LGSPF enhances deep semantic alignment between LLM and GNN. Experiments across diverse fraud detection benchmarks demonstrate our method achieves state-of-the-art performance. Moreover, we further validate the contribution of LGSPF on enhancing the semantic interpretability of fraud behaviors. --- ### ClinicalEncoder26AM: A Multlilingual Diagnosable ColBERT Model; Evidences from the MultiClinNER Shared Task Authors: François Remy Published: 2026-05-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.28521v1 ClinicalEncoder26AM is a multilingual Diagnosable ColBERT for clinical and biomedical texts, which aligns at multiple levels its token-level semantic with ClinicalMap25, a clinical latent space inspired by BioLORD-2023 and enriched with synthetic and annotated supervision. The post-training recipe builds upon BGE-M3, and combines synthetic clinical notes, patient--doctor conversations, and annotated resources such as MedMentions, while considering both named-entity-level and sentence-level representations in a multi-adapter distillation, along with a ColBERT-style retrieval objective. In this system demonstration paper, we evaluate the model in the MultiClinNER shared task by finetuning it as a BIO tagger for patient symptoms, disorders, and procedure spans, using a lightweight two-layer CNN head to improve local boundary detection. The resulting system remains simple, processes most documents in a single 8192-token window, and achieves state-of-the-art multilingual entity recall, while achieving Top 5 overall across all entity types and languages in Character-weighted F1 scores. Training curves further show that ClinicalEncoder26AM is markedly more data-efficient than the base M3 model, supporting the usefulness of its clinical post-training for downstream information extraction. The model can be downloaded on https://huggingface.co/Parallia/ClinicalEncoder26AM-Diagnosable-Colbert-L2-for-multilingual-medical-texts ---