# Research Papers — 2026-05 · bundle page 140 of 326 > Full-text markdown of papers #6951–7000 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/140 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/139.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/141.md) ### Physics-Informed Neural Networks for Radial Consolidation of Combined Electroosmotic, Vacuum and Surcharge Preloading Considering Smear Effects Authors: Dong Li, Yapeng Cao, Shuai Huang, Yujun Cui, Haiping Fu, Lu Yang, He Wei Published: 2026-05-18 Categories: cs.CE, cs.AI, cs.LG, physics.app-ph arXiv: https://arxiv.org/abs/2606.00056v1 This study develops a dimensionless multi-domain physics-informed neural network (PINN) framework for electro-osmotic radial consolidation considering smear effects and combined vacuum and surcharge loading. Three PINN-based models are investigated: a standard soft-constrained PINN (Std-PINN), a modified gated PINN (Mod-PINN), and a modified gated PINN with hard-constraint boundary encoding (Mod-HC-PINN). The models are evaluated against FEM reference solutions under four loading cases, including constant vacuum, exponential vacuum, exponential vacuum with ramp surcharge, and exponential vacuum with cyclic haversine surcharge. The results indicate that the gated architecture applied in Mod-PINN improves the resolution of steep pressure gradients near the cathode and smear-zone interface under constant vacuum loading. Under time-dependent loading, the soft-constrained Mod-PINN shows reduced accuracy because it must learn multiple competing objectives simultaneously. The Mod-HC-PINN mitigates this issue by embedding the cathode boundary and initial conditions into the output structure, thereby reducing the optimization burden and improving physical consistency. The Mod-HC-PINN achieves MAE values of 0.43, 0.41, and 0.27 kPa for the exponential vacuum, ramp surcharge, and cyclic surcharge cases, respectively. Sensitivity analyses further demonstrate that the proposed framework remains robust across practical ranges of network architecture, collocation density, and permeability contrast. --- ### From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data Authors: Zhiyuan Feng, Qixiu Li, Huizhi Liang, Rushuai Yang, Yichao Shen, Zhiying Du, Zhaowei Zhang, Yu Deng, Li Zhao, Hao Zhao, Zongqing Lu, Oier Mees et al. Published: 2026-05-18 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.00054v1 Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models. However, most existing approaches rely on large collections of robot demonstrations, which are costly to obtain and tightly coupled to specific embodiments. Human videos, by contrast, are abundant and capture rich interactions, providing diverse semantic and physical cues for real-world manipulation. Yet, embodiment differences and the frequent absence of task-aligned annotations make their direct use in VLA models challenging. This survey provides a unified view of how human videos are transformed into effective knowledge for VLA models. We categorize existing approaches into four classes based on the action-related information they derive: (i) latent action representations that encode inter-frame changes; (ii) predictive world models that forecast future frames; (iii) explicit 2D supervision that extracts image-plane cues; and (iv) explicit 3D reconstruction that recovers geometry or motion. Beyond this taxonomy, we highlight three key open challenges in this area: structuring unstructured videos into training-ready episodes, grounding video-derived supervision into robot-executable actions under embodiment and viewpoint heterogeneity, and designing evaluation protocols that better predict real-world deployment performance and transfer efficiency, thereby informing future research directions. A curated list of papers and resources is available at https://github.com/AaronFengZY/HumanCentricToVLA-Survey. --- ### Reinterpreting Safety Thresholds as Neuron Spiking Thresholds Authors: Enrico Del Re, Mohamed Sabry, Cristina Olaverri-Monreal Published: 2026-05-18 Categories: cs.NE, cs.AI, cs.RO, q-bio.NC arXiv: https://arxiv.org/abs/2605.30368v1 Surrogate Safety Measures (SSMs) are extensively utilised in the evaluation of traffic risk in automated driving contexts. However, the majority of SSM-based evaluations employ fixed thresholds that fail to capture the human response to sustained borderline conditions or the reaction to brief, high-risk peaks. The present work proposes a biologically inspired reinterpretation of SSM thresholds. This is modelled as spiking thresholds of leaky integrate-and-fire (LIF) neurons, with multiple SSM inputs combined into a spiking neural network (SNN). The SNN is trained to emit spikes that are aligned with human braking onsets. The training data was recorded in a controlled car-following experiment using the 3D-CoAutoSim platform with CARLA/Unreal and a 6-DOF motion platform, where induced critical events were generated. The results demonstrate that the learned spiking activity qualitatively aligns with braking behaviour across scenarios and captures reactions that are not consistently explained by threshold crossings alone. Analysis across participants further indicates that learned input thresholds remain relatively consistent, while learned decay factors encode different temporal sensitivities for the SSMs. The findings of this study indicate that spiking dynamics may serve as a mechanism to facilitate the convergence of objective SSMs with subjective human safety perception. --- ### Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation Authors: Yizhu Wen, Shuhao Zhang, Nan Zhang, Long Cheng, Hanqing Guo Published: 2026-05-18 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2605.30365v1 Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption dataset. This design introduces an integrity dependency on the music knowledge database. We show that an attacker can poison the database by injecting a small number of crafted music captions, causing the system to retrieve malicious captions that bias prompt augmentation and steer generation away from the user's intended function, without modifying the user prompt, retriever, or generator. To achieve the music caption poisoning attack, we propose a dual-layer caption poisoning strategy that preserves high-level retrieval anchors while injecting low-level acoustic descriptors to steer prompt augmentation and downstream music generation toward an attacker-chosen target intent. In a MusicCaps knowledge database, CLAP retriever, and MusicGen pipeline, poisoned generations move substantially closer to the attacker's target, while remaining comparably aligned with the original user query. These results expose a practical integrity risk for retrieval-augmented creative AI systems. Our demo can be found at: https://yizhu-wen.github.io/Mental-Damage/ --- ### Quantum Machine Learning-based 6G edge Network: Enabling Adaptive Communication and Model Aggregation Authors: Wenjing Xiao, Jiatai Yan, Chenglong Shi, Shixin Chen, Miaojiang Chen, Min Chen, Saif Al-Kuwari, Ahmed Farouk Published: 2026-05-18 Categories: quant-ph, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.27417v1 With the advent of sixth-generation (6G) mobile communication technology, vehicle-to-everything (V2X) communication faces unprecedented challenges in communication efficiency, system generalization capabilities, and model collaboration. Conventional machine learning struggles with high-dimensional state spaces, slow convergence, and poor generalization under heterogeneous V2X nodes, rapidly varying channels, and multimodal sensing data in V2X systems. To address these issues, we propose a quantum-enhanced framework for V2X communication and model aggregation that targets efficient, robust, and intelligent transportation in 6G, which includes four modules: the channel-adaptive semantic communication module, the multimodal fusion module, the model transfer module, and the federated aggregation module. Specifically, the channel-adaptive semantic communication module leverages quantum convolutional neural networks (CNN) and quantum distortion metrics to enable efficient transmission and strong generalization across diverse conditions. The multimodal fusion module exploits quantum attention and entanglement to compress features and associate semantics across heterogeneous data. The model transfer module employs quantum reinforcement learning to model decision-making and improve adaptability in dynamic environments. The federated aggregation module integrates quantum tensor decomposition with backpropagation-based corrections to provide privacy preservation with low overhead and to strengthen global model robustness. This work outlines a new paradigm for communication and model collaboration in future 6G intelligent transportation. --- ### Can Quantum Federated Learning Withstand Circuit-Level Backdoors? Authors: Aakar Mathur, Mohammed Ruknuddin, Ashish Gupta Published: 2026-05-18 Categories: quant-ph, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2605.27416v1 Quantum Federated Learning (QFL) inherits the core vulnerability of federated optimization to malicious clients, while also introducing an attack surface from variational circuit training and measurement-driven gradients. This work proposes a novel CircUit-Level backdoor Threat (CULT) model that formalizes four stealthy attacks by exploiting quantum-aware mechanisms, including Grover, Pauli, Bit-flip, and Sign-flip. By enabling malicious clients on both in-training and post-training surfaces, these attacks can critically undermine the learning process. We establish a rigorous theoretical foundation to demonstrate attack stealthiness under standard smoothness assumptions. Experiments on the MNIST and CIFAR-10 datasets with non-IID splits and varying fractions of malicious clients show that even a single malicious client can induce severe accuracy degradation under FedAvg aggregation. While popular defenses, including Krum, Multi-Krum, FoolsGold, FLGuardian, and Mud-HoG, reduce degradation in many regimes, they fail to eliminate worst-case failure cases, where accuracy drops up to 50\%. The experimental analysis further reveals that under the CULT model, malicious updates effectively mask their presence by staying close to benign norms, thereby helping attackers evade detection. --- ### Rapid online deep artifact suppression for real-time spiral bSSFP CMR with blipped-CAIPI simultaneous multi-slice imaging at 1.5 T Authors: Julius Åkesson, Iulius Dragonu, Einar Heiberg, Tina Yao, Rebecca Baker, Ruta Virsinskaite, Daniel Knight, Vivek Muthurangu, Jennifer Steeden Published: 2026-05-18 Categories: physics.med-ph, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2605.26127v1 Purpose: Real-time (RT) bSSFP MRI enables fast free-breathing cardiovascular imaging but requires 10-16 slices for functional assessment, resulting in prolonged scan times. Simultaneous multi-slice (SMS) imaging can reduce acquisition time but when combined with non-Cartesian trajectories, it relies on iterative reconstructions that preclude online use. This study investigates deep artifact suppression to facilitate rapid, online reconstruction of RT-SMS. Methods: A spiral bSSFP SMS RT sequence with two simultaneously acquired slices was implemented at 1.5 T. Reconstruction used slice separation in k-space, followed by deep artifact suppression in image space using a 3D U-Net. Ten healthy volunteers were imaged. RT-SMS image quality and reconstruction time were compared between deep artifact suppression and compressed sensing (CS) reconstructions. Left (LV) and right (RV) ventricular volumes at end diastole (EDV) and end systole (ESV) and LV mass (LVM) were compared between RT-SMS with deep artifact suppression and reference-standard breath-hold (BH) imaging. Results: The RT-SMS acquisition was ~13x faster than BH imaging (15 s vs 3 min 15 s). RT-SMS reconstruction using deep artifact suppression was ~50x faster than CS (30 s vs 24 min 55 s). Deep artifact suppression consistently outperformed CS in quantitative and qualitative image quality (p<0.001). Functional agreement between BH and RT-SMS with deep artifact suppression was good (LVEDV: -7.5 +/- 6.8 ml, LVESV: -0.9 +/- 4.2 ml, RVEDV: -6.4 +/- 8.4 ml, RVESV: 0.2 +/- 10.7 ml, LVM: -10.3 +/- 11.0 g). Conclusion: Online deep artifact suppression reconstruction for RT-SMS bSSFP CMR enables free-breathing short-axis coverage with a substantial reduction in acquisition and reconstruction time while maintaining diagnostic image quality. --- ### Harnessing AtomisticSkills for Agentic Atomistic Research Authors: Bowen Deng, Bohan Li, Matthew Cox, Hoje Chun, Juno Nam, Artur Lyssenko, Sathya Edamadaka, Jurgis Ruza, Xiaochen Du, Nofit Segal, Jesus Diaz Sanchez, Mingrou Xie et al. Published: 2026-05-18 Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2605.24002v1 Computational materials science and chemistry span vast knowledge domains and fractured software ecosystems. Although large language models (LLMs) have demonstrated research capabilities, scaling monolithic agents to manage the rigor and complexity of atomistic research remains a challenge. Here, we introduce AtomisticSkills, an open-source harness framework that empowers general-purpose AI coding agents to conduct atomistic research across materials science, chemistry, and drug discovery. By hierarchically decomposing scientific workflows into agent skills and tools, AtomisticSkills provides agents with modular, extensible, and plug-and-play research capabilities. The framework integrates more than 100 human-curated multidisciplinary skills, including database access, thermodynamics and kinetics modeling, and diverse simulation engines employing machine learning interatomic potentials (MLIPs) and density functional theory (DFT). We validate its functional coverage against scientific literature and demonstrate robust orchestration capabilities across diverse scientific campaigns: generative design of Li-ion solid-state electrolytes, high-throughput screening of metal-organic frameworks for CO2 capture, autonomous MLIP benchmarking and fine-tuning, multi-stage structure-based virtual screening for drug design, multimodal X-ray diffraction pattern analysis, and screening of Fe-oxide catalysts for oxygen evolution reaction. AtomisticSkills provides a critical agent infrastructure towards building fully autonomous AI scientists. --- ### Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL Authors: Junyi Wu, Weijian Luo, Haoyang Zheng, Ruizhe Zhang, Guang Lin Published: 2026-05-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24001v2 Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the underlying generative dynamics. As a result, optimization tends to exploit stochastic degrees of freedom, often improving reward at the expense of image fidelity. To address this issue, we propose Diff-Instruct with Diffused Reward (DIDR), a data-free trajectory-level alignment framework derived from Integral KL minimization. DIDR propagates the RLHF-optimal reward-tilted clean-image distribution across all noise levels along the diffusion trajectory. We show that this objective admits the same minimizer as clean-image RLHF, while naturally inducing the Diffused Reward Score (DRS), which acts as a reward-driven correction to the reference score function. To make this practical, we further introduce the Diffused Reward Proxy (DRP), an efficient estimator of DRS based on differentiable short-step denoising. Extensive experiments demonstrate that DIDR consistently Pareto-dominates existing one-step SDXL baselines. Moreover, when transferred to a 6B DiT backbone (Z-Image), DIDR surpasses its 50-step teacher in preference alignment while requiring only a single generation step. --- ### Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities Authors: Ronja Fuchs, Florian Rupp, Timo Bertram, Kai Eckert, Alexander Dockhorn Published: 2026-05-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.24000v1 Toxicity in online gaming communities remains a persistent challenge, manifesting across genres, platforms, and player interactions. While much research is focused on in-game toxicity, less is known about how toxic behavior varies between gaming communities on streaming platforms. To address this shortcoming, we analyze approximately 20 million chat messages from 4,452 streams, spanning seven game genres on Twitch. We categorize messages according to Twitch's toxicity taxonomy with a pre-trained Large Language Model using zero-shot classification. The taxonomy comprises four categories and eight subclasses, including harassment, discrimination, sexual content, and profanity. Our approach achieves an F1 score of 94.5% on the TextDetox dataset and demonstrates human-model agreement comparable to inter-human agreement. Our analysis reveals that 2.4% of all messages are classified as toxic, with notable differences across genres: streams of MOBA games exhibit the highest relative rate of toxicity (3.2%), and sports games show the lowest rate (2%). Furthermore, results indicate that individual games differ significantly in their toxicity distributions, even within genres, suggesting the existence of game-specific community norms and mechanics that shape toxic behavior beyond genre-level effects. These findings offer empirical insights into genre- and game-specific toxicity patterns on Twitch and can inform more targeted moderation strategies for gaming communities. --- ### IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement Learning Authors: Chenghao Li, Fusheng Hao, Xikai Zhang, Likang Xiao, Yanwei Ren, Fuxiang Wu, Quan Chen, Liu Liu Published: 2026-05-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.23997v1 Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual hallucination and logical error. Current methods typically pre-encode high-dimensional visual scenes into discrete textual proxies to facilitate downstream reasoning. As the reasoning chain unfolds, however, the inherent information asymmetry between text and visual scenes tends to erode visual grounding, resulting in misguided reasoning and erroneous outputs. To address this issue, we introduce IVR-R1 (Iterative Visual-grounded Reasoning), a novel RL training framework that facilitates dynamic visual re-alignment that actively rectifies reasoning trajectories to guide policy optimization. Specifically, by leveraging a reward-driven screening mechanism to identify flawed rollouts, IVR-R1 executes a fine-grained, step-level error attribution within the multimodal context. By iteratively cross-referencing intermediate reasoning states against pristine visual priors, a Re-Reasoning Loop enables automated trajectory rectification, effectively synthesizing expert-level demonstrations that serve as high-fidelity reasoning templates for the policy model. Our experiments across diverse multimodal benchmarks demonstrate that IVR-R1 consistently outperforms existing reinforcement learning methods, establishing a superior paradigm for maintaining logical and visual consistency in complex multimodal reasoning. --- ### Brain-to-Image Retrieval and Reconstruction via Multimodal EEG Alignment Authors: Chi Kit Wong, Yan Liu, Haowen Yan Published: 2026-05-18 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2605.23996v1 We present a brain-to-image system that decodes visual stimuli from EEG signals recorded during natural image viewing. Our system addresses two tasks: (1) EEG-to-image retrieval, which ranks the correct stimulus image among 200 candidates given an EEG segment, and (2) EEG-to-image reconstruction, which generates an image consistent with the perceived stimulus. For retrieval, we implement a multi-level blurring approach improved with biologically inspired EVNet features and trained with the InfoNCE loss. Evaluated over 10 random seeds for a single subject, the retrieval model achieves a mean final-epoch Top-1 accuracy of 86.30% and Top-5 accuracy of 98.55%. For reconstruction, we implement CognitionCapturerPro, which aligns EEG representations to multi-modal CLIP embeddings, including image, text, depth, and edge embeddings, and synthesizes images with SDXL-Turbo conditioned via IP-Adapter. Averaged over 10 seeds, the reconstruction model achieves a CLIP score of 0.903 using ViT-H-14, a CLIP score of 0.870 using ViT-L/14, and an SSIM of 0.409. These results demonstrate the feasibility of decoding rich visual representations from EEG signals using modern multi-modal alignment and generative modeling techniques. --- ### Task-Aligned Self-Supervised Learning for Medical Image Analysis: A Task-Oriented Review with Practical Design Guidelines Authors: Chathura Wimalasiri, Yuchong Yao, Kishor Nandakishor, Marimuthu Palaniswami Published: 2026-05-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.23995v5 Self-supervised learning (SSL) is increasingly used in medical image analysis to reduce dependence on costly expert annotations by learning transferable representations from unlabeled data. However, SSL performance depends not only on model architecture but also on whether the self-supervised objective preserves the information required by the downstream clinical task. This review presents a task-oriented synthesis of SSL methods for medical imaging, focusing on how the design of the self-supervised objective interacts with imaging modality, label availability, and downstream performance. We analyze $78$ studies published from 2017 to 2025 and organize them into four paradigms: contrastive, non-contrastive and predictive, generative and reconstruction-based, and hybrid learning. Rather than cataloging methods chronologically, we examine how these paradigms support classification, segmentation, detection, reconstruction, and regression. The evidence suggests that effectiveness is governed by the match among objective, modality, and downstream task rather than by any single strategy. Contrastive objectives favor global discriminative representations suited to classification but may underrepresent localized pathology, whereas spatial-prediction, masked-modeling, and reconstruction objectives better preserve anatomical structure for segmentation and dense prediction. Critically, misaligned objectives can cause negative transfer through shortcut learning on acquisition signatures or augmentation that erases diagnostic signal rather than merely weaker gains. SSL is most beneficial in low-label regimes, but its effectiveness depends on modality-aware augmentation, pathology-preserving corruption, and clinically meaningful evaluation. We conclude with practical design guidelines and open challenges for clinically aligned SSL. --- ### Topological Signal Processing: An Application-Oriented Tutorial Authors: Flavia Petruso, Maria Giulia Preti, Dimitri Van De Ville Published: 2026-05-18 Categories: eess.SP, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2605.22853v1 Many modern datasets are large and carry complex structural relationships. Graph-based methods have traditionally been used to represent networked data, modeling individual elements as nodes and pairwise interactions as edges. Furthermore, Graph Signal Processing (GSP) has been developed to analyze signals on graph nodes, such as temperature measurements (node signals) across different regions of a country represented as a graph. Topological Signal Processing (TSP) is an emerging field that generalizes GSP, enabling the analysis of signals defined not only on nodes but also on edges, triangles, and higher-dimensional network elements, modeled as simplicial complexes and related topological structures. This makes TSP naturally well-suited for studying higher-order interactions in complex systems by extending classical signal processing concepts, such as filtering and Fourier transforms, to the topological level. Despite its versatility, TSP remains challenging for many practitioners. Therefore, we present an accessible overview of TSP foundations while drawing connections with application-oriented settings. We focus on processing techniques based on the combinatorial Hodge Laplacian, which generalizes the graph Laplacian to simplicial complexes. In particular, we review key TSP concepts, relate them to real-world examples, and discuss how higher-order structures and signals can be derived from datasets. For instance, we introduce an edge-level signal capturing lagged interactions between nodal signals, and demonstrate its use in a case study on TSP-based analysis of brain imaging data, revealing nontrivial interactions between sets of brain regions. Overall, we aim to promote a broader adoption of TSP by bridging methodological developments with applications, fostering its use among a wide community of theoretical and applied researchers. --- ### Expressive Power of Deep Homomorphism Networks over Relational Databases Authors: Moritz Schönherr, Balder ten Cate, Maurice Funk, Benny Kimelfeld, Carsten Lutz, Arie Soeteman Published: 2026-05-18 Categories: cs.DB, cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2605.22852v1 The expressive limitations of message-passing Graph Neural Networks (GNNs) have motivated a wide range of more powerful graph learning architectures. We advocate Deep Homomorphism Networks (DHNs) as a model particularly well-suited for learning over relational databases, due to their close connection to important fragments of SQL such as conjunctive queries. We study the precise expressive power of DHNs by relating them to various natural fragments and extensions of first-order logic (FO). For DHNs with max, sum, and mean aggregations, we establish connections to the unary negation fragment (UNFO) and to the extensions of UNFO with counting quantifiers and with ratio quantifiers. We further relate sum-aggregation DHNs to the unary quantifier alternation fragment of FO and to an extension of FO with expressive counting. Through the classical correspondence between FO and SQL, these results also illuminate the relation between DHNs and SQL. They also enable us to study the decidability of two fundamental static analysis problems for DHNs, the emptiness problem and the subsumption problem. Finally, we confirm through experiments that the established differences in expressive power are reflected in the performance on suitable prediction tasks. --- ### Neural Acceleration for Graph Partitioning Authors: Joshua Dennis Booth, Vishvam Patel Published: 2026-05-18 Categories: cs.SI, cs.LG arXiv: https://arxiv.org/abs/2605.21519v1 Graph Partitioning is a critical problem in numerous scientific and engineering domains including social network analysis, VLSI design, and many more. Spectral methods are known to produce quality partitions while minimizing edge cuts for a wide range of problems. However, the computational cost associated with the calculation of the Fiedler vector, an eigenvector associated with the second smallest eigenvalue of the graph Laplacian, remains a significant bottleneck due to memory issues and computational costs. In this paper, we present an accelerated approach to spectral bisection partitioning by replacing the traditional eigenvalue calculation with a simple artificial neural network model to approximate the Fiedler vector. We demonstrate that our approach achieves partitioning quality comparable to spectral bisection while significantly reducing the computational overhead, making it more scalable and efficient for large-scale problems --- ### Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversity Authors: Ernest Fokoué Published: 2026-05-18 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.20271v1 We develop a rigorous statistical theory of multi-head attention (MHA) as an ensemble of Nadaraya-Watson (NW) kernel regression estimators. Building on the algebraic identity between single-head softmax attention and the NW estimator, we prove that MHA is a structured ensemble of H NW estimators, each operating in a distinct learned projection subspace of the key space. We derive an explicit Bias-Variance-Covariance decomposition of the MHA mean squared error, showing that variance reduction depends not merely on the number of heads H but fundamentally on the decorrelation of head outputs. Decorrelation is governed by the principal angles between learned projection subspaces: orthogonal projections yield maximum variance reduction; aligned projections yield none. We introduce the Head Diversity Index (HDI), a computable spectral measure of inter-head decorrelation, and prove that MHA mean squared error is monotonically decreasing in HDI. This provides the first rigorous theoretical explanation for the empirically observed specialization of attention heads. Under a fixed total-dimension budget D = H * d_k, we solve the optimal head-dimension allocation problem, deriving the MSE-minimizing pair (H*, d_k*) from data distribution and regression smoothness. The solution yields a new architectural scaling law: the optimal per-head dimension grows logarithmically with training set size, while the optimal number of heads grows nearly linearly with the total budget D. Our framework unifies three strands of prior work: the NW theory of single-head attention, the general weighting theory for ensemble learning, and the decorrelation-variance-reduction isomorphism between biological and computational ensembles. Multi-head attention is the Transformer's instantiation of a universal principle: identical agents plus diversity-enforcing mechanisms yields emergent optimality. --- ### Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs Authors: Hamed Khosravi, Xiaoming Huo Published: 2026-05-18 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.20270v1 A local specialist LLM, fine-tuned with reinforcement learning from verifiable rewards (RLVR) on operator-local data, is installed in a regulated organization with per-deployment error budget $α$. The operator needs a safety certificate for this deployment's stream at every round: no pooling across deployments, no waiting for a long-run average. Existing wrappers cannot deliver this on adaptive, online-updated streams: offline conformal-risk methods require exchangeability; online-conformal methods bound only long-run averages; non-exchangeable extensions are marginally valid; and the closest anytime wrapper, A-RCPS, controls marginal rather than selective risk. Using a (test statistic, validity guarantee, deployment rule) framework, we identify one empty cell forced by deployment requirements: e-process per threshold, selective risk, anytime-pathwise validity, max-certified-threshold rule. Conformal Selective Acting (CSA) fills it as a per-round wrapper maintaining a Ville-type e-process per threshold on a Bonferroni grid, evaluated against the RLVR filtration. Under predictable updates and isotonic-calibrated monotone risk we prove (i) an anytime-pathwise selective-risk bound $R_T^{\mathrm{act}}\leα+O(N_T^{-1/2})$, (ii) rate-optimal certification matching $Θ(\barη^{-2}\log(1/δ))$, and (iii) a horizon-independent release-rate gap. Across eight specialist benchmarks ($480$ streams), sixteen adversarial distribution-shift cells ($160$ streams), and five live Expert-Iteration RLVR cells with online LoRA over four base models in three architecture families ($10{,}300$ rounds), CSA is the only method among ten compared that satisfies pathwise validity and non-refusing deployment on every cell. We do not propose a new LLM, training algorithm, or policy class; CSA is the deployment-side complement, orthogonal to the model, for operators who cannot use a frontier API. --- ### Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity Authors: Hamed Khosravi, Xiaoming Huo Published: 2026-05-18 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2605.20269v1 Many bandit deployments (recommendation, clinical dosing, ad targeting) share two facts prior work handles only in isolation: rewards live on a low-dimensional latent subspace, and that subspace drifts. Stationary low-rank bandits exploit rank but break under subspace change; non-stationary linear bandits adapt to drift but pay ambient rate $\widetilde{O}(d\sqrt{T})$. We study piecewise-stationary low-rank linear contextual bandits with scalar feedback: $θ_t = B_k^\star w_t$ with rank-$r$ factor $B_k^\star\in\mathbb{R}^{d\times r}$ constant within each of $K$ unknown segments and able to shift at boundaries. Our results are tight along three axes. (i) Identification boundary. With single-play scalar rewards, the moving subspace is recoverable through quadratic functionals of rewards iff three probe-side conditions hold: known noise variance, bounded state-noise coupling, and full-dimensional probe support. Each is necessary in the unrestricted-second-moment problem, and jointly they are sufficient, characterizing the boundary of the solvable region. (ii) Algorithm and dynamic regret. SPSC interleaves isotropic probes with windowed projected ridge-UCB exploitation inside the learned $r$-dimensional subspace; a CUSUM-style variant discovers segment boundaries online. The costed dynamic regret is $\widetilde{O}(r\sqrt{T})+\widetilde{O}(T^{2/3})+O(W\,V_{\mathrm{in}})$, replacing the ambient $d\sqrt{T}$ rate with the intrinsic rank. (iii) Empirics. On eleven benchmarks spanning synthetic, UCI/MovieLens, semi-synthetic clinical, and ZOZOTOWN production-log data, SPSC outperforms non-stationary and low-rank baselines whenever $d-r\gtrsim T^{1/6}$, matching the analytical crossover. To our knowledge, this is the first work to characterize the identification boundary and attain the intrinsic-rank dynamic-regret rate in this setting. --- ### Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding Authors: Paul Quinlan, Jeremy Levasseur, Qingguo Li, Xiaodan Zhu Published: 2026-05-18 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.20268v1 Real-world time series come with text: metadata, descriptions, news, reports. Yet time series foundation models process numerical sequences in isolation, and the multimodal text-and-time-series models that attempt to bridge the two all adapt a pretrained language model post hoc, inheriting representations shaped without ever seeing temporal data. These models are also evaluated almost exclusively against other multimodal baselines, not against the strongest unimodal foundation models in either domain, leaving open whether joint training is needed at all. We present Chronicle, a compact 324M-parameter decoder-only transformer trained from scratch on natural language and time series within a single unified architecture. Both modalities share the same transformer blocks, attention mechanism, and residual stream; the bulk of pretraining uses unimodal batches so cross-modal capability emerges purely from shared parameters, with a short alignment stage that interleaves the two. To our knowledge, Chronicle is the first model jointly pretrained on text and time series from scratch, and the first multimodal model evaluated against dedicated foundation models in both domains. It matches Gemma-3-270M-PT on 19 NLU tasks, sets a new bar for frozen-embedding time series classification on 24 UCR/UEA datasets, and produces multimodal forecasts on Time-MMD that beat every supervised fusion baseline, all from a single backbone. --- ### Generation of Heterogeneous PET Images from Uniform Organ Activity Maps Using a Pretrained Domain-Adapted Diffusion Model Authors: Suya Li, Kaushik Dutta, Debojyoti Pal, Jingqin Luo, Kooresh I. Shoghi Published: 2026-05-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.20267v1 Synthetic PET images are valuable for quantitative imaging workflow development, scalable virtual imaging trials, and deep learning model training, but conventional physics-based simulation approaches are computationally intensive, limited in anatomical variability, and often fail to capture heterogeneous PET uptake. This study developed a pretrained domain-adapted diffusion (PAD) model for anatomy-conditioned PET synthesis from uniform organ activity maps. PAD adopts a natural-image pretrained text-to-image decoder with an upstream conditioning encoder and a downstream PET-domain adapter. A two-phase training strategy was used, with the first phase learning coarse uptake distributions and the second refining local image details. Uniform organ activity maps were generated from CT-based segmentations by assigning each organ its mean uptake from the paired PET image. Evaluation included quantitative accuracy, noise assessment, radiomic analysis, tumor segmentation performance, and a human observer study. PAD-generated images achieved high quantitative accuracy, with concordance correlation coefficients above 0.92 between organ mean SUVs and assigned activity values. The synthesized images showed noise levels and texture characteristics similar to target PET images and produced comparable tumor segmentation performance. In a two-alternative forced-choice observer study, four readers achieved approximately 50% accuracy, indicating visual indistinguishability between synthesized and target images. PAD also generated realistic PET images from XCAT-derived activity maps, demonstrating compatibility with phantom-based anatomical priors. Overall, PAD provides a diffusion-based framework for generating clinically relevant heterogeneous PET images from uniform organ activity maps derived from clinical segmentations or digital phantoms, supporting data augmentation and downstream imaging studies. --- ### Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing Authors: Bryce Hinkley, Peyman Najafirad Published: 2026-05-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.20262v1 We study selective refusal editing as a three-way control problem: induce non-refusal on designated edit prompts while preserving benign behavior and harmful refusals outside the edit set. We introduce Residual Paving, a routed residual editing method for frozen instruction-tuned transformers that separates route selectivity, whether to intervene, from residual-edit capacity, what edit to apply. An early-layer router predicts a scalar gate and expert mixture; when active, prompt-conditioned bottleneck residual experts apply later-layer residual updates while leaving the backbone unchanged. This decomposition supports an oracle-routing diagnostic where only the learned scalar gate is replaced with the held-out edit/keep label, leaving the residual editor and frozen backbone fixed. On the primary Gemma-3-4B-IT held-out split, learned Residual Paving reduces edit refusal from 88.6% to 4.0%, with 95.5% benign distribution preservation and 87.3% harmful distribution preservation. Same-protocol one-direction steering controls are much weaker on edit success, leaving edit refusal at 86.8% for Edit-target ActAdd and 78.9% for DIM-style refusal steering. The remaining failure is off-target harmful-keep degradation: harmful refusal remains below the frozen-base rate, 65.3% vs. 81.6%. Across six backbones, oracle routing improves the keep-side diagnostic score on every reported row, with median gain +12.9 pp, supporting the interpretation that learned route selectivity is the main observed bottleneck. Trajectory diagnostics on two backbones further suggest directed movement toward edit-target continuations rather than generic refusal suppression. --- ### It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs Authors: Sangwoo Park, Woongyeong Yeo, Seanie Lee, Yumin Choi, Hyomin Lee, Kangsan Kim, Jinheon Baek, Seong Joon Oh, Sung Ju Hwang Published: 2026-05-18 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.20258v1 Contextual Integrity (CI) defines privacy not merely as keeping information hidden, but as governing information flows according to the norms of a given context. As large language models are increasingly deployed as personal agents handling sensitive workflows, adhering to CI becomes critical. However, even frontier models remain unreliable in making disclosure decisions, and existing mitigation strategies often degrade underlying task performance. To overcome this privacy-utility trade-off, we propose SELFCI, a complementary self-distillation framework that decouples information suppression from task resolution. SELFCI jointly optimizes two independent reverse KL divergences over distinct teacher distributions derived from feedback: one encourages preserving task-relevant information for utility, while the other enforces minimal and appropriate disclosure. This complementary formulation induces a Product-of-Experts (PoE) target, aligning the policy with the intersection of capability and privacy requirements. Empirical evaluations demonstrate that SELFCI, without relying on costly external supervision, consistently outperforms competitive baselines such as online reinforcement learning algorithms (e.g., GRPO). These trends further extend to out-of-domain settings involving agentic workflows and accumulated private context, suggesting that SELFCI provides a practical path toward CI alignment. --- ### Instance Discrimination for Link Prediction Authors: Valentin Cuzin-Rambaud, Mathieu Lefort, Rémy Cazabet Published: 2026-05-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.20257v1 Recently, instance discrimination models have emerged as a major solution for self-supervised learning. Having already demonstrated its effectiveness in the image domain, instance discrimination learning is now proving equally convincing in the graph domain, in particular for node classification. However, fewer contributions have tackled the link prediction task. In this contribution, we propose to adapt existing methods to this context. We first provide a rigorous evaluation of existing self-supervised models in the field of link prediction, showing that the main performance depends on the augmentation process (like in computer vision). We then propose a new structural augmentation based on the community structure that is relevant for link prediction. Our main contribution introduces two new models, L-GRACE and L-BGRL, based on link representations instead of node representations, which improve the performance of the existing methods, especially on unattributed graphs, and we show that they perform on par with the state of the art, both in supervised and self-supervised contexts. --- ### FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning Authors: Xikai Zhang, Yongzhi Li, Likang Xiao, Yingze Zhang, Yanhua Cheng, Quan Chen, Peng Jiang, Wenjun Wu, Liu Liu Published: 2026-05-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.20256v3 Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models. At its core, the training loop of GRPO and its variants alternates between rollout sampling and policy update: the policy first samples rollouts from its action space, and then updates its parameters according to the advantages computed over them. Unlike supervised learning, where each gradient step is anchored to an explicit ground-truth target, the optimal gradient direction for updating model parameters in this setting is not known a priori; the high-quality rollouts drawn during the sampling stage therefore act as the implicit "teacher" that guides every parameter update. However, mainstream RL algorithms such as GRPO adopt a simple sampling scheme that conditions all rollouts on the same original prompt. When a task lies beyond the policy model's current capability, this sampling scheme rarely yields a high-quality rollout, leaving the policy model without a meaningful gradient direction when updating its parameters, which causes training to stall. To address this issue, we propose FBOS-RL. Specifically, we let the model perform Feedback-Guided Exploration Enhancement based on the feedback provided by the environment, and on top of this we design two mutually reinforcing training objectives: EPA and ECC. Extensive experiments demonstrate that EPA and ECC can mutually reinforce each other, forming a positive flywheel effect that significantly improves both the training efficiency and the final performance ceiling of reinforcement learning. Specifically, under both an identical number of rollouts and the same number of training steps, FBOS-RL learns substantially faster than GRPO and feedback-based baselines and ultimately attains a higher performance ceiling, while exhibiting higher policy entropy and lower gradient norms throughout training. --- ### Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty Authors: Prakash Aryan, Kaushik Raghupathruni, Timo Kehrer, Sebastiano Panichella Published: 2026-05-18 Categories: cs.LG, cs.AI, cs.HC, cs.RO arXiv: https://arxiv.org/abs/2605.20255v2 Simulation-based testing of self-driving cars (SDCs) typically relies on scripted pedestrian models that do not capture the heterogeneity and uncertainty of real crossing behavior, limiting the realism of safety assessments, especially for jaywalking, which is governed by latent personality traits the vehicle cannot observe. We hypothesize that jointly training pedestrians and the SDC with multi-agent reinforcement learning (MARL) yields more realistic interaction scenarios than training against fixed pedestrian policies, and that the behavior gap between predictable and unpredictable crossings can be measured directly from trajectories. We co-train an SDC and 12 pedestrians using Multi-Agent Proximal Policy Optimization (MAPPO): pedestrian locomotion follows scripted Dijkstra pathfinding while an RL policy controls high-level go/wait decisions, and jaywalking probability depends on a per-pedestrian trait sampled at episode start and hidden from the SDC. In 500-episode evaluations, the co-trained SDC reached 78% of goals with a 14% collision rate, versus 35%/33% for the best rule-based baseline. A speed differential metric shows the SDC traveled 2.65 m/s faster near jaywalkers than near crosswalk users at close range (0-3 m), indicating jaywalking encounters were not anticipated. Jaywalking was 13% of crossing events but 62% of collisions, and co-training reduced collisions by 30% relative to single-agent RL as pedestrians learned to wait when the SDC approached at speed. --- ### Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting Authors: Amritansh Maurya, Navjot Singh, Mohammed Javed, Omar Moured Published: 2026-05-18 Categories: cs.IR, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.20254v2 Large Language Models (LLMs) have shown promising results on NLP tasks, however, their performance on tabular data still needs research attention, because Table Question-Answering (TQA) requires precise cell retrieval and multi-step structured reasoning. Existing work improves TQA either by fine-tuning or training LLMs on task-specific tabular data, but often lacks verifiable control over how the model navigates tables and derives answers. In this work, we propose a training-free TQA approach with two structured prompting frameworks: TableGrid Navigation (TGN), which iteratively navigates rows and columns via a three-module loop to locate evidence and refine answers, and Progressive Inference Prompting (PIP), which enforces columns identification for explicit progressive row selection constraint according to the query. We evaluate 17 LLMs against 6 baselines on TableBench and FeTaQa dataset. On TableBench, TGN improves over the strongest baseline by 3.8 points, and on FeTaQa, PIP achieves SOTA performance over ReAct and Chain-of-Thought. Beyond inference-time gains, PIP and TGN can also serve as supervision templates to fine-tune small models, narrowing the performance gap to much larger architectures in resource-constrained settings, offering versatile and cost-efficient solution for TQA. --- ### Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting Authors: Amritansh Maurya, Navjot Singh, Mohammed Javed, Omar Moured Published: 2026-05-18 Categories: cs.IR, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.20254v1 Large Language Models (LLMs) have shown promising results on NLP tasks, however, their performance on tabular data still needs research attention, because Table Question-Answering (TQA) requires precise cell retrieval and multi-step structured reasoning. Existing work improves TQA either by fine-tuning or training LLMs on task-specific tabular data, but often lacks verifiable control over how the model navigates tables and derives answers. In this work, we propose a training-free TQA approach with two structured prompting frameworks: TableGrid Navigation (TGN), which iteratively navigates rows and columns via a three-module loop to locate evidence and refine answers, and Progressive Inference Prompting (PIP), which enforces columns identification for explicit progressive row selection constraint according to the query. We evaluate 17 LLMs against 6 baselines on TableBench and FeTaQa dataset. On TableBench, TGN improves over the strongest baseline by 3.8 points, and on FeTaQa, PIP achieves SOTA performance over ReAct and Chain-of-Thought. Beyond inference-time gains, PIP and TGN can also serve as supervision templates to fine-tune small models, narrowing the performance gap to much larger architectures in resource-constrained settings, offering versatile and cost-efficient solution for TQA. --- ### ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents Authors: Jiawei He, Jie Jia, Chenbo Liu, Chaoyi Xue, Yapeng Song, Xikai Yang, Dong Sun Published: 2026-05-18 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2605.20251v4 Existing benchmarks for LLM coding agents primarily evaluate final outcomes. While useful for measuring overall capability, these metrics provide limited visibility and often miss defects that arise during execution. We present ProcCtrlBench, a benchmark for execution-process evaluation in LLM coding agents. ProcCtrlBench organizes recurrent execution defects into a reusable ontology covering 11 defect types in 4 categories, and evaluates agent trajectories through standardized process evidence rather than final outcomes alone. To support comparison across heterogeneous agents, ProcCtrlBench standardizes raw logs into a unified trajectory representation and reports calibrated scorecards over process-level findings. In addition, ProcCtrlBench uses control preservation as a way to quantify execution-process quality, capturing whether execution remains interpretable, interruptible, correctable, reversible, and able to hand back authority when needed. We evaluate ProcCtrlBench on 200 cases sampled from three benchmarks: AndroidBench, TerminalBench, and SWE-bench-Verified. Results show that ProcCtrlBench can be instantiated with useful reliability, provides more stable semantics than direct thresholding, and reveals meaningful differences in execution quality that are often overlooked by conventional outcome-based evaluation. --- ### Physics-informed convolutional neural networks for fluid flow through porous media Authors: Rafał Topolnicki, Paweł Dłotko, Maciej Matyka Published: 2026-05-18 Categories: cs.LG, physics.comp-ph, physics.flu-dyn arXiv: https://arxiv.org/abs/2605.20250v1 Accurate simulation of fluid flow in porous media is challenging due to complex pore-space geometries and the computational cost of solving the Navier-Stokes equations. This difficulty is particularly important when repeated simulations are required, as standard numerical solvers may converge slowly in intricate porous domains. We present a neural-network-based framework for predicting pore-scale velocity fields directly from sample geometry. The method uses a convolutional encoder-decoder architecture with skip connections to preserve spatial detail while extracting multi-scale features. Physical consistency is encouraged through a custom loss function combining velocity reconstruction with incompressibility, no-flow conditions inside solids, periodicity constraints, and agreement with the global tortuosity index. We analyze the influence of the corresponding loss weights and quantify the contribution of individual loss components to prediction accuracy. Several CNN backbones are evaluated to identify architectures providing accurate and robust predictions. The generalization ability of the trained model is tested on samples outside the training distribution, including changes in obstacle geometry, boundary conditions, porosity, and realistic porous structures. Finally, we demonstrate a practical use of the predicted velocity fields as initial conditions for Lattice-Boltzmann simulations. This warm-start strategy accelerates solver convergence, reducing the number of iterations in over 90% of tested cases. --- ### Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization Authors: Taeyoung Yun, Woocheol Shin, Inhyuck Song, Jaewoo Lee, Jinkyoo Park Published: 2026-05-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.20249v1 Gaussian Process (GP) kernels are central to Bayesian optimization (BO), yet designing effective kernels for high-dimensional problems still relies on extensive manual engineering. Existing automated approaches struggle in high dimensions for two bottlenecks: their kernel search space is limited to additions and multiplications of base kernels, and LLM-based approaches require conditioning on raw observations, which becomes infeasible due to context-length limits and the difficulty of extracting meaningful patterns. We introduce \textbf{Kernel Discovery}, a LLM-driven evolutionary framework for high-dimensional BO that searches a broader kernel space beyond predefined composition rules and does not require conditioning on observations. Motivated by the observation that directly prompting an LLM to generate kernel code yields syntactically varied but functionally identical kernels, we adopt a two-stage approach: an LLM first proposes novel mathematical forms, then a second LLM call converts each form into validated, executable code. We also propose a leave-one-out continuous ranked probability score (LOO-CRPS) as a selection criterion that penalizes overfitted kernels. On five high-dimensional BO benchmarks, our method achieves an average rank of \textbf{1.2 out of 17}, outperforming competitive baselines. We further analyze the discovered kernels to identify which kernels lead to improvements in high-dimensional BO. --- ### Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification Authors: Brown Zaz, Mar Gonzàlez I Català, Ferran Hernandez Caralt, Moshe Eliasof, Pietro Liò Published: 2026-05-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.20248v1 In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classification has largely focused on architectural innovation. In this paper, we revisit an orthogonal axis: the training objective. We start from a simple observation: transductive models produce predictions for every node during training, including nodes without labels. These unlabeled-node predictions may contain useful training signal, but standard supervised objectives discard them because no ground-truth labels are available. Inspired by the decomposition of cross-entropy into a label-dependent alignment term and a label-independent entropy term, we propose prediction confidence as a natural way to extract this signal in the absence of labels. This motivates Transductive Sharpening (TS): a loss-level modification that minimizes prediction entropy on unlabeled nodes while counterbalancing this effect on labeled nodes. We evaluate Transductive Sharpening across a wide range of node-classification benchmarks and observe consistent performance improvements without requiring any changes to the backbone architecture. Code is available at https://github.com/transductive-sharpening/tunedGNN. --- ### CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning Authors: Yang Liu, Toan Nguyen, Flora D. Salim Published: 2026-05-18 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2605.20247v2 Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scaling, existing LoRA-based MoE continual learning methods still face a fundamental trade-off: they either isolate experts too aggressively, limiting knowledge transfer across tasks, or allow task-specific updates to overwrite important existing parameters, leading to severe forgetting. To address this, we propose CP-MoE, a continual learning framework built around a transient expert that captures early task-specific updates and guides their integration into stable experts. CP-MoE introduces a consistency-preserving routing bias, which uses the transient expert to estimate representation similarity with stable experts and steer routing towards more compatible expert selection, and a transient expert-guided regularisation mechanism, which selectively protects important historical parameters during merging. Together, these components reduce parameter interference and forgetting while preserving cross-task knowledge transfer. We validate CP-MoE on both unimodal and multimodal continual learning benchmarks with LLM-based and VLM-based MoE models. On SuperNI benchmark, spanning diverse sequential language tasks, CP-MoE achieves state-of-the-art performance and stronger zero-shot transfer to unseen tasks. On VQA v2 dataset, it scales effectively to multimodal visual reasoning, consistently reduces forgetting, and outperforms strong MoE baselines. --- ### GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents Authors: Xiongbin Wu, Zhihao Luo, Shanzhe Lei, Lechao Zhang, Xuhong Wang, Jie Yang, Zhonglong Zheng, Yuanjie Zheng, Xin Tan, Wei Liu Published: 2026-05-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.20246v2 Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple turns of visual perception and action execution. However, existing methods still rely primarily on Supervised Fine-Tuning (SFT) with expert demonstrations, while the advanced reinforcement learning (RL) algorithm, specifically Group Relative Policy Optimization (GRPO), has not been effectively employed for multi-turn RL in these tasks because standard GRPO requires full trajectories as training samples which leads to excessively long context and noise. To address this issue, we propose GROW, a RL framework for open-world VLM agents that decomposes collected trajectories into state-action samples, and computes advantages between these samples rather than treating a full trajectory as a single entity. We further provide a surrogate analysis indicating that, even though the grouped samples are conditioned on different local states rather than an identical prompt context, the objective can preserve the core relative policy optimization signal of GRPO under simplifying assumptions. Experiments on more than 800 Minecraft tasks show that our method achieves state-of-the-art (SOTA) performance, demonstrating the effectiveness of our proposed RL framework for open-world VLM agents. --- ### Prism: Structural Symmetry Scanning via Duality-Constrained Laplacian Projection Authors: Jiatong Xie Published: 2026-05-18 Categories: cs.SI, cs.LG arXiv: https://arxiv.org/abs/2605.20245v1 We introduce \textbf{Prism}, a framework for structural symmetry diagnosis in complex networks. Given a graph Laplacian $L$ and a duality operator $P$ (a symmetric involution), Prism computes the \emph{duality defect} $δ(L,P) = \|LP - PL\|_F / \|L\|_F$ -- a scalar measuring how far the network deviates from structural self-consistency. When $P$ encodes the network's true symmetry, $δ$ starts near zero and rises monotonically as structure degrades; an arbitrary $P$ gives noise. We prove that the optimal $L'$ satisfying $(L', P) = 0$ is given by a closed-form block-diagonal projection, and provide an unsupervised alternating optimization that learns $P$ from the graph's own Fiedler vector. Experiments on synthetic networks show the true-$P$ defect is $3.38\times$ more sensitive to structural degradation than an index-reversal baseline and more sensitive than modularity. On Zachary's Karate Club with edge noise, Prism achieves $94.5\%$ community detection accuracy at $5\%$ noise versus $76.6\%$ for the raw Laplacian baseline. Applied to live S\&P~500 data (2026-05-17), Prism detects rising structural stress (defect $0.43 \to 0.73$ over 90 days) while surface correlations remain low -- a signal invisible to correlation-based methods. In a historical backtest spanning five major stress events (2011--2020), the duality defect exhibits a consistent pattern: it reaches elevated levels \emph{before} the correlation spike that accompanies each crisis, and sustains high readings during periods of structural fragility that conventional metrics classify as calm. The duality defect is a first-principles structural admissibility condition, requiring no training data and computable in milliseconds. --- ### Lean Refactor: Multi-Objective Controllable Proof Optimization via Agentic Strategy Search Authors: Jialin Lu, Soonho Kong, Rodrigo Stehling, Kaiyu Yang, Zhangyang Wang, Weiran Sun, Wuyang Chen Published: 2026-05-18 Categories: cs.LO, cs.AI, cs.CL, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2605.20244v2 We present Lean Refactor, a plug-and-play retrieval-augmented agentic framework for multi-objective, controllable, and version-robust refactoring of Lean proofs. LLM-generated proofs are notoriously correct-but-verbose and brittle across library versions, yet existing refactoring works overlook three practical challenges: 1) Lean refactoring is natively multi-objective (proof length, compilation cost, and version compatibility are often in tension); 2) Lean repositories have fragile compatibility, whereas LLM releases are unaware of Lean/Mathlib versions; 3) Training-based pipelines require repeated fine-tuning with each new LLM release, scaling neither with model churn nor with Lean's release cycle. Lean Refactor steers a frozen agentic LLM with retrievals from a curated database of multi-objective refactoring strategies, each densely annotated with metadata such as supported Lean/Mathlib versions and expected compilation-cost reduction. Experiments show over $70\%$ token-level compression on competition benchmarks, over $20\%$ on research repositories, and up to $60\%$ compilation-time reduction, outperforming prior work and Claude Code. Version-filtered retrieval further improves compression on the target Lean version, and refactored miniF2F proofs exhibit stronger zero-shot version transfer to future Lean releases than their unrefactored counterparts. --- ### LEAP: A closed-loop framework for perovskite precursor additive discovery Authors: Xin-De Wang, Zhi-Rui Chen, Ze-Feng Gao, Peng-Jie Guo, Cheng Mu, Zhong-Yi Lu Published: 2026-05-18 Categories: cs.LG, cond-mat.mtrl-sci, cs.AI, physics.chem-ph arXiv: https://arxiv.org/abs/2605.20242v1 Efficient discovery of precursor additives is essential for improving the performance of perovskite solar cells, yet the large chemical space makes conventional trial-and-error screening inefficient. We develop LEAP(LLM-driven Exploration via Active Learning for Perovskites), an expert-in-the-loop closed framework that couples a domain-specialized large language model(LLM) with active learning for iterative additive prioritization. The LLM is trained to extract mechanism-relevant knowledge from the perovskite additive literature and to represent candidate molecules through interpretable descriptors, which are further integrated into a Bayesian optimization workflow for uncertainty-aware prioritization under low-data conditions. Benchmark results on unseen literature show that the domain-specialized model outperforms general-purpose models in mechanism-consistent reasoning. Experimental validation in an expert-in-the-loop proof-of-concept study suggests improved additive prioritization across three screening rounds, leading to average device PCEs of 20.13% and 20.87% for the later-round 6-CDQ- and 2-CNA-treated devices, respectively, compared with 19.25% for the control, with a champion PCE of 21.32%. These results provide preliminary evidence that literature-grounded mechanistic descriptors, when coupled with Bayesian optimization and expert feasibility review, can support mechanism-aware additive prioritization in perovskite photovoltaics. --- ### Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry Authors: Woo Seob Sim, Yu Rang Park Published: 2026-05-18 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2605.20241v1 Prompt-level safety probes for large language models use hidden-state representations to separate safe from unsafe prompts, but strong average detection performance does not explain the geometry of this separation. In particular, it remains unclear how safety evidence is formed across layers, which aspects of that layer-wise geometry support low-false-positive decisions, and which geometric biases remain stable under benchmark shift. We study this as an empirical decomposition problem and introduce Geometry-Lite, a compact prompt-level probe that maps each layer's final prompt-token representation to signed margins under centroid, local-neighborhood, and supervised linear-boundary readouts, then summarizes the resulting margin profiles by boundary position, layer-to-layer change, and coarse shape. Across nine instruction-tuned backbones ($1.2$B--$70$B) and seven safety benchmarks, Geometry-Lite improves over single-layer probes while remaining close to raw multi-layer score stacking, making it a useful instrument for analyzing the multi-layer safety signal. The decomposition shows that safety evidence is expressed primarily through persistent boundary-position geometry: final or extremal margins and unsafe-side layer occupancy dominate aggregate detection performance. In contrast, finite-difference drift and structural summaries add little to pooled AUROC, although drift can provide small recall-oriented corrections under shifted low-FPR thresholds. Under benchmark shift, optimized linear boundaries are sharp on the training mixture, whereas class-conditional mean geometry retains separation more reliably on a predefined hard held-out subset. Overall, prompt-level safety evidence is not primarily a layer-to-layer motion signal, but a persistent layer-wise margin geometry whose useful components and readout-level biases become visible in decision-critical regimes. --- ### Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents? Authors: Leyao Wang, Yanan He, Peng Chen, Asaf Yehudai, Yixin Liu, Rex Ying, Michal Shmueli-Scheuer, Arman Cohan Published: 2026-05-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.19196v1 Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning LLM-as-judge as a supervision paradigm for assessing factual accuracy, evidence use, and reasoning quality. Yet the reliability of these judges for deep research agents remains poorly understood, posing a critical meta-evaluation problem: before deploying LLM judges to supervise research agents, we must first evaluate the judges themselves. Existing meta-evaluations fall short in two ways: (1) reliance on coarse, subjective human-preference agreement; (2) focus on instruction-following or verifiable tasks, leaving open-ended agent executions unexplored. To address these gaps, we introduce REFLECT (REliable Fine-grained LLM judge Evaluation via Controlled inTervention), a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments. REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions on quality-screened agent execution traces. This yields verifiable, comprehensive, and fine-grained instances for validating the judge models. Our experiments show that current LLM judges remain unreliable: even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures, with especially poor performance on evidence verification. Together, our taxonomy and findings expose systematic judge limitations, reveal tradeoffs in cost and reliability, and offer actionable guidance for building more reliable evaluation pipelines for deep research agents. --- ### The Thermodynamic Costs of Simple Linear Regression Authors: Samuel H. D'Ambrosia, Sultan M. Daniels, Michael R. DeWeese, Anant Sahai Published: 2026-05-18 Categories: cond-mat.stat-mech, cs.IT, stat.ML arXiv: https://arxiv.org/abs/2605.19195v1 The construction of models from data is a significant contributor to the energetic costs of computation. Because of this, understanding how foundational thermodynamic bounds apply to modeling algorithms will be increasingly important. Here, we study the thermodynamic costs of a basic and fundamental modeling algorithm: simple linear regression. Following Landauer, we approximate the thermodynamic lower bound on irreversibly performing both exact linear regression and linear regression via stochastic gradient descent as implemented on floating-point numbers. From this, we derive energycost aware scaling laws for the optimal dataset size for training a linear regression model given a generalization error dependent demand for inference. Additionally, we discuss a method to lower bound the entropy production from the mismatch cost for algorithms with continuous input variables. --- ### MMoA: An AI-Agent framework with recurrence for Memoried Mixure-of-Agent Authors: Rui Chu Published: 2026-05-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.19194v1 The Mixture-of-Agents (MoA) framework has shown promise in improving large language model (LLM) performance by aggregating outputs from multiple agents. However, existing MoA systems often rely on static routers that do not fully capture temporal and contextual dependencies across aggregation layers. To address this limitation, we propose MMoA, a recurrent MoA architecture that integrates LSTM-based gating into the agent selection process. The recurrence router adaptively modulates agent contributions based on both current inputs and historical routing decisions, enabling more context-aware aggregation. We evaluate MMoA on standard instruction-following benchmarks, including AlpacaEval 2.0, MT-Bench, and Arena-Hard. The results show that MMoA achieves comparable accuracy to traditional MoA while reducing computational overhead by dynamically activating fewer agents. For example, on AlpacaEval 2.0, MMoA achieves a win rate of 58.0%, compared with 59.8% for MoA, while improving runtime efficiency by up to 4.6%. These results suggest that MMoA provides a scalable and efficient approach for adaptive multi-agent LLM systems. --- ### Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detection Authors: Andrea Morandi Published: 2026-05-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.19193v1 Multi-agent LLM debate improves factuality and reasoning, but most recipes pick a fixed round count, over-spending on easy items and under-spending on hard ones. We adapt Wald's Sequential Probability Ratio Test (SPRT) as a plug-in compute governor for LLM debates. After each round, an LLM judge emits a (0,1) consensus score on the latest agent positions; a Wald monitor accumulates the log-likelihood ratio of "useful convergence" vs "not yet useful" under a Beta likelihood family, and stops when either boundary is crossed or returns a capped best-effort outcome at R_max. Under i.i.d. assumptions the rule inherits SPRT type-I/type-II error guarantees; in deployment the calibration itself is the more important object, since it estimates whether the judge score actually separates useful from unhelpful convergence in a given domain. We evaluate two tracks: (i) a Monte-Carlo study under calibrated Beta models characterising working curves, error rates, capping behaviour, and sensitivity; and (ii) a real-LLM evaluation on 200 attempted MMLU and 200 attempted GSM8K items with three heterogeneous agents (gpt-5, claude-opus-4-6, gemini-2.5-pro) and a claude-opus-4-6 judge, using disjoint 40-item calibration subsets. On GSM8K the rule stops in 1.01 average rounds (4.06 LLM calls) at 97.0% accuracy vs 99.0% for fixed-5 debate at 15 calls: a 3.7x call reduction at -2pp accuracy. On MMLU the calibrated KL collapses to about 0 and the rule caps on 99.5% of items at 2.1x cost. The takeaway is not that SPRT makes debate more accurate, but that a classical sequential test serves as a cheap compute-control and failure-detection layer for multi-agent LLM systems. --- ### Hallucination as Exploit: Evidence-Carrying Multimodal Agents Authors: Guijia Zhang, Hao Zheng, Harry Yang Published: 2026-05-18 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2605.19192v2 Multimodal agents increasingly choose tool calls from screenshots, documents, and webpages, where a false perceptual claim can turn hallucination from an answer-quality error into an authorization failure. We formalize this failure mode as hallucination-to-action conversion: an unsupported claim supplies the precondition for a privileged action. We propose evidence-carrying multimodal agents (ECA), which treat free-form model text as inadmissible evidence, decompose each tool call into action-critical predicates, obtain typed certificates from constrained DOM/OCR/AX verifiers, and use a deterministic gate to authorize only the privileges those certificates support. Rather than hiding perception error, ECA converts opaque model belief into auditable residuals at the verifier, schema, and implementation levels. Verifier red-teaming across 17 canonical attack categories shows that four targeted hardening steps are each necessary; after hardening, canonical gate bypass is 0/1,700 (Wilson 95% upper bound 0.22%). With content-derived certificates, ECA observes zero unsafe executions on 200 end-to-end tasks (Wilson 95% upper bound 2.67%) and 120 browser tasks (upper bound 4.3%). A HACR audit on 500 stratified task keys shows that unsupported action-critical claims reach unsafe execution for naive agents (100.0%) and prompt-only defenses (49.6%), but not for ECA. Oracle-certificate replay over 7,488 GPT-5.4 traces isolates gate correctness, while neural judge baselines still admit most unsafe actions under the same threat model. The resulting principle is simple: model language may propose tool use, but certified predicates must authorize it. --- ### Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South Authors: Charvi Rastogi, Mukul Bhutani, Minsuk Kahng, Shamsuddeen Hassan Muhammad, Evgeniia Razumovskaia, Priyanka Suresh, Ibrahim Said Ahmad, Charu Kalia, Yaaseen Mahomed, Madhurima Maji, Minjae Lee, Alicia Parrish et al. Published: 2026-05-18 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2605.19190v1 Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant vulnerabilities for the rest of the world. To embrace cultural pluralism and bring historically under-represented perspectives in T2I safety, we conduct localised community-centered red teaming studies in the Global South. Our two-fold approach prioritizes localization and participation, by focusing on secondary urban centers in these regions, and conducting community engagement and training workshops to contextualize local norms. As a result, we present PLACES, a dataset comprising over 26,000 examples of T2I model failures collected in partnership with universities in Ghana, Nigeria, and two regions of India (Karnataka and Punjab). Analysis of prompts collected reveals a wide-ranging diversity in socio-cultural and linguistic attributes, when compared to existing geography-agnostic crowdsourced red-teaming data. We observe unique adversarial patterns enabled by local cultural and linguistic nuances, and distinct clusters within region around specific themes, such as religion in India. Moreover, we uncover structural contextual gaps in existing safety frameworks by identifying novel harms showing normative dissonance (e.g., violating religious norms, ignoring local customs, and ominous symbolism). This work argues that expanding T2I safety requires moving beyond mere scale to incorporate deeply localised, participatory methodologies for data collection and contextualization. Content warning: This paper includes examples containing potentially harmful or offensive content. --- ### Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version) Authors: Terry R. Payne, Valentina Tamma, Enrico Daga Published: 2026-05-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.19186v3 Two decades ago, the Semantic Web Services community was asked how agents with different ontological commitments could discover, compose, and invoke web services coherently. The response was OWL-S and WSMO: formally grounded capability descriptions specifying what a service could do, what the agent must already know for invocation to be epistemically sound, and how ontological mismatches could be formally bridged. Current KG metadata standards such as VoID and DCAT describe what a KG contains, yet say nothing about what a specific agent can prove from it, what closure assumptions govern empty results, or whether the agent's task vocabulary is grounded in the schema. Furthermore, in deployed KGs the governing schema DL and the operative entailment regime can diverge: an epistemic failure mode invisible to current metadata. We revisit and extend these insights for the KG setting with a four-dimensional formal framework; Semantic Expressivity, Agentic Discoverability, Task-Relative Grounding, and Epistemic Trust Scope, from which we derive the Agentic Affordance Profile (AAP): a semantic layer above VoID and DCAT enabling principled KG selection, composition, and failure diagnosis at agent planning time. The four dimensions operationalise the affordance structure of the Ontological Continuum at the individual-agent level, specifically for \kg selection, composition, and failure diagnosis. A worked example drawn from a scholarly-search task concretely grounds the framework, and identifies the formal, computational, and engineering work needed to realise AAP-based affordance matching at scale though a five-point research agenda. --- ### Discoverable Agent Knowledge -- A Formal Framework for Agentic KG Affordances (Extended Version) Authors: Terry R. Payne, Valentina Tamma, Enrico Daga Published: 2026-05-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.19186v2 Two decades ago, the Semantic Web Services community was asked how agents with different ontological commitments could discover, compose, and invoke web services coherently. The response was OWL-S and WSMO: formally grounded capability descriptions specifying what a service could do, what the agent must already know for invocation to be epistemically sound, and how ontological mismatches could be formally bridged. Current KG metadata standards such as VoID and DCAT describe what a KG contains, yet say nothing about what a specific agent can prove from it, what closure assumptions govern empty results, or whether the agent's task vocabulary is grounded in the schema. Furthermore, in deployed KGs the governing schema DL and the operative entailment regime can diverge: an epistemic failure mode invisible to current metadata. We revisit and extend these insights for the KG setting with a four-dimensional formal framework; Semantic Expressivity, Agentic Discoverability, Task-Relative Grounding, and Epistemic Trust Scope, from which we derive the Agentic Affordance Profile (AAP): a semantic layer above VoID and DCAT enabling principled KG selection, composition, and failure diagnosis at agent planning time. The four dimensions operationalise the affordance structure of the Ontological Continuum at the individual-agent level, specifically for \kg selection, composition, and failure diagnosis. A worked example drawn from a scholarly-search task concretely grounds the framework, and identifies the formal, computational, and engineering work needed to realise AAP-based affordance matching at scale though a five-point research agenda. --- ### Planner-Admissible Graph-PDE Value Extensions for Sparse Goal-Conditioned Planning Authors: Shiheng Zhang Published: 2026-05-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.19185v1 Sparse goal-conditioned planning with few cost-to-go labels can be viewed as a graph-PDE Dirichlet extension problem: extend sparse labels on a goal-dependent boundary to unlabelled graph vertices so that greedy rollouts reach the goal. We study which graph value extensions are planner-admissible under the operational argmin-Q planner. Our main result is a local action-gap certificate: if the surrogate value error along the rollout stays below half the true action gap, then the greedy rollout reaches the goal. Absolutely Minimal Lipschitz Extension (AMLE), the p=infinity endpoint of the graph p-Laplacian family, instantiates this certificate through a comparison-principle fill-distance bound. Harmonic extension, by contrast, can mis-rank local actions because its values reflect boundary hitting probabilities rather than shortest-path greedy order. On 120 AntMaze layout-derived graph configurations, harmonic extension achieves 0.584 aggregate rollout success, while AMLE reaches 0.970. Finite high-p methods also enter a high-success regime, with success 0.903 for p=4, 0.973 for p=8, and 0.982 for a fixed-budget p=16 solver, though the p=16 row is not used as a converged endpoint ranking due to incomplete solver certification. Mechanism audits show that many rollout decisions occur in AMLE-compatible but harmonic-incompatible local geometry, and that AMLE corrects most harmonic inversions on the rollout-weighted decision scope. --- ### A Cloud-Based Tool for Meteorite Recovery Using Drones and Machine Learning Authors: Seamus L. Anderson, Hadrien A. R. Devillepoix, Lewis Lakerink, Sawitchaya Tippaya, Dale P. Giancono, Martin C. Towner, Iona Clemente, Martin Cupák, Ashley F. Rogers, John H. Fairweather, Mia Walker, Daniel Burgin et al. Published: 2026-05-18 Categories: astro-ph.EP, astro-ph.IM, cs.LG arXiv: https://arxiv.org/abs/2605.19179v1 We present a cloud-based tool that uses drones and machine learning to help recover instrumentally observed meteorite falls. We showcase a collection of improvements made upon previous iterations of our system, as well as detail the successes and limitations of this technique when applied to observed meteorite falls in South and Western Australia. This tool is available to the meteoritics research community upon request at https://find.gfo.rocks. --- ### Activation Functions, Statistics and Learning of Higher-Order Interactions in Restricted Boltzmann Machines Authors: Giovanni di Sarra, Yasser Roudi Published: 2026-05-18 Categories: cond-mat.dis-nn, cond-mat.stat-mech, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2605.19178v2 The great success of neural networks primarily arises from the presence of the large number of weight parameters combined with nonlinearities in the input-output relationship of single neurons. In this work, we study the relationship between the statistical properties of the weights and the nonlinearity of the hidden unit in Restricted Boltzmann Machines (RBMs) on the one side, and the distribution induced on binary visible units. We do this for four commonly used activation functions: Linear, Step, ReLU, and Exponential, and make qualitative predictions about the ability of these models to learn distributions with strong higher order interactions over the visible nodes. We show that in general, in an ensemble of RBMs with Gaussian weights, these distributions are rare and hard to learn, except when the hidden unit activation function is an Exponential. --- ### Prompting language influences diagnostic reasoning and accuracy of large language models Authors: Adrien Bazoge, Josselin Corvellec, Sofiane Djillali Sid-Ahmed, Pierre-Antoine Gourraud Published: 2026-05-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.19173v1 Large language models (LLMs) are increasingly explored for clinical decision support, yet most evaluations are conducted in English, leaving their reliability in other languages uncertain. Here we evaluate the impact of prompting language on diagnostic reasoning and final diagnosis accuracy by comparing English and French performance across five LLMs (o3, DeepSeek-R1, GPT-4-Turbo, Llama-3.1-405B-Instruct, and BioMistral-7B). A total of 180 clinical vignettes covering 16 medical specialties were assessed by two physicians using an 18-point scale evaluating both diagnosis accuracy and reasoning quality. Four of the five models performed better in English (mean difference 0.37-0.91, adjusted p < 0.05), with the gap spanning multiple aspects of reasoning, including differential diagnosis, logical structure, and internal validity. o3 was the only model showing no overall language effect. These findings demonstrate that prompting language remains a critical determinant of LLM clinical performance, with implications for equitable linguistico-cultural deployment worldwide. ---