# Research Papers — 2026-05 · bundle page 304 of 326 > Full-text markdown of papers #15151–15200 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/304 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/303.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/305.md) ### SAIL: Structure-Aware Interpretable Learning for Anatomy-Aligned Post-hoc Explanations in OCT Authors: Tienyu Chang, Tianhao Li, Ruogu Fang, Jiang Bian, Yu Huang Published: 2026-05-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.02707v1 Optical coherence tomography (OCT), a commonly used retinal imaging modality, plays a central role in retinal disease diagnosis by providing high-resolution visualization of retinal layers. While deep learning (DL) has achieved expert-level accuracy in OCT-based retinal disease detection, its "black box" nature poses challenges for clinical adoption, where explainability is essential for clinical trust and regulatory approval. Existing post-hoc explainable AI (XAI) methods often struggle to delineate fine-grained lesion structures, respect anatomical boundaries, or suppress noise, limiting the trustworthiness of their explanations. To bridge these gaps, we propose a Structure-Aware Interpretable Learning (SAIL) framework that integrates retinal anatomical priors at the representation level and couples them with semantic features via a fusion design. Without modifying standard post-hoc explainability methods, this representation yields sharper and more anatomically aligned attribution maps. Comprehensive experiments on diverse OCT datasets demonstrate that our structure-aware method consistently enhances interpretability, producing clinically meaningful and anatomy-aware explanations. Ablation studies further show that strong interpretability requires both structural priors and semantic features, and that properly fusing the two is critical to achieve the best explanation quality. Together, these results highlight structure-aware representations as a key step toward reliable explainability in OCT. --- ### Federated Reinforcement Learning for Efficient Mobile Crowdsensing under Incomplete Information Authors: Sumedh J. Dongare, Patrick Weber, Andrea Ortiz, Walid Saad, Oliver Hinz, Anja Klein Published: 2026-05-04 Categories: cs.LG, cs.NI arXiv: https://arxiv.org/abs/2605.02705v1 Mobile crowdsensing (MCS) is a distributed sensing architecture that utilizes existing sensors on mobile units (MUs) to perform sensing tasks. A mobile crowdsensing platform (MCSP) publishes the sensing tasks and the MUs decide whether to participate in exchange for money. The MCS system is dynamic: the task requirements, the MUs' availability, and their available resources change over time. The MUs aim to find an efficient task participation strategy to maximize their income while the MCSP focuses on maximizing the number of completed tasks. As optimal strategies require perfect non-causal information about the MCS system, which is unavailable in realistic scenarios, the main challenge is to find an efficient task participation strategy for the MUs under incomplete information. To this end, a novel fully decentralized federated deep reinforcement learning algorithm, FDRL-PPO, is proposed. FDRL-PPO enables every MU to learn its own task participation strategy based on its experiences, available resources, and preferences, without relying on perfect non-causal information about the MCS system. To replenish their batteries, the MUs rely on energy harvesting. As a result, their available energy varies over time, leading to varying availability and fragmented learning experiences. To mitigate these challenges, the proposed approach leverages federated learning, enabling MUs to collaboratively improve their models without sharing private raw data like their own experiences. By exchanging only learned models, MUs collectively compensate for individual limitations, and find more scalable, robust, and efficient task participation strategies. Comprehensive evaluations on both synthetic and real-world datasets show that FDRL-PPO consistently outperforms benchmark algorithms in terms of task completion ratio, fairness in task completion, energy consumption, and number of conflicting proposals. --- ### ProPACT: A Proactive AI-Driven Adaptive Collaborative Tutor for Pair Programming Authors: Anahita Golrang, Kshitij Sharma, olga viberg Published: 2026-05-04 Categories: cs.HC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.02703v1 Effective pair programming depends on coordination of attention, cognitive effort, and joint regulation over time, yet most adaptive learning systems remain individual-centric and reactive. This paper introduces ProPACT, a proactive AI-driven adaptive collaborative tutor that treats collaboration itself as the object of instruction. ProPACT constructs a multimodal dyadic learner model based on Joint Visual Attention (JVA), Joint Mental Effort (JME), and individual mental effort, and employs an XGBoost-based forecasting model to predict emerging suboptimal collaboration states up to 30 seconds in advance. These predictions drive a hierarchical adaptive policy that delivers minimally intrusive scaffolds while fading support during productive collaboration. A within-subject study with 26 pair-programming dyads shows that proactive feedback significantly improves debugging success, task efficiency, feedback uptake, and post-intervention gains in JVA and JME, demonstrating the potential of forecast-driven dyadic adaptivity for real-time collaborative learning regulation. --- ### Robust and Fast Training via Per-Sample Clipping Authors: Davide Nobile, Philipp Grohs Published: 2026-05-04 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.02701v2 We propose a robust gradient estimator based on per-sample gradient clipping and analyze its properties both theoretically and empirically. We show that the resulting method, per-sample clipped SGD (PS-Clip-SGD), achieves optimal in-expectation convergence rates for non-convex optimization problems under heavy-tailed gradient noise. Moreover, we establish high-probability convergence guarantees that match the in-expectation rates up to polylogarithmic factors in the failure probability. We complement our theoretical results with multiple numerical experiments. In particular, we demonstrate that PS-Clip-SGD outperforms both vanilla SGD with momentum and standard gradient clipping when training AlexNet on the CIFAR-100 dataset, even after accounting for the additional computational time caused by per-sample clipping. We also empirically show that, in the presence of gradient accumulation, applying clipping at the mini-batch level can improve training performance while incurring virtually no additional computational cost. This finding is particularly interesting, as it contradicts the common practice of applying clipping only after all accumulation steps have been completed. --- ### Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions Authors: Sergio Orozco, Tushar Kusnur, Brandon May, George Konidaris, Laura Herlant Published: 2026-05-04 Categories: cs.RO, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.02699v1 Learning data-efficient object dynamics models for robotic manipulation remains challenging, especially for deformable objects. A popular approach is to model objects as sets of 3D particles and learn their motion using graph neural networks. In practice, this is not enough to maintain physical feasibility over long horizons and may require large amounts of interaction data to learn. We introduce PIEGraph, a novel approach to combining analytical physics and data-driven models to capture object dynamics for both rigid and deformable bodies using limited real-world interaction data. PIEGraph consists of two components: (1) a \textbf{P}hysically \textbf{I}nformed particle-based analytical model (implemented as a spring--mass system) to enforce physically feasible motion, and (2) an \textbf{E}quivariant \textbf{Graph} Neural Network with a novel action representation that exploits symmetries in particle interactions to guide the analytical model. We evaluate PIEGraph in simulation and on robot hardware for reorientation and repositioning tasks with ropes, cloth, stuffed animals and rigid objects. We show that our method enables accurate dynamics prediction and reliable downstream robotic manipulation planning, which outperforms state of the art baselines. --- ### mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection Authors: Dominik Macko, Alok Debnath, Jakub Simko Published: 2026-05-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.02695v1 SemEval-2026 Task 9 is focused on multilingual polarization detection. Specifically, it covers the identification of multilingual, multicultural and multievent polarization along three axes (in subtasks), namely detection, type, and manifestation. Online polarization presents a concern, because it is often followed by hate speech, offensive discourse, and social fragmentation. Therefore, its detection before it escalates is crucial for a safer and more inclusive online space. We have coped with this SemEval task by finetuning mid-size LLMs for the sequence-classification task using the QLoRA parameter-efficient finetuning technique. The training data augmented the multilingual (22 languages) training sets by anonymized, lower-cased, upper-cased, and homoglyphied counterparts, making the detection more robust. --- ### Random-Effects Algorithm for Random Objects in Metric Spaces Authors: Marcos Matabuena, Mateo Cámara Published: 2026-05-04 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2605.02693v1 Across many scientific disciplines, multiple observations are collected from the same experimental units, and in modern datasets these observations often arise as non-Euclidean random objects. In such settings, the incorporation of random effects is a critical modeling step for efficient estimation and personalized prediction. Although mixed-effects models are well established for scalar outcomes and, more recently, for functional data in Hilbert spaces, general random-effects frameworks for objects in metric spaces remain underdeveloped. In this paper, we propose a nonlinear Fréchet-based algorithm for random-effects modeling of arbitrary random objects defined on a metric space. Using M-estimation theory, we establish conditions under which the proposed metric-space prediction target is consistently estimated under a working random-effects formulation. We then evaluate the empirical performance of the proposed method using both synthetic data and digital health datasets that require practical tools for analyzing random objects in metric spaces, such as multivariate probability distributions and random graphs. We show that, although our method is developed beyond Hilbert spaces, it can outperform existing Hilbert space-based methods. --- ### ParaRNN: An Interpretable and Parallelizable Recurrent Neural Network for Time-Dependent Data Authors: Yuxi Cai, Lan Li, Feiqing Huang, Guodong Li Published: 2026-05-04 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.02692v1 The proliferation of large-scale and structurally complex data has spurred the integration of machine learning methods into statistical modeling. Recurrent neural networks (RNNs), a foundational class of models for time-dependent data, can be viewed as nonlinear extensions of classical autoregressive moving average models. Despite their flexibility and empirical success in machine learning, RNNs often suffer from limited interpretability and slow training, which hinders their use in statistics. This paper proposes the Parallelized RNN (ParaRNN), a novel model composed of multiple small recurrent units. ParaRNN admits an additive representation that decouples recurrent dynamics into interpretable components, whose behavior can be characterized through recurrence features. This interpretability enables its applications in nonparametric regression for time-dependent data, while the design also allows efficient parallelization. The approximation capacity and non-asymptotic prediction error bounds in a nonparametric regression setting are established for ParaRNN. Empirical results on three sequential modeling tasks further demonstrate that ParaRNN achieves performance comparable to vanilla RNNs while offering improved interpretability and efficiency. --- ### Caliper-in-the-Loop: Black-Box Optimization for Hyperledger Fabric Performance Tuning Authors: Yash Madhwal, Arseny Bolotnikov, Mark Prikhno, Irina Lebedeva, Ivan Laishevskiy, Vladimir Gorgadze, Artem Barger, Yury Yanovich Published: 2026-05-04 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2605.02690v1 Hyperledger Fabric performance depends on many interacting configuration parameters, making manual tuning difficult. We study automated throughput tuning by treating benchmarking as a noisy black-box optimization problem and applying Bayesian optimization (BO) with dimensionality reduction (DR). We implement an end-to-end Caliper-in-the-loop pipeline that deploys candidate configurations, benchmarks them, and updates the optimizer from observed throughput. The search space, derived from Fabric configuration files, has 317 dimensions. In a cloud testbed, we evaluate 16 BO+DR variants and a random-search baseline. The best method, DYCORS-PCA, achieves a 12% TPS improvement relative to the first evaluated configuration, while MPI-REMBO achieves 9%. These results suggest that BO with DR is a practical approach for high-dimensional Hyperledger Fabric tuning, while also highlighting the role of measurement noise in interpreting gains. --- ### MSMixer: Learned Multi-Scale Temporal Mixing with Complementary Linear Shortcut for Long-Term Time Series Forecasting Authors: Ahmed Cherif Published: 2026-05-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.02689v2 Long-term time series forecasting requires models that simultaneously capture rapid oscillations, medium-range periodicities, and slowly evolving macro-trends from a fixed look-back window. Existing lightweight MLP-based models typically operate on a single temporal resolution, limiting their ability to explicitly model patterns at multiple scales. We propose MSMixer, a channel-independent multi-scale MLP architecture that addresses this limitation through three complementary innovations: (i) three parallel scale branches at down-sample factors {1x, 4x, 16x} with independent MLP blocks, (ii) a learnable softmax gate that dynamically weighs branch outputs, and (iii) a DLinear complementary shortcut that provides full-window trend and seasonality context. MSMixer contains only 112K parameters at H=96 and runs at O(T) complexity. Evaluated on four ETT benchmarks with standard chronological splits and three random seeds, MSMixer achieves the lowest average MSE (0.357) among lightweight models, outperforming DLinear (0.386, -7.4%) and NLinear (0.365, -2.1%), winning 12 of 16 configurations. Against five Transformer-based baselines from the literature, MSMixer achieves best or second-best MSE in 9 of 16 configurations while using 5x fewer parameters than PatchTST. Ablation and sensitivity analyses confirm the complementary contributions of the multi-scale branches and the DLinear shortcut. --- ### Spectral Model eXplainer: a chemically-grounded explainability framework for spectral-based machine learning models Authors: Jose Vinicius Ribeiro, Rafael Figueira Goncalves, Fabio Luiz Melquiades, Sylvio Barbon Junior Published: 2026-05-04 Categories: cs.LG, physics.app-ph arXiv: https://arxiv.org/abs/2605.02684v1 Spectral-based machine learning models have been increasingly deployed in chemometrics and spectroscopy, where predictive accuracy is as important as explainability. Current employed eXplainable Artificial Intelligence (XAI) methods are largely adapted from tabular or generic multivariate domains, assigning relevance to isolated spectral variables rather than to the chemically meaningful spectral zones. Widely adopted tools such as SHapley Additive exPlanations (SHAP), Permutation Feature Importance (PFI), and Variable Importance in Projection scores (VIP) were not designed for the physical continuity and high collinearity of spectral data, and their variable-level outputs require post-hoc aggregation to recover zone-level information. This study introduces the Spectral Model eXplainer (SMX), a post-hoc, global, model-agnostic XAI framework that explains spectral classifiers through expert-informed spectral zones. SMX summarizes each zone via PCA, defines quantile-based logical predicates, estimates predicate relevance with perturbation in stochastic subsamples, and aggregates bag-wise rankings in a directed weighted graph summarized by Local Reaching Centrality. A key component is threshold spectrum reconstruction, which back-projects predicate boundaries to the original spectral domain in natural measurement units, enabling direct visual comparison with measured spectra. The method was evaluated on eight real spectral datasets (six based on X-ray Fluorescence--XRF and two based on Gamma-ray Spectrometry) and one synthetic benchmark with known gr --- ### Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI Authors: Majed El Helou, Benjamin Ryder, Chiara Troiani, Jean Diaconu, Hervé Muyal, Marcelo Yannuzzi Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.02682v1 Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale toward distributed collaboration. A compromised or malicious agentic application can tamper with tool calls, falsify results, or request permissions beyond the scope of the subject's intended tasks, which could go unnoticed with current delegated authorization flows given their lack of visibility into the original subject's intent. In light of this, we make the following contributions towards Continuous Agent Semantic Authorization (CASA). First, we propose a hybrid runtime enforcement model that combines deterministic and semantic controls enabled by a zero-trust interception layer. Five deterministic controls enforce structural and data-integrity guarantees over the message flow, while a semantic inspection layer evaluates whether tool call choices align with the intended tasks commissioned to the agent. Second, differently from prior Task-Based Access Control (TBAC) techniques that operate on single-turn interactions, we decompose the semantic layer into two stages: i) a task-extraction step that distills the subject's objectives from multi-turn conversations at the interception layer, and ii) a task-tool semantic matching step at the authorization server that evaluates whether the requested tools are appropriate for the extracted tasks. Third, we extend the ASTRA dataset that we introduced in a prior work, by generating novel conversation-tool datasets with multi-turn interactions containing relevant and irrelevant tool calls for a given task. Lastly, we provide the first experimental results for TBAC under multi-turn conversations. --- ### The Design and Composition of Structural Causal Decision Processes Authors: Sebastian Benthall, Alan Lujan Published: 2026-05-04 Categories: cs.CE, cs.AI, cs.GT, econ.TH arXiv: https://arxiv.org/abs/2605.02681v1 We present two new classes of causal models of decision-making agents. Our approach is motivated by the needs of modeling the economics of computing systems. These systems are composed of subsystems and can exhibit endogenous limits on cognitive resources and value discounting. Structural Causal Decision Models (SCDMs) expand on Structural Causal Influence Models. Like SCIMs, they explicitly represent the causal relationships between model variables and the payoffs of agent decisions. Additionally, agent decisions can be constrained by their causal antecedents, and SCDMs can have open root variables for which no probability distribution or structural equation is given. We show that SCDMs have a well-defined and computationally useful property of composability. Building on SCDMs, we then define a Structural Causal Decision Process (SCDP) as a recurring SCDM with a discount variable. SCDPs benefit from the useful composition properties of SCDMs. Moreover, SCDPs are strictly more expressive than POMDPs because they do not assume rational belief formation. Indeed, an SCDP can endogenously model the memory-formation process, and is thus useful for modeling resource rational agents in dynamic settings. SCDPs are also capable of modeling variable discounting, a tool used widely in social scientific modeling. We pose that SCDPs are a useful framework for policy simulation for the digital economy, mechanism design for information systems, and digital twin modeling of cyberinfrastructure. --- ### Online Generalised Predictive Coding Authors: Mehran H. Z. Bazargani, Szymon Urbas, Adeel Razi, Thomas Brendan Murphy, Karl Friston Published: 2026-05-04 Categories: stat.ML, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2605.02675v1 This paper introduces an extension of generalised filtering for online applications. Generalised filtering refers to data assimilation schemes that jointly infer latent states, learn unknown model parameters, and estimate uncertainty in an integrated framework -- e.g., estimate state and observation noise -- at the same time (i.e., triple estimation). This framework appears across disciplines under different names, including variational Kalman-Bucy filtering in engineering, generalised predictive coding in neuroscience, and Dynamic Expectation Maximisation (DEM) in time-series analysis. Here, we specialise DEM for ``online'' data assimilation, through a separation of temporal scales. We describe the variational principles and procedures that allow one to assimilate data in a way that allows for a slow updating of parameters and precisions, which contextualise fast Bayesian belief updating about the dynamic hidden states. Using numerical studies, we demonstrate the validity of online DEM (ODEM) using a non-linear -- and potentially chaotic -- generative model, to show that the ODEM scheme can track the latent states of the generative process, even when its functional form differs fundamentally from the dynamics of the generative model. Framed from a neuro-mimetic predictive coding perspective, ODEM offers a biologically inspired solution to online inference, learning, and uncertainty estimation in dynamic environments. --- ### The 2026 ACII Dyadic Conversations (DaiKon) Workshop & Challenge Authors: Panagiotis Tzirakis, Alice Baird, Jeffrey Brooks, Emilia Parada-Cabaleiro, Lukas Stappen, Sharath Rao, Theo Lebryk, Jakub Piotr Clapa, Jens Madsen Published: 2026-05-04 Categories: cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2605.02672v1 The 2026 ACII Dyadic Conversations (ACII-DaiKon) Workshop & Challenge introduces a benchmark for modeling interpersonal affect and social dynamics in dyadic conversations. Although conversational affect modeling has advanced rapidly, most benchmarks remain speaker-centric and underrepresent coupled, time-evolving processes between partners, including directional influence, conversational timing coordination, and rapport development. To address this gap, ACII-DaiKon presents three coordinated sub-challenges built on a shared dataset: (1) directional interpersonal influence prediction, (2) turn-taking prediction (next-speaker and time-to-next-speech), and (3) rapport trajectory prediction across full interactions. The challenge is built on the Hume-DaiKon dataset, comprising 945 dyadic conversations (743.4 hours of audiovisual data) collected under naturalistic conditions across five languages. The benchmark supports multimodal modeling, temporal reasoning, and cross-context generalization through fixed train/validation/test splits, standardized metrics, and released baseline systems. Evaluation uses Concordance Correlation Coefficient (CCC), Pearson correlation, Macro-F1, and Mean Absolute Error (MAE) depending on the sub-challenge. Baseline experiments establish initial reference performance, with best test results of 0.40 CCC and 0.50 Pearson for influence prediction, 0.66 Macro-F1 and 1.50~s MAE for turn-taking, and 0.68 CCC and 0.70 Pearson for rapport trajectory modeling. These results indicate that while current methods capture coarse dyadic patterns, robust modeling of directional dependence and long-horizon interpersonal dynamics remains challenging. The workshop provides a shared platform for rigorous comparison and cross-disciplinary discussion on data validity, evaluation protocols, and culturally aware modeling for dyadic interaction. --- ### An explainable hypothesis-driven approach to Drug-Induced Liver Injury with HADES Authors: Maciej Wisniewski, Bartosz Topolski, Pawel Dabrowski-Tumanski, Dariusz Plewczynski, Tomasz Jetka Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.02669v2 Drug-induced liver injury (DILI) remains a leading cause of late-stage clinical trial attrition. However, existing computational predictors primarily rely on binary classification, a framing that limits generalization and yields no mechanistic insight to guide translational decisions. We argue that DILI prediction is better posed as an explainable hypothesis-generation problem. To support this shift, we introduce the DILER Benchmark, a dataset that extends beyond binary labels by augmenting a curated set of molecules with mechanistic hepatotoxicity hypotheses derived from biomedical literature. We further present HADES, an agentic system designed to generate transparent and auditable reasoning traces. By combining molecular-level predictions, metabolite decomposition, structural understanding, and toxicity pathway evidence, HADES mechanistically assesses DILI risk. Evaluated on the DILER Benchmark, HADES outperforms existing models in binary classification, achieving a ROC-AUC of 0.68 on the Test Set and 0.59 on the challenging Post-2021 Set, compared with 0.63 and 0.50 for DILI-Predictor, respectively. More importantly, we establish a baseline for mechanistic hypothesis generation, where HADES achieves a Hypothesis Alignment Fuzzy Jaccard Index of 0.16. This result underscores the inherent complexity of the task while highlighting the need for advanced explainable approaches in predictive toxicology. --- ### AnchorD: Metric Grounding of Monocular Depth Using Factor Graphs Authors: Simon Dorer, Martin Büchner, Nick Heppert, Abhinav Valada Published: 2026-05-04 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2605.02667v1 Dense and accurate depth estimation is essential for robotic manipulation, grasping, and navigation, yet currently available depth sensors are prone to errors on transparent, specular, and general non-Lambertian surfaces. To mitigate these errors, large-scale monocular depth estimation approaches provide strong structural priors, but their predictions can be potentially skewed or mis-scaled in metric units, limiting their direct use in robotics. Thus, in this work, we propose a training-free depth grounding framework that anchors monocular depth estimation priors from a depth foundation model in raw sensor depth through factor graph optimization. Our method performs a patch-wise affine alignment, locally grounding monocular predictions in metric real-world depth while preserving fine-grained geometric structure and discontinuities. To facilitate evaluation in challenging real-world conditions, we introduce a benchmark dataset with dense scene-wide ground truth depth in the presence of non-Lambertian objects. Ground truth is obtained via matte reflection spray and multi-camera fusion, overcoming the reliance on object-only CAD-based annotations used in prior datasets. Extensive evaluations across diverse sensors and domains demonstrate consistent improvements in depth performance without any (re-)training. We make our implementation publicly available at https://anchord.cs.uni-freiburg.de. --- ### Fuzzy Fingerprinting Encoder Pre-trained Language Models for Emotion Recognition in Conversations: Human Assessment and Validity Study Authors: Patrícia Pereira, Helena Moniz, Joao Paulo Carvalho Published: 2026-05-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.02665v1 In Emotion Recognition in Conversations (ERC), model decisions should align with nuanced human perception and ideally provide insights on the classification process. Standard encoder pre-trained language models (PLMs) are the state-of-the-art at these tasks but offer little insight into why a certain prediction is made. This is especially problematic in imbalanced datasets, where most utterances are labeled as neutral, making these models frequently misclassify minority emotions as the majority neutral class. To tackle this issue, we introduced a novel, interpretable approach to ERC by combining PLMs with Fuzzy Fingerprints (FFPs). FFP provide class-specific prototypes that reflect the characteristic class activation patterns in the PLM's latent space. They are derived by ranking and fuzzifying the activations of the pooled conversational context-dependent embeddings across training instances for each emotion. At inference time, each input utterance is similarly fuzzy fingerprinted and matched to the emotion prototypes using a fuzzy similarity function based on the aggregation of the intersection of the fuzzy sets that define each FFP. Experimental results show that FFP integration reduces overclassification into the neutral class and human evaluation further supports the adequacy of FFP predictions. Our proposed method thus bridges the gap between deep neural inference and human perception, performing at state-of-the-art level while simultaneously offering valuable insights into the classification procedure. --- ### AcademiClaw: When Students Set Challenges for AI Agents Authors: Junjie Yu, Pengrui Lu, Weiye Si, Hongliang Lu, Jiabao Wu, Kaiwen Tao, Kun Wang, Lingyu Yang, Qiran Zhang, Xiuting Guo, Xuanyu Wang, Yang Wang et al. Published: 2026-05-04 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2605.02661v1 Benchmarks within the OpenClaw ecosystem have thus far evaluated exclusively assistant-level tasks, leaving the academic-level capabilities of OpenClaw largely unexamined. We introduce AcademiClaw, a bilingual benchmark of 80 complex, long-horizon tasks sourced directly from university students' real academic workflows -- homework, research projects, competitions, and personal projects -- that they found current AI agents unable to solve effectively. Curated from 230 student-submitted candidates through rigorous expert review, the final task set spans 25+ professional domains, ranging from olympiad-level mathematics and linguistics problems to GPU-intensive reinforcement learning and full-stack system debugging, with 16 tasks requiring CUDA GPU execution. Each task executes in an isolated Docker sandbox and is scored on task completion by multi-dimensional rubrics combining six complementary techniques, with an independent five-category safety audit providing additional behavioral analysis. Experiments on six frontier models show that even the best achieves only a 55\% pass rate. Further analysis uncovers sharp capability boundaries across task domains, divergent behavioral strategies among models, and a disconnect between token consumption and output quality, providing fine-grained diagnostic signals beyond what aggregate metrics reveal. We hope that AcademiClaw and its open-sourced data and code can serve as a useful resource for the OpenClaw community, driving progress toward agents that are more capable and versatile across the full breadth of real-world academic demands. All data and code are available at https://github.com/GAIR-NLP/AcademiClaw. --- ### Biological Spatial Priors Regularize Foundation Model Representations for Cross-Site MSI Generalization in Colorectal Cancer Authors: Dasari Naga Raju Published: 2026-05-04 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2605.02660v1 Predicting microsatellite instability (MSI) status from routine hematoxylin and eosin (H&E) whole slide images (WSIs) offers a practical alternative to molecular testing, but models trained at one institution tend to generalize poorly to slides acquired at a different site. Foundation model representations, despite their generality, still encode site-specific texture alongside the conserved biological morphology underlying MSI. We investigate whether tile-level spatial priors derived from known MSI histology can guide these representations toward more site-invariant features. We introduce a biologically motivated spatial prior based on peripheral distance encoding, reflecting the Crohn's-like peripheral lymphocytic reaction at the tumor invasive margin, and evaluate a secondary local immune neighborhood encoding reflecting the lymphocyte-to-tumor ratio in each tile's immediate spatial neighborhood. Both priors are injected into a TransMIL aggregator before self-attention, allowing the transformer to integrate spatial biological context with UNI2-h or Virchow2 features across all attention layers. We evaluate six foundation model and MIL aggregator combinations as a reference, then assess the effect of each spatial prior. Training on TCGA-COAD (137 slides) and evaluating externally on TCGA-READ (50 slides) without retraining, peripheral distance encoding achieves MSI AUC 0.959 +/- 0.012 on COAD and MSS specificity 1.000 on READ, compared to 0.957 and 0.939 for the strongest reference configuration. Local immune neighborhood encoding achieves comparable internal AUC but lower cross-site specificity, suggesting margin proximity encodes a more site-invariant biological signal than local immune density. Results suggest biologically grounded spatial priors act as regularizers that reduce reliance on site-specific imaging patterns. --- ### Human Activity Recognition Method for Moderate Violence Detection Authors: Luis Angel Aparicio Borjas, Victor Elias Nieto, Juan Irving Vasquez, Alfonso Fernandez-Vazquez, Gerardo Antonio Alvarez Hernandez Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.02659v1 Physical violence in public spaces is a significant public health concern, with minor incidents such as pushing often serving as precursors to more severe escalations. This research develops an automated system for the real-time detection of moderate physical violence, specifically pushing, in surveillance camera footage. The proposed solution integrates state-of-the-art computer vision models, utilizing YOLO11 and YOLO11-Pose for human detection and skeletal keypoint extraction. By calculating body inclination and joint angles between shoulders and hips, a Random Forest classifier was trained to distinguish between normal behavior and aggressive physical contact. The system's performance was evaluated through three progressive case studies representing increasing levels of difficulty. In controlled environments with frontal views, the model achieved a precision of 0.98. In the most challenging scenario, featuring high-altitude, steep-angle recordings from real-world surveillance infrastructure, the system maintained a precision of 0.72 despite significant perspective distortion and visual noise. These results demonstrate the feasibility of using skeletal analysis for early violence intervention in urban security contexts. --- ### Deciphering Shortcut Learning from an Evolutionary Game Theory Perspective Authors: Xiayang Li, Kuo Gai, Shihua Zhang Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.02658v2 Shortcut learning causes deep learning models to rely on non-essential features within the data. However, its formation in deep neural network training still lacks theoretical understanding. In this paper, we provide a formal definition of core and shortcut features and employ evolutionary game theory to analyze the origins of shortcut bias by modeling data samples as players and their corresponding neural tangent features as strategies, assuming the existence of core and shortcut subnetworks. We find that gradient descent (GD) and stochastic gradient descent (SGD) lead to two distinct stochastically stable states, each corresponding to a different strategy. The former primarily optimizes the shortcut subnetwork, while the latter primarily optimizes the core subnetwork. We investigate the influence of these strategies on shortcut bias through a continuous stochastic differential equation, and reveal the impact of data noise and optimization noise on the formation of shortcut bias. In brief, our work employs evolutionary game theory to characterize the dynamics of shortcut bias formation and provides a theoretical view on its mitigation. --- ### CARD: Coarse-to-fine Autoregressive Modeling with Radix-based Decomposition for Transferable Free Energy Estimation Authors: Ziyang Yu, Yi He, Wenbing Huang, Wen Yan, Yang Liu Published: 2026-05-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.02657v1 Estimating free energy differences quantifies thermodynamic preferences in molecular interactions, which is central to chemistry and drug discovery. Despite fruitful progress, existing methods still face key limitations: classical computational approaches remain prohibitively expensive due to their reliance on extensive molecular dynamics simulations, while deep learning-based methods are constrained by either less-expressive generative models or input dimensions tied to a specific system, resulting in negligible generalization. To address these challenges, we propose CARD, a generative framework that employs a novel radix-based decomposition to bijectively convert 3D coordinates into mixed discrete-continuous sequences, enabling coarse-to-fine autoregressive modeling with enhanced expressiveness. Notably, the model corresponds to a distribution with zero free energy, serving as a proposal for absolute free energy computation of arbitrary systems without relying on alchemical pathways. Experiments across diverse tasks demonstrate that CARD matches the accuracy of classical computational methods on unseen systems with diverse topologies, while achieving an approximately 40-fold speedup in inference. --- ### ARA: Agentic Reproducibility Assessment For Scalable Support Of Scientific Peer-Review Authors: Kevin Riehl, Andres L. Marin, Nikofors Zacharof, Fan Wu, Patrick Langer, Robert Jakob, Anastasios Kouvelas, Georgios Fontaras, Michail A. Makridis Published: 2026-05-04 Categories: cs.DL, cs.LG arXiv: https://arxiv.org/abs/2605.02651v2 Scientific peer review increasingly struggles to assess reproducibility at the scale and complexity of modern research output. Evaluating reproducibility requires reconstructing experimental dependencies, methodological choices, data flows, and result-generating procedures, which often exceeds what human reviewers can provide. Agentic Reproducibility Assessment (ARA) formalizes reproducibility assessment as a structured reasoning task over scientific documents. Given a paper, ARA extracts a directed workflow graph linking sources, methods, experiments, and outputs, then evaluates its reconstructability using structural and content-based scores for reproducibility assessments. Experiments on 213 ReScience C articles - the largest cross-domain benchmark of human-validated computational reproducibility studies considered to date - demonstrate ARA's generalizability and consistent workflow reconstruction and assessment across LLMs, model temperatures, and scientific domains. ARA achieves ~61% accuracy on three benchmarks, and the highest accuracy reported on ReproBench (60.71% vs. 36.84%) and GoldStandardDB (61.68% vs. 43.56%), highlighting its potential to complement human review at scale and enabling next-generation peer review. Code and Data available: https://github.com/AndresLaverdeMarin/agentic_reproducibility_assessment. --- ### ContextualJailbreak: Evolutionary Red-Teaming via Simulated Conversational Priming Authors: Mario Rodríguez Béjar, Francisco J. Cortés-Delgado, S. Braghin, Jose L. Hernández-Ramos Published: 2026-05-04 Categories: cs.CL, cs.CR arXiv: https://arxiv.org/abs/2605.02647v1 Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety alignment and elicit harmful responses. A growing body of work shows that contextual priming, where earlier turns covertly bias later replies, constitutes a powerful attack surface, with hand-crafted multi-turn scaffolds consistently outperforming single-turn manipulations on capable models. However, automated optimization-based red-teaming has remained largely limited to the single-turn setting, iterating over static prompts and lacking the ability to reason about which forms of conversational priming induce compliance. While recent multi-turn, search-based approaches have begun to bridge this gap, the mutator design space underlying effective primed dialogues remains largely unexplored. We present ContextualJailbreak, a black-box red-teaming strategy that performs evolutionary search over a simulated multi-turn primed dialogue. The strategy leverages a graded 0-5 harm score from a two-level judge as an in-loop signal, enabling partially harmful responses to guide the search process rather than being discarded. Search is driven by five semantically defined mutation operators: roleplay, scenario, expand, troubleshooting, and mechanistic, of which the last two are novel contributions of this work. Across 50 representative HarmBench behaviors, ContextualJailbreak achieves an ASR of 100% on gpt-oss:20B, 100% on qwen3-8B, 100% on llama3.1:70B, and 90% on gpt-oss:120B, outperforming four single- and multi-turn baselines by 31-96 percentage points on average. The 40 maximally harmful attacks discovered against gpt-oss:120B transfer without adaptation to closed frontier models, achieving 90.0% on gpt-4o-mini, 70.0% on gpt-5, and 70.0% on gemini-3-flash, but only 17.5% on claude-opus-4-7 and 15.0% on claude-sonnet-4-6, revealing a pronounced provider-level asymmetry in alignment robustness. --- ### Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE Authors: Yangming Shi, Shixiang Zhu, Tao Shen, Zhimiao Yu, Dengsheng Chen, Taicai Chen, Yunfei Yang, Juan Zhou, Chen Cheng, Liang Ma, Xibin Wu, Benxuan Yan et al. Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.02641v1 We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture. To efficiently enhance the model's generation capability, we equip the Diffusion Transformer backbone with a fine-grained Mixture-of-Experts (MoE) design (128 experts, Top-8 routing), yielding a 25B-parameter model that activates only 3B parameters, significantly reducing training costs while scaling up the model capacity. Mamoda2.5 achieves top-tier generation performance on VBench 2.0 and sets a new record in video editing quality, surpassing evaluated open-source models and matching the performance of current top-tier proprietary models, including the Kling O1 on OpenVE-Bench. Furthermore, we introduce a joint few-step distillation and reinforcement learning framework that compresses the 30-step editing model into a 4-step model and greatly accelerates model inference. Compared to open-source baselines, Mamoda2.5 achieves up to $95.9\times$ faster video editing inference. In real-world applications, Mamoda2.5 has been successfully deployed for content moderation and creative restoration tasks in advertising scenarios, achieving a 98% success rate in internal advertising video editing scenario. --- ### Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution Authors: Ruta Binkyte, Ivaxi Sheth, Zhijing Jin, Mohammad Havaei, Bernhard Schölkopf, Mario Fritz Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.02640v2 As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), are increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously, especially while preserving utility. This position paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI. We ground our arguments in re-interpreting trustworthy AI trade-offs as incompatible invariance requirements under different changes to the data-generating process. We then illustrate this argument through case-study analyses from the literature and a stylized synthetic-data simulation, showing that causality provides a unifying framework for understanding how trade-offs in trustworthy AI arise and how they can be softened or resolved through selective invariance. This perspective applies to both classical ML models and large-scale FMs. Finally, we outline open challenges and opportunities for using causality to build both trustworthy and high-performing AI. --- ### ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Tracking Authors: Jiawei Ge, Xintian Zhang, Jiuxin Cao, Bo Liu, Fabian Deuser, Chang Liu, Gong Wenkang, Siyou Li, Juexi Shao, Wenqing Wu, Chen Feng, Ioannis Patras Published: 2026-05-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.02638v1 Cross-view Referring Multi-Object Tracking (CRMOT) aims to track multiple objects specified by natural language across multiple camera views, with globally consistent identities. Despite recent progress, existing methods rely heavily on costly frame-level spatial annotations and cross-view identity supervision. To reduce such reliance, we explore CRMOT under weak supervision by leveraging the capabilities of foundation models. However, our empirical study shows that directly applying foundation models such as SAM2 and SAM3, even with task-specific modifications, fails to accurately understand referring expressions and maintain consistent identities across views. Yet, they remain effective at producing reliable object tracklets that can serve as pseudo supervision. We therefore repurpose foundation models as pseudo-label generators and propose a two-stage framework for weakly supervised CRMOT, using only object category labels as coarse-grained supervision. In the first stage, we design an Affinity-guided Cross-view Re-prompting strategy to refine and associate SAM3-generated tracklets across cameras, producing reliable cross-view pseudo labels for subsequent training. In the second stage, we introduce ViewSAM, a CRMOT model built upon SAM2 that explicitly models view-aware cross-modal semantics. By formulating view-induced variations as learnable conditions, ViewSAM bridges the gap between view-variant visual observations and view-invariant textual expressions, enabling robust cross-view referring tracking with only approximately 10% additional parameters. Extensive experiments demonstrate that ViewSAM achieves SOTA performance under weak supervision and remains competitive with fully supervised methods. --- ### Convolutional Neural Networks in Vis-NIR Chemometrics: From Contradiction to Conditional Design Authors: Dário Passos Published: 2026-05-04 Categories: cs.LG, physics.optics arXiv: https://arxiv.org/abs/2605.02636v2 Near-infrared (NIR and Vis-NIR) spectroscopy is widely used for rapid, non-destructive analysis in food, agriculture, pharmaceuticals, process analytical technology, and bioprocess monitoring. Nevertheless, deep-learning studies in NIR chemometrics often reach conflicting conclusions about convolutional neural network (CNN) design, including kernel size, depth, preprocessing, model complexity, and transfer robustness. This review argues that many apparent contradictions reflect incomplete experimental conditioning rather than incompatible findings. CNN performance depends on interactions among spectral physics, dataset regime, acquisition protocol, validation design, and deployment conditions. We organize the literature around three moderators. First, NIR signals are indirect, highly collinear, and shaped by broad overlapping bands, scattering, temperature, and matrix effects. Second, CNN design should be interpreted through receptive-field reasoning: kernel size, depth, dilation, and multi-scale branches determine the wavelength span available to the model, whereas the effective receptive field indicates which parts are actually used. Third, validation design can behave as a hidden hyperparameter because random splits may reward architectures that exploit shared batch, instrument, season, or process-run structure instead of transferable chemical information. We therefore propose a conditional design framework in which preprocessing, architecture, hyperparameter optimization, transfer evaluation, interpretability, and reproducibility are treated as coupled components. Rather than seeking a universally optimal CNN, the framework aims to support physics-aware, shift-aware, and reproducible model comparison in NIR chemometrics. --- ### AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding Authors: Ruilin Yao, Shegnwu Xiong, Tianyu Zou, Shili Xiong, Yi Rong Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.02630v1 Vision-Language Models (VLMs) have enabled autonomous GUI agents that translate natural language instructions into executable screen coordinates. However, grounding performance degrades in high-resolution interfaces, where dense layouts and small interactive elements expose a resolution gap between modern displays and model input constraints. Existing zoom-in strategies rely on fixed anchors, heuristic grids, or reinforcement learning, lacking a principled mechanism to adaptively determine where refinement is needed and how much spatial uncertainty should be explored. We propose AutoFocus, a training-free, uncertainty-aware active visual search framework for GUI grounding. Our key insight is that token-level perplexity in coordinate generation naturally reflects spatial uncertainty. Rather than committing to a single prediction, AutoFocus samples multiple coordinate hypotheses and converts their axial perplexities into an anisotropic gaussian spatial probability field, explicitly modeling directional uncertainty. Based on this field, we generate global and local region proposals and introduce Shape-Aware Zooming to balance tight localization with contextual preservation. A visual prompt-based aggregation step then selects the most consistent prediction via structured comparison. Extensive experiments on ScreenSpot-Pro and ScreenSpot-V2 demonstrate consistent improvements across both general-purpose and GUI-specialized VLMs. --- ### Mapping Discourse Reframing: A Multi-Layer Network Approach to Italian HPV Vaccine Discourse on X (2010-2024) Authors: Lorella Viola Published: 2026-05-04 Categories: cs.CL, cs.CY, cs.NI arXiv: https://arxiv.org/abs/2605.02629v1 Understanding how online narratives travel through coalitions is critical for identifying information disorder, yet computational analyses often rely on conservative network constructions that erase initially sparse but salient signals. This paper proposes a novel multi-layer framework that captures low-frequency signals of emerging information disorder allowing for locating where online discourse is reframed and amplified over time. The use case is 14 years of Italian discourse on X regarding the Human Papillomavirus (HPV) vaccine across three pivotal epochs (2010-2024). Utilizing hashtag co-occurrence networks, we introduce a dual-layer approach. We first identify robust core discourse coalitions through conservative community detection, revealing a stable prevention-oriented backbone contrasted with increasingly separable skepticism coalitions. We then introduce a coverage layer and project fringe hashtags into core coalitions based on weighted connectivity. Using a manually labelled set of skeptical and conspiratorial seed tweets, we demonstrate that this core-coverage projection significantly improves the recovery of long-tail, problematic hashtags while preserving an interpretable coalition structure. Our findings characterize the structural maturation of polarized narratives and provide a methodology for mapping how discourse is reframed and amplified by information disorder over time. --- ### Neuromorphic Control for 3D Navigation in Minecraft Using Genetic Algorithms Authors: Eric Zipor Published: 2026-05-04 Categories: cs.NE arXiv: https://arxiv.org/abs/2605.02628v1 The popular 2009 voxel based videogame, Minecraft, contains several distinct disciplines. One of which is "parkour," gameplay that focuses on traversing a world's environment with maximum efficiency. The Minecraft online community has turned the game's physics engine into dynamic puzzles, requiring players to masterfully manipulate motion mechanics through frame precise timing of keystrokes. Actions such as sprinting, sneaking, and mouse direction are all combined to clear specific difficult jumps. Through this project, we design a genetic algorithm to generate weights for a neural network to autonomously evaluate inputs for block distances, terrain, and obstacles to determine the most optimal pathing. --- ### Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective Authors: Guangrui Bai, Yifan Mei, Yahui Deng, Yuhan Chen, Yuze Qiu, Wenhai Liu, Erbao Dong Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.02627v1 Explicit reconstruction constraints derived from the decoupled representation are further imposed to suppress abnormal channel amplification and chromatic noise. Experiments on LOLv2-Real, MIT-Adobe FiveK, and LSRW show that the proposed method achieves competitive or superior quantitative and visual performance, reaching 29.71 dB PSNR and 0.89 SSIM on LOLv2-Real. DarkFace experiments further indicate improved downstream face detection under low-light conditions. Code and pretrained models are available at: https://github.com/mubaisam/ICD. --- ### Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models Authors: Inoussa Mouiche, Abderaouf Bahi Published: 2026-05-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.02626v2 Direct Preference Optimization (DPO) improves relative preference by increasing the margin between chosen and rejected responses, but this objective does not specify how probability mass should be redistributed to achieve that margin. Consequently, preference separation can improve even as probability mass collapses away from both preferred and unrelated responses, a phenomenon associated with the squeezing effect. We show that this pathology is localized: continued negative updates become destructive when rejected responses enter low-probability valleys, where further suppression induces harmful redistribution through the coupled softmax geometry. We introduce Gradient-Gated Preference Optimization (Gate-DPO), which uses the current probability geometry of each rejected response to selectively attenuate its contribution, limiting excessive rejected suppression while delaying preference-loss saturation. Gate-DPO is objective-agnostic and composes with existing preference methods. Across four architectures, two preference datasets, and multiple objectives, gating consistently reduces squeezing and improves chosen-response likelihood, while exhibiting robust reductions in rejected-response collapse across architectures and objectives. Mass-dynamics analysis further shows that large preference margins can conceal substantial suppression of unrelated responses, while gating achieves healthier redistribution. Together, our results show that preference margin alone is insufficient to characterize optimization health and that selectively controlling probability dynamics provides a simple, general mechanism for stabilizing preference optimization. --- ### Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models Authors: Inoussa Mouiche Published: 2026-05-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.02626v1 Preference optimization has become a central paradigm for aligning large language models with human feedback. Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback by directly optimizing pairwise preferences, removing the need for reward modeling and policy optimization. However, recent work shows that DPO exhibits a squeezing effect, where negative gradients applied to rejected responses concentrate probability mass on high-confidence predictions while suppressing alternative responses. This phenomenon arises even in simple softmax models and can lead to systematic probability collapse during training. We introduce Gradient-Gated Preference Optimization (Gate-DPO), a method that stabilizes training by modulating rejected gradients according to the model's probability geometry. When updates target extremely low-probability responses, the gate attenuates harmful gradients while preserving standard optimization behavior. Gate-DPO addresses this optimization pathology without modifying the underlying preference objective and is complementary to existing methods such as extended SFT, IPO, and Cal-DPO. Experiments across multiple architectures and preference datasets show that Gate-DPO consistently reduces squeezing and improves chosen-response likelihood. Mass-dynamics analysis further reveals healthier optimization behavior, with improved preferred responses and reduced suppression of the overall distribution. Notably, smaller gated models can exhibit stronger chosen-response improvements than larger ungated models, suggesting that controlling gradient dynamics, rather than scale alone, is key to stable and efficient alignment. --- ### Synthetic Users, Real Differences: an Evaluation Framework for User Simulation in Multi-Turn Conversations Authors: Yu Lu Liu, Hyokun Yun, Tanya Roosta, Ziang Xiao Published: 2026-05-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.02624v1 There is growing interest in exploring user simulation as an alternative to gathering and scoring real user-chatbot interactions for AI chatbot evaluation. For this purpose, it is important to ensure the realism of the simulation, i.e., the extent to which simulated dialogues reflect real dialogues users have with chatbots. Most existing methods evaluating simulation realism produce coarse quality signal and remain solely at the level of individual dialogues. To support more rigorous evaluation in this area, we propose realsim, an evaluation framework that enables practitioners to take a distributional view of real vs. simulated dialogues along 8 dimensions, covering attributes related to the communicative functions of the interaction, user states, and the surface form of user messages. We then instantiate the framework with a curated dataset of 1K multi-turn task-focused real user-chatbot dialogues that cover 16 domains of chatbot applications. Overall, we find that simulated users tend to struggle at capturing communication frictions that real users introduce to interactions, which could make evaluations based on such simulations overly optimistic. We also observe variability in performance across different domains, which may indicate a need for domain-specific user simulators. --- ### Retrieving Any Relevant Moments: Benchmark and Models for Generalized Moment Retrieval Authors: Yiming Ding, Siyu Cao, Luyuan Jiao, Yixuan Li, Zitong Wang, Zhiyong Liu, Lu Zhang Published: 2026-05-04 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2605.02623v1 Video Moment Retrieval (VMR) aims to localize temporal segments in videos that correspond to a natural language query, but typically assumes only a single matching moment for each query. This assumption does not always hold in real-world scenarios, where queries may correspond to multiple or no moments. Thus, we formulate Generalized Moment Retrieval (GMR), a unified setting that requires retrieving the complete set of relevant moments or predicting an empty set. To enable systematic study of GMR, we introduce Soccer-GMR, a large-scale benchmark built on challenging soccer videos that reflect general GMR scenarios, with realistic negative and positive queries. The benchmark is constructed via a duration-flexible semi-automated pipeline with human verification, enabling scalable data generation while maintaining high annotation quality. We further design a unified evaluation protocol with complementary metrics tailored for null-set rejection, positive-query localization, and end-to-end GMR performance. Finally, we establish strong baselines across two modeling paradigms: a lightweight plug-and-play GMR adapter for discriminative VMR models, and a GMR-tailored GRPO reward for fine-tuning multimodal large language models (MLLMs). Extensive experiments show consistent gains across all metrics and expose key limitations of current methods, positioning GMR as a more realistic and challenging benchmark for video-language understanding. --- ### Beating the Style Detector: Three Hours of Agentic Research on the AI-Text Arms Race Authors: Andreas Maier, Moritz Zaiss, Siming Bayer Published: 2026-05-04 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.02620v1 Reproducing an empirical NLP study used to take weeks. Given the released data and a modern agentic-research harness, we redo every experiment of a recent ACL\,2026 study on personal-style post-editing of LLM drafts -- and add three new ones -- with the human investigator acting only as a reviewer-in-the-loop. We reproduce all seven preregistered hypotheses and recover the paper's headline correlation between perceived self-similarity and embedding-measured self-similarity to three decimal places ($r{=}{+}0.244$, $p{<}10^{-8}$, $n{=}648$). Under a leakage-free held-out protocol, GPT-5.5 and Claude\,Opus\,4.7 close $71$--$75\,\%$ of the style gap to the same-author ceiling on $324$ paired tasks, against $24\,\%$ for the human post-edit, and beat the human post-edit on $\sim$$80\,\%$ of tasks. We then frame the same data as an AI-text detection arms race. A leave-authors-out linear SVM on LUAR-MUD embeddings reaches AUC $0.93$--$1.00$ across approaches; six diagnostics show that GPT-5.5 detection is mostly a length confound while Opus detection is a genuine stylistic signature. Given $T{=}20$ feedback iterations against the frozen detector, an Opus agent flips two of five held-out test mimics to the human half-space and shrinks every margin by an order of magnitude. With moderate effort against a known detector, a frontier LLM can already efficiently lower its own AI-detection probability. All code, $648$ mimic drafts, trained detectors, diagnostics, and adversarial trajectories are released. --- ### SCGNN: Semantic Consistency enhanced Graph Neural Network Guided by Granular-ball Computing Authors: Genhao Tian, Taihua Xu, Shuyin Xia, Qinghua Zhang, Jie Yang, Jianjun Chen Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.02617v2 Capturing semantic consistency among nodes is crucial for effective graph representation learning. Existing approaches typically rely on $k$-nearest neighbors ($k$NN) or other node-level full search algorithms (FSA) to mine semantic relationships via exhaustive pairwise similarity computation, which suffer from high computational complexity and rigid neighbor selection, limiting scalability and introducing noisy connections. In this paper, we propose the Semantic Consistency enhanced Graph Neural Network (SCGNN), a novel plug-and-play framework that leverages granular-ball computing (GBC) to efficiently capture semantic consistency in a scalable manner. Unlike node-level FSA methods, SCGNN models group-level semantic structure by adaptively partitioning nodes into granular balls, significantly reducing computational cost while improving robustness to noise. To effectively utilize the discovered group-level semantic consistency, we design a dual enhancement strategy. Specifically, (1) a structure enhancement module constructs an anchor-based graph structure, where each anchor is a virtual node representing the group-level semantic carried by a granular ball, then injecting group-level semantic information into the graph structure; and (2) a supervision enhancement module performs label consistency checking (LCC) by combining GBC predictions with model-generated pseudo-labels, thereby producing more reliable supervision signals. SCGNN is compatible with various GNN backbones. During the forward propagation of SCGNN, the vanilla graph and the augment graph are jointly encoded, and their predictions are fused; during the backpropagation, the supervision enhancement module provides enhanced supervision signals to guide parameter updates. --- ### Global-Local Feature Decoding with Adapter-Guided SAMv2 for Salient Object Detection Authors: Morteza Moradi, Mohammad Moradi, Simone Palazzo, Ali Borji, Concetto Spampinato Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.02616v1 Salient Object Detection (SOD) remains an essential yet underexplored task in the era of large-scale vision models. Although foundation models like SAM exhibit strong generalization, their potential for SOD is not fully realized, and training or fully fine-tuning them is computationally expensive and prone to overfitting under limited data. To overcome these challenges, we introduce GLASSNet, a Global-Local feature decoding framework that uses SAMv2 as a frozen encoder paired with a lightweight, spatially aware convolutional adapter-reducing learnable encoder parameters by over 97%. To enhance saliency quality, GLASSNet employs a dual-decoder architecture: one decoder captures global, long-range semantics with an expanded receptive field, while the other captures fine local details such as edges and textures. Fusing these complementary cues yields saliency maps that combine global coherence with local precision, producing accurate final masks. Extensive experiments on standard SOD and camouflaged object detection benchmarks show that GLASSNet surpasses state-of-the-art methods, demonstrating the power of frozen foundation models combined with targeted adaptation and global-local decoding. --- ### TRACED: In vivo imaging of extracellular intrinsic diffusivity, tortuosity, cell size distribution and cell density in human glioma patients Authors: Joshua K. Marchant, Hong-Hsi Lee, Elizabeth R. Gerstner, Susie Y. Huang, Bruce R. Rosen Published: 2026-05-04 Categories: physics.med-ph, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2605.02615v1 The lack of analytical models describing diffusion time dependence at intermediate time scales in complex tissue microstructure limits the accurate quantification of extracellular diffusivity and tissue microstructure. We introduce TRACED, a biophysical model that incorporates diffusion time dependence in cell distributions to quantify pathologically-relevant properties in solid tumors. Neural networks were trained on Monte Carlo diffusion simulations using sphere distribution-based geometries to enable the rapid computation of time-dependent diffusion MRI signals in cell populations of variable cell size. Model sensitivity and fit performance were assessed via simulation. Diffusion data from eight mixed-grade glioma patients was fitted using the TRACED model. Data fitting was performed using a novel physics-informed transfer learning pipeline, Sim2PINN. In two patients, cell size measurements were compared directly with image-localized histology. Simulation results indicate improved parameter estimation compared to the simple two-compartment model. TRACED enabled the simultaneous in vivo quantification of intracellular volume fraction, cell size distribution, extracellular intrinsic diffusivity, and tortuosity in glioma patients. Neural network implementations of diffusion time-dependence and tortuosity showed behavior consistent with coarse-graining and effective medium theory, respectively. Future work will explore the clinical utility of TRACED parameters in additional patients. --- ### Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples Authors: Xiaoyi Ji, Renata Zelic, Oskar Aspegren, Nita Mulliqi, Michelangelo Fiorentino, Francesca Giunchi, Luca Molinaro, Sol Erika Boman, Lorenzo Richiardi, Andreas Pettersson, Per Henrik Vincent, Martin Eklund et al. Published: 2026-05-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2605.02614v1 Artificial intelligence (AI) is becoming a clinical tool for prostate pathology, but generalization across variations in sample preparation and preservation over prolonged time periods remains poorly understood. We evaluated GleasonAI, an end-to-end attention-based multiple instance learning model, on an independent validation cohort comprising 10,366 biopsy cores from 1,028 patients across 14 Swedish regions, using archival diagnostic specimens from the ProMort cohorts collected between 1998-2015. The model achieved an overall quadratic-weighted kappa of 0.86 for core-level ISUP grading, comparable to several experienced pathologists and consistent across geographic regions. Notably, performance remained stable across the 17-year collection period, demonstrating robustness to time-related variation in archival material, a property not consistently observed with foundation model-based approaches, with exploratory analysis demonstrating a significant prognostic gradient across AI-assigned grade groups for prostate cancer-specific mortality. These findings support the generalizability of the AI grading model and demonstrate the potential of pathology archives as a large-scale resource for AI development, validation, and retrospective prognostic research. --- ### Selective Prediction from Agreement: A Lipschitz-Consistent Version Space Approach Authors: Mohamadsadegh Khosravani Published: 2026-05-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.02611v1 We consider selective classification with abstention in the fixed-pool (or transductive) setting, where the unlabeled pool is given beforehand and only a subset of points can be queried for labels. Our main insight is to view selective prediction through agreement: given queried labels and Lipschitz margin constraints in an embedding space, the version space of Lipschitz-consistent classification heads is well defined. We obtain upper and lower Lipschitz margin bounds that define, for each pool point, a set of certified valid labels containing the prediction of every head in the version space. The model therefore predicts only when the label is forced (i.e., all consistent heads agree), and abstains otherwise. We also propose a monotone submodular geometric proxy for budgeted querying, and show that a greedy algorithm retains the standard approximation factor. --- ### Gradient-Discrepancy Acquisition for Pool-Based Active Learning Authors: Mohamadsadegh Khosravani, Sandra Zilles Published: 2026-05-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.02609v2 The effectiveness of active learning hinges on the choice of the acquisition criterion by which a learning algorithm selects potentially informative data points whose label is subsequently queried. This paper proposes a novel gradient-based acquisition criterion, derived from a generalization bound introduced by Luo et al. (2022). This criterion can be applied in lieu of uncertainty measures in uncertainty sampling, or incorporated into diversity-based methods that consider the spread of sampled points in addition to the uncertainty of their labels. We provide a theoretical justification of the proposed acquisition criterion, and demonstrate its effectiveness in an empirical evaluation. --- ### Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages Authors: Kevin Guan, Happy Buzaaba, Christiane Fellbaum Published: 2026-05-04 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.02608v2 Transformer-based models achieve state-of-the-art dependency parsing for high-resource languages, yet their advantage over simpler architectures in low-resource settings remains poorly understood. We evaluate four parsers---the Biaffine LSTM, Stack-Pointer Network, AfroXLMR-large, and RemBERT---across twelve typologically diverse languages, with a focus on low-resource African languages. We find that the Biaffine LSTM consistently outperforms transformer models in low-resource regimes, with transformers recovering their advantage as training data increases. The crossover falls within a resource range typical of treebanks for under-resourced languages. Morphological complexity (measured via MATTR) emerges as a significant secondary predictor of transformers' relative disadvantage after controlling for corpus size. These results indicate that the Biaffine LSTM may be better suited for syntactic tool development in low-resource regimes until sufficient annotated data is available to leverage the representational capacity of pre-trained transformers. --- ### Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages Authors: Kevin Guan, Happy Buzaaba, Christiane Fellbaum Published: 2026-05-04 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.02608v1 Transformer-based models achieve state-of-the-art dependency parsing for high-resource languages, yet their advantage over simpler architectures in low-resource settings remains poorly understood. We evaluate four parsers -- the Biaffine LSTM, Stack-Pointer Network, AfroXLMR-large, and RemBERT -- across ten typologically diverse languages, with a focus on low-resource African languages. We find that the Biaffine LSTM consistently outperforms transformer models in low-resource regimes, with transformers recovering their advantage as training data increases. The crossover falls within a resource range typical of treebanks for under-resourced languages. Morphological complexity (measured via MATTR) emerges as a significant secondary predictor of transformers' relative disadvantage after controlling for corpus size. These results indicate that the Biaffine LSTM may be better suited for syntactic tool development in low-resource regimes until sufficient annotated data is available to leverage the representational capacity of pre-trained transformers. --- ### Rethinking the Need for Source Models: Source-Free Domain Adaptation from Scratch Guided by a Vision-Language Model Authors: Zhou Bingtao, Xiang Mian, Ning Qian Published: 2026-05-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.02604v1 Source-Free Domain Adaptation (SFDA) adapts source models to target domains without accessing source data, addressing privacy and transmission issues. However, existing methods still initialize from a source pre-trained model and thus are not truly source-free. Recent works have introduced Vision-Language (ViL) models to guide the adaptation process, in these methods, we observe that for the same target domain, different source models yield minimal variation in final results, indicating the source model itself has limited impact. Motivated by this, we propose ViL-Only Domain Adaptation (VODA) , a stricter setting that eliminates all dependencies on source domain, relying solely on a randomly initialized model, a ViL model, and unlabeled target data. We analyze the adaptation dynamics of VODA and introduce Two-Stage Denoised-Region Distillation (TS-DRD) , a two-stage framework that first warms up the model with ViL guidance, then seek a Denoised-Region inherent in both the ViL and adapting model, yielding cleaner supervision for distillation. Experiments on Office-Home, VisDA, and DomainNet-126 show that under VODA, TS-DRD achieves competitive or superior performance to existing SFDA methods that still use source models, demonstrating its effectiveness and the potential of the VODA setting. --- ### Counterfactual Reasoning in Automated Planning Authors: Alberto Pozanco, Daniel Borrajo, Manuela Veloso Published: 2026-05-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.02603v1 Automated planning traditionally assumes that all aspects of a planning task (initial state, goals, and available actions) are fully specified in advance, an approach well-suited to domains with fixed rules and deterministic execution. However, real-world planning often requires flexibility, allowing for deviations from the original task parameters in response to unforeseen circumstances or to improve outcomes. This paper surveys existing works on counterfactual reasoning in automated planning, categorizing them by what elements are changed, when the reasoning is triggered, and why and how these changes are made. We conclude by discussing key findings and outlining open research questions to guide future work in this area. --- ### SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures Authors: Nedjma Ousidhoum, Junho Myung, Carla Perez-Almendros, Jiho Jin, Amr Keleg, Meriem Beloucif, Yi Zhou, Rodrigo Agerri, Vladimir Araujo, Naomi Baes, James Barry, Joanne Boisson et al. Published: 2026-05-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.02601v1 We present our shared task on evaluating the adaptability of LLMs and NLP systems across multiple languages and cultures. The task data consist of an extended version of our manually constructed BLEnD benchmark (Myung et al. 2024), covering more than 30 language-culture pairs, predominantly representing low-resource languages spoken across multiple continents. As the task is designed strictly for evaluation, participants were not permitted to use the data for training, fine-tuning, few-shot learning, or any other form of model modification. Our task includes two tracks: (a) Short-Answer Questions (SAQ) and (b) Multiple-Choice Questions (MCQ). Participants were required to predict labels and were allowed to submit any NLP system and adopt diverse modelling strategies, provided that the benchmark was used solely for evaluation. The task attracted more than 140 registered participants, and we received final submissions from 62 teams, along with 19 system description papers. We report the results and present an analysis of the best-performing systems and the most commonly adopted approaches. Furthermore, we discuss shared insights into open questions and challenges related to evaluation, misalignment, and methodological perspectives on model behaviour in low-resource languages and for under-represented cultures. --- ### CoRAL: Contact-Rich Adaptive LLM-based Control for Robotic Manipulation Authors: Berk Çiçek, Mert K. Er, Ozgur S. Oguz Published: 2026-05-04 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2605.02600v2 While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understanding, applying them directly to contact-rich manipulation remains a challenge due to their lack of explicit physical grounding and inability to perform adaptive control. To bridge this gap, we propose CoRAL (Contact-Rich Adaptive LLM-based control), a modular framework that enables zero-shot planning by decoupling high-level reasoning from low-level control. Unlike black-box policies, CoRAL uses LLMs not as direct controllers, but as cost designers that synthesize context-aware objective functions for a sampling-based motion planner (MPPI). To address the ambiguity of physical parameters in visual data, we introduce a neuro-symbolic adaptation loop: a VLM provides semantic priors for environmental dynamics, such as mass and friction estimates, which are then explicitly refined in real time via online system identification, while the LLM iteratively modulates the cost-function structure to correct strategic errors based on interaction feedback. Furthermore, a retrieval-based memory unit allows the system to reuse successful strategies across recurrent tasks. This hierarchical architecture ensures real-time control stability by decoupling high-level semantic reasoning from reactive execution, effectively bridging the gap between slow LLM inference and dynamic contact requirements. We validate CoRAL on both simulation and real-world hardware across challenging and novel tasks, such as flipping objects against walls by leveraging extrinsic contacts. Experiments demonstrate that CoRAL outperforms state-of-the-art VLA and foundation-model-based planner baselines by boosting success rates over 50% on average in unseen contact-rich scenarios, effectively handling sim-to-real gaps through its adaptive physical understanding. ---