# Research Papers — 2026-04 · bundle page 152 of 233 > Full-text markdown of papers #7551–7600 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/152 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/151.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/153.md) ### SemEnrich: Self-Supervised Semantic Enrichment of Radiology Reports for Vision-Language Learning Authors: Halil Ibrahim Gulluk, Olivier Gevaert Published: 2026-04-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.09887v1 Medical vision-language datasets are often limited in size and biased toward negative findings, as clinicians report abnormalities mostly but might omit some positive/neutral findings because they might be considered as irrelevant to the patient's condition. We propose a self-supervised data enrichment method that leverages semantic clustering of report sentences. Then we enrich the findings in the medical reports in the training set by adding positive/neutral observations from different clusters in a self-supervised manner. Our approach yields consistent gains in supervised fine-tuning (5.63%, 3.04%, 7.40%, 5.30%, 7.47% average gains on COMET score, Bert score, Sentence Bleu, CheXbert-F1 and RadGraph-F1 scores respectively). Ablation studies confirm that improvements stem from semantic clustering rather than random augmentation. Furthermore, we introduce a way to incorporate semantic cluster information into the reward design for GRPO training, which leads to further performance gains (2.78%, 3.14%, 12.80% average gains on COMET score, Bert score and Sentence Bleu scores respectively). We share our code at https://anonymous.4open.science/r/SemEnrich-75CF --- ### Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception Authors: Gautham Vinod, Bruce Coburn, Siddeshwar Raghavan, Fengqing Zhu Published: 2026-04-10 Categories: cs.CV, cs.AI, cs.LG, cs.MM, eess.IV arXiv: https://arxiv.org/abs/2604.09886v1 Accurate volume estimation of objects from visual data is a long-standing challenge in computer vision with significant applications in robotics, logistics, and smart health. Existing methods often rely on complex 3D reconstruction pipelines or struggle with the ambiguity inherent in single-view images. To address these limitations, we introduce a new method that fuses implicit 3D cues from stereo vision with explicit prior knowledge from natural language text. Our approach extracts deep features from a stereo image pair and a descriptive text prompt that contains the object's class and an approximate volume, then integrates them using a simple yet effective projection layer into a unified, multi-modal representation for regression. We conduct extensive experiments on public datasets demonstrating that our text-guided approach significantly outperforms vision-only baselines. Our findings show that leveraging even simple textual priors can effectively guide the volume estimation task, paving the way for more context-aware visual measurement systems. Code: https://gitlab.com/viper-purdue/stereo-typical-estimator. --- ### What do your logits know? (The answer may surprise you!) Authors: Masha Fedzechkina, Eleonora Gualdoni, Rita Ramos, Sinead Williamson Published: 2026-04-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.09885v1 Recent work has shown that probing model internals can reveal a wealth of information not apparent from the model generations. This poses the risk of unintentional or malicious information leakage, where model users are able to learn information that the model owner assumed was inaccessible. Using vision-language models as a testbed, we present the first systematic comparison of information retained at different "representational levels'' as it is compressed from the rich information encoded in the residual stream through two natural bottlenecks: low-dimensional projections of the residual stream obtained using tuned lens, and the final top-k logits most likely to impact model's answer. We show that even easily accessible bottlenecks defined by the model's top logit values can leak task-irrelevant information present in an image-based query, in some cases revealing as much information as direct projections of the full residual stream. --- ### Topo-ADV: Generating Topology-Driven Imperceptible Adversarial Point Clouds Authors: Gayathry Chandramana Krishnan Nampoothiry, Raghuram Venkatapuram, Anirban Ghosh, Ayan Dutta Published: 2026-04-10 Categories: cs.CV, cs.CG arXiv: https://arxiv.org/abs/2604.09879v1 Deep neural networks for 3D point cloud understanding have achieved remarkable success in object classification and recognition, yet recent work shows that these models remain highly vulnerable to adversarial perturbations. Existing 3D attacks predominantly manipulate geometric properties such as point locations, curvature, or surface structure, implicitly assuming that preserving global shape fidelity preserves semantic content. In this work, we challenge this assumption and introduce the first topology-driven adversarial attack for point cloud deep learning. Our key insight is that the homological structure of a 3D object constitutes a previously unexplored vulnerability surface. We propose Topo-ADV, an end-to-end differentiable framework that incorporates persistent homology as an explicit optimization objective, enabling gradient-based manipulation of topological features during adversarial example generation. By embedding persistence diagrams through differentiable topological representations, our method jointly optimizes (i) a topology divergence loss that alters persistence, (ii) a misclassification objective, and (iii) geometric imperceptibility constraints that preserve visual plausibility. Experiments demonstrate that subtle topology-driven perturbations consistently achieve up to 100% attack success rates on benchmark datasets such as ModelNet40, ShapeNet Part, and ScanObjectNN using PointNet and DGCNN classifiers, while remaining geometrically indistinguishable from the original point clouds, beating state-of-the-art methods on various perceptibility metrics. --- ### Genie 4D: Semantic-Prior-Guided 4D Dynamic Scene Reconstruction Authors: Yiru Yang, Zhuojie Wu, Nishant Kumar Singh, Max Schulthess Published: 2026-04-10 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2604.09877v2 At the intersection of computer vision and robotic perception, 4D reconstruction of dynamic scenes connects low-level geometric sensing with high-level semantic understanding. We present Genie 4D, a framework that turns hand-held phone capture into a semantically grounded, action-controllable 4D world model. Genie 4D couples a real-time visual-inertial Gaussian splatting front-end for metric geometry with a feed-forward 4D backbone regularized by frozen DINOv3 features acting as structural priors. The semantic priors suppress identity drift during dynamic tracking, while a short conditional diffusion refiner recovers high-frequency surface detail that regression backbones smooth away. Finally, a lightweight latent-action head exposes the reconstructed 4D state to a Genie-style world model trained with a JEPA-style next-embedding objective, so that the scene can be rolled forward under user actions. On the Point Odyssey and TUM-Dynamics benchmarks, Genie 4D retains the linear time complexity O(T) of feed-forward baselines while improving 3D tracking accuracy (APD) and reconstruction completeness, and it runs interactively on a single consumer GPU (RTX 5090) from iPhone, Mac, Windows, and Linux capture clients. Genie 4D offers a practical, semantic-prior-guided path toward physically grounded world models. --- ### Efficient Personalization of Generative User Interfaces Authors: Yi-Hao Peng, Jeffrey P. Bigham, Jason Wu Published: 2026-04-10 Categories: cs.LG, cs.AI, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2604.09876v2 Generative user interfaces (GenUIs) create new opportunities to adapt interfaces to individual users on demand. Yet personalization is difficult because it is not possible to provide settings for screens that have not yet been generated, making it necessary to learn preferences from users' feedback on generated interfaces. Such feedback is sparse, subjective, and often difficult to articulate. We study this problem through a new dataset in which 20 participants each judge the same 600 pairs of GenUIs. Their judgments differ substantially (Krippendorff's alpha = 0.25), and written rationales show that even when participants consider similar UI properties, such as color tone or hierarchy, they often make different choices and prioritize them differently. We develop a sample-efficient personalization method that uses a few pairwise judgments to weight prior users' preferences rather than relying on a fixed rubric of UI attributes. Our method outperforms a pretrained UI evaluator and a larger multimodal model offline. In an online study with 12 new users, participants preferred interfaces personalized by our method over all baselines, including shared guidelines and users' own written preferences. --- ### Efficient Personalization of Generative User Interfaces Authors: Yi-Hao Peng, Samarth Das, Jeffrey P. Bigham, Jason Wu Published: 2026-04-10 Categories: cs.LG, cs.AI, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2604.09876v1 Generative user interfaces (UIs) create new opportunities to adapt interfaces to individual users on demand, but personalization remains difficult because desirable UI properties are subjective, hard to articulate, and costly to infer from sparse feedback. We study this problem through a new dataset in which 20 trained designers each provide pairwise judgments over the same 600 generated UIs, enabling direct analysis of preference divergence. We find substantial disagreement across designers (average kappa = 0.25), and written rationales reveal that even when designers appeal to similar concepts such as hierarchy or cleanliness, designers differ in how they define, prioritize, and apply those concepts. Motivated by these findings, we develop a sample-efficient personalization method that represents a new user in terms of prior designers rather than a fixed rubric of design concepts. In a technical evaluation, our preference model outperforms both a pretrained UI evaluator and a larger multimodal model, and scales better with additional feedback. When used to personalize generation, it also produces interfaces preferred by 12 new designers over baseline approaches, including direct user prompting. Our findings suggest that lightweight preference elicitation can serve as a practical foundation for personalized generative UI systems. --- ### Simulating Organized Group Behavior: New Framework, Benchmark, and Analysis Authors: Xinkai Zou, Yiming Huang, Zhuohang Wu, Jian Sha, Nan Huang, Longfei Yun, Jingbo Shang, Letian Peng Published: 2026-04-10 Categories: cs.CL, cs.SI arXiv: https://arxiv.org/abs/2604.09874v2 Simulating how organized groups (e.g., corporations) make decisions (e.g., responding to a competitor's move) is essential for understanding real-world dynamics and could benefit relevant applications (e.g., market prediction). In this paper, we formalize this problem as a concrete research platform for group behavior understanding, providing: (1) a task formalization with benchmark and evaluation criteria, (2) a structured and adaptive analytical framework, and (3) detailed temporal and cross-group analysis. Specifically, we propose Organized Group Behavior Simulation, a task that models organized groups as collective entities from a practical perspective: given a group facing a particular situation (e.g., AI Boom), predict the decision it would take. To support this task, we present GROVE (GRoup Organizational BehaVior Evaluation), a benchmark covering 44 organized groups with 8,052 real-world context-decision pairs collected from Wikipedia and TechCrunch across 9 domains, with an end-to-end evaluation protocol assessing consistency, initiative, scope, magnitude, and horizon. Beyond straightforward prompting pipelines, we propose a structured analytical framework that converts collective decision-making events into an interpretable, adaptive, and traceable behavioral model, achieving stronger performance than summarization- and retrieval-based baselines. It further introduces an adapter mechanism for time-aware evolution and group-aware transfer, and traceable evidence nodes grounding each decision rule in originating historical events. Our analysis reveals temporal behavioral drift within individual groups, which the time-aware adapter effectively captures for stronger prediction, and structured cross-group similarity that enables knowledge transfer for data-scarce organizations. --- ### Simulating Organized Group Behavior: New Framework, Benchmark, and Analysis Authors: Xinkai Zou, Yiming Huang, Zhuohang Wu, Jian Sha, Nan Huang, Longfei Yun, Jingbo Shang, Letian Peng Published: 2026-04-10 Categories: cs.CL, cs.SI arXiv: https://arxiv.org/abs/2604.09874v1 Simulating how organized groups (e.g., corporations) make decisions (e.g., responding to a competitor's move) is essential for understanding real-world dynamics and could benefit relevant applications (e.g., market prediction). In this paper, we formalize this problem as a concrete research platform for group behavior understanding, providing: (1) a task definition with benchmark and evaluation criteria, (2) a structured analytical framework with a corresponding algorithm, and (3) detailed temporal and cross-group analysis. Specifically, we propose Organized Group Behavior Simulation, a task that models organized groups as collective entities from a practical perspective: given a group facing a particular situation (e.g., AI Boom), predict the decision it would take. To support this task, we present GROVE (GRoup Organizational BehaVior Evaluation), a benchmark covering 44 entities with 8,052 real-world context-decision pairs collected from Wikipedia and TechCrunch across 9 domains, with an end-to-end evaluation protocol assessing consistency, initiative, scope, magnitude, and horizon. Beyond straightforward prompting pipelines, we propose a structured analytical framework that converts collective decision-making events into an interpretable, adaptive, and traceable behavioral model, achieving stronger performance than summarization- and retrieval-based baselines. It further introduces an adapter mechanism for time-aware evolution and group-aware transfer, and traceable evidence nodes grounding each decision rule in originating historical events. Our analysis reveals temporal behavioral drift within individual groups, which the time-aware adapter effectively captures for stronger prediction, and structured cross-group similarity that enables knowledge transfer for data-scarce organizations. --- ### Relational Preference Encoding in Looped Transformer Internal States Authors: Jan Kirin Published: 2026-04-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.09870v2 We investigate how looped transformers encode human preference, training lightweight evaluator heads on frozen Ouro-2.6B loop-iteration states on Anthropic HH-RLHF. v2: an erratum is prepended; the original manuscript is unchanged. A post-publication audit found the three headline results inflated by two independent evaluation errors. The 95.2% pairwise evaluator accuracy is a canonical-ordering artifact: the data were correctly split, but the evaluator learned to prefer the first-presented argument; its strict antisymmetrized accuracy on the full 8,552-pair test set is 63.9%. The 84.5% pairwise probe and the below-chance 21.75% pointwise probe were source-item leaks (orientation rows and pair partners crossing the train/test split); corrected pair-disjoint values are 56.5% and 54.2% -- above chance, so the "inverted polarity" finding is withdrawn. The central finding survives at much smaller magnitude: preference is decoded more accurately relationally than pointwise (paired +2.3 points, 95% CI (+1.3, +3.3)), and the antisymmetrized evaluator still beats the linear probe, but no corrected readout rivals end-to-end reward models. The methodological findings stand (constant-output degeneracy, flip test, swap-protocol metric deflation), with one correction: antisymmetrized accuracy, not antisymmetry correlation, certifies relational discrimination. The two errors are mutually invisible -- a split audit cannot see an ordering prior, antisymmetrization cannot see a leak -- so both checks are required. Full audit in the follow-up work (Kirin, 2026, in preparation). --- ### Automating Structural Analysis Across Multiple Software Platforms Using Large Language Models Authors: Ziheng Geng, Jiachen Liu, Ian Franklin, Ran Cao, Dan M. Frangopol, Minghui Cheng Published: 2026-04-10 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.09866v1 Recent advances in large language models (LLMs) have shown the promise to significantly accelerate the workflow by automating structural modeling and analysis. However, existing studies primarily focus on enabling LLMs to operate a single structural analysis software platform. In practice, structural engineers often rely on multiple finite element analysis (FEA) tools, such as ETABS, SAP2000, and OpenSees, depending on project needs, user preferences, and company constraints. This limitation restricts the practical deployment of LLM-assisted engineering workflows. To address this gap, this study develops LLMs capable of automating frame structural analysis across multiple software platforms. The LLMs adopt a two-stage multi-agent architecture. In Stage 1, a cohort of agents collaboratively interpret user input and perform structured reasoning to infer geometric, material, boundary, and load information required for finite element modeling. The outputs of these agents are compiled into a unified JSON representation. In Stage 2, code translation agents operate in parallel to convert the JSON file into executable scripts across multiple structural analysis platforms. Each agent is prompted with the syntax rules and modeling workflows of its target software. The LLMs are evaluated using 20 representative frame problems across three widely used platforms: ETABS, SAP2000, and OpenSees. Results from ten repeated trials demonstrate consistently reliable performance, achieving accuracy exceeding 90% across all cases. --- ### PAS: Estimating the target accuracy before domain adaptation Authors: Raphaella Diniz, Jackson de Faria, Martin Ester Published: 2026-04-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09863v1 The goal of domain adaptation is to make predictions for unlabeled samples from a target domain with the help of labeled samples from a different but related source domain. The performance of domain adaptation methods is highly influenced by the choice of source domain and pre-trained feature extractor. However, the selection of source data and pre-trained model is not trivial due to the absence of a labeled validation set for the target domain and the large number of available pre-trained models. In this work, we propose PAS, a novel score designed to estimate the transferability of a source domain set and a pre-trained feature extractor to a target classification task before actually performing domain adaptation. PAS leverages the generalization power of pre-trained models and assesses source-target compatibility based on the pre-trained feature embeddings. We integrate PAS into a framework that indicates the most relevant pre-trained model and source domain among multiple candidates, thus improving target accuracy while reducing the computational overhead. Extensive experiments on image classification benchmarks demonstrate that PAS correlates strongly with actual target accuracy and consistently guides the selection of the best-performing pre-trained model and source domain for adaptation. --- ### FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views Authors: Chaoyi Zhou, Run Wang, Feng Luo, Mert D. Pesé, Zhiwen Fan, Yiqi Zhong, Siyu Huang Published: 2026-04-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09862v1 Recent advances in vision foundation models have revolutionized geometry reconstruction and semantic understanding. Yet, most of the existing approaches treat these capabilities in isolation, leading to redundant pipelines and compounded errors. This paper introduces FF3R, a fully annotation-free feed-forward framework that unifies geometric and semantic reasoning from unconstrained multi-view image sequences. Unlike previous methods, FF3R does not require camera poses, depth maps, or semantic labels, relying solely on rendering supervision for RGB and feature maps, establishing a scalable paradigm for unified 3D reasoning. In addition, we address two critical challenges in feedforward feature reconstruction pipelines, namely global semantic inconsistency and local structural inconsistency, through two key innovations: (i) a Token-wise Fusion Module that enriches geometry tokens with semantic context via cross-attention, and (ii) a Semantic-Geometry Mutual Boosting mechanism combining geometry-guided feature warping for global consistency with semantic-aware voxelization for local coherence. Extensive experiments on ScanNet and DL3DV-10K demonstrate FF3R's superior performance in novel-view synthesis, open-vocabulary semantic segmentation, and depth estimation, with strong generalization to in-the-wild scenarios, paving the way for embodied intelligence systems that demand both spatial and semantic understanding. --- ### Evolutionary Token-Level Prompt Optimization for Diffusion Models Authors: Domício Pereira Neto, João Correia, Penousal Machado Published: 2026-04-10 Categories: cs.AI, cs.NE arXiv: https://arxiv.org/abs/2604.09861v1 Text-to-image diffusion models exhibit strong generative performance but remain highly sensitive to prompt formulation, often requiring extensive manual trial and error to obtain satisfactory results. This motivates the development of automated, model-agnostic prompt optimization methods that can systematically explore the conditioning space beyond conventional text rewriting. This work investigates the use of a Genetic Algorithm (GA) for prompt optimization by directly evolving the token vectors employed by CLIP-based diffusion models. The GA optimizes a fitness function that combines aesthetic quality, measured by the LAION Aesthetic Predictor V2, with prompt-image alignment, assessed via CLIPScore. Experiments on 36 prompts from the Parti Prompts (P2) dataset show that the proposed approach outperforms the baseline methods, including Promptist and random search, achieving up to a 23.93% improvement in fitness. Overall, the method is adaptable to image generation models with tokenized text encoders and provides a modular framework for future extensions, the limitations and prospects of which are discussed. --- ### RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies Authors: Jenai Xuning Yang, Rishit Dagli, Alex Zook, Hugo Hadfield, Ankit Goyal, Stan Birchfield, Fabio Ramos, Jonathan Tremblay Published: 2026-04-10 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.09860v4 The pursuit of general-purpose robotics has yielded impressive foundation models, yet simulation-based benchmarking remains a bottleneck due to rapid performance saturation and a lack of true generalization testing. Existing benchmarks often exhibit significant domain overlap between training and evaluation, trivializing success rates and obscuring insights into robustness. We introduce RoboLab, a simulation benchmarking framework designed to address these challenges. Concretely, our framework is designed to answer two questions: (1) to what extent can we understand the performance of a real-world policy by analyzing its behavior in simulation, and (2) which factor most strongly affect policy behavior. First, RoboLab enables human-authored and LLM-enabled generation of scenes and tasks in a robot- and policy-agnostic manner within a high-fidelity simulation environment. We introduce an accompanying RoboLab-120 benchmark, consisting of 120 tasks categorized into three competency axes: visual, procedural, relational, across three difficulty levels. Second, we introduce a systematic analysis of real-world policies that quantify both their performance and the sensitivity of their behavior to controlled perturbations, exposing significant performance gap in current state-of-the-art models. By providing granular metrics and a scalable toolset, RoboLab offers a scalable framework for evaluating the true generalization capabilities of task-generalist robotic policies. Project website: https://research.nvidia.com/labs/srl/projects/robolab/. --- ### RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies Authors: Xuning Yang, Rishit Dagli, Alex Zook, Hugo Hadfield, Ankit Goyal, Stan Birchfield, Fabio Ramos, Jonathan Tremblay Published: 2026-04-10 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2604.09860v3 The pursuit of general-purpose robotics has yielded impressive foundation models, yet simulation-based benchmarking remains a bottleneck due to rapid performance saturation and a lack of true generalization testing. Existing benchmarks often exhibit significant domain overlap between training and evaluation, trivializing success rates and obscuring insights into robustness. We introduce RoboLab, a simulation benchmarking framework designed to address these challenges. Concretely, our framework is designed to answer two questions: (1) to what extent can we understand the performance of a real-world policy by analyzing its behavior in simulation, and (2) which factor most strongly affect policy behavior. First, RoboLab enables human-authored and LLM-enabled generation of scenes and tasks in a robot- and policy-agnostic manner within a high-fidelity simulation environment. We introduce an accompanying RoboLab-120 benchmark, consisting of 120 tasks categorized into three competency axes: visual, procedural, relational, across three difficulty levels. Second, we introduce a systematic analysis of real-world policies that quantify both their performance and the sensitivity of their behavior to controlled perturbations, exposing significant performance gap in current state-of-the-art models. By providing granular metrics and a scalable toolset, RoboLab offers a scalable framework for evaluating the true generalization capabilities of task-generalist robotic policies. Project website: https://research.nvidia.com/labs/srl/projects/robolab/. --- ### Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards Authors: Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao, Lei Lei, Yuheng Zhang, Yisong Yue, David Simchi-Levi Published: 2026-04-10 Categories: cs.AI, cs.CL, cs.GT, econ.GN arXiv: https://arxiv.org/abs/2604.09855v1 The recent advancement of Large Language Models (LLMs) has established their potential as autonomous interactive agents. However, they often struggle in strategic games of incomplete information, such as bilateral price negotiation. In this paper, we investigate if Reinforcement Learning from Verifiable Rewards (RLVR) can effectively teach LLMs to negotiate. Specifically, we explore the strategic behaviors that emerge during the learning process. We introduce a framework that trains a mid-sized buyer agent against a regulated LLM seller across a wide distribution of real-world products. By grounding reward signals directly in the maximization of economic surplus and strict adherence to private budget constraints, we reveal a novel four-phase strategic evolution. The agent progresses from naive bargaining to using aggressive starting prices, moves through a phase of deadlock, and ultimately develops sophisticated persuasive skills. Our results demonstrate that this verifiable training allows a 30B agent to significantly outperform frontier models over ten times its size in extracting surplus. Furthermore, the trained agent generalizes robustly to stronger counterparties unseen during training and remains effective even when facing hostile, adversarial seller personas. --- ### Spoiler Alert: Narrative Forecasting as a Metric for Tension in LLM Storytelling Authors: Peiqi Sui, Yutong Zhu, Tianyi Cheng, Peter West, Richard Jean So, Hoyt Long, Ari Holtzman Published: 2026-04-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.09854v1 LLMs have so far failed both to generate consistently compelling stories and to recognize this failure--on the leading creative-writing benchmark (EQ-Bench), LLM judges rank zero-shot AI stories above New Yorker short stories, a gold standard for literary fiction. We argue that existing rubrics overlook a key dimension of compelling human stories: narrative tension. We introduce the 100-Endings metric, which walks through a story sentence by sentence: at each position, a model predicts how the story will end 100 times given only the text so far, and we measure tension as how often predictions fail to match the ground truth. Beyond the mismatch rate, the sentence-level curve yields complementary statistics, such as inflection rate, a geometric measure of how frequently the curve reverses direction, tracking twists and revelations. Unlike rubric-based judges, 100-Endings correctly ranks New Yorker stories far above LLM outputs. Grounded in narratological principles, we design a story-generation pipeline using structural constraints, including analysis of story templates, idea formulation, and narrative scaffolding. Our pipeline significantly increases narrative tension as measured by the 100-Endings metric, while maintaining performance on the EQ-Bench leaderboard. --- ### Do vision models perceive illusory motion in static images like humans? Authors: Isabella Elaine Rosario, Fan L. Cheng, Zitang Sun, Nikolaus Kriegeskorte Published: 2026-04-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09853v2 Understanding human motion processing is essential for building reliable, human-centered computer vision systems. Although deep neural networks (DNNs) achieve strong performance in optical flow estimation, they remain less robust than humans and rely on fundamentally different computational strategies. Visual motion illusions provide a powerful probe into these mechanisms, revealing how human and machine vision align or diverge. While recent DNN-based motion models can reproduce dynamic illusions such as reverse-phi, it remains unclear whether they can perceive illusory motion in static images, exemplified by the Rotating Snakes illusion. We evaluate several representative optical flow models on Rotating Snakes and show that most fail to generate flow fields consistent with human perception. Under simulated conditions mimicking saccadic eye movements, only the human-inspired Dual-Channel model exhibits the expected rotational motion, with the closest correspondence emerging during the saccade simulation. Ablation analyses further reveal that both luminance-based and higher-order color--feature--based motion signals contribute to this behavior and that a recurrent attention mechanism is critical for integrating local cues. Our results highlight a substantial gap between current optical-flow models and human visual motion processing, and offer insights for developing future motion-estimation systems with improved correspondence to human perception and human-centric AI. --- ### MEMENTO: Teaching LLMs to Manage Their Own Context Authors: Vasilis Kontonis, Yuchen Zeng, Shivam Garg, Lingjiao Chen, Hao Tang, Ziyan Wang, Ahmed Awadallah, Eric Horvitz, John Langford, Dimitris Papailiopoulos Published: 2026-04-10 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.09852v1 Reasoning models think in long, unstructured streams with no mechanism for compressing or organizing their own intermediate state. We introduce MEMENTO: a method that teaches models to segment reasoning into blocks, compress each block into a memento, i.e., a dense state summary, and reason forward by attending only to mementos, reducing context, KV cache, and compute. To train MEMENTO models, we release OpenMementos, a public dataset of 228K reasoning traces derived from OpenThoughts-v3, segmented and annotated with intermediate summaries. We show that a two-stage SFT recipe on OpenMementos is effective across different model families (Qwen3, Phi-4, Olmo 3) and scales (8B--32B parameters). Trained models maintain strong accuracy on math, science, and coding benchmarks while achieving ${\sim}2.5\times$ peak KV cache reduction. We extend vLLM to support our inference method, achieving ${\sim}1.75\times$ throughput improvement while also enabling us to perform RL and further improve accuracy. Finally, we identify a dual information stream: information from each reasoning block is carried both by the memento text and by the corresponding KV states, which retain implicit information from the original block. Removing this channel drops accuracy by 15\,pp on AIME24. --- ### Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning Authors: Yang Deng, David Mould, Paul L. Rosin, Yu-Kun Lai Published: 2026-04-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09850v1 Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized byproduct. This imbalance compromises global scene coherence and constrains compositional control. To address the limitation, we propose a training-free framework that restructures diffusion sampling to explicitly account for foreground-background interactions. Our approach consists of two key components. First, Dynamic Spatial Guidance introduces a soft, time step dependent gating mechanism that modulates foreground and background attention during the diffusion process, enabling spatially balanced generation. Second, Multi-Path Pruning performs multi-path latent exploration and dynamically filters candidate trajectories using both internal attention statistics and external semantic alignment signals, retaining trajectories that better satisfy object-background constraints. We further develop a benchmark specifically designed to evaluate object-background compositionality. Extensive evaluations across multiple diffusion backbones demonstrate consistent improvements in background coherence and object-background compositional alignment. --- ### Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models Authors: Oliver McLaughlin, Daniel Shubin, Carsten Eickhoff, Ritambhara Singh, William Rudman, Michal Golovanevsky Published: 2026-04-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09841v1 Vision-language models (VLMs) are increasingly adapted through domain-specific fine-tuning, yet it remains unclear whether this improves reasoning beyond superficial visual cues, particularly in high-stakes domains like medicine. We evaluate four paired open-source VLMs (LLaVA vs. LLaVA-Med; Gemma vs. MedGemma) across four medical imaging tasks of increasing difficulty: brain tumor, pneumonia, skin cancer, and histopathology classification. We find that performance degrades toward near-random levels as task difficulty increases, indicating limited clinical reasoning. Medical fine-tuning provides no consistent advantage, and models are highly sensitive to prompt formulation, with minor changes causing large swings in accuracy and refusal rates. To test whether closed-form VQA suppresses latent knowledge, we introduce a description-based pipeline where models generate image descriptions that a text-only model (GPT-5.1) uses for diagnosis. This recovers a limited additional signal but remains bounded by task difficulty. Analysis of vision encoder embeddings further shows that failures stem from both weak visual representations and downstream reasoning. Overall, medical VLM performance is fragile, prompt-dependent, and not reliably improved by domain-specific fine-tuning. --- ### Steered LLM Activations are Non-Surjective Authors: Aayush Mishra, Daniel Khashabi, Anqi Liu Published: 2026-04-10 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.09839v2 Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating activations into human-readable explanations) and safety research (e.g., jailbreakability). However, it is unclear whether steered behavior is realizable by any textual prompt. In this work, we cast this question as a surjectivity problem: for a fixed model, does every steered activation admit a preimage under the model's natural forward pass? Under practical assumptions, we prove that activation steering pushes the residual stream off the manifold of states reachable from discrete prompts. Almost surely, no prompt can reproduce the same internal behavior induced by steering. We also illustrate this finding empirically across three widely used LLMs. Our results establish a formal separation between white-box steerability and black-box prompting. We therefore caution against interpreting the ease and success of activation steering as evidence of prompt-based interpretability or vulnerability, and argue for evaluation protocols that explicitly decouple white-box and black-box interventions. --- ### Vector Field Synthesis with Sparse Streamlines Using Diffusion Model Authors: Nguyen K. Phan, Ricardo Morales, Sebastian D. Espriella, Guoning Chen Published: 2026-04-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09838v1 We present a novel diffusion-based framework for synthesizing 2D vector fields from sparse, coherent inputs (i.e., streamlines) while maintaining physical plausibility. Our method employs a conditional denoising diffusion probabilistic model with classifier-free guidance, enabling progressive reconstruction that preserves both geometric and physical constraints. Experimental results demonstrate our method's ability to synthesize plausible vector fields that adhere to physical laws while maintaining fidelity to sparse input observations, outperforming traditional optimization-based approaches in terms of flexibility and physical consistency. --- ### COMPOSITE-Stem Authors: Kyle Waters, Lucas Nuzzi, Tadhg Looram, Alessandro Tomasiello, Ariel Ghislain Kemogne Kamdoum, Bikun Li, Damien Sileo, Egor Kretov, Francesco Fournier-Facio, Georgios Soloupis, Haile Kassahun, Hew Wolff et al. Published: 2026-04-10 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.09836v2 AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this stage have become saturated and only measure performance on constrained outputs. To help address this gap, we introduce COMPOSITE-STEM, a benchmark of 70 expert-written tasks in physics, biology, chemistry, and mathematics, curated by doctoral-level researchers. Our benchmark combines exact-match grading and criterion-based rubrics with an LLM-as-a-jury grading protocol, allowing more flexible assessment of scientifically meaningful outputs. Using an adapted multimodal Terminus-2 agent harness within the Harbor agentic evaluation framework, we evaluate four frontier models. The top-performing model achieves 21%, demonstrating that COMPOSITE-STEM captures capabilities beyond current agent reach. All tasks are open-sourced with contributor permission to support reproducibility and to promote additional research towards AI's acceleration of scientific progress in these domains. --- ### F3G-Avatar : Face Focused Full-body Gaussian Avatar Authors: Willem Menu, Erkut Akdag, Pedro Quesado, Yasaman Kashefbahrami, Egor Bondarev Published: 2026-04-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09835v1 Existing full-body Gaussian avatar methods primarily optimize global reconstruction quality and often fail to preserve fine-grained facial geometry and expression details. This challenge arises from limited facial representational capacity that causes difficulties in modeling high-frequency pose-dependent deformations. To address this, we propose F3G-Avatar, a full-body, face-aware avatar synthesis method that reconstructs animatable human representations from multi-view RGB video and regressed pose/shape parameters. Starting from a clothed Momentum Human Rig (MHR) template, front/back positional maps are rendered and decoded into 3D Gaussians through a two-branch architecture: a body branch that captures pose-dependent non-rigid deformations and a face-focused deformation branch that refines head geometry and appearance. The predicted Gaussians are fused, posed with linear blend skinning (LBS), and rendered with differentiable Gaussian splatting. Training combines reconstruction and perceptual objectives with a face-specific adversarial loss to enhance realism in close-up views. Experiments demonstrate strong rendering quality, with face-view performance reaching PSNR/SSIM/LPIPS of 26.243/0.964/0.084 on the AvatarReX dataset. Ablations further highlight contributions of the MHR template and the face-focused deformation. F3G-Avatar provides a practical, high-quality pipeline for realistic, animatable full-body avatar synthesis. --- ### Beyond Silicon: Materials, Mechanisms, and Methods for Physical Neural Computing Authors: Stefan Fischer, Nihat Ay, Olaf Landsiedel, Esfandiar Mohammadi, Sebastian Otte, Bernd-Christian Renner, Nele Rußwinkel Published: 2026-04-10 Categories: cs.NE, cs.ET arXiv: https://arxiv.org/abs/2604.09833v2 Physical implementations of neural computation now extend far beyond silicon hardware, encompassing substrates such as memristive devices, photonic circuits, mechanical metamaterials, microfluidic networks, chemical reaction systems, and living neural tissue. By exploiting intrinsic physical processes such as charge transport, wave interference, elastic deformation, mass transport, and biochemical regulation, these substrates can realize neural inference and adaptation directly in matter. As silicon GPU-centered AI faces growing energy and data-movement constraints, physical neural computation is becoming increasingly relevant as a complementary path beyond conventional digital accelerators. This trend is driven in particular by pervasive intelligence, i.e., the deployment of on-device and edge AI across large numbers of resource-constrained systems. In such settings, co-locating computation with sensing and memory can reduce data shuttling and improve efficiency. Meanwhile, physical neural approaches have emerged across disparate disciplines, yet progress remains fragmented, with limited shared terminology and few principled ways to compare platforms. This survey unifies the field by mapping neural primitives to substrate-specific mechanisms, analyzing architectural and training paradigms, and identifying key engineering constraints including scalability, precision, programmability, and I/O interfacing overhead. To enable cross-domain comparison, we introduce a first-order benchmarking scheme based on standardized static and dynamic tasks and physically interpretable performance dimensions. We show that no single substrate dominates across the considered dimensions; instead, physical neural systems occupy complementary operating regimes, enabling applications ranging from ultrafast signal processing and in-memory inference to embodied control and in-sample biochemical decision making. --- ### ProGAL-VLA: Grounded Alignment through Prospective Reasoning in Vision-Language-Action Models Authors: Nastaran Darabi, Amit Ranjan Trivedi Published: 2026-04-10 Categories: cs.RO, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2604.09824v1 Vision language action (VLA) models enable generalist robotic agents but often exhibit language ignorance, relying on visual shortcuts and remaining insensitive to instruction changes. We present Prospective Grounding and Alignment VLA (ProGAL-VLA), which constructs a 3D entity-centric graph (GSM), uses a slow planner to produce symbolic sub-goals, and aligns them with grounded entities via a Grounding Alignment Contrastive (GAC) loss. All actions are conditioned on a verified goal embedding $g_t$, whose attention entropy provides an intrinsic ambiguity signal. On LIBERO-Plus, ProGAL-VLA increases robustness under robot perturbations from 30.3 to 71.5 percent, reduces language ignorance by 3x-4x, and improves entity retrieval from 0.41 to 0.71 Recall@1. On the Custom Ambiguity Benchmark, it reaches AUROC 0.81 (vs. 0.52), AUPR 0.79, and raises clarification on ambiguous inputs from 0.09 to 0.81 without harming unambiguous success. The verification bottleneck increases mutual information of language-actions, the GAC loss imposes an entity-level InfoNCE bound, and attention entropy yields calibrated selective prediction, indicating that explicit verified grounding is an effective path toward instruction-sensitive, ambiguity-aware agents. --- ### ACCIDENT: A Benchmark Dataset for Vehicle Accident Detection from Traffic Surveillance Videos Authors: Lukas Picek, Michal Čermák, Marek Hanzl, Vojtěch Čermák Published: 2026-04-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09819v1 We introduce ACCIDENT, a benchmark dataset for traffic accident detection in CCTV footage, designed to evaluate models in supervised (IID and OOD) and zero-shot settings, reflecting both data-rich and data-scarce scenarios. The benchmark consists of a curated set of 2,027 real and 2,211 synthetic clips annotated with the accident time, spatial location, and high-level collision type. We define three core tasks: (i) temporal localization of the accident, (ii) its spatial localization, and (iii) collision type classification. Each task is evaluated using custom metrics that account for the uncertainty and ambiguity inherent in CCTV footage. In addition to the benchmark, we provide a diverse set of baselines, including heuristic, motion-aware, and vision-language approaches, and show that ACCIDENT is challenging. You can access the ACCIDENT at: https://accidentbench.github.io --- ### Below-ground Fungal Biodiversity Can be Monitored Using Self-Supervised Learning Satellite Features Authors: Robin Young, Michael E. Van Nuland, E. Toby Kiers, Tomáš Větrovský, Petr Kohout, Petr Baldrian, Srinivasan Keshav Published: 2026-04-10 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2604.09818v2 Mycorrhizal fungi are vital to terrestrial ecosystem functioning. Yet monitoring their biodiversity at landscape scales is often unfeasible due to time and cost constraints. Current predictions suggest that 90% of mycorrhizal diversity hotspots remain unprotected, opening questions of how to broadly and effectively map underground fungal communities. We show that self-supervised learning (SSL) applied to satellite imagery can predict below-ground ectomycorrhizal fungal richness across diverse environments. Our models explain over half the variance in species richness across ~12,000 field samples spanning Europe and Asia. SSL-derived features are the most informative tested predictor group, and outperform each of the established climate, soil, and land cover baselines. We achieve a 10,000-fold increase in spatial resolution over existing techniques, moving from 1km landscape averages to 10m habitat-scale observations. As satellite observations are dynamic rather than static, this enables temporal monitoring of below-ground biodiversity at landscape scales for the first time. We apply this approach across two UK National Park woodlands, where ancient forests are predicted to have high but declining ectomycorrhizal diversity, marking key areas for further field verification. These results establish SSL satellite features as a scalable tool for extending sparse field observations to continuous, high-resolution biodiversity maps for monitoring the invisible half of terrestrial ecosystems. --- ### Below-ground Fungal Biodiversity Can be Monitored Using Self-Supervised Learning Satellite Features Authors: Robin Young, Michael E. Van Nuland, E. Toby Kiers, Tomáš Větrovský, Petr Kohout, Petr Baldrian, Srinivasan Keshav Published: 2026-04-10 Categories: cs.LG, cs.CE arXiv: https://arxiv.org/abs/2604.09818v1 Mycorrhizal fungi are vital to terrestrial ecosystem functioning. Yet monitoring their biodiversity at landscape scales is often unfeasible due to time and cost constraints. Current predictions suggest that 90\% of mycorrhizal diversity hotspots remain unprotected, opening questions of how to broadly and effectively map underground fungal communities. Here, we show that self-supervised learning (SSL) applied to satellite imagery can predict below-ground ectomycorrhizal fungal richness across diverse environments. Our models explain over half the variance in species richness across ~12,000 field samples spanning Europe and Asia. SSL-derived features prove to be the single most informative predictor, subsuming the majority of information contained in climate, soil, and land cover datasets. Using this approach, we achieve a 10,000-fold increase in spatial resolution over existing techniques, moving from 1km landscape averages to 10m habitat-scale observations with nearly no systematic bias. As satellite observations are dynamic rather than static, this enables temporal monitoring of below-ground biodiversity at landscape scales for the first time. We analyze multi-year trends in predicted fungal richness across UK National Park woodlands, finding that ancient forests may be losing ectomycorrhizal diversity at disproportionate rates. These results establish SSL satellite features as a scalable tool for extending sparse field observations to continuous, high-resolution biodiversity maps for monitoring the invisible half of terrestrial ecosystems. --- ### NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity Authors: Weijian Mai, Mu Nan, Yu Zhu, Jiahang Cao, Rui Zhang, Yuqin Dai, Chunfeng Song, Andrew F. Luo, Jiamin Wu Published: 2026-04-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.09817v1 Visual encoding and decoding models act as gateways to understanding the neural mechanisms underlying human visual perception. Typically, visual encoding models that predict brain activity from stimuli and decoding models that reproduce stimuli from brain activity are treated as distinct tasks, requiring separate models and training procedures. This separation is inefficient and fails to model the consistency between encoding and decoding processes. To address this limitation, we propose NeuroFlow, the first unified framework that jointly models visual encoding and decoding from neural activity within a single flow model. NeuroFlow introduces two key components: (1) NeuroVAE is designed as a variational backbone to model neural variability and establish a compact, semantically structured latent space for bidirectional modeling across visual and neural modalities. (2) Cross-modal Flow Matching (XFM) bypasses the typical paradigm of noise-to-data diffusion guided by a specific modality condition, instead learning a reversibly consistent flow model between visual and neural latent distributions. For the first time, visual encoding and decoding are reformulated as a time-dependent, reversible process within a shared latent space for unified modeling. Empirical results demonstrate that NeuroFlow achieves superior overall performance in visual encoding and decoding tasks with higher computational efficiency compared to any isolated methods. We further analyze principal factors that steer the model toward encoding-decoding consistency and, through brain functional analyses, demonstrate that NeuroFlow captures consistent activation patterns underlying neural variability. NeuroFlow marks a major step toward unified visual encoding and decoding from neural activity, providing mechanistic insights that inform future bidirectional visual brain-computer interfaces. --- ### EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning Authors: Tiantian He, Yihang Chen, Keyue Jiang, Ka Yiu Lee, Kaiwen Zhou, Kun Shao, Shuai Wang Published: 2026-04-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.09815v1 Computer-use agents that combine GUI interaction with structured API calls via the Model Context Protocol (MCP) show promise for automating software tasks. However, existing approaches lack a principled understanding of how agents should balance these two modalities and how to enable iterative self-improvement across diverse applications. We formulate MCP-GUI interplay as a unified hybrid policy learning problem where the agent learns when each modality provides complementary advantages, and show that distillation and experience augmentation target fundamentally different failure modes - requiring application-aware mechanism selection. Built on this formulation, we propose a self-evolving framework with a fully automatic pipeline that orchestrates automatic environment generation and validation, trajectory collection, gap-driven task synthesis, and quality-filtered training - all without manual intervention. A key innovation is our experience bank, which accumulates LLM-learned rules from trajectory comparison, enabling inference-time improvement without fine-tuning. Systematic \textbf{cross-application analysis} across three desktop applications reveals that the optimal strategy depends on MCP-GUI composition: distillation achieves 77.8\% pass rate on MCP-dominant tasks (+17.8pp), while the experience bank excels on GUI-intensive tasks (+10.0pp). --- ### RobustMedSAM: Degradation-Resilient Medical Image Segmentation via Robust Foundation Model Adaptation Authors: Jieru Li, Matthew Chen, Micky C. Nnamdi, J. Ben Tamo, Benoit L. Marteau, May D. Wang Published: 2026-04-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09814v1 Medical image segmentation models built on Segment Anything Model (SAM) achieve strong performance on clean benchmarks, yet their reliability often degrades under realistic image corruptions such as noise, blur, motion artifacts, and modality-specific distortions. Existing approaches address either medical-domain adaptation or corruption robustness, but not both jointly. In SAM, we find that these capabilities are concentrated in complementary modules: the image encoder preserves medical priors, while the mask decoder governs corruption robustness. Motivated by this observation, we propose RobustMedSAM, which adopts module-wise checkpoint fusion by initializing the image encoder from MedSAM and the mask decoder from RobustSAM under a shared ViT-B architecture. We then fine-tune only the mask decoder on 35 medical datasets from MedSegBench, spanning six imaging modalities and 12 corruption types, while freezing the remaining components to preserve pretrained medical representations. We additionally investigate an SVD-based parameter-efficient variant for limited encoder adaptation. Experiments on both in-distribution and out-of-distribution benchmarks show that RobustMedSAM improves degraded-image Dice from 0.613 to 0.719 (+0.106) over SAM, demonstrating that structured fusion of complementary pretrained models is an effective and practical approach for robust medical image segmentation. --- ### Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Authors: Siyuan Xu, Shiyang Li, Xin Liu, Tianyi Liu, Yixiao Li, Zhan Shi, Zixuan Zhang, Zilong Wang, Qingyu Yin, Jianshu Chen, Tuo Zhao, Bing Yin Published: 2026-04-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.09813v1 Existing synthetic tool-use corpora are primarily designed for offline supervised fine-tuning, yet reinforcement learning (RL) requires executable environments that support reward-checkable online rollouts. We propose COVERT, a two-stage pipeline that first generates reliable base tool-use trajectories through self-evolving synthesis with multi-level validation, and then applies oracle-preserving augmentations that systematically increase environmental complexity. These augmentations introduce distractor tools, indirect or ambiguous user queries, and noisy, multi-format, or erroneous tool outputs, while strictly preserving oracle tool calls and final answers as ground truth. This design enables automatic reward computation via reference matching for standard cases and lightweight judge-assisted verification for special behaviors such as error detection, supporting RL optimization of tool-calling policies. On Qwen2.5-Instruct-14B, COVERT-RL improves overall accuracy on BFCL v3 from 56.5 to 59.9 and on ACEBench from 53.0 to 59.3, with minimal regressions on general-ability benchmarks; when stacked on SFT, it further reaches 62.1 and 61.8, confirming additive gains. These results suggest that oracle-preserving synthetic environments offer a practical RL refinement stage, complementary to SFT, for improving tool-use robustness under ambiguity and unreliable tool feedback. --- ### Claim2Vec: Embedding Fact-Check Claims for Multilingual Similarity and Clustering Authors: Rrubaa Panchendrarajan, Arkaitz Zubiaga Published: 2026-04-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.09812v2 Recurrent claims present a major challenge for automated fact-checking systems designed to combat misinformation, especially in multilingual settings. While tasks such as claim matching and fact-checked claim retrieval aim to address this problem by linking claim pairs, the broader challenge of effectively representing groups of similar claims that can be resolved with the same fact-check via claim clustering remains relatively underexplored. To address this gap, we introduce Claim2Vec, the first multilingual embedding model optimized to represent fact-check claims as vectors in an improved semantic embedding space. We fine-tune a multilingual encoder using contrastive learning with similar multilingual claim pairs. Experiments on the claim clustering task using three datasets, 14 multilingual embedding models, and 7 clustering algorithms demonstrate that Claim2Vec significantly improves clustering performance. Specifically, it enhances both cluster label alignment and the geometric structure of the embedding space across different cluster configurations. Our multilingual analysis shows that clusters containing multiple languages benefit from fine-tuning, demonstrating cross-lingual knowledge transfer. --- ### Explainable Human Activity Recognition: A Unified Review of Concepts and Mechanisms Authors: Mainak Kundu, Catherine Chen, Rifatul Islam, Ismail Uysal, Ria Kanjilal Published: 2026-04-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.09799v1 Human activity recognition (HAR) has become a key component of intelligent systems for healthcare monitoring, assistive living, smart environments, and human-computer interaction. Although deep learning has substantially improved HAR performance on multivariate sensor data, the resulting models often remain opaque, limiting trust, reliability, and real-world deployment. Explainable artificial intelligence (XAI) has therefore emerged as a critical direction for making HAR systems more transparent and human-centered. This paper presents a comprehensive review of explainable HAR methods across wearable, ambient, physiological, and multimodal sensing settings. We introduce a unified perspective that separates conceptual dimensions of explainability from algorithmic explanation mechanisms, reducing ambiguities in prior surveys. Building on this distinction, we present a mechanism-centric taxonomy of XAI-HAR methods covering major explanation paradigms. The review examines how these methods address the temporal, multimodal, and semantic complexities of HAR, and summarize their interpretability objectives, explanation targets, and limitations. In addition, we discuss current evaluation practices, highlight key challenges in achieving reliable and deployable XAI-HAR, and outline directions toward trustworthy activity recognition systems that better support human understanding and decision-making. --- ### GIANTS: Generative Insight Anticipation from Scientific Literature Authors: Joy He-Yueya, Anikait Singh, Ge Gao, Michael Y. Li, Sherry Yang, Chelsea Finn, Emma Brunskill, Noah D. Goodman Published: 2026-04-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.09793v1 Scientific breakthroughs often emerge from synthesizing prior ideas into novel contributions. While language models (LMs) show promise in scientific discovery, their ability to perform this targeted, literature-grounded synthesis remains underexplored. We introduce insight anticipation, a generation task in which a model predicts a downstream paper's core insight from its foundational parent papers. To evaluate this capability, we develop GiantsBench, a benchmark of 17k examples across eight scientific domains, where each example consists of a set of parent papers paired with the core insight of a downstream paper. We evaluate models using an LM judge that scores similarity between generated and ground-truth insights, and show that these similarity scores correlate with expert human ratings. Finally, we present GIANTS-4B, an LM trained via reinforcement learning (RL) to optimize insight anticipation using these similarity scores as a proxy reward. Despite its smaller open-source architecture, GIANTS-4B outperforms proprietary baselines and generalizes to unseen domains, achieving a 34% relative improvement in similarity score over gemini-3-pro. Human evaluations further show that GIANTS-4B produces insights that are more conceptually clear than those of the base model. In addition, SciJudge-30B, a third-party model trained to compare research abstracts by likely citation impact, predicts that insights generated by GIANTS-4B are more likely to lead to higher citations, preferring them over the base model in 68% of pairwise comparisons. We release our code, benchmark, and model to support future research in automated scientific discovery. --- ### Pioneer Agent: Continual Improvement of Small Language Models in Production Authors: Dhruv Atreja, Julia White, Nikhil Nayak, Kelton Zhang, Henrijs Princis, George Hurn-Maloney, Ash Lewis, Urchade Zaratiana Published: 2026-04-10 Categories: cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2604.09791v1 Small language models are attractive for production deployment due to their low cost, fast inference, and ease of specialization. However, adapting them to a specific task remains a challenging engineering loop, driven not by training itself but by surrounding decisions: data curation, failure diagnosis, regression avoidance, and iteration control. We present Pioneer Agent, a closed-loop system that automates this lifecycle. In cold-start mode, given only a natural-language task description, the agent acquires data, constructs evaluation sets, and iteratively trains models by jointly optimizing data, hyperparameters, and learning strategy. In production mode, given a deployed model with labeled failures, it diagnoses error patterns, constructs targeted training data, and retrains under explicit regression constraints. To evaluate this setting, we introduce AdaptFT-Bench, a benchmark of synthetic inference logs with progressively increasing noise, designed to test the full adaptation loop: diagnosis, curriculum synthesis, retraining, and verification. Across eight cold-start benchmarks spanning reasoning, math, code generation, summarization, and classification, Pioneer Agent improves over base models by 1.6-83.8 points. On AdaptFT-Bench, it improves or preserves performance in all seven scenarios, while naive retraining degrades by up to 43 points. On two production-style deployments built from public benchmark tasks, it raises intent classification from 84.9% to 99.3% and Entity F1 from 0.345 to 0.810. Beyond performance gains, the agent often discovers effective training strategies, including chain-of-thought supervision, task-specific optimization, and quality-focused data curation, purely from downstream feedback. --- ### Learning What's Real: Disentangling Signal and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics Authors: Pablo Mercader-Perez, Carolina Cuesta-Lazaro, Daniel Muthukrishna, Jeroen Audenaert, V. Ashley Villar, David W. Hogg, Marc Huertas-Company, William T. Freeman Published: 2026-04-10 Categories: astro-ph.IM, astro-ph.GA, cs.LG arXiv: https://arxiv.org/abs/2604.09787v2 Data collected from the physical world is always a combination of multiple sources: an underlying signal from the physical process of interest and a signal from measurement-dependent artifacts from the sensor or instrument. This secondary signal acts as a confounding factor, limiting our ability to extract information about the physics underlying the phenomena we observe. Furthermore, it complicates the combination of observations in heterogeneous or multi-instrument settings. We propose a deep learning framework that leverages overlapping observations, a dual-encoder architecture, and a counterfactual generation objective to disentangle these factors of variation. The resulting representations explicitly separate intrinsic signals from sensor-specific distortions and noise, and can be used for counterfactual view generation, parameter inference unconfounded by measurement distortions, and instrument-independent similarity search. We demonstrate the effectiveness of our approach on astrophysical galaxy images from the DESI Legacy Imaging Survey (Legacy) and the Hyper Suprime-Cam (HSC) Survey as a representative multi-instrument setting. This framework provides a general recipe for scientific and multi-modal self-supervised pretraining: construct training pairs from overlapping observations of the same physical system, treat sensor- or modality-specific effects as augmentations, and learn invariant representations through counterfactual generation. --- ### Discrete Flow Maps Authors: Peter Potaptchik, Jason Yim, Adhi Saravanan, Peter Holderrieth, Eric Vanden-Eijnden, Michael S. Albergo Published: 2026-04-10 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.09784v2 The sequential nature of autoregressive next-token prediction imposes a fundamental speed limit on large language models. While continuous flow models offer a path to parallel generation, they traditionally demand expensive iterative integration. Flow Maps bypass this bottleneck by compressing generative trajectories into single-step mappings, theoretically enabling the generation of full text sequences from noise in a single forward pass. However, standard formulations rely on Euclidean regression losses that are geometrically ill-suited for discrete data. In this work, we resolve this conflict with Discrete Flow Maps, a framework that reconciles trajectory compression with the geometry of the probability simplex. We recast standard flow map training for the discrete domain, aligning the training dynamics with the discrete nature of language. Empirically, this strict geometric alignment allows our method to surpass previous state-of-the-art results in discrete flow modeling. --- ### Biomarker-Based Pretraining for Chagas Disease Screening in Electrocardiograms Authors: Elias Stenhede, Arian Ranjbar Published: 2026-04-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09782v1 Chagas disease screening via ECGs is limited by scarce and noisy labels in existing datasets. We propose a biomarker-based pretraining approach, where an ECG feature extractor is first trained to predict percentile-binned blood biomarkers from the MIMIC-IV-ECG dataset. The pretrained model is then fine-tuned on Brazilian datasets for Chagas detection. Our 5-model ensemble, developed by the Ahus AIM team, achieved a challenge score of 0.269 on the hidden test set, ranking 5th in Detection of Chagas Disease from the ECG: The George B. Moody PhysioNet Challenge 2025. Source code and the model are shared on GitHub: github.com/Ahus-AIM/physionet-challenge-2025 --- ### Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents Authors: Sangwon Baik, Gunhee Kim, Mingi Choi, Hanbyul Joo Published: 2026-04-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09781v2 Vision-Language Models (VLMs) exhibit strong visual reasoning capabilities, yet they still struggle with 3D understanding. In particular, VLMs often fail to infer a text-consistent goal 6D pose of a target object in a 3D scene. However, we find that with some inference-time techniques and iterative reasoning, VLMs can achieve dramatic performance gains. Concretely, given a 3D scene represented by an RGB-D image (or a compositional scene of 3D meshes) and a text instruction specifying a desired state change, we repeat the following loop: observe the current scene; evaluate whether it is faithful to the instruction; propose a pose update for the target object; apply the update; and render the updated scene. Through this closed-loop interaction, the VLM effectively acts as an agent. We further introduce three inference-time techniques that are essential to this closed-loop process: (i) multi-view reasoning with supporting view selection, (ii) object-centered coordinate system visualization, and (iii) single-axis rotation prediction. Without any additional fine-tuning or new modules, our approach surpasses prior methods at predicting the text-guided goal 6D pose of the target object. It works consistently across both closed-source and open-source VLMs. Moreover, when combining our 6D pose prediction with simple robot motion planning, it enables more successful robot manipulation than recent Vision-Language-Action models (VLAs). Finally, we conduct an ablation study to demonstrate the necessity of each proposed technique. --- ### The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise Authors: Xi Wang, Soufiane Hayou, Eric Nalisnick Published: 2026-04-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.09780v1 Mixture of Experts (MoEs) are now ubiquitous in large language models, yet the mechanisms behind their "expert specialization" remain poorly understood. We show that, since MoE routers are linear maps, hidden state similarity is both necessary and sufficient to explain expert usage similarity, and specialization is therefore an emergent property of the representation space, not of the routing architecture itself. We confirm this at both token and sequence level across five pre-trained models. We additionally prove that load-balancing loss suppresses shared hidden state directions to maintain routing diversity, which might provide a theoretical explanation for specialization collapse under less diverse data, e.g. small batch. Despite this clean mechanistic account, we find that specialization patterns in pre-trained MoEs resist human interpretation: expert overlap between different models answering the same question is no higher than between entirely different questions ($\sim$60\%); prompt-level routing does not predict rollout-level routing; and deeper layers exhibit near-identical expert activation across semantically unrelated inputs, especially in reasoning models. We conclude that, while the efficiency perspective of MoEs is well understood, understanding expert specialization is at least as hard as understanding LLM hidden state geometry, a long-standing open problem in the literature. --- ### Differentiable free energy surface: a variational approach to directly observing rare events using generative deep-learning models Authors: Shuo-Hui Li, Chen Chen, Yao-Wen Zhang, Ding Pan Published: 2026-04-10 Categories: physics.comp-ph, cond-mat.stat-mech, cs.LG arXiv: https://arxiv.org/abs/2604.09769v1 Rare events are central to the evolution of complex many-body systems, characterized as key transitional configurations on the free energy surface (FES). Conventional methods require adequate sampling of rare event transitions to obtain the FES, which is computationally very demanding. Here we introduce the variational free energy surface (VaFES), a dataset-free framework that directly models FESs using tractable-density generative models. Rare events can then be immediately identified from the FES with their configurations generated directly via one-shot sampling of generative models. By extending a coarse-grained collective variable (CV) into its reversible equivalent, VaFES constructs a latent space of intermediate representation in which the CVs explicitly occupy a subset of dimensions. This latent-space construction preserves the physical interpretability and transparent controllability of the CVs by design, while accommodating arbitrary CV formulations. The reversibility makes the system energy exactly accessible, enabling variational optimization of the FES without pre-generated simulation data. A single optimization yields a continuous, differentiable FES together with one-shot generation of rare-event configurations. Our method can reproduce the exact analytical solution for the bistable dimer potential and identify a chignolin native folded state in close alignment with the experimental NMR structure. Our approach thus establishes a scalable, systematic framework for advancing the study of complex statistical systems. --- ### Sustainable Transformer Neural Network Acceleration with Stochastic Photonic Computing Authors: S. Afifi, O. Alo, I. Thakkar, S. Pasricha Published: 2026-04-10 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2604.09759v1 Transformers achieve state-of-the-art performance in natural language processing, vision, and scientific computing, but demand high computation and memory. To address these challenges, we present ASTRA, the first silicon-photonic accelerator leveraging stochastic computing for transformers. ASTRA employs novel optical stochastic multipliers and unary/analog homodyne accumulation in a crosstalk-minimal organization to efficiently process dynamic tensor computations. Evaluations show at least 7.6x speedup and 1.3x lower energy overheads compared to state-of-the-art accelerators, highlighting ASTRA's potential for efficient, scalable, and sustainable transformer inference. --- ### MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering Authors: Suyang Xi, Songtao Hu, Yuxiang Lai, Wangyun Dan, Yaqi Liu, Shansong Wang, Xiaofeng Yang Published: 2026-04-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.09757v2 Medical vision--language models (VLMs) have shown strong potential for medical visual question answering (VQA), yet their reasoning remains largely text-centric: images are encoded once as static context, and subsequent inference is dominated by language. This paradigm is fundamentally limited in clinical scenarios, where accurate answers often depend on subtle, localized visual evidence that cannot be reliably preserved in static embeddings. We propose \textsc{MedLVR}, a latent visual reasoning framework that introduces an explicit visual evidence state into autoregressive decoding. Instead of relying solely on text-based intermediate reasoning, \textsc{MedLVR} interleaves a short latent reasoning segment within the decoder by reusing hidden states as continuous latent steps, enabling iterative preservation and refinement of query-relevant visual evidence before answer generation. To support effective visual supervision, we adopt a two-stage training strategy: region of interest (ROI)-supervised fine-tuning aligns latent states with clinically relevant image evidence, and Visual-Latent Policy Optimization (VLPO) further optimizes latent reasoning and answer generation under outcome-level rewards. Experiments on OmniMedVQA and five external medical VQA benchmarks show that \textsc{MedLVR} consistently outperforms recent reasoning baselines and improves the average score over the Qwen2.5-VL-7B backbone from 48.3\% to 53.4\%. These results show that latent visual reasoning provides an effective mechanism for preserving diagnostically relevant visual evidence and improving the reliability of medical VQA. --- ### A-IO: Adaptive Inference Orchestration for Memory-Bound NPUs Authors: Chen Zhang, Yan Ding, Haotian Wang, Chubo Liu, Keqin Li, Kenli Li Published: 2026-04-10 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2604.09752v2 During the deployment of Large Language Models (LLMs), the autoregressive decoding phase on heterogeneous NPU platforms (e.g., Ascend 910B) faces severe memory-bound challenges. This study reveals the ``Model Scaling Paradox'' caused by the static deployment of single-sized models. It also points out the kernel synchronization overhead of fine-grained speculative decoding \cite{leviathan2023fast, chen2023speculative} under NPU computational graph compilation, and the severe limitations of purely relying on micro-level acceleration algorithms like Prompt LookUp Decoding (PLD) --- ### Conflicts Make Large Reasoning Models Vulnerable to Attacks Authors: Honghao Liu, Chengjin Xu, Xuhui Jiang, Cehao Yang, Shengming Yin, Zhengwu Ma, Lionel Ni, Jian Guo Published: 2026-04-10 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.09750v1 Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood. This work investigates how LRMs respond to harmful queries when confronted with two categories of conflicts: internal conflicts that pit alignment values against each other and dilemmas, which impose mutually contradictory choices, including sacrificial, duress, agent-centered, and social forms. Using over 1,300 prompts across five benchmarks, we evaluate three representative LRMs - Llama-3.1-Nemotron-8B, QwQ-32B, and DeepSeek R1 - and find that conflicts significantly increase attack success rates, even under single-round non-narrative queries without sophisticated auto-attack techniques. Our findings reveal through layerwise and neuron-level analyses that safety-related and functional representations shift and overlap under conflict, interfering with safety-aligned behavior. This study highlights the need for deeper alignment strategies to ensure the robustness and trustworthiness of next-generation reasoning models. Our code is available at https://github.com/DataArcTech/ConflictHarm. Warning: This paper contains inappropriate, offensive and harmful content. --- ### See Fair, Speak Truth: Equitable Attention Improves Grounding and Reduces Hallucination in Vision-Language Alignment Authors: Mohammad Anas Azeez, Ankan Deria, Zohaib Hasan Siddiqui, Adinath Madhavrao Dukre, Rafiq Ali, Sara Atito, Yutong Xie, Imran Razzak Published: 2026-04-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09749v1 Multimodal large language models (MLLMs) frequently hallucinate objects that are absent from the visual input, often because attention during decoding is disproportionately drawn to visually dominant or frequently occurring content. We observe that this inequity in attention allocation is a root cause of object hallucination: when rare, small, or contextually peripheral objects receive insufficient attention, the model fails to ground its generation in the full visual scene. We argue that every object in an image, regardless of its size, frequency or visual salience, deserves equal representational opportunity during decoding. To this end, we propose DOP-OBC, a training-free and architecture-agnostic decoding strategy built on the principle of equitable attention. Two complementary object-aware signals work in tandem: a Dominant Object Penalty (DOP) that softly suppresses attention over-concentration on visually dominant regions, and an Outlier Boost Coefficient (OBC) that amplifies attention toward rare yet confidently detected objects. These signals are injected as per-row logit modulations within the causal attention mask, requiring no weight updates and preserving autoregressive decoding properties. Extensive experiments across image and video MLLMs demonstrate consistent reductions in object hallucination on CHAIR and POPE benchmarks, alongside improvements in GPT-4o assessed captioning quality across correctness, consistency, detail, context and temporal dimensions. DOP-OBC establishes that fairness in attention allocation is not merely a design principle but a practical and effective path toward more faithful multimodal generation. ---