# Research Papers — 2026-05 · bundle page 99 of 326 > Full-text markdown of papers #4901–4950 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/99 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/98.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/100.md) ### Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment Authors: Haoyuan Wang, Xiaohao Liu, Jiajie Su, Jianmao Xiao, Chaochao Chen Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.23780v1 Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimodal knowledge editing achieves strong reliability and locality, it often exhibits limited generality, failing to propagate edits across semantically equivalent visual and linguistic variations. This issue arises from the lack of explicit semantic supervision, rigid editing scopes, and biased anchoring to individual samples in high-dimensional multimodal spaces. We address robust intrinsic multimodal knowledge editing by explicitly targeting generalization. We formalize robustness through knowledge units that group semantically equivalent multimodal inputs and define generality as consistent predictions within each unit. To expose fragile semantic regions, we introduce Latent Adversarial Robustification (LAR), which generates adversarial yet semantically coherent variants in the joint latent space. We further propose Rank-Constrained Subspace Learning (RCSL), enforcing low-rank alignment of adversarial representations at the edit layer via a singular value-based objective. Extensive analysis demonstrates the effectiveness of ASAM empirically. --- ### The physics of AI weather models Authors: George Craig, Tobias Selz, Matthias Beylich, Kirsten I. Tempest Published: 2026-05-22 Categories: physics.ao-ph, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2605.23778v1 Could it be that AI weather models are solving physical equations, although they may not be the equations used by conventional NWP models? We compute correlations of forecast skill and Centered Kernel Alignment, providing evidence that different AI weather models represent the atmosphere in similar ways, despite differences in architecture and capacity. We argue that the architecture and training of the AI models constrains the form of the physical laws that they might simulate. In particular, we propose that the models implement a particle description of the atmosphere, where the latent variables at each mesh point correspond to the position of a particle in the high dimensional latent space. We hypothesize that the movement of the particles follows a gradient flow in the latent space towards a minimum of a learned free energy functional. Analysis of the GraphCast and Aurora models show that they make changes on large spatial scales in the early processor layers and move to smaller scale with increasing layer depth, consistent with the gradient flow hypothesis. --- ### Machine learning applied to emerald gemstone grading: framework proposal and creation of a public dataset Authors: FB Pena, D Crabi, Sandro C Izidoro, Érick O Rodrigues, G Bernardes Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23777v1 The grading of gemstones is currently a manual procedure performed by gemologists. A popular approach uses reference stones, where those are visually inspected by specialists that decide which one of the available reference stone is the most similar to the inspected stone. This procedure is very subjective as different specialists may end up with different grading choices. This work proposes a complete framework that entails the image acquisition and goes up to the final stone categorization. The proposal is able to automate the entire process apart from including the stone in the created chamber for the image acquisition. It discards the subjective decisions made by specialists. This is the first work to propose a machine learning approach coupled with image processing techniques for emerald grading. The proposed framework achieves 98% of accuracy (correctly categorized stones), outperforming a deep learning approach. Furthermore, we also create and publish the used dataset that contains 192 images of emerald stones along with their extracted and pre-processed features. --- ### A Novel Approach for the Counting of Wood Logs Using cGANs and Image Processing Techniques Authors: João VC Mazzochin, Giovani Bernardes Vitor, Gustavo Tiecker, Elioenai MF Diniz, Gilson A Oliveira, Marcelo Trentin, Érick O Rodrigues Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23775v1 This study tackles the challenge of precise wood log counting, where applications of the proposed methodology can span from automated approaches for materials management, surveillance, and safety science to wood traffic monitoring, wood volume estimation, and others. We introduce an approach leveraging Conditional Generative Adversarial Networks (cGANs) for eucalyptus log segmentation in images, incorporating specialized image processing techniques to handle noise and intersections, coupled with the Connected Components Algorithm for efficient counting. To support this research, we created and made publicly available a comprehensive database of 466 images containing approximately 13,048 eucalyptus logs, which served for both training and validation purposes. Our method demonstrated robust performance, achieving an average Accuracy_pixel of 96.4% and Accuracy_logs of 92.3%, with additional measures such as F1 scores ranging from 0.879 to 0.933 and IoU values between 0.784 and 0.875, further validating its effectiveness. The implementation proves to be efficient with an average processing time of 0.713s per image on an NVIDIA T4 GPU, making it suitable for realtime applications. The practical implications of this method are significant for operational forestry, enabling more accurate inventory management, reducing human errors in manual counting, and optimizing resource allocation. Furthermore, the segmentation capabilities of the model provide a foundation for advanced applications such as eucalyptus stack volume estimation, contributing to a more comprehensive and refined analysis of forestry operations. The methodology's success in handling complex scenarios, including intersecting logs and varying environmental conditions, positions it as a valuable tool for practical applications across related industrial sectors. --- ### Agentic Proving for Program Verification Authors: Alessandro Sosso, Akhil Arora, Bas Spitters Published: 2026-05-22 Categories: cs.AI, cs.LO, cs.PL, cs.SE arXiv: https://arxiv.org/abs/2605.23772v1 Agentic systems have recently emerged as state-of-the-art approaches for automated theorem proving in formal mathematics. To assess how far these capabilities extend to program verification, we evaluate Claude Code in an agentic proving framework on CLEVER, a Lean 4 benchmark for verifiable code generation. Our results show that Claude generates arguably valid specifications for 98.8% of problems (with 81.3% also accepted by CLEVER's isomorphism-based scoring on the correct portion of the benchmark), certifies implementations against correct ground-truth specifications for 87.5% of problems, and reaches a 98.1% success rate on the end-to-end program generation and verification pipeline over entries with self-consistent premises. Across all stages, Claude further provides high-quality feedback on its own attempts (as confirmed under manual review), identifying underlying causes of failure and lingering bugs in the dataset. These findings highlight a growing mismatch between the difficulty of existing program verification benchmarks and the capabilities of modern agentic provers, and point to the need for more rigorous, bug-resilient evaluation methodologies, and in particular for alternatives to isomorphism-based scoring of generated specifications. More broadly, our results provide empirical evidence that tight compiler-in-the-loop agentic paradigms are currently the most effective approach for foundational program verification. --- ### PhotoFlow: Agentic 3D Virtual Photography Missions Authors: Jiarui Guo, Haojia Wei, Yiming Zhang, Yifei Liu, Yuning Gong, Hongjie Zhang, Xue Yang, Zhihang Zhong Published: 2026-05-22 Categories: cs.CV, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.23771v1 Virtual photography asks an agent to enter a prepared 3D scene with no preselected camera pose or reference image, infer a suitable shot from scene information and a language intent, choose executable camera parameters, and render the final photograph. Recent progress in vision-language models makes this kind of spatial agent increasingly plausible, but the task stresses two capabilities that remain hard to evaluate together: complex 3D spatial understanding and abstract aesthetic judgment. We introduce PhotoFlow, a Director-Reviewer-Reflector agent for closed-loop camera search. The Director builds a soft photographic blueprint and proposes diverse candidate cameras; the Reviewer combines rule checks, visual critique, and pairwise incumbent selection; and the Reflector converts failures into region memory, dead-zone suppression, and high-explore relocation. We also introduce VPhotoBench, a benchmark of 47 open-license Blender scenes and 141 language-conditioned photography missions spanning subject placement, relational composition, and atmosphere/style. On held-out experiments, PhotoFlow achieves the strongest external quality-alignment composite and success rate among one-shot prediction, single-chain reflection, anchor-bank selection, and random search under a six-round rendering budget. To our knowledge, this is the first work to make language-conditioned virtual photography in arbitrary Blender scenes an executable agent task, and our results show that an LLM-centered spatial agent can already produce strong photographs in a setting designed to challenge both 3D reasoning and aesthetic choice. --- ### LLM-driven design of physics-constrained constitutive models: two agents are better than one Authors: Marius Tacke, Matthias Busch, Kian Abdolazizi, Jonas Eichinger, Kevin Linka, Roland Aydin, Christian Cyron Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23754v2 Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics, machine learning, and scientific programming. Large language models (LLMs) have recently been shown to lower this barrier by generating constitutive models on demand, but existing single-agent pipelines lack systematic checks that the resulting models respect fundamental physical laws. To close this gap, we introduce the first multi-agent LLM-driven approach for constitutive model generation: a Creator agent proposes a model tailored to the data, while an Inspector agent critically audits each proposal against nine physical constraints and returns it for refinement whenever a violation is detected. We demonstrate this concept with constitutive artificial neural networks (CANNs) and benchmark it on brain tissue and rubber as isotropic materials, and on porcine skin tissue as a transversely isotropic material with a preferred fiber direction, using two different LLM backbones (Claude Opus 4.7 and Kimi K2.5). Whether a generated model satisfies the physical constraints is assessed numerically, by probing each constraint across a broad sample of deformation states, rotations, and perturbation directions. Adding the Inspector raises the share of exported models that pass all these checks from 90\% to 95\% for Opus and from 47\% to 60\% for Kimi. In addition, the generated models are on par with or even surpass expert-designed models in accuracy, extrapolate reliably beyond the training data, and generalize remarkably well to unseen loading paths. Separating generation from inspection thus turns LLM-driven constitutive modeling into a substantially more trustworthy process. The paradigm is deliberately technique-agnostic... --- ### LLM-driven design of physics-constrained constitutive models: two agents are better than one Authors: Marius Tacke, Matthias Busch, Kian Abdolazizi, Jonas Eichinger, Kevin Linka, Roland Aydin, Christian Cyron Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23754v1 Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics, machine learning, and scientific programming. Large language models (LLMs) have recently been shown to lower this barrier by generating constitutive models on demand, but existing single-agent pipelines lack systematic checks that the resulting models respect fundamental physical laws. To close this gap, we introduce the first multi-agent LLM-driven approach for constitutive model generation: a Creator agent proposes a model tailored to the data, while an Inspector agent critically audits each proposal against nine physical constraints and returns it for refinement whenever a violation is detected. We demonstrate this concept with constitutive artificial neural networks (CANNs) and benchmark it on brain tissue, experimental rubber, and synthetic rubber, using two different LLM backbones (Claude Opus 4.7 and Kimi K2.5). Adding the Inspector raises the share of exported models that truly satisfy all physical constraints from 91% to a perfect 100% for Opus and from 37% to 56% for Kimi, while preserving near-baseline accuracy and remarkable generalization to unseen loading paths. In combination, the generated models are physically valid, highly accurate, and extrapolate reliably beyond the training data - properties that together make them directly usable in practice. Separating generation from inspection thus turns LLM-driven constitutive modeling into a genuinely trustworthy process. The paradigm is deliberately technique-agnostic and scales automatically with advances in LLM capability, opening a promising path toward automated, physics-aware model discovery. --- ### SeedER: Seed-and-Expand Retrieval from Knowledge Graphs Authors: Hamed Shirzad, Frederik Wenkel, Dominique Beaini, Danica J. Sutherland, Emmanuel Noutahi Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23753v1 Knowledge graphs (KGs) offer a rich representation for relational knowledge, but their irregular structure makes retrieval challenging: ego-graph expansion grows rapidly, and dense embedding methods struggle with multi-hop compositional queries. Existing agent-based graph exploration approaches, while expressive, are often too expensive for large-scale retrieval. We introduce SeedER (Seed-and-Expand Retrieval), a retrieval framework that explicitly leverages KG structure through iterative, low-cost expansion. SeedER first seeds a compact set of core nodes using lightweight dense and entity-based retrieval, then selectively expands this set via a learned graph-aware policy trained with reinforcement learning. This design decomposes global reasoning into reusable local decisions, enabling efficient discovery of query-relevant nodes while tightly controlling expansion cost. We show theoretical limitations of dense retrieval on compositional graph queries, and establish advantages of SeedER from both compositional generalization and graph-constrained submodular optimization perspectives. Empirically, SeedER substantially improves recall with compact candidate sets over strong dense and graph-augmented baselines, making it an effective first-stage retriever for knowledge-intensive reasoning systems. --- ### Approaching I/O-optimality for Approximate Attention Authors: Pál András Papp, Aleksandros Sobczyk, Anastasios Zouzias Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23751v1 We revisit the I/O complexity of attention in large language models. Given query-key-value matrices $Q,K,V\in\mathbb{R}^{n\times d}$, and a machine with fast memory size $M$, the goal is to compute the "attention matrix" $A=\text{softmax}(Q K ^{\top}/\sqrt{d}) V$ with the minimal number of data transfers between fast and slow memory. Existing methods in the literature, most notably FlashAttention and its variants, incur an I/O cost that depends quadratically on $n$, while a trivial lower bound only requires $Ω(nd)$ I/O's to read the inputs and write the output. In this work, we present a technique for computing attention where the I/O cost only depends almost-linearly on $n$ in most parameter regimes. This is achieved by developing I/O-efficient algorithms inspired by the recent approximate attention framework of Alman and Song. We also prove corresponding lower bounds in each parameter regime to show that our algorithms are indeed close to I/O-optimal. --- ### Revitalizing Dense Material Segmentation: Stabilized Vision Transformers and the Generalization Paradox Authors: Allan Kazakov, Duygu Cakir, Hilal Kurt İrfanoğlu, Yavuz İrfanoğlu Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23747v1 Material segmentation, the pixel-wise classification of physical surface properties, remains a challenging problem in computer vision, requiring physicochemical understanding distinct from object-centric parsing. Despite the introduction of the rigorous Apple Dense Material Segmentation (DMS) dataset, the benchmark has suffered from attrition and stagnation, increasingly overshadowed by geometry-biased foundation models. In this paper, we revive the Apple-DMS benchmark to establish a modern Vision Transformer baseline. We conduct an exhaustive evaluation of SegFormer and Mask2Former architectures, revealing that standard training paradigms fail on amorphous texture fields due to high-variance gradients. To address this, we introduce a stabilized training recipe featuring High-Fidelity Logit Projection, Query Entropy Regularization, and a domain-specific, physics-compliant augmentation pipeline. Our optimized SegFormer-B5 achieves a new State-of-the-Art (SOTA) of 0.4572 mIoU on the original dataset split, significantly surpassing the prior convolutional baseline. Furthermore, we identify a critical "Generalization Paradox": while re-partitioning the dataset into a data-rich 80/10/10 split inflates the metric to 0.5276 mIoU, expert qualitative analysis reveals this induces distributional homogenization, severely degrading real-world, out-of-distribution performance. By releasing our recovered dataset index and robust training framework, we demonstrate that material perception is far from solved and urge the community to leverage the rigorous original split to drive genuine progress in physically grounded artificial intelligence. --- ### Contrast to Detect: Dynamic Graph Contrastive Regularization for Unsupervised Anomaly Detection in Multivariate Time Series Authors: Yunhua Pei, Zixing Song, Jin Zheng, John Cartlidge Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23744v1 Anomaly detection in multivariate time series (MTS) is hindered by dynamic inter-variable dependencies and feature entanglement under spectral noise, and in practice, is further complicated by the absence of anomaly labels. Existing reconstruction-based detectors tend to recover anomalies as faithfully as normal patterns, while prevailing graph contrastive methods enforce invariance across views and thus assume a stationary relational structure, an assumption that breaks under structural drift in real systems. We propose ContrastAD, an unsupervised framework that turns structural evolution itself into a learning signal rather than suppressing it. A Multi-Perspective Embedder encodes inputs from temporal, attribute, and structural perspectives. A Frequency-Aware Attention Mixer then performs spectral top-K filtering before attention, preventing noise from leaking into query-key similarities. The core component, a Dynamic Graph Contrastive Learner, builds power-law-inspired sparse graph snapshots from batch-level DTW distances and contrasts the most divergent pair against a stable anchor, regularizing the latent space without imposing rigid invariance. Across five real-world benchmarks, ContrastAD attains the highest mean F1 on all five datasets and the highest AUC on three (SWaT 93.60, SMD 98.66, PSM 97.79), with statistically significant F1 and AUC margins over the strongest baseline on SWaT and PSM. On MSL and SMAP, it trails the AUC leader by under 0.7 points while still leading on F1. Ablation and sensitivity studies further confirm that the contrastive objective works best as a soft regularizer, supporting our claim that strict invariance is suboptimal under non-stationary dynamics. --- ### Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking Authors: Ming Yang, Tao Yu, Feng Li, Hua Chen Published: 2026-05-22 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.23733v3 Whole-body tracking (WBT) models have become a key foundation for humanoid robots, enabling them to imitate diverse motions with high fidelity. Training such models from scratch requires large-scale data and computation, making rapid deployment on new humanoid platforms costly. This raises a natural question: Can pretrained WBT models transfer across embodiments with minimal adaptation? To answer this question, we propose Any2Any, a paradigm that efficiently transfers an existing WBT specialist to a new humanoid embodiment with only a small amount of data and compute. Any2Any first performs kinematic alignment between source and target humanoids, aligning their input and output spaces so that the pretrained source policy can be meaningfully reused on the target embodiment.Any2Any then performs dynamics adaptation by applying lightweight parameter-efficient fine-tuning (PEFT) components to selected dynamics-sensitive modules, preserving useful behavioral priors while enabling targeted adaptation to the target robot. Extensive experiments on multiple humanoid platforms and pretrained backbones show that Any2Any substantially accelerates convergence and reduces training cost compared with training from scratch, while achieving competitive or superior tracking performance. Notably, using only 1% of the compute and data required for full training, Any2Any successfully transfers Sonic models pre-trained on Unitree G1 to LimX Oli and LimX Luna. These results suggest that pretrained WBT specialists can be efficiently reused across embodiments, providing a scalable path toward deploying humanoid whole-body control on new robots. More results and videos are available on our project page: https://any2any.top/. --- ### Optimal Dimension-Free Sampling for Regularized Classification Authors: Meysam Alishahi, Alexander Munteanu, Simon Omlor, Jeff M. Phillips Published: 2026-05-22 Categories: cs.LG, cs.DS, stat.ML arXiv: https://arxiv.org/abs/2605.23726v1 We prove optimal sampling bounds achieving $(1\pm\varepsilon)$-relative error for a broad class of Lipschitz continuous classification loss functions under various regularization terms. This includes important functions such as logistic and sigmoid loss, hinge loss, and ReLU loss, as prominent and popular representative examples. In particular, we prove $k^2/\varepsilon^2$ upper and lower bounds for $\|\cdot\|_2/k$ regularization, and $k/\varepsilon^2$ upper and lower bounds for $\|\cdot\|_1/k$ regularization. For $\|\cdot\|_2^2/k$ regularization, the sampling complexity depends mainly on a bounded derivative property: if $|g'(x)|\leq g(x)$, and $g(0)>0$, and $g$ is monotonic or convex, then it admits linear in $k$ sampling complexity; otherwise the general bound is $k^2/\varepsilon^2$. However, if $g(0)=0$, our results indicate that no dimension-free bounds are possible, and even sublinear bounds are ruled out. All upper bounds are complemented by matching lower bounds up to polylogarithmic terms. Moreover, our work relies conceptually and algorithmically on simple uniform or (squared) norm sampling and hereby improves over recent cubic $k^3/\varepsilon^2$ sensitivity sampling bounds of (Alishahi and Phillips, ICML'24). This is achieved by refined arguments involving higher moment bounds and empirical process analyses to avoid overcounting that appears in the de-facto standard VC-dimension and sensitivity framework. --- ### MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection Authors: Zhewen Tan, Yilun Yao, Huiyan Jin, Wenhan Yu, Guoan Wang, Mengyuan Fan, liang lu, Feng Liu, Xiangzheng Zhang, Duohe Ma, Tong Yang, Lin Sun Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.23723v1 Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizon task execution. However, this memory mechanism also creates a practical security vulnerability: an adversarial user may inject malicious records into the agent's memory through ordinary interaction, and these records can later be retrieved to steer the agent's reasoning and actions. Existing defenses primarily focus on online intervention, such as prompt filtering or output blocking, but they do not address the post-hoc question of which stored memories are responsible after harmful behavior has already been observed. We propose \textbf{MemAudit}, a post-hoc causal memory auditing framework for memory-augmented LLM agents. The framework combines two complementary signals: (1) a counterfactual memory influence score that measures each memory's causal contribution to harmful outputs, and (2) a memory consistency graph that identifies structurally anomalous memories within the broader memory store. We evaluate MemAudit against MINJA, a query-only memory injection attack in which malicious records are generated and stored through normal agent interactions rather than direct memory-bank modification. Across both QA and reasoning-agent settings, MemAudit substantially reduces attack success rates under realistic post-hoc auditing scenarios. The results show that QA attack success is reduced from $70\%$ to $0\%$, while RAP attack success drops from $83.3\%$ to $0\%$. --- ### NLG Evaluation: Past, Present, Future Authors: Ehud Reiter Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23715v1 Natural Language Generation (NLG) evaluation has changed dramatically since 1990, and will continue to evolve in the future. In 1990, when NLG had close ties to linguistics, there was very little formal experimental evaluation in the modern sense. In 2026, when NLG is closely linked to machine learning, experimental evaluation is expected and indeed fundamental to research. Many evaluation techniques were developed over this period, including most recently LLM-as-Judge. I expect NLG evaluation will continue to evolve in the future. In particular, impact, qualitative, and safety evaluation will become more important as large numbers of people routinely use NLG technology. --- ### Operator Learning for Reconstructing Flow Fields from Sparse Measurements: a Language Model Approach Authors: Qian Zhang, George Em Karniadakis Published: 2026-05-22 Categories: cs.CE, cs.LG arXiv: https://arxiv.org/abs/2605.23712v1 Reconstructing flow fields from sparse measurements is a fundamental problem in fluid mechanics with broad implications for modeling, control, and design. In this work, we propose a novel operator learning framework that leverages the architecture of language models to perform flow reconstruction in a mesh-free manner. We reformulate flow field reconstruction as a sequence-to-sequence learning task, where sparse measurements are treated as context and unobserved locations as queries. Our model learns to reconstruct the full flow field from sparse inputs, effectively capturing spatial correlations and long-range dependencies. We evaluate the proposed approach on four benchmark datasets: (1) two-dimensional vortex street simulations, (2) daily average temperature data across the contiguous United States, (3) three-dimensional blood flow simulations based on dissipative particle dynamics, and (4) three-dimensional turbulent jet flow measurements obtained via particle tracking velocimetry. Across all cases, our method demonstrates competitive reconstruction accuracy, even with highly incomplete data (less than 10\% observed), and achieves efficient performance. The results highlight the potential of language models as robust and scalable tools for scientific data reconstruction, and suggest a promising direction toward the development of foundation models for scientific and engineering applications. --- ### A graph-based analysis of semantic types and coercion in contextualized word embeddings Authors: Long Chen, Deniz Ekin Yavas Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23710v1 Semantic type mismatch between a noun and its context is central to coercion phenomena. This paper introduces a graph-based method to examine how lexical and contextual type information is reflected in word embeddings. We select nouns from ten semantic types, annotate corpus instances for type matching (matching vs. coercion vs. other mismatch vs. unrestricted), and construct graphs using BERT and sense-enhanced embeddings. Two metrics -- Neighbor Type Probability (NTP) and Neighbor Type Entropy (NTE) -- are proposed to analyze neighborhood type distributions. Results show that graphs constructed with sense-enhanced embeddings reflect semantic type information better, and matching and mismatch sentences can be distinguished through the proposed metrics. --- ### Learning Dynamic Stability Landscapes in Synchronization Networks Authors: Christian Nauck, Junyou Zhu, Michael Lindner, Frank Hellmann Published: 2026-05-22 Categories: cs.LG, eess.SY, nlin.AO arXiv: https://arxiv.org/abs/2605.23708v1 The robustness of synchronization is typically characterized by scalar, per-node stability indices whose dependence on topology is studied via network science or graph neural networks (GNNs). We propose a novel upstream task, learning stability landscapes, which provide deeper insights into synchronization behavior and from which many such scalar indices can be derived. Crucially, we pioneer a graph-to-image prediction paradigm: learning image-like landscapes as per-node targets directly from graph topology, a formulation we are not aware of having been established elsewhere in the literature. To support this task, we release two datasets of 10,000 graphs each at 20 and 100 nodes with per-node landscape labels, based on a conceptual oscillator model, capturing power grid synchronization behavior. A GNN encodes topology and a CNN decoder renders per-node images, learned end-to-end with good in-distribution accuracy, generalizing across graph sizes and to realistic power grid topologies. This demonstrates that stability landscapes, while beyond the reach of conventional network science, are learnable from topology and open new avenues for moving beyond scalar stability indices in biology, neuroscience, and power grids. --- ### Metadata Predictability Is Not Evidence Dependence: An Intervention-Based Audit for Weak-Label Benchmarks Authors: Kan Shao Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23701v2 We study a protocol-level test for weak-label benchmarks: whether benchmark outputs change when the provided evidence is intervened on. Metadata-only shortcut checks answer a different question, namely whether outputs are predictable from metadata priors. We therefore combine a metadata statistic, the Metadata Prior Dominance Score (MPDS), with an evidence-intervention statistic, ΔEvi, measuring sensitivity to evidence identity under cross-item shuffling. Synthetic HotpotQA gives a constructed counterexample to metadata-only screening: MPDS is only moderate (0.643), yet ΔEvi is zero. Stronger-reader reruns show why calibration belongs in the test procedure: SNLI shows a calibration reversal, reconstructed HotpotQA occupies a question-dominant warning region, and FEVER is a strongly evidence-sensitive positive control across four transformers. The practical lesson is simple: benchmark audits should report metadata-only screening, evidence intervention, and reader-strength calibration together. --- ### CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models Authors: León Begiristain, Olaf Dünkel, Adam Kortylewski Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23699v1 Video prediction is increasingly viewed as a path toward generalizable world models, yet it remains unclear whether these systems learn underlying causal structure or merely exploit superficial visual correlations for future prediction. We introduce CRONOS, an intervention-based benchmark designed to evaluate counterfactual physical consistency: whether a model's predictions of physical events respond appropriately to controlled changes in the visual input, such as variations of scene context, viewpoint, object appearance, and object category. Built in a photorealistic Unreal Engine environment, CRONOS enables controlled, high-fidelity generation of videos across diverse scenes and dynamics. In contrast to previous benchmarks, CRONOS systematically intervenes on four key factors - viewpoint, scene, object category, and object appearance - while keeping the underlying physical event type, such as a collision, occlusion, or fall, fixed. Our evaluation of recent open-source video generators reveals substantial failures in counterfactual physical consistency: prediction quality for the same physical event type is affected by appearance, environment, and, particularly by viewpoint changes. CRONOS provides a controlled and reproducible testbed for diagnosing how the quality of generated videos changes for different interventions, establishing a concrete target for developing models that perform consistently across changes of multiple conditions. The dataset and code are available at our project page. --- ### Graph-based Complexity Forecasts in UK En Route Airspace Using Relevant Aircraft Interactions Authors: Edward Henderson, George De Ath, Nick Pepper Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23696v1 Effectively managing Air Traffic Control Officer (ATCO) workload is crucial in maintaining operational safety. Group supervisors use tools that estimate upcoming traffic load to aid decision-making. However, industry-standard models can fail to capture the nuances of upcoming air traffic complexity. This study presents a probabilistic approach to forecast the complexity of an airspace sector using the number of relevant aircraft pairs, i.e., those that require monitoring or deconfliction by a controller, as a proxy measure for ATCO workload. We adapted an existing filter algorithm to make it suitable for use in London Middle Sector (LMS), a complex airspace sector with multiple flows of traffic above some of the busiest airports in Europe. Through iterative feedback with ATCOs, the algorithm was refined and extended to handle specific geometric and operational considerations. The updated algorithm outperformed the original, with an F1-score of 0.84 compared to 0.69 on a labelled set of 50 traffic scenarios. To produce forecasts of future numbers of relevant aircraft pairs in the sector, a graph representation of the LMS route network was constructed, standardising the spatial fidelity of route legs. The forecasting method accounts for uncertainty in aircraft arrival times by modelling the probability of each aircraft occupying route segments at future query times. When combined with historic distributions of relevant interactions and a live operational data stream, predictions of upcoming ATCO workload could be made up to 45 minutes in advance. The proposed method to forecast upcoming workload showed a significantly stronger correlation with actual relevant interactions (Spearman's $ρ= 0.68$) than a standard traffic volume prediction ($ρ= 0.55$). The resulting data-driven tool shows promise for use by group supervisors to inform sector configuration and ATCO rostering decisions. --- ### ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models Authors: Fen Wang, Zekai Shao, Qiman Kang, Chunran Hu, Zhixuan Zhang, Lexu Xie, Chao Liu, Siming Chen Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23694v3 Chart descriptions are essential for accessibility, cross-modal retrieval, and assisting readers in extracting insights from complex visualizations. As multimodal large language models (MLLMs) are increasingly adopted for automated chart description generation, a critical question arises: how faithfully and insightfully do these models actually describe charts? Current benchmarks fall short on two fronts: existing datasets consist of simple, homogeneous charts paired with shallow, fact-enumerating descriptions; and prevailing metrics fail to capture the multi-faceted nature of description quality. To address these gaps, we present the Chart Faithfulness and Insightfulness Benchmark (ChartFI-Bench). We first summarize four dimensions that characterize high-quality chart descriptions: factual accuracy, salient feature emphasis, domain-informed guidance, and chart-text complementarity. Guided by these dimensions, we construct a high-quality benchmark comprising 896 chart-description pairs, which feature visually complex charts and semantically rich descriptions. Furthermore, we design four aligned evaluation metrics -- Faithfulness, Coverage, Informativeness, and Acuity -- to systematically assess the quality of descriptions across these dimensions. Experiments conducted on mainstream MLLMs demonstrate the effectiveness of the proposed framework and reveal common weaknesses among existing models. --- ### ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models Authors: Fen Wang, Zekai Shao, Qiman Kang, Chunran Hu, Zhixuan Zhang, Lexu Xie, Chao Liu, Siming Chen Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23694v2 Chart descriptions are essential for accessibility, cross-modal retrieval, and assisting readers in extracting insights from complex visualizations. As multimodal large language models (MLLMs) are increasingly adopted for automated chart description generation, a critical question arises: how faithfully and insightfully do these models actually describe charts? Current benchmarks fall short on two fronts: existing datasets consist of simple, homogeneous charts paired with shallow, fact-enumerating descriptions; and prevailing metrics fail to capture the multi-faceted nature of description quality. To address these gaps, we present the Chart Faithfulness and Insightfulness Benchmark (ChartFI-Bench). We first summarize four dimensions that characterize high-quality chart descriptions: factual accuracy, salient feature emphasis, domain-informed guidance, and chart-text complementarity. Guided by these dimensions, we construct a high-quality benchmark comprising 896 chart-description pairs, which feature visually complex charts and semantically rich descriptions. Furthermore, we design four aligned evaluation metrics -- Faithfulness, Coverage, Informativeness, and Acuity -- to systematically assess the quality of descriptions across these dimensions. Experiments conducted on mainstream MLLMs demonstrate the effectiveness of the proposed framework and reveal common weaknesses among existing models. --- ### Optimization of randomized neural networks for transfer operator approximation Authors: Mohammad Tabish, Stefan Klus Published: 2026-05-22 Categories: cs.LG, math.DS arXiv: https://arxiv.org/abs/2605.23689v1 RaNNDy is a randomized neural network architecture for the data-driven approximation of transfer operators associated with complex dynamical systems. The weights and biases of the hidden layers of the network are randomly initialized and kept fixed, only the output layer is trained. This has several advantages over fully optimized neural networks, notably a closed-form solution for the output layer and significantly lower training costs. Despite these advantages, RaNNDy is restricted to the initial selection of weights and biases that parametrize the basis functions required for the operator approximation. Since the basis functions are determined by the activation function, choosing an appropriate activation function for the hidden layers is crucial. In this work, we propose an algorithm that optimizes the activation function itself, while keeping the weights and biases in the randomized neural network fixed, providing a more suitable dictionary. We illustrate the efficacy of the approach using various benchmark problems, including stochastic differential equations and random walks on graphons. --- ### Relevant Walk Search for Explaining Graph Neural Networks Authors: Ping Xiong, Thomas Schnake, Michael Gastegger, Grégoire Montavon, Klaus-Robert Müller, Shinichi Nakajima Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23673v1 Graph Neural Networks (GNNs) have become important machine learning tools for graph analysis, and its explainability is crucial for safety, fairness, and robustness. Layer-wise relevance propagation for GNNs (GNN-LRP) evaluates the relevance of \emph{walks} to reveal important information flows in the network, and provides higher-order explanations, which have been shown to be superior to the lower-order, i.e., node-/edge-level, explanations. However, identifying relevant walks by GNN-LRP requires {\em exponential} computational complexity with respect to the network depth, which we will remedy in this paper. Specifically, we propose {\em polynomial-time} algorithms for finding top-$K$ relevant walks, which drastically reduces the computation and thus increases the applicability of GNN-LRP to large-scale problems. Our proposed algorithms are based on the \emph{max-product} algorithm -- a common tool for finding the maximum likelihood configurations in probabilistic graphical models -- and can find the most relevant walks exactly at the neuron level and approximately at the node level. Our experiments demonstrate the performance of our algorithms at scale and their utility across application domains, i.e., on epidemiology, molecular, and natural language benchmarks. We provide our codes under \href{https://github.com/xiong-ping/rel_walk_gnnlrp}{github.com/xiong-ping/rel\_walk\_gnnlrp}. --- ### RiGS: Rigid-aware 4D Gaussian Splatting from a Single Monocular Video Authors: Chenyu Wu, Wanhua Li, Zhu-Tian Chen, Hanspeter Pfister Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23672v1 Reconstructing dynamic 3D scenes from monocular videos is a fundamental yet highly challenging task, as real-world motions often involve both long-term smooth transformations and short-term complex deformations. Existing methods either struggle to maintain temporal consistency or fail to capture high-frequency dynamics due to limited motion modeling capacity. In this work, we present Rigid-aware 4D Gaussian Splatting (RiGS), which simultaneously captures motions across multiple temporal scales. Specifically, RiGS introduces three types of Gaussian primitives: static, rigid, and transient, which represent static backgrounds, long-term low-frequency motions, and short-term high-frequency dynamics, respectively. An object-wise dynamic mask is proposed to aggregate long-range spatiotemporal motion information and guide the decomposition of static and dynamic regions. To jointly model motion across scales, rigid Gaussians are allowed to transition into transient Gaussians based on their temporal duration, and both are optimized under scene flow guidance, providing dense 3D motion supervision. Extensive experiments demonstrate that RiGS achieves state-of-the-art performance on novel view synthesis benchmarks. Code is available at \hyperlink{https://github.com/ladvu/RiGS}{https://github.com/ladvu/RiGS}. --- ### OnePred: Next-Query Prediction via Recursive Intent Memory in Multi-Turn Conversations Authors: Jiangwang Chen, Bowen Zhang, Zixin Song, Jiazheng Kang, Xiao Yang, Da Zhu, Guanjun Jiang Published: 2026-05-22 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.23668v2 Although large language model (LLM) conversational systems process millions of multi-turn dialogues daily, they remain fundamentally reactive: they respond only after the user types a query. A key step toward proactive interaction is next-query prediction, which anticipates the user's subsequent query based solely on the preceding dialogue. Progress on this task is hindered by the lack of dedicated benchmarks and a fundamental efficiency--quality trade-off: naively concatenating full dialogue history incurs linearly growing token consumption, while truncating to the latest turn discards crucial cross-turn context. Our key insight is that accurate prediction does not require re-reading raw history; it suffices to track the user's evolving intent trajectory across topics, unresolved needs, and interest shifts. We propose OnePred, which maintains a recursively updated memory as its sole cross-turn context, bounding the per-turn cost independently of conversation length. We train the model via a two-stage reinforcement learning pipeline that first teaches what to predict, then what to compress, shaping the memory into a prediction-oriented intent chain. To establish a rigorous testbed, we introduce NQP-Bench, spanning three diverse subsets. Experiments demonstrate that OnePred reduces per-turn token consumption by up to 22$\times$ compared to full-history inputs while consistently exceeding all baselines in prediction quality, with larger gains on longer conversations. Our code is publicly available at https://github.com/ZBWpro/OnePred. --- ### Detecting Drunk Driving Using Off-the-Shelf Smartwatches Authors: Robin Deuber, Lanlan Yang, Michal Bechny, Christoph Heck, Matthias Pfäffli, Matthias Bantle, Florian von Wangenheim, Elgar Fleisch, Wolfgang Weinmann, Manuel Günther, Felix Wortmann, Varun Mishra Published: 2026-05-22 Categories: cs.HC, cs.LG arXiv: https://arxiv.org/abs/2605.23663v1 Alcohol-impaired driving remains a major yet preventable cause of road traffic injury and death, with many drivers underestimating their level of intoxication. Compared to in-vehicle systems, mobile drunk-driving detection using consumer smartwatches offers a scalable way to trigger preventive interventions and increase awareness without additional in-vehicle hardware. We introduce a system that leverages wrist accelerometer data and heart rate variability-derived physiological signals to detect alcohol-related driving impairment. We collected data in a randomized, controlled three-arm test-track study (n=54) and trained both logistic regression models with window-aggregated features and a two-tower 1D convolutional neural network (CNN), to detect alcohol-impaired driving. The CNN achieved a participant-averaged area under the receiver operating characteristic (AUROC) of 0.88 for detecting any alcohol intoxication and 0.86 for detecting driving above the WHO-recommended limit of 0.05 g/dL. To the best of our knowledge, this is the first work to (1) demonstrate drunk-driving detection using consumer smartwatches, (2) develop and evaluate such a system in a real vehicle on a closed test track, and (3) rigorously assess generalization to unseen participants. Together, these findings highlight the potential of wearable-based sensing to support scalable, measurement-driven prevention of alcohol-related traffic harm. --- ### OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents Authors: Jiahao Ying, Boxian Ai, Wei Tang, Siyuan Liu, Yixin Cao Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23657v2 Skills, i.e., structured workflow instructions distilled for large language models (LLMs), are becoming an increasingly important mechanism for improving agent performance on real-world downstream tasks. However, as the open-source skill ecosystem rapidly expands, it remains unclear how different models and agent frameworks interact with skills, how to evaluate skill quality, and how users should select skills under practical cost-performance trade-offs. In this paper, we present \textsc{OpenSkillEval}, an automatic evaluation framework for both skill-augmented agent systems and the skills themselves. Instead of relying on static benchmarks, \textsc{OpenSkillEval} automatically constructs realistic task instances from evolving real-world artifacts across five categories of downstream applications: presentation generation, front-end web design, poster generation, data visualization, and report generation. It further collects and organizes community-contributed skills for controlled comparison under unified task settings. Using more than 600 dynamically generated task instances and 30 open-source skills, we conduct a systematic evaluation of state-of-the-art models and agent frameworks. Our results show that skill availability does not guarantee effective skill usage, that the benefit of skill augmentation depends strongly on both the underlying model and the agent framework, and that many publicly popular skills do not consistently outperform base agents without skills. These findings highlight the need for dynamic, task-grounded evaluation and provide practical insights into the design, selection, and deployment of skills for LLM agents. Additional cases and benchmark resources are available on the project website: https://yingjiahao14.github.io/OpenSkillEval-Web/. --- ### Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models Authors: Maxim Henry, Adrien Deliège, Sébastien Piérard, Marc Van Droogenbroeck Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23656v2 Training high-capacity vision models from scratch requires substantial computational resources. To improve training efficiency of a wide target model, existing growth methods often assume the availability of narrower models, obscuring the true computational cost of the entire pipeline. We propose an efficient training protocol, RBDC, that builds wide models by coupling in a parameter-free block-diagonal way narrower, independently trained models in a recursive way. This allows a flexible allocation of the training budget available across all the models involved. Evaluated with vision transformers (DeiT) and convolutional networks (ResNet) on ImageNet, our RBDC training protocol shows a much better efficiency than models trained from scratch with the standard protocol, yielding 30% FLOPs reduction at similar test accuracies. It also achieves higher performances at same training FLOPs than training protocols from the model growth literature. Finally, we show that our models can serve as better backbones than their original counterparts for downstream object detection and instance segmentation tasks. --- ### Recursive Block-Diagonal Coupling for Resource-Efficient Training of Vision Models Authors: Maxim Henry, Adrien Deliège, Sébastien Piérard, Marc Van Droogenbroeck Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23656v1 Training high-capacity vision models from scratch requires substantial computational resources. To improve training efficiency of a wide target model, existing growth methods often assume the availability of narrower models, obscuring the true computational cost of the entire pipeline. We propose an efficient training protocol, RBDC, that builds wide models by coupling in a parameter-free block-diagonal way narrower, independently trained models in a recursive way. This allows a flexible allocation of the training budget available across all the models involved. Evaluated with vision transformers (DeiT) and convolutional networks (ResNet) on ImageNet, our RBDC training protocol shows a much better efficiency than models trained from scratch with the standard protocol, yielding 30% FLOPs reduction at similar test accuracies. It also achieves higher performances at same training FLOPs than training protocols from the model growth literature. Finally, we show that our models can serve as better backbones than their original counterparts for downstream object detection and instance segmentation tasks. --- ### CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception Authors: Liupeng Li, Haoqian Kang, Zhenyu Lu, Jinpeng Wang, Bin Chen, Ke Chen, Yaowei Wang Published: 2026-05-22 Categories: cs.CV, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2605.23655v1 High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency. Visual expert-assisted search is efficient but prone to blind spots when proposals fail, whereas scan-based search guarantees coverage at the cost of computational redundancy and semantic fragmentation. To address this dilemma, we introduce CVSearch, a training-free adaptive framework that dynamically schedules search strategies via an Assess-then-Search workflow. Specifically, CVSearch first invokes expert-assisted search when global information is insufficient, and only triggers a novel semantic-aware scanning mechanism upon failure. Distinct from rigid grid partitioning, this efficient scanning paradigm incorporates Semantic Guided Adaptive Patching to decompose images into semantically consistent regions, effectively mitigating object fragmentation. Furthermore, we devise a Dynamic Bottom-Up Search strategy driven by a Visual Complexity prior to enable efficient and precise iterative exploration of local details. Extensive experiments on HR benchmarks demonstrate that CVSearch achieves state-of-the-art accuracy while substantially improving search efficiency. Code is released at https://github.com/liliupeng28/ICML26-CVSearch. --- ### ExpOS: Explainable Open-Surgery Skills Assessment Using 3D Hand Reconstruction Authors: Roi Papo, Idan Smoller, Shlomi Laufer Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23653v1 Timely and transparent feedback is essential for effective surgical training, yet current assessment remains dependent on expert observation, limiting scalability and opportunities for autonomous practice. We present ExpOS, an explainable framework for data-driven assessment of open-surgery skills designed to enable automatic, feedback-oriented evaluation. Rather than relying on expert-defined metrics, ExpOS learns discriminative temporal patterns directly from motion data and identifies the segments and behaviors most predictive of skill level. We trained and evaluated the method on 221 videos of medical students performing three open-surgery tasks. Hand poses and tool detections were extracted from each frame to derive kinematic descriptors and global motion statistics. Spatiotemporal hand-tool dynamics were modeled using a temporal convolutional backbone with attention-based pooling to generate frame-level importance maps. These representations were fused with global motion statistics to predict skill level and to provide interpretable feedback. ExpOS provides multi-level explainability by identifying when informative events occur through attention weights and which motion characteristics most influence predictions through global feature analysis. Across tasks, the framework achieved strong correlation with expert ratings, with best performance on fascial closure (r = 0.778, R2 = 0.74). These results demonstrate that combining weakly-supervised temporal importance learning with interpretable motion statistics enables scalable and actionable surgical skill assessment. --- ### One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents Authors: Yoosung Hong Published: 2026-05-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.23652v1 On a 300-persona life-simulation benchmark, pcsp achieves compositional zero-shot persona identification up to 17x above chance, Spearman rho approx 0.73 semantic-behavioral alignment, and 22x faster inference than an LLM-as-policy baseline. Life simulation games require hundreds to thousands of non-player characters (NPCs) that behave consistently with distinct personalities while remaining controllable through designer-authored natural language. Existing methods fail on constraints like persona consistency, controllability, or real-time inference. We introduce pcsp (Persona Conditioned Shared Policy), a single reinforcement learning policy conditioned on frozen LLM embeddings of free-form persona descriptions. pcsp combines once-per-NPC persona encoding, low-rank persona projection, neural persona conditioning, and a PPO + InfoNCE consistency + KL diversity training objective. Across three experimental settings, ablations show that the InfoNCE trajectory-consistency objective is load bearing: removing it collapses zero-shot persona identification to chance. External validation on Melting Pot 2.4.0 substrates confirms that our method produces persona-conditioned behavioral divergence in multi-agent strategic environments. We distinguish two senses of held-out evaluation: compositional zero-shot and vocabulary-expansion held-out. Finally, a UE5 deployment reproduces the in-engine persona-conditioning ablation at 64 agents with a low failure rate, showing that the sub-frame inference profile survives in a commercial game engine. These results prove that shared RL policies can support scalable, real-time, persona-conditioned NPC control. --- ### How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework Authors: Björn Nieth, Marianna Gracheva, Michaela Mahlberg, Bjoern Eskofier, Emmanuelle Salin Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23651v4 While factual correctness and task-performance have been in focus of Large Language Model (LLM) research for a long time, the fundamental question of how human-like generated texts are on a linguistic level has been underexplored. From a corpus-linguistic perspective, language production is inherently context-dependent, with distinct communicative contexts giving rise to differences in frequencies and co-occurrence patterns of linguistic features. A text failing to adhere to these patterns can be content-wise correct, but still be unfavorable to human readers. In this work, we propose a context-aware evaluation framework in which human-likeness is assessed using a two-sample problem between the linguistic feature distribution of a human reference corpus for a given register and a corresponding LLM-generated corpus. We implement this framework using the Maximum Mean Discrepancy (MMD) and the 67 lexico-grammatical features introduced by Biber, which are commonly applied in corpus linguistics. In our experiments, we compare seven instruction-tuned, open-source models across five English-language datasets spanning distinct registers against a human baseline. While across all tested setups, LLMs deviate from the human baseline, which models are closest to human language depends on the register and is not dictated by model size. --- ### How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework Authors: Björn Nieth, Marianna Gracheva, Michaela Mahlberg, Bjoern Eskofier, Emmanuelle Salin Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23651v2 While factual correctness and task-performance have been in focus of Large Language Model (LLM) research for a long time, the fundamental question of how human-like generated texts are on a linguistic level has been underexplored. From a corpus-linguistic perspective, language production is inherently context-dependent, with distinct communicative contexts giving rise to differences in frequencies and co-occurrence patterns of linguistic features. A text failing to adhere to these patterns can be content-wise correct, but still be unfavorable to human readers. In this work, we propose a context-aware evaluation framework in which human-likeness is assessed using a two-sample problem between the linguistic feature distribution of a human reference corpus for a given register and a corresponding LLM-generated corpus. We implement this framework using the Maximum Mean Discrepancy (MMD) and the 67 lexico-grammatical features introduced by Biber, which are commonly applied in corpus linguistics. In our experiments, we compare seven instruction-tuned, open-source models across five English-language datasets spanning distinct registers against a human baseline. While across all tested setups, LLMs deviate from the human baseline, which models are closest to human language depends on the register and is not dictated by model size. --- ### Learning Kernel-Based MDPs from Episodic Preferential Feedback Authors: Nikola Pavlovic, Sattar Vakili, Qing Zhao Published: 2026-05-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.23650v2 Human feedback often arrives as preferences rather than calibrated numeric rewards, motivating reinforcement learning from preferential feedback, also referred to as reinforcement learning from human feedback (RLHF). We present a rigorous theoretical study of preference-only learning in episodic kernel MDPs. In each episode, the learner deploys two policies from a common start state and receives a single binary label indicating which trajectory is preferred, modeled by a Bradley--Terry--Luce link on the difference of cumulative (unobserved) rewards. Under kernel-based assumptions on the reward and transition functions (one of the most general models amenable to theoretical analysis) we develop preference-based value estimation and confidence sets tailored to end-of-episode comparisons. We prove high-probability regret bounds that scale sublinearly in the number of episodes, implying that the value of the learned policy converges to that of the optimal policy. --- ### Learning Through Noise: Why Subliminal Learning Works and When It Fails Authors: Vincent C. Brockers, Roman D. Ventzke, Valentin Neuhaus, Belén Hidalgo-Ogalde, Viola Priesemann Published: 2026-05-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.23645v1 In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher to student models through distillation on task-unrelated input$\unicode{x2013}$output pairs. Prior explanations tie this effect to shared or closely matched teacher$\unicode{x2013}$student initialization. We show that a closely matched initialization is not necessary. Instead, subliminal learning is governed by compatible output heads. Using a controlled MNIST setting, we split outputs into an auxiliary head (for auxiliary, task-unrelated noise signals) and a class head (for classification) to demonstrate subliminal learning occurs$\unicode{x2014}$even when we randomly initialize hidden layers and remove layers, add new layers, or change the architecture (MLP-to-CNN). Compatible auxiliary heads enable transfer of a recoverable teacher signal, bringing the student's representations closer to the teacher's. When the class heads remain compatible as well, students trained only on task-unrelated noise can approach, and in favorable regimes match, teacher-level task performance. Our setting enables us to develop a theory that explains the mechanism of subliminal learning and to derive upper bounds on when subliminal learning fails. Together, our results turn subliminal learning from a surprising transfer effect into a theoretically grounded mechanism with predictable limits. --- ### Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in Tamarin Authors: Matthias Cosler, Cas Cremers, Bernd Finkbeiner, Mohamed Ghanem, Niklas Medinger Published: 2026-05-22 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.23643v1 Tools like Tamarin and ProVerif have achieved notable success in analyzing and verifying complex real-world protocols such as EMV, 5G, and WPA2, even detecting zero-day exploits. Despite these successes, verifying such protocols remains a time-consuming, challenging task, often requiring significant human effort and expertise. In this paper, we present a reinforcement learning (RL) framework inspired by AlphaZero and AlphaProof that implements a new style of proof search for Tamarin. We have developed a stateless API for Tamarin that acts as a classical RL environment. We guide a Monte Carlo Tree Search (MCTS) by a neural heuristic that learns from completed subproofs. We evaluate our framework on 16 case studies, ranging from classical protocol models to challenging state-of-the-art protocol models from recent publications. Our method finds more proofs automatically than Tamarin's standard search and produces shorter proofs than both the standard and human-engineered heuristics. Our pipeline is applicable out of the box to assist Tamarin users in active research, reducing the human effort required. Moreover, our standardized interface provides a programmatic way for users to interact with Tamarin. Finally, our work demonstrates the promising potential of adapting RL-based methods to the Tamarin domain. --- ### Dirichlet-Based Monte Carlo Dropout for Uncertainty Estimation in Neural Networks Authors: Rouaa Hoblos, Noura Dridi, Noureddine Zerhouni, Zeina Al Masry Published: 2026-05-22 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.23635v1 Traditional neural networks provide deterministic predictions without inherent uncertainty estimates. While Bayesian Neural Networks (BNNs) offer a principled approach to uncertainty quantification, their computational complexity limits scalability. Monte Carlo (MC) Dropout, initially introduced as a regularization technique, has been shown to approximate Bayesian inference by enabling probabilistic modeling through multiple stochastic forward passes. In this work, we enhance uncertainty estimation in deep learning by integrating a Dirichlet-based framework within MC Dropout. Specifically, we leverage the formulation proposed by Sensoy et al. (2018), where class probabilities are modeled using a Dirichlet distribution, allowing for a more informative uncertainty representation. The proposed approach maintains the computational efficiency of MC Dropout while improving the quality of uncertainty estimates. We discuss the theoretical foundations of our method and compare it with existing uncertainty quantification techniques. The results highlight the effectiveness of the proposed method in producing well-calibrated uncertainty estimates, offering a practical solution for uncertainty-aware deep learning models. --- ### DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in Open-World Object Detection Authors: Yingjun Xiao, Xi Chen, Gang Fang, Siyuan Chen Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.23634v1 Open-world object detection (OWOD) requires detectors to localize known classes while identifying unknown objects for future incremental learning. We find that the unknown prediction streams of strong OWOD detectors are heavily polluted: on M-OWODB, across PROB, OW-DETR, and HypOW, future-task positive unknowns make up less than 10% of unknown predictions, whereas background false positives account for 46-71%. We show that this is not a missing-information problem, but an information bottleneck at the objectness head. On PROB Task 1, a linear probe on the 256-D decoder query achieves an AUROC of 0.908 for positive-versus-negative unknown discrimination, but the final one-dimensional objectness scalar drops to 0.642. A frozen SigLIP feature, without access to the detector, independently recovers much of this proposal-level separability at the filtering stage (AUROC = 0.871). Motivated by this finding, we propose DualMem, a calibrated post-hoc filter that assumes a small image-disjoint annotated calibration split of held-out future-task objects and performs a non-parametric likelihood ratio test in frozen SigLIP feature space. DualMem uses a k-nearest-neighbor positive memory to protect future-task objects and a negative memory to suppress background-like proposals. Its decision threshold is chosen by Neyman-Pearson calibration, giving users an explicit trade-off between false-unknown suppression and novel recall. Across PROB, OW-DETR, and HypOW on M-OWODB Task 1, DualMem reduces background-type false unknown proposals per image by 44.9%-66.3%, with a mean reduction of 56.6%. On PROB Task 1, it more than doubles the reduction achieved by a natural K-means prototype baseline, while leaving known-class mAP unchanged because known detections bypass the filter. --- ### Gaussian Mixture Copula Processes for Irregular Time Series Authors: Christian Klötergens, Tom Hanika, Lars Schmidt-Thieme, Vijaya Krishna Yalavarthi Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23632v2 We introduce Gaussian Mixture Copula Processes (GMCP), a conditional copula process for irregularly sampled multivariate time series (IMTS) that is expressive and marginalization consistent at the same time. Existing conditional copula processes achieve only one of the two. Gaussian copula processes are consistent by construction but confined to elliptical dependence, whereas attentional copulas such as TACTiS-2 are far more expressive but neither preserve the marginals they are built on nor guarantee that integrating out a target point returns the joint over the remaining ones. GMCP closes this gap by inferring the parameters of a Gaussian Mixture Copula from the context in a way that guarantees consistent marginalization. This yields a non-elliptical copula process with tractable likelihood and consistency guarantees. Our experiments show that copulas equipped with MargFlow, a normalizing-flow model for the univariate marginals fitted in isolation, outperform jointly trained baselines in probabilistic IMTS forecasting. We further provide evidence that GMCP is more expressive than Gaussian copula processes, and on par with the inconsistent TACTiS-2. --- ### Valid and Expressive Copulas for Irregular Multivariate Time Series Authors: Christian Klötergens, Tom Hanika, Lars Schmidt-Thieme, Vijaya Krishna Yalavarthi Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23632v1 We introduce CopFITi, a copula model for probabilistic forecasting of irregular multivariate time series (IMTS). Our model combines the expressivity of normalizing flows for univariate marginals with the consistency and flexibility of a Gaussian Mixture Copula for the joint dependency structure. Our experiments show that copula-based approaches, which decouple the marginals from the joint, yield better marginal models than architectures that directly fit the full joint. With CopFITi, we propose the first IMTS copula that is marginalization-consistent by construction and establish a new state of the art in joint IMTS density modeling. --- ### DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs Authors: Jiazhen Pan, Weixiang Shen, Jun Li, Julian Canisius, Felix Bitzer, Paula Roßmüller, Jiancheng Yang, Virginie Kreutzinger, Daniel Rueckert, Benedikt Wiestler Published: 2026-05-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.23629v1 Medical diagnosis is not a single prediction from a fully specified vignette. It is a sequential workup: clinicians decide what evidence to obtain, revise a differential diagnosis, and stop when the diagnosis is sufficiently supported. Most medical AI benchmarks instead reveal the relevant context upfront and score only the final answer, making unsupported correct guesses, premature closure, inefficient workups, and poor uncertainty updating invisible. We introduce DDX-TRACE, a physician-adjudicated benchmark for multimodal neuroradiology that evaluates diagnostic trajectories under hidden evidence over 211 challenging cases. Each case begins with limited clinical history; models request imaging studies in free form, receive matched image bundles when available, update a probabilistic differential diagnosis after each turn, and stop with a localized final diagnosis. Evaluating state-of-the-art VLMs, we find that final diagnosis scores can substantially misrepresent workup quality: models may guess plausible diagnoses without essential evidence, request useful studies but misinterpret raw images, or acquire evidence inefficiently while updating uncertainty poorly. Controlled evidence variants isolate bottlenecks in planning, visual evidence extraction, and downstream differential reasoning. DDX-TRACE shifts medical AI evaluation from final answers to evidence-supported diagnostic trajectories. --- ### How Hard is it to Rig a Benchmark? A Social Choice Analysis of Leaderboard Robustness Authors: Polina Gordienko, Georg Schollmeyer, Frauke Kreuter, Christoph Jansen Published: 2026-05-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.23628v1 Multi-task benchmarks have become a central pillar of machine learning research, yet their growing influence has incentivised benchmark gaming -- strategic actions taken to improve the leaderboard rank of a specific model. Treating datasets as voters and models as candidates, we consider benchmark-specific training -- the inclusion of benchmark data in training -- as a form of election manipulation. For any ordinal benchmark, the problem of choosing datasets to train on so that a target model becomes top-ranked corresponds to shift bribery, a class of manipulation problems from computational social choice. Leveraging this identification, we show that the benchmark-specific training problem is NP-hard under Borda count and mean win rate. Complementing this worst-case perspective, we introduce the instance-level robustness, the minimum number of datasets a model developer must include in training to top a given leaderboard, and derive expressions for it under arithmetic mean, median, mean win rate and pairwise majority. We evaluate these expressions on MMLU under HELM and on BIG-Bench Hard (BBH) under the Open LLM Leaderboard. Across both suites, mean win rate is hardest to manipulate: this gap is clear on BBH (24 tasks, 4507 models), where its median robustness is 22 tasks (92%), compared with 13 (54%) under arithmetic mean and 12 (50%) under median and pairwise majority. --- ### Adversarial Vulnerability Under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection Authors: Ahmed Sabbah, Mohammed Kharma, Radi Jarrar, Samer Zein, David Mohaisen Published: 2026-05-22 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23623v1 We present a longitudinal, drift-aware evaluation of adversarial robustness across more than a decade of Android applications using static and dynamic feature representations extracted from emulator and real-device executions. The dataset is organized into yearly slices and evaluated under three deployment protocols that emulate realistic learning scenarios: (1) same-year training and testing, (2) cross-year deployment without model updates, and (3) expanding-window retraining with cumulative historical data. Across multiple classifier families, adversarial examples are generated using FGSM and SPSA under feasibility constraints. We measure clean performance, Adversarial Accuracy (AA), Attack Success Rate (ASR), and introduce temporal linkage metrics -- RobustDrop, $Δ$ASR, and Adversarial Amplification Factor (AAF) -- to quantify the relationship between distribution shift and robustness degradation.nResults show that temporal separation is associated with reduced adversarial robustness under the evaluated transfer-based feature-space setting. As the train-test gap increases, clean accuracy and adversarial accuracy decline, while attack success exhibits configuration-dependent increases, particularly under FGSM perturbations and static features. Expanding-window retraining mitigates, but does not eliminate, robustness loss under continued distributional evolution. These findings indicate that temporal drift should be considered when assessing the long-term robustness of intelligent detection systems under evolving data distributions and highlight the need for drift-aware robustness assessment frameworks in long-lived adversarial environments. --- ### Benchmarking Google Embeddings 2 against Open-Source Models for Multilingual Dense Retrieval and RAG Systems Authors: Stefano Cirillo, Domenico Desiato, Giuseppe Polese, Giandomenico Solimando Published: 2026-05-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.23618v1 We benchmark Google Embeddings (GE2), a Vertex-AI-hosted bi-encoder with 2,048-token context and explicit task-type conditioning, against five open-source alternatives: BGE-M3, E5-large, Multilingual-E5-large (mE5-L), LaBSE, and Paraphrase-Multilingual-MPNet (mMPNet). Evaluation covers four BEIR subsets, a synthetic Italian RAG corpus, a chunking ablation considering 5 sizes of tokens with three strategies, and per-query latency on commodity CPU hardware. GE2 ranks first on every task, achieving BEIR avg.nDCG@10 = 0.638 and IT-RAG-Bench nDCG@10 = 0.282, but at 231.6 ms median latency, it is roughly 14x slower than the fastest local models. mE5-L reaches within 0.003 nDCG of GE2 on Italian at 31 ms, making it the preferred option when sub-100 ms SLAs matter. A more striking finding concerns LaBSE, which, despite widespread multilingual deployment scores 0.188 average nDCG@10 on BEIR, below every dedicated retrieval model including mMPNet. Chunking experiments show that all six models saturate at 32-token chunks on our corpus, with semantic chunking providing measurable gains only at 16 tokens. --- ### EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation Authors: Jente Vandersanden, Matheus Gadelha, Chun-Hao P. Huang, Hyeonho Jeong, Yulia Gryaditskaya Published: 2026-05-22 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.23610v1 Multi-shot video generation requires maintaining a consistent appearance of recurring entities across shots while remaining faithful to shot-specific text prompts. Recent autoregressive methods reuse previously generated frames as memory. However, full-frame storage entangles persistent entity information with transient scene context, leading to irrelevant information leakage and high computational cost. We propose an entity-centric memory in the form of an entity-indexed bank of latent patches. We introduce sparse token conditioning compatible with pretrained models, restricting self-attention to entity-relevant tokens and reducing computational cost. To support this, we introduce a structured multi-shot script format. We additionally propose a budgeted memory update strategy to maintain a compact, evolving memory. Finally, we equip the entity representation with a noise-injection mechanism that enables fine-grained appearance control, preventing leakage of irrelevant information. Our method improves prompt adherence and efficiency while preserving subject consistency. --- ### DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling Authors: Jean-Marie Lemercier, Tomas Geffner, Karsten Kreis, Morteza Mardani, Arash Vahdat, Ante Jukić Published: 2026-05-22 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.23605v1 Diffusion language models intrinsically fail to capture correlations between decoded tokens, which leads to a harsh trade-off between sampling quality and throughput. To solve this issue, we propose DiLaDiff, a variant of masked diffusion language models with three components: (1) a continuous latent space with semantic capabilities, learned by an auto-encoder fine-tuned from an existing masked diffusion language model; (2) a latent diffusion model learning the prior over the encoder distribution; (3) a consistency model distilling the learned prior into a few-step latent generative model. We show that, even without distillation, our latent-guided diffusion model outperforms the masked diffusion baseline while significantly accelerating inference. Consistency distillation further lowers the computational overhead of continuous diffusion, such that the latent is generated in negligible time compared to discrete decoding. ---