# Research Papers — 2026-04 · bundle page 81 of 233 > Full-text markdown of papers #4001–4050 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/81 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/80.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/82.md) ### CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement Authors: Pan Wang, Yihao Hu, Xiujin Liu, Hang Wang Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.18032v1 Traditional shadow removal networks often treat image restoration as an unconstrained mapping, lacking the physical interpretability required to balance localized texture recovery with global illumination consistency. To address this, we propose CFSR, a multi-modal prior-driven framework that reframes shadow removal as a physics-constrained restoration process. By seamlessly integrating 3D geometric cues with large-scale foundation model semantics, CFSR effectively bridges the 2D-3D domain gap. Specifically, we first map observations into a custom HVI color space to suppress shadow-induced noise and robustly fuse RGB data with estimated depth priors. At its core, our Geometric & Semantic Dual Explicit Guided Attention mechanism utilizes DINO features and 3D surface normals to directly modulate the attention affinity matrix, structurally enforcing physical lighting constraints. To recover severely degraded regions, we inject holistic priors via a frozen CLIP encoder. Finally, our Frequency Collaborative Reconstruction Module (FCRM) achieves an optimal synthesis by decoupling the decoding process. Conditioned on geometric priors, FCRM seamlessly harmonizes the reconstruction of sharp high-frequency occlusion boundaries with the restoration of low-frequency global illumination. Extensive experiments demonstrate that CFSR achieves state-of-the-art performance across multiple challenging benchmarks. --- ### How Creative Are Large Language Models in Generating Molecules? Authors: Wen Tao, Yiwei Wang, Peng Zhou, Bryan Hooi, Wanlong Fang, Tianle Zhang, Xiao Luo, Yuansheng Liu, Alvin Chan Published: 2026-04-20 Categories: cs.CL, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2604.18031v1 Molecule generation requires satisfying multiple chemical and biological constraints while searching a large and structured chemical space. This makes it a non-binary problem, where effective models must identify non-obvious solutions under constraints while maintaining exploration to improve success by escaping local optima. From this perspective, creativity is a functional requirement in molecular generation rather than an aesthetic notion. Large language models (LLMs) can generate molecular representations directly from natural language prompts, but it remains unclear what type of creativity they exhibit in this setting and how it should be evaluated. In this work, we study the creative behavior of LLMs in molecular generation through a systematic empirical evaluation across physicochemical, ADMET, and biological activity tasks. We characterize creativity along two complementary dimensions, convergent creativity and divergent creativity, and analyze how different factors shape these behaviors. Our results indicate that LLMs exhibit distinct patterns of creative behavior in molecule generation, such as an increase in constraint satisfaction when additional constraints are imposed. Overall, our work is the first to reframe the abilities required for molecule generation as creativity, providing a systematic understanding of creativity in LLM-based molecular generation and clarifying the appropriate use of LLMs in molecular discovery pipelines. --- ### CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corpora Authors: Shangyu Li, Juyong Jiang, Meibo Ren, Sizhe Zhong, Huiri Tan, Yunhao Gou, Xu Han, Chun Yong Chong, Yun Peng, Jiasi Shen Published: 2026-04-20 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2604.18027v1 Transpilation, or code translation, aims to convert source code from one programming language (PL) to another. It is beneficial for many downstream applications, from modernizing large legacy codebases to augmenting data for low-resource PLs. Recent large language model (LLM)-based approaches have demonstrated immense potential for code translation. Among these approaches, training-based methods are particularly important because LLMs currently do not effectively adapt to domain-specific settings that suffer from a lack of knowledge without targeted training. This limitation is evident in transpilation tasks involving low-resource PLs. However, existing training-based approaches rely on a pairwise transpilation paradigm, making it impractical to support a diverse range of PLs. This limitation is particularly prominent for low-resource PLs due to a scarcity of training data. Furthermore, these methods suffer from suboptimal reinforcement learning (RL) reward formulations. To address these limitations, we propose CodePivot, a training framework that leverages Python as an intermediate representation (IR), augmented by a novel RL reward mechanism, Aggressive-Partial-Functional reward, to bootstrap the model's multilingual transpilation ability without requiring parallel corpora. Experiments involving 10 PLs show that the resulting 7B model, trained on Python-to-Others tasks, consistently improves performance across both general and low-resource PL-related transpilation tasks. It outperforms substantially larger mainstream models with hundreds of billions more parameters, such as Deepseek-R1 and Qwen3-235B-A22B-Instruct-2507, on Python-to-Others tasks and Others-to-All tasks, respectively. In addition, it outperforms its counterpart trained directly on Any-to-Any tasks on general transpilation tasks. The code and data are available at https://github.com/lishangyu-hkust/CodePivot. --- ### RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments Authors: Enze Pan Published: 2026-04-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.18026v1 Many deployed systems expose black-box objectives whose minimizing configuration shifts with an externally observed context. When contexts revisit a small set of latent regimes, an optimizer that discards history pays repeated adaptation cost; when each step must remain inexpensive, full Gaussian-process (GP) refits at high observation counts are difficult to sustain. We cast online tuning as context-conditioned regret minimization and present RASP-Tuner, which instantiates a decomposition motivated by first principles: (i) identify a regime proxy by retrieving similar past contexts; (ii) predict short-horizon loss with a mixture-of-experts surrogate whose input concatenates parameters, context, and a retrieved soft prompt; (iii) adapt chiefly in a low-dimensional prompt subspace, invoking full surrogate updates only when scalarized error or disagreement spikes. A RealErrorComposer maps heterogeneous streaming metrics to (0,1) via EMA-stabilized logistic scores, supplying a single differentiable training target. On nine synthetic non-stationary benchmarks, an adversarial-context sanity check, and three tabular real-world streams (Section on real-world experiments), RASP-Tuner improves or matches cumulative regret relative to our GP-UCB and CMA-ES implementations on seven of nine synthetic tasks under paired tests at horizon T=100, while recording 8-12 times lower wall-clock per step than sliding-window GP-UCB on identical hardware. Idealized analysis in a cluster-separated, strongly convex regime model (RA-GD) supplies sufficient conditions for bounded dynamic regret; the deployed pipeline violates several of these premises, and we articulate which gaps remain open. --- ### Clusterability-Based Assessment of Potentially Noisy Views for Multi-View Clustering Authors: Mudi Jiang, Jiahui Zhou, Xinying Liu, Zengyou He, Zhikui Chen Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18024v1 In multi-view clustering, the quality of different views may vary substantially, and low-quality or degraded views can impair overall clustering performance. However, existing studies mainly address this issue within the clustering process through view weighting or noise-robust optimization, while paying limited attention to data-level assessment before clustering. In this paper, we study the problem of pre-clustering noisy-view analysis in multi-view data from a clusterability perspective. To this end, we propose a Multi-View Clusterability Score (MVCS), which quantifies the strength of latent cluster-related structures in multi-view data through three complementary components: per-view structural clusterability, joint-space clusterability, and cross-view neighborhood consistency. To the best of our knowledge, this is the first clusterability score specifically designed for multi-view data. We further use it to perform potentially noisy view analysis and noisy-view detection before clustering. Extensive experiments on real-world datasets demonstrate that noisy views can significantly degrade clustering performance, and that, compared with existing clusterability measures designed for single-view data, the proposed method more effectively supports noisy-view analysis and detection. --- ### Boltzmann Machine Learning with a Parallel, Persistent Markov chain Monte Carlo method for Estimating Evolutionary Fields and Couplings from a Protein Multiple Sequence Alignment Authors: Sanzo Miyazawa Published: 2026-04-20 Categories: q-bio.BM, cond-mat.stat-mech, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.18022v1 The inverse Potts problem for estimating evolutionary single-site fields and pairwise couplings in homologous protein sequences from their single-site and pairwise amino acid frequencies observed in their multiple sequence alignment would be still one of useful methods in the studies of protein structure and evolution. Since the reproducibility of fields and couplings are the most important, the Boltzmann machine method is employed here, although it is computationally intensive. In order to reduce computational time required for the Boltzmann machine, parallel, persistent Markov chain Monte Carlo method is employed to estimate the single-site and pairwise marginal distributions in each learning step. Also, stochastic gradient descent methods are used to reduce computational time for each learning. Another problem is how to adjust the values of hyperparameters; there are two regularization parameters for evolutionary fields and couplings. The precision of contact residue pair prediction is often used to adjust the hyperparameters. However, it is not sensitive to these regularization parameters. Here, they are adjusted for the fields and couplings to satisfy a specific condition that is appropriate for protein conformations. This method has been applied to eight protein families. --- ### Multi-View Hierarchical Graph Neural Network for Sketch-Based 3D Shape Retrieval Authors: Hang Cheng, Muyan He, Mingyu Fan, Chengfeng Xie, Xi Cheng, Long Zeng Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.18019v1 Sketch-based 3D shape retrieval (SBSR) aims to retrieve 3D shapes that are consistent with the category of the input hand-drawn sketch. The core challenge of this task lies in two aspects: existing methods typically employ simplified aggregation strategies for independently encoded 3D multi-view features, which ignore the geometric relationships between views and multi-level details, resulting in weak 3D representation. Simultaneously, traditional SBSR methods are constrained by visible category limitations, leading to poor performance in zero-shot scenarios. To address these challenges, we propose Multi-View Hierarchical Graph Neural Network (MV-HGNN), a novel framework for SBSR. Specifically, we construct a view-level graph and capture adjacent geometric dependencies and cross-view message passing via local graph convolution and global attention. A view selector is further introduced to perform hierarchical graph coarsening, enabling a progressively larger receptive field for graph convolution and mitigating the interference of redundant views, which leads to more discriminate discriminative hierarchical 3D representation. To enable category agnostic alignment and mitigate overfitting to seen classes, we leverage CLIP text embeddings as semantic prototypes and project both sketch and 3D features into a shared semantic space. We use a two-stage training strategy for category-level retrieval and a one-stage strategy for zero-shot retrieval under the same model architecture. Under both category-level and zero-shot settings, extensive experiments on two public benchmarks demonstrate that MV-HGNN outperforms state-of-the-art methods. --- ### Neural Shape Operator Surrogates -- Expression Rate Bounds Authors: Helmut Harbrecht, Christoph Schwab Published: 2026-04-20 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2604.18012v1 We prove error bounds for operator surrogates of solution operators for partial differential and boundary integral equations on families of domains which are diffeomorphic to one common reference (or latent) domain $D_{ref}$. The pullback of the PDE to $D_{ref}$ via affine-parametric shape encoding produces a collection of holomorphic parametric PDEs on $D_{ref}$. Sufficient conditions for (uniformly with respect to the parameter) well-posedness are given, implying existence, uniqueness and stability of parametric solution families on $D_{ref}$. We illustrate the abstract hypotheses by reviewing recent holomorphy results for a suite of elliptic and parabolic PDEs. Quantified parametric holomorphy implies existence of finite-parametric, discrete approximations of the parametric solution families with convergence rates in terms of the number $N$ of parameters. We obtain constructive proofs of existence of Neural and Spectral Operator surrogates for the shape-to-solution maps with error bounds and convergence rate guarantees uniform on the collection of admissible shapes. We admit principal-component shape encoders and frame decoders. Our results support in particular the (empirically reported) ability of neural operators to realize data-to-solution maps for elliptic and parabolic PDEs and BIEs that generalize across parametric families of shapes. --- ### Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation Authors: Nuo Chen, Yicheng Tong, Yuzhe Yang, Yufei He, Xueyi Zhang, Qingyun Zou, Qian Wang, Bingsheng He Published: 2026-04-20 Categories: cs.MA, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.18005v2 Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the exploration diversity. However, when and why such collaboration truly expands the solution space remains unclear. We present a systematic empirical study of diversity in MAS-based ideation across three bottom-up levels: model intelligence, agent cognition, and system dynamics. At the model level, we identify a compute efficiency paradox, where stronger, highly aligned models yield diminishing marginal diversity despite higher per-sample quality. At the cognition level, authority-driven dynamics suppress semantic diversity compared to junior-dominated groups. At the system level, group-size scaling yields diminishing returns and dense communication topologies accelerate premature convergence. We characterize these outcomes as collective failures emerging from structural coupling, a process where interaction inadvertently contracts agent exploration and triggers diversity collapse. Our analysis shows that this collapse arises primarily from the interaction structure rather than inherent model insufficiency, highlighting the importance of preserving independence and disagreement when designing MAS for creative tasks. Our code is available at https://github.com/Xtra-Computing/MAS_Diversity. --- ### SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression Authors: Shaowei Zhang, Faqiang Qian, Yan Chen, Ziliang Wang, Kang An, Yong Dai, Mengya Gao, Yichao Wu Published: 2026-04-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.18003v1 Emotion Recognition in Conversation (ERC) has become a fundamental capability for large language models (LLMs) in human-centric interaction. Beyond accurate recognition, coherent emotional expression is also crucial, yet both are limited by the scarcity and static nature of high-quality annotated data. In this work, we propose SELF-EMO, a self-evolution framework grounded in the hypothesis that better emotion prediction leads to more consistent emotional responses. We introduce two auxiliary tasks, emotional understanding and emotional expression, and design a role-based self-play paradigm where the model acts as both an emotion recognizer and a dialogue responder. Through iterative interactions, the model generates diverse conversational trajectories, enabling scalable data generation. To ensure quality, we adopt a data flywheel mechanism that filters candidate predictions and responses using a smoothed IoU-based reward and feeds selected samples back for continuous self-improvement without external supervision. We further develop SELF-GRPO, a reinforcement learning algorithm that stabilizes optimization with multi-label alignment rewards and group-level consistency signals. Experiments on IEMOCAP, MELD, and EmoryNLP show that SELF-EMO achieves state-of-the-art performance, improving accuracy by +6.33% on Qwen3-4B and +8.54% on Qwen3-8B, demonstrating strong effectiveness and generalization. --- ### Neural Garbage Collection: Learning to Forget while Learning to Reason Authors: Michael Y. Li, Jubayer Ibn Hamid, Emily B. Fox, Noah D. Goodman Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.18002v1 Chain-of-thought reasoning has driven striking advances in language model capability, yet every reasoning step grows the KV cache, creating a bottleneck to scaling this paradigm further. Current approaches manage these constraints on the model's behalf using hand-designed criteria. A more scalable approach would let end-to-end learning subsume this design choice entirely, following a broader pattern in deep learning. After all, if a model can learn to reason, why can't it learn to forget? We introduce Neural Garbage Collection (NGC), in which a language model learns to forget while learning to reason, trained end-to-end from outcome-based task reward alone. As the model reasons, it periodically pauses, decides which KV cache entries to evict, and continues to reason conditioned on the remaining cache. By treating tokens in a chain-of-thought and cache-eviction decisions as discrete actions sampled from the language model, we can use reinforcement learning to jointly optimize how the model reasons and how it manages its own memory: what the model evicts shapes what it remembers, what it remembers shapes its reasoning, and the correctness of that reasoning determines its reward. Crucially, the model learns this behavior entirely from a single learning signal - the outcome-based task reward - without supervised fine-tuning or proxy objectives. On Countdown, AMC, and AIME tasks, NGC maintains strong accuracy relative to the full-cache upper bound at 2-3x peak KV cache size compression and substantially outperforms eviction baselines. Our results are a first step towards a broader vision where end-to-end optimization drives both capability and efficiency in language models. --- ### Trustworthy Endoscopic Super-Resolution Authors: Julio Silva-Rodríguez, Ender Konukoglu Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.18001v1 Super-resolution (SR) models are attracting growing interest for enhancing minimally invasive surgery and diagnostic videos under hardware constraints. However, valid concerns remain regarding the introduction of hallucinated structures and amplified noise, limiting their reliability in safety-critical settings. We propose a direct and practical framework to make SR systems more trustworthy by identifying where reconstructions are likely to fail. Our approach integrates a lightweight error-prediction network that operates on intermediate representations to estimate pixel-wise reconstruction error. The module is computationally efficient and low-latency, making it suitable for real-time deployment. We convert these predictions into operational failure decisions by constructing Conformal Failure Masks (CFM), which localize regions where the SR output should not be trusted. Built on conformal risk control principles, our method provides theoretical guarantees for controlling both the tolerated error limit and the miscoverage in detected failures. We evaluate our approach on image and video SR, demonstrating its effectiveness in detecting unreliable reconstructions in endoscopic and robotic surgery settings. To our knowledge, this is the first study to provide a model-agnostic, theoretically grounded approach to improving the safety of real-time endoscopic image SR. --- ### Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection Authors: Pooyan Khosravinia, João Gama, Bruno Veloso Published: 2026-04-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.17998v1 Anomaly detection in multivariate time series is a central challenge in industrial monitoring, as failures frequently arise from complex temporal dynamics and cross-sensor interactions. While recent deep learning models, including graph neural networks and Transformers, have demonstrated strong empirical performance, most approaches remain primarily correlational and offer limited support for causal interpretation and root-cause localization. This study introduces a causally-constrained probabilistic forecasting framework which is a Causally Guided Transformer (CGT) model for multivariate time-series anomaly detection, integrating an explicit time-lagged causal graph prior with deep sequence modeling. For each target variable, a dedicated forecasting block employs a hard parent mask derived from causal discovery to restrict the main prediction pathway to graph-supported causes, while a latent Gaussian head captures predictive uncertainty. To leverage residual correlational information without compromising the causal representation, a shadow auxiliary path with stop-gradient isolation and a safety-gated blending mechanism is incorporated to suppress non-causal contributions when reliability is low. Anomalies are identified using negative log-likelihood scores with adaptive streaming thresholding, and root-cause variables are determined through per-dimension probabilistic attribution and counterfactual clamping. Experiments on the ASD and SMD benchmarks indicate that the proposed method achieves state-of-the-art detection performance, with F1-scores of 96.19% on ASD and 95.32% on SMD, and enhances variable-level attribution quality. These findings suggest that causal structural priors can improve both robustness and interpretability in detecting deep anomalies in multivariate sensor systems. --- ### AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculum Authors: Jiaqi Li, Lvyang Zhang, Yang Zhao, Wen Lu, Lidong Zhai Published: 2026-04-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17989v1 What does it mean to give an AI agent a complete education? Current agent development produces specialists systems optimized for a single capability dimension, whether tool use, code generation, or security awareness that exhibit predictable deficits wherever they were not trained. We argue this pattern reflects a structural absence: there is no curriculum theory for agents, no principled account of what a fully developed agent should know, be, and be able to do across the full scope of intelligent behavior. This paper introduces the AIT Academy (Agents Institute of Technology Academy), a curriculum framework for cultivating AI agents across the tripartite structure of human knowledge. Grounded in Kagan's Three Cultures and UNESCO ISCED-F 2013, AIT organizes agent capability development into three domains: Natural Science and Technical Reasoning (Domain I), Humanities and Creative Expression (Domain II), and Social Science and Ethical Reasoning (Domain III). The Confucian Six Arts (liuyi) a 2,500-year-old holistic education system are reinterpreted as behavioral archetypes that map directly onto trainable agent capabilities within each domain. Three representative training grounds instantiate the framework across multiple backbone LLMs: the ClawdGO Security Dojo (Domain I), Athen's Academy (Domain II), and the Alt Mirage Stage (Domain III). Experiments demonstrate a 15.9-point improvement in security capability scores under weakest-first curriculum scheduling, and a 7-percentage-point gain in social reasoning performance under principled attribution modeling. A cross-domain finding Security Awareness Calibration Pathology (SACP), in which over-trained Domain I agents fail on out-of-distribution evaluation illustrates the diagnostic value of a multi-domain perspective unavailable to any single-domain framework. --- ### Employing General-Purpose and Biomedical Large Language Models with Advanced Prompt Engineering for Pharmacoepidemiologic Study Design Authors: Xinyao Zhang, Nicole Sonne Heckmann, Manuela Del Castillo Suero, Francesco Paolo Speca, Maurizio Sessa Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17988v1 Background: The potential of large language models (LLMs) to automate and support pharmacoepidemiologic study design is an emerging area of interest, yet their reliability remains insufficiently characterized. General-purpose LLMs often display inaccuracies, while the comparative performance of specialized biomedical LLMs in this domain remains unknown. Methods: This study evaluated general-purpose LLMs (GPT-4o and DeepSeek-R1) versus biomedically fine-tuned LLMs (QuantFactory/Bio-Medical-Llama-3-8B-GGUF and Irathernotsay/qwen2-1.5B-medical_qa-Finetune) using 46 protocols (2018-2024) from the HMA-EMA Catalogue and Sentinel System. Performance was assessed across relevance, logic of justification, and ontology-code agreement across multiple coding systems using Least-to-Most (LTM) and Active Prompting strategies. Results: GPT-4o and DeepSeek-R1 paired with LTM prompting achieved the highest relevance and logic of justification scores, with GPT-4o-LTM reaching a median relevance score of 4 in 8 of 9 questions for HMA-EMA protocols. Biomedical LLMs showed lower relevance overall and frequently generated insufficient justification. All LLMs demonstrated limited proficiency in ontology-code mapping, although LTM provided the most consistent improvements in reasoning stability. Conclusion: Off-the-shelf general-purpose LLMs currently offer superior support for pharmacoepidemiologic design compared to biomedical LLMs. Prompt strategy strongly influenced LLM performance. --- ### Latent Fourier Transform Authors: Mason Wang, Cheng-Zhi Anna Huang Published: 2026-04-20 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2604.17986v1 We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical patterns by timescale. By masking latents in the frequency domain during training, our method yields representations that can be manipulated coherently at inference. This allows us to generate musical variations and blends from reference examples while preserving characteristics at desired timescales, which are specified as frequencies in the latent space. LatentFT parallels the role of the equalizer in music production: while traditional equalizers operates on audible frequencies to shape timbre, LatentFT operates on latent-space frequencies to shape musical structure. Experiments and listening tests show that LatentFT improves condition adherence and quality compared to baselines. We also present a technique for hearing frequencies in the latent space in isolation, and show different musical attributes reside in different regions of the latent spectrum. Our results show how frequency-domain control in latent space provides an intuitive, continuous frequency axis for conditioning and blending, advancing us toward more interpretable and interactive generative music models. --- ### Online Conformal Prediction with Adversarial Semi-bandit Feedback via Regret Minimization Authors: Junyoung Yang, Kyungmin Kim, Sangdon Park Published: 2026-04-20 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.17984v1 Uncertainty quantification is crucial in safety-critical systems, where decisions must be made under uncertainty. In particular, we consider the problem of online uncertainty quantification, where data points arrive sequentially. Online conformal prediction is a principled online uncertainty quantification method that dynamically constructs a prediction set at each time step. While existing methods for online conformal prediction provide long-run coverage guarantees without any distributional assumptions, they typically assume a full feedback setting in which the true label is always observed. In this paper, we propose a novel learning method for online conformal prediction with partial feedback from an adaptive adversary-a more challenging setup where the true label is revealed only when it lies inside the constructed prediction set. Specifically, we formulate online conformal prediction as an adversarial bandit problem by treating each candidate prediction set as an arm. Building on an existing algorithm for adversarial bandits, our method achieves a long-run coverage guarantee by explicitly establishing its connection to the regret of the learner. Finally, we empirically demonstrate the effectiveness of our method in both independent and identically distributed (i.i.d.) and non-i.i.d. settings, showing that it successfully controls the miscoverage rate while maintaining a reasonable size of the prediction set. --- ### Mitigating Multimodal Hallucination via Phase-wise Self-reward Authors: Yu Zhang, Chuyang Sun, Kehai Chen, Xuefeng Bai, Yang Xiang, Min Zhang Published: 2026-04-20 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.17982v1 Large Vision-Language Models (LVLMs) still struggle with vision hallucination, where generated responses are inconsistent with the visual input. Existing methods either rely on large-scale annotated data for fine-tuning, which incurs massive computational overhead, or employ static post-hoc strategies that overlook the dynamic nature of hallucination emergence. To address these, we introduce a new self-rewarding framework, enabling dynamic hallucination mitigation at inference time without external supervision. On the empirical side, we reveal that visual hallucination exhibits phase-wise dynamic patterns, peaking at the onset of each semantic phase. Drawing on these insights, we propose \textbf{PSRD} (\textbf{Phase-wise \textbf{S}elf-\textbf{R}eward \textbf{D}ecoding) for online hallucination correction guided by phase-wise self-reward signals. To reduce the cost of repeated self-evaluation during decoding, we distill the hallucination guidance signal from LVLMs into a lightweight reward model. The reward model subsequently provides on-the-fly guidance for targeted intervention during the decoding process, enabling precise hallucination suppression. The proposed PSRD significantly reduces the hallucination rate of LLaVA-1.5-7B by 50.0% and consistently outperforms existing post-hoc methods across five hallucination evaluation benchmarks for four LVLMs. Further analysis confirms that PSRD effectively mitigates hallucination propagation and achieves a highly controllable trade-off between strong performance and inference efficiency. --- ### ltzGLUE: Luxembourgish General Language Understanding Evaluation Authors: Alistair Plum, Felicia Körner, Anne-Marie Lutgen, Laura Bernardy, Fred Philippy, Emilia Milano, Nils Rehlinger, Cédric Lothritz, Tharindu Ranasinghe, Barbara Plank, Christoph Purschke Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17976v1 This paper presents ltzGLUE, the first Natural Language Understanding (NLU) benchmark for Luxembourgish (LTZ) based on the popular GLUE benchmark for English. Although NLU tasks are available for many European languages nowadays, LTZ is one of the official national languages that is often overlooked. We construct new tasks and reuse existing ones to introduce the first official NLU benchmark and accompanying evaluation of encoder models for the language. Our tasks include common natural language processing tasks in binary and multi-class classification settings, including named entity recognition, topic classification, and intent classification. We evaluate various pre-trained language models for LTZ to present an overview of the current capabilities of these models on the LTZ language. --- ### Modeling Multiple Support Strategies within a Single Turn for Emotional Support Conversations Authors: Jie Zhu, Huaixia Dou, Junhui Li, Lifan Guo, Feng Chen, Jinsong Su, Chi Zhang, Fang Kong Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17972v1 Emotional Support Conversation (ESC) aims to assist individuals experiencing distress by generating empathetic and supportive dialogue. While prior work typically assumes that each supporter turn corresponds to a single strategy, real-world supportive communication often involves multiple strategies within a single utterance. In this paper, we revisit the ESC task by formulating it as multi-strategy utterance generation, where each utterance may contain one or more strategy-response pairs. We propose two generation methods: All-in-One, which predicts all strategy-response pairs in a single decoding step, and One-by-One, which iteratively generates strategy-response pairs until completion. Both methods are further enhanced with cognitive reasoning guided by reinforcement learning to improve strategy selection and response composition. We evaluate our models on the ESConv dataset under both utterance-level and dialogue-level settings. Experimental results show that our methods effectively model multi-strategy utterances and lead to improved supportive quality and dialogue success. To our knowledge, this work provides the first systematic empirical evidence that allowing multiple support strategies within a single utterance is both feasible and beneficial for emotional support conversations. All code and data will be publicly available at https://github.com/aliyun/qwen-dianjin. --- ### Identifying Ethical Biases in Action Recognition Models Authors: Ana Baltaretu, Pascal Benschop, Jan van Gemert Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17971v1 Human Action Recognition (HAR) models are increasingly deployed in high-stakes environments, yet their fairness across different human appearances has not been analyzed. We introduce a framework for auditing bias in HAR models using synthetic video data, generated with full control over visual identity attributes such as skin color. Unlike prior work that focuses on static images or pose estimation, our approach preserves temporal consistency, allowing us to isolate and test how changes to a single attribute affect model predictions. Through controlled interventions using the BEDLAM simulation platform, we show whether some popular HAR models exhibit statistically significant biases on the skin color even when the motion remains identical. Our results highlight how models may encode unwanted visual associations, and we provide evidence of systematic errors across groups. This work contributes a framework for auditing HAR models and supports the development of more transparent, accountable systems in light of upcoming regulatory standards. --- ### E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes Authors: Koya Sakamoto, Taiki Miyanishi, Daichi Azuma, Shuhei Kurita, Shu Morikuni, Naoya Chiba, Motoaki Kawanabe, Yusuke Iwasawa, Yutaka Matsuo Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17969v3 Visual search in 3D environments requires embodied agents to actively explore their surroundings and acquire task-relevant evidence. However, existing visual search and embodied AI benchmarks, including EQA, typically rely on static observations or constrained egocentric motion, and thus do not explicitly evaluate fine-grained viewpoint-dependent phenomena that arise under unrestricted 5-DoF viewpoint control in real-world 3D environments, such as visibility changes caused by vertical viewpoint shifts, revealing contents inside containers, and disambiguating object attributes that are only observable from specific angles. To address this limitation, we introduce {E3VS-Bench}, a benchmark for embodied 3D visual search where agents must control their viewpoints in 5-DoF to gather viewpoint-dependent evidence for question answering. E3VS-Bench consists of 99 high-fidelity 3D scenes reconstructed using 3D Gaussian Splatting and 2,014 question-driven episodes. 3D Gaussian Splatting enables photorealistic free-viewpoint rendering that preserves fine-grained visual details (e.g., small text and subtle attributes) often degraded in mesh-based simulators, thereby allowing the construction of questions that cannot be answered from a single view and instead require active inspection across viewpoints in 5-DoF. We evaluate multiple state-of-the-art VLMs and compare their performance with humans. Despite strong 2D reasoning ability, all models exhibit a substantial gap from humans, highlighting limitations in active perception and coherent viewpoint planning specifically under full 5-DoF viewpoint changes. --- ### From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives? Authors: Hasan Amin, Harry Yizhou Tian, Xiaoni Duan, Chien-Ju Ho, Rajiv Khanna, Ming Yin Published: 2026-04-20 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.17968v1 Although large language models (LLMs) are increasingly used as annotators at scale, they are typically treated as a pragmatic fallback rather than a faithful estimator of human perspectives. This work challenges that presumption. By framing perspective-taking as the estimation of a latent group-level judgment, we characterize the conditions under which modern LLMs can outperform human annotators, including in-group humans, when predicting aggregate subgroup opinions on subjective tasks, and show that these conditions are common in practice. This advantage arises from structural properties of LLMs as estimators, including low variance and reduced coupling between representation and processing biases, rather than any claim of lived experience. Our analysis identifies clear regimes where LLMs act as statistically superior frontline estimators, as well as principled limits where human judgment remains essential. These findings reposition LLMs from a cost-saving compromise to a principled tool for estimating collective human perspectives. --- ### A Sugeno Integral View of Binarized Neural Network Inference Authors: Ismaïl Baaj, Henri Prade Published: 2026-04-20 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.17967v1 In this article, we establish a precise connection between binarized neural networks (BNNs) and Sugeno integrals. The advantage of the Sugeno integral is that it provides a framework for representing the importance of inputs and their interactions, while being equivalent to a set of if-then rules. For a hidden BNN neuron at inference time, we show that the activation threshold test can be written as a Sugeno integral on binary inputs. This yields an explicit set-function representation of each neuron decision, and an associated rule-based representation. We also provide a Sugeno-integral expression for the last-layer score. Finally, we discuss how the same framework can be adapted to support richer input interactions and how it can be extended beyond the binary case induced by binarized neural networks. --- ### TPS-CalcBench: A Benchmark and Diagnostic Evaluation Framework for LLM Analytical Calculation Competence in Hypersonic Thermal Protection System Engineering Authors: Jinglai Zheng, Chuhan Qiao, Haiming Huang Published: 2026-04-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17966v1 Deploying LLMs as reasoning assistants in safety-critical aerospace engineering requires stricter evaluation criteria than general scientific benchmarks. In hypersonic thermal protection system (TPS) design, inaccurate stagnation-point heat flux or boundary-layer calculations may cause catastrophic design margin violations. Models with numerically reasonable but physically invalid answers are more dangerous than those declining to respond. Current scientific benchmarks only test abstract math and basic physics, evaluate final answers solely, ignore engineering reasoning processes, and cannot detect such critical failures. We propose TPS-CalcBench, the first diagnostic benchmark for closed-form analytical calculations in hypersonic aerodynamics and high-temperature gas dynamics that experienced TPS engineers conduct without simulations. Our contributions include domain-oriented task taxonomy with 4 difficulty levels and 8 categories from Anderson's textbook, dual-track evaluation measuring result accuracy and reasoning quality via an 8-dimension rubric and calibrated judge with human audit to identify right answer wrong reasoning issues, human-AI data pipeline producing 420 high-confidence core items and 810 noise-controlled pre-gating items from 4560 raw data, noise-sensitivity analysis measuring data quality impacts on model ranking, and three diagnostic intervention methods: DFA-TPS fine-tuning, RAG-EQ retrieval grounding and PA-CoT process-aware prompting. Tests on 13 models from 7 groups show wide performance differences (KPI 12.6-87.9), hidden formula selection defects, data-driven rank changes and effective intervention improvements, establishing a complete diagnose-evaluate-intervene framework for safety-critical engineering LLM deployment assessment. --- ### MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene Authors: Wenjie Mu, Zhan Li, Chuanzhou Su, Xuanyi Shen, Ziniu Liu, Fan Lu, Yujian Mo, Junqiao Zhao, Tiantian Feng, Chen Ye, Guang Chen Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17965v1 Generalizable Neural Radiance Fields (GeNeRFs) enable high-quality scene reconstruction from sparse views and can generalize to unseen scenes. However, in real-world settings, transient distractors break cross-view structural consistency, corrupting supervision and degrading reconstruction quality. Existing distractor-free NeRF methods rely on per-scene optimization and estimate uncertainty from per-view reconstruction errors, which are not reliable for GeNeRFs and often misjudge inconsistent static structures as distractors. To this end, we propose MU-GeNeRF, a Multi-view Uncertainty-guided distractor-aware GeNeRF framework designed to alleviate GeNeRF's robust modeling challenges in the presence of transient distractions. We decompose distractor awareness into two complementary uncertainty components: Source-view Uncertainty, which captures structural discrepancies across source views caused by viewpoint changes or dynamic factors; and Target-view Uncertainty, which detects observation anomalies in the target image induced by transient distractors.These two uncertainties address distinct error sources and are combined through a heteroscedastic reconstruction loss, which guides the model to adaptively modulate supervision, enabling more robust distractor suppression and geometric modeling.Extensive experiments show that our method not only surpasses existing GeNeRFs but also achieves performance comparable to scene-specific distractor-free NeRFs. --- ### DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection Authors: Lazaro J. Gonzalez-Soler, André Dörsch, Christian Rathgeb, Christoph Busch Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17961v2 In this work, we introduce DifFoundMAD, a parameter-efficient D-MAD framework that exploits the generalisation capabilities of vision foundation models (FM) to capture discrepancies between suspected morphs and live capture images. In contrast to conventional D-MAD systems that rely on face recognition embeddings or handcrafted feature differences, DifFoundMAD follows the standard differential paradigm while replacing the underlying representation space with embeddings extracted from FMs. By combining lightweight finetuning with class-balanced optimisation, the proposed method updates only a small subset of parameters while preserving the rich representational priors of the underlying FMs. Extensive cross-database evaluations on standard D-MAD benchmarks demonstrate that DifFoundMAD achieves consistent improvements over state-of-the-art systems, particularly at the strict security levels required in operational deployments such as border control: The error rates reported in the current state-of-the-art were reduced from 6.16% to 2.17% for high-security levels using DifFoundMAD --- ### The Umwelt Representation Hypothesis: Rethinking Universality Authors: Victoria Bosch, Rowan Sommers, Adrien Doerig, Tim C Kietzmann Published: 2026-04-20 Categories: q-bio.NC, cs.LG arXiv: https://arxiv.org/abs/2604.17960v1 Recent studies reveal striking representational alignment between artificial neural networks (ANNs) and biological brains, leading to proposals that all sufficiently capable systems converge on universal representations of reality. Here, we argue that this claim of Universality is premature. We introduce the Umwelt Representation Hypothesis (URH), proposing that alignment arises not from convergence toward a single global optimum, but from overlap in ecological constraints under which systems develop. We review empirical evidence showing that representational differences between species, individuals, and ANNs are systematic and adaptive, which is difficult to reconcile with Universality. Finally, we reframe ANN model comparison as a method for mapping clusters of alignment in ecological constraint space rather than searching for a single optimal world model. --- ### Chatting about Upper-Body Expressive Human Pose and Shape Estimation Authors: Yuxiang Zhao, Wei Huang, Yujie Song, Liu Wang, Huan Zhao Published: 2026-04-20 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2604.17959v1 Expressive Human Pose and Shape Estimation (EHPS) plays a crucial role in various AR/VR applications and has witnessed significant progress in recent years. However, current state-of-the-art methods still struggle with accurate parameter estimation for facial and hand regions and exhibit limited generalization to wild images. To address these challenges, we present CoEvoer, a novel one-stage synergistic cross-dependency transformer framework tailored for upper-body EHPS. CoEvoer enables explicit feature-level interaction across different body parts, allowing for mutual enhancement through contextual information exchange. Specifically, larger and more easily estimated regions such as the torso provide global semantics and positional priors to guide the estimation of finer, more complex regions like the face and hands. Conversely, the localized details captured in facial and hand regions help refine and calibrate adjacent body parts. To the best of our knowledge, CoEvoer is the first framework designed specifically for upper-body EHPS, with the goal of capturing the strong coupling and semantic dependencies among the face, hands, and torso through joint parameter regression. Extensive experiments demonstrate that CoEvoer achieves state-of-the-art performance on upper-body benchmarks and exhibits strong generalization capability even on unseen wild images. --- ### Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards Authors: Raffaele Pisano, Roberto Navigli Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17957v1 Process Reward Models (PRMs) have emerged as a powerful tool for providing step-level feedback when evaluating the reasoning of Large Language Models (LLMs), which frequently produce chains of thought (CoTs) containing errors even when the final answer is correct. However, existing PRM datasets remain expensive to construct, prone to annotation errors, and predominantly limited to the mathematical domain. This work introduces a novel and scalable approach to PRM dataset generation based on planning logical problems expressed in the Planning Domain Definition Language (PDDL). Using this method, we generate a corpus of approximately one million reasoning steps across various PDDL domains and use it to train PRMs. Experimental results show that augmenting widely-used PRM training datasets with PDDL-derived data yields substantial improvements in both mathematical and non-mathematical reasoning, as demonstrated across multiple benchmarks. These findings indicate that planning problems constitute a scalable and effective resource for generating robust, precise, and fine-grained training data for PRMs, going beyond the classical mathematical sources that dominate this field. --- ### Federated Rule Ensemble Method in Medical Data Authors: Ke Wan, Kensuke Tanioka, Toshio Shimokawa Published: 2026-04-20 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2604.17956v1 Machine learning has become integral to medical research and is increasingly applied in clinical settings to support diagnosis and decision-making; however, its effectiveness depends on access to large, diverse datasets, which are limited within single institutions. Although integrating data across institutions can address this limitation, privacy regulations and data ownership constraints hinder these efforts. Federated learning enables collaborative model training without sharing raw data; however, most methods rely on complex architectures that lack interpretability, limiting clinical applicability. Therefore, we proposed a federated RuleFit framework to construct a unified and interpretable global model for distributed environments. It integrates three components: preprocessing based on differentially private histograms to estimate shared cutoff values, enabling consistent rule definitions and reducing heterogeneity across clients; local rule generation using gradient boosting decision trees with shared cutoffs; and coefficient estimation via $\ell_1$-regularized optimization using a Federated Dual Averaging algorithm for sparse and consistent variable selection. In simulation studies, the proposed method achieved a performance comparable to that of centralized RuleFit while outperforming existing federated approaches. Real-world analysis demonstrated its ability to provide interpretable insights with competitive predictive accuracy. Therefore, the proposed framework offers a practical and effective solution for interpretable and reliable modeling in federated learning environments. --- ### Complex normalizing flows can almost be information Kähler-Ricci flows Authors: Andrew Gracyk Published: 2026-04-20 Categories: math.DG, cs.LG arXiv: https://arxiv.org/abs/2604.17954v3 We develop interconnections between the complex normalizing flow for data drawn from Borel probability measures on the twofold realification of the complex manifold and a nonlinear flow nearly Kähler-Ricci. The complex normalizing flow relates the initial and target realified densities under the complex change of variables, necessitating the log determinant of the ensemble of Wirtinger Jacobians. The Ricci curvature of a Kähler manifold is the second order mixed Wirtinger partial derivative of the log of the local density of the volume form. Therefore, we reconcile these two facts by drawing forth the connection that the log determinant used in the complex normalizing flow matches a Ricci curvature term under differentiation and conditions. The log density under the normalizing flow is kindred to a spatial information metric under an augmented Jacobian and a Bayesian perspective to the parameter, thus under the continuum limit the log likelihood matches a Fisher metric, or more closely a Kähler cross-entropy Hessian. This recovers a Kähler-Ricci flow variation up to a time derivative and expectation, or an average-valued Kähler-Einstein flow. Using this framework, we establish other relevant results, attempting to bridge the statistical and ordinary behaviors of the complex normalizing flow to the geometric features of our derived Kähler flow. --- ### CADMAS-CTX: Contextual Capability Calibration for Multi-Agent Delegation Authors: Chuhan Qiao Published: 2026-04-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17950v1 We revisit multi-agent delegation under a stronger and more realistic assumption: an agent's capability is not fixed at the skill level, but depends on task context. A coding agent may excel at short standalone edits yet fail on long-horizon debugging; a planner may perform well on shallow tasks yet degrade on chained dependencies. Static skill-level capability profiles therefore average over heterogeneous situations and can induce systematic misdelegation. We propose CADMAS-CTX, a framework for contextual capability calibration. For each agent, skill, and coarse context bucket, CADMAS-CTX maintains a Beta posterior that captures stable experience in that part of the task space. Delegation is then made by a risk-aware score that combines the posterior mean with an uncertainty penalty, so that agents delegate only when a peer appears better and that assessment is sufficiently well supported by evidence. This paper makes three contributions. First, a hierarchical contextual capability profile replaces static skill-level confidence with context-conditioned posteriors. Second, based on contextual bandit theory, we formally prove context-aware routing achieves lower cumulative regret than static routing under sufficient context heterogeneity, formalizing the bias-variance tradeoff. Third, we empirically validate our method on GAIA and SWE-bench benchmarks. On GAIA with GPT-4o agents, CADMAS-CTX achieves 0.442 accuracy, outperforming static baseline 0.381 and AutoGen 0.354 with non-overlapping 95% confidence intervals. On SWE-bench Lite, it improves resolve rate from 22.3% to 31.4%. Ablations show the uncertainty penalty improves robustness against context tagging noise. Our results demonstrate contextual calibration and risk-aware delegation significantly improve multi-agent teamwork compared with static global skill assignments. --- ### ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly Detection Authors: Qiuhui Chen, Jiaxiang Song, Shuai Tan, Weimin Zhong Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17949v1 Deep learning-based industrial anomaly detectors often behave as black boxes, making it hard to justify decisions with physically meaningful defect evidence. We propose ZSG-IAD, a multimodal vision-language framework for zero-shot grounded industrial anomaly detection. Given RGB images, sensor images, and 3D point clouds, ZSG-IAD generates structured anomaly reports and pixel-level anomaly masks. ZSG-IAD introduces a language-guided two-hop grounding module: (1) anomaly-related sentences select evidence-like latent slots distilled from multimodal features, yielding coarse spatial support; (2) selected slots modulate feature maps via channel-spatial gating and a lightweight decoder to produce fine-grained masks. To improve reliability, we further apply Executable-Rule GRPO with verifiable rewards to promote structured outputs, anomaly-region consistency, and reasoning-conclusion coherence. Experiments across multiple industrial anomaly benchmarks show strong zero-shot performance and more transparent, physically grounded explanations than prior methods. We will release code and annotations to support future research on trustworthy industrial anomaly detection systems. --- ### RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs Authors: Parteek Jamwal, Minghao Shao, Boyuan Chen, Achyuta Muthuvelan, Asini Subanya, Boubacar Ballo, Kashish Satija, Mariam Shafey, Mohamed Mahmoud, Moncif Dahaji Bouffi, Pasindu Wickramasinghe, Siyona Goel et al. Published: 2026-04-20 Categories: cs.CR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.17948v2 Large Language Models (LLMs) have demonstrated remarkable capabilities across various cybersecurity tasks, including vulnerability classification, detection, and patching. However, their potential in automated vulnerability report documentation and analysis remains underexplored. We present RAVEN (Retrieval Augmented Vulnerability Exploration Network), a framework leveraging LLM agents and Retrieval Augmented Generation (RAG) to synthesize comprehensive vulnerability analysis reports. Given vulnerable source code, RAVEN generates reports following the Google Project Zero Root Cause Analysis template. The framework uses four modules: an Explorer agent for vulnerability identification, a RAG engine retrieving relevant knowledge from curated databases including Google Project Zero reports and CWE entries, an Analyst agent for impact and exploitation assessment, and a Reporter agent for structured report generation. To ensure quality, RAVEN includes a task specific LLM Judge evaluating reports across structural integrity, ground truth alignment, code reasoning quality, and remediation quality. We evaluate RAVEN on 105 vulnerable code samples covering 15 CWE types from the NIST-SARD dataset. Results show an average quality score of 54.21%, supporting the effectiveness of our approach for automated vulnerability documentation. --- ### ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering Authors: Yindong Zhang, Wenmian Yang, Yiquan Zhang, Weijia Jia Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17944v1 Developing agents capable of navigating fragmented, multi-source information remains challenging, primarily due to the scarcity of benchmarks reflecting hybrid workflows combining database querying with external APIs. To bridge this gap, we introduce ReCoQA, a large-scale benchmark of 29,270 real-estate instances featuring machine-verifiable supervision for intermediate steps, including structured intent labels, SQL queries, and API calls. Complementarily, we propose HIRE-Agent, a hierarchical framework instantiating an understand-plan-execute architecture as a strong baseline. By orchestrating a Front-end parser, a planning Supervisor, and execution Specialists, HIRE-Agent effectively integrates heterogeneous evidence. Extensive experiments demonstrate that HIRE-Agent constitutes a strong baseline and substantiates the necessity of hierarchical collaboration for complex, real-world reasoning tasks. --- ### A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents Authors: Bao Gia Doan, Aditya Joshi, Pantelis Elinas, Aarya Bodhankar, Oscar Leslie, Tom Marchant, Flora Salim Published: 2026-04-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.17943v2 RAG-based question-answering (QA) in specialist domains faces a cold-start problem: lack of evaluative benchmarks and absence of labeled data for post-training. We present DoRA (Domain-oriented RAG Assessment), a novel benchmark construction and evaluation framework using only a small set of specialist domain documents. DoRA systematically generates synthetic QA training and evaluation datasets with auditable evidence across five domain-specific intents. To mitigate same-pipeline circularity, DoRA's training and test splits use different LLM families (Claude Sonnet for training; GPT-4o for test) drawn from disjoint seed-document corpora. Instantiated on 40 defense-related documents (written in English), DoRA yields ~6.6K curated instances. Compared against 8 LLM baselines over a benchmark of 1,259 samples, a LoRA-adapted Llama3.1-8B trained on the synthetic training set consistently improves performance over 6 coverage and faithfulness metrics, especially reducing hallucination by more than half under the default GTE retrieval setting, with gains persisting across alternative retrievers and prompting-based baselines. Defense-domain expertise is incorporated in three stages of our evaluation: (a) determining the quality of the synthetic QA generated by DoRA, (b) ascertaining the reliability of LLM-as-judge scores, and (c) evaluating the generalization of the QA pipeline on completely human-written QA examples. We position DoRA as a practical framework for specialist-domain RAG under domain shift, with defense as a high-stakes case study. --- ### From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models Authors: Qidong Wang, Junjie Hu, Ming Jiang Published: 2026-04-20 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.17941v1 Recent work has increasingly explored neuron-level interpretation in vision-language models (VLMs) to identify neurons critical to final predictions. However, existing neuron analyses generally focus on single tasks, limiting the comparability of neuron importance across tasks. Moreover, ranking strategies tend to score neurons in isolation, overlooking how task-dependent information pathways shape the write-in effects of feed-forward network (FFN) neurons. This oversight can exacerbate neuron polysemanticity in multi-task settings, introducing noise into the identification and intervention of task-critical neurons. In this study, we propose HONES (Head-Oriented Neuron Explanation & Steering), a gradient-free framework for task-aware neuron attribution and steering in multi-task VLMs. HONES ranks FFN neurons by their causal write-in contributions conditioned on task-relevant attention heads, and further modulates salient neurons via lightweight scaling. Experiments on four diverse multimodal tasks and two popular VLMs show that HONES outperforms existing methods in identifying task-critical neurons and improves model performance after steering. Our source code is released at: https://github.com/petergit1/HONES. --- ### ContraPrompt: Contrastive Prompt Optimization via Dyadic Reasoning Trace Analysis Authors: Rishav Rishav, Pushpak Pujari, Pushpendre Rastogi Published: 2026-04-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17937v1 Prompt optimization methods either analyze individual failures in isolation or compare prompt variants across examples, operating on single execution traces with no access to the reasoning process distinguishing success from failure on the same input. We introduce ContraPrompt, built on the observation that when a model fails but succeeds on a retry with feedback, the difference between its two chain-of-thought traces constitutes an optimization signal not captured by prior methods. Unlike prior contrastive methods, we compare complete intermediate reasoning processes: the two traces share model, input, and base prompt, so remaining differences reflect reasoning strategy and appended error feedback -- we call this dyadic reasoning trace analysis. The multi-attempt solving phase is an instrumented agentic retry loop that generates contrastive data automatically without human annotation. Extracted rules are organized into an input-aware decision tree routing instructions by observable input characteristics. On four reasoning and compliance benchmarks, ContraPrompt outperforms GEPA (Agrawal et al., 2026) on all four, with absolute gains of +8.29 pp on HotPotQA (+20.8% rel.), +2.21 pp on GDPR-Bench (+18.2% rel.), +7.14 pp on GPQA Diamond (+10.6% rel.), and +0.74 pp on BBH (+0.85% rel.). Ablations confirm dyadic trace contrastivity is the critical component, with a -16% relative average drop upon its removal. On 53 EvalSet black-box optimization problems, ContraPrompt beats GEPA on 11, ties on 41, and loses on 1 at equal budget. On FiNER-139 financial named entity recognition (Loukas et al., 2022), ContraPrompt achieves +7.77 pp over the unoptimized baseline (+11.6% rel.) and +1.94 pp over GEPA (+2.66% rel.), with branch conditions aligning with standard US GAAP financial-instrument categories. --- ### How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers Authors: Xiao Wang Published: 2026-04-20 Categories: cs.LG, cs.AI, cs.CC arXiv: https://arxiv.org/abs/2604.17935v1 The key-value (KV) cache is the dominant memory bottleneck during Transformer inference, yet little is known theoretically about how aggressively it can be compressed before multi-step reasoning degrades. We study this through $k$-hop pointer chasing on $n$ tokens under a shared KV cache of size $s$, attention dimension $m$, $H$ heads, $p$-bit precision, and a locality-respecting cache controller (satisfied by all standard KV-compression methods). We give three results. (1) Product depth lower bound (conjectured). We conjecture that any such Transformer ($n \geq 4k$, $s \leq \sqrt{n}/4$) requires depth $L = Ω(\lceil k/s \rceil \cdot \lceil \log_2 n/(Hmp) \rceil)$, and isolate the sole remaining gap as a probabilistic step on the joint distribution of cache trace and pointer chain. Unconditionally, we prove a matching upper bound $L = O(\min(k, \lceil k/s \rceil \log s) \cdot \log n/(mp))$ via windowed pointer doubling, and a max-bound $L = Ω(\max(\lceil k/s \rceil, \log n/(Hmp)))$. Closing the conjecture amounts to upgrading max to product. (2) Bandwidth barrier. The product bound binds only when $Hmp \lesssim \log n$. Any lower bound provable via per-window distinguishability counting -- including reachability, bandwidth, and combinations -- cannot exceed $\lceil k/s \rceil$ once $Hmp \geq \log_2 n$. Breaking this requires lifting unconditional communication-complexity bounds for pointer chasing to Cache-Transformer depth. (3) Adaptive vs oblivious error scaling. Under random cache over $T = \lceil \log_2 k \rceil$ doubling stages, oblivious caches give $\Pr(\mathcal{E}) \leq (s/(n-T))^T + 2T^3/n$ (exponential in $T$), while adaptive locality-respecting caches achieve $\Pr(\mathcal{E}) = s/n$ exactly, independent of $T$. The $Ω((n/s)^{T-1})$ separation explains why heavy-hitter eviction empirically dominates random eviction for multi-hop reasoning. --- ### LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent Authors: Bince Qu, Wanli Li, Bo Pan, Jianyu Zhang, Zheng Liu, Pan Zhang, Wei Chen, Bo Zhang Published: 2026-04-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.17931v5 Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains constrained by two coupled challenges: hand-crafted synthetic data fails to elicit genuine real-world search capabilities, and real-world search dependency during RL training introduces instability and prohibitive cost, which limits the scalability of Agentic RL. LiteResearcher is a training framework that makes Agentic RL scalable: by constructing a lite virtual world that mirrors real-world search dynamics, we enable a continuously improving training recipe that empowers a tiny search agent to outperform large-scale open-source and commercial models (e.g., Tongyi DeepResearch and Claude-4.5 Sonnet). Specifically, on common benchmarks such as GAIA and Xbench, our LiteResearcher-4B achieves open-source state-of-the-art results of 71.3% and 78.0% respectively, demonstrating that scalable RL training is a key enabler for Deep Research Agents. --- ### Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck? Authors: H S V N S Kowndinya Renduchintala, Sumit Bhatia Published: 2026-04-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.17930v1 Large Language Models (LLMs) exhibit a puzzling disparity in their formal linguistic competence: while they learn some linguistic phenomena with near-perfect mastery, they often perform below chance on others, even after training on trillions of tokens. In this work, we investigate whether these failures stem from inherent architectural limitations or simply the scarcity of these specific grammatical constructions in web-scale corpora. We pre-train simple GPT-2 Small (124M) models on a 100M-token random sample of the FineWeb corpus and intervene by injecting a minimal amount (1%) of synthetic data targeting specific linguistic phenomena. We find that this targeted intervention substantially improves model performance in 8 out of the 9 worst-performing BLiMP paradigms - notably the accuracy on a specific paradigm, only_npi_scope, surges from 20.9% to 69.4%. Furthermore, we observe that these interventions generally preserve or slightly improve aggregate performance. However, while we also identify a resistant phenomenon, principle_A_c_command, whose performance remains below chance even after our data augmentation, our findings do serve as an optimistic existence proof that even small language models can substantially improve on those linguistic phenomena on which models typically perform poorly, provided the pre-training data contains sufficient exposure to them. This suggests that efforts towards human-scale language modeling may benefit greatly by focusing on data composition. The code to reproduce our results is open-sourced at https://github.com/kowndinya-renduchintala/heterogeneity-in-formal-linguistic-competence. --- ### HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment Authors: Zhanyu Liu, Qingguo Hu, Ante Wang, Chenqing Liu, Zhishang Xiang, Hui Li, Delai Qiu, Jinsong Su Published: 2026-04-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.17928v1 Reinforcement Learning with Verifiable Reward (RLVR) has proven effective for training reasoning-oriented large language models, but existing methods largely assume high-resource settings with abundant training data. In low-resource scenarios, RLVR is prone to more severe entropy collapse, which substantially limits exploration and degrades reasoning performance. To address this issue, we propose Hybrid-domain Entropy dynamics ALignment (HEAL), a framework tailored for few-shot RLVR. HEAL first selectively incorporates high-value general-domain data to promote more diverse exploration. Then, we introduce Entropy Dynamics Alignment (EDA), a reward mechanism that aligns trajectory-level entropy dynamics between the target and general domains, capturing both entropy magnitude and fine-grained variation. Through this alignment, EDA not only further mitigates entropy collapse but also encourages the policy to acquire more diverse exploration behaviors from the general domain. Experiments across multiple domains show that HEAL consistently improves few-shot RLVR performance. Notably, using only 32 target-domain samples, HEAL matches or even surpasses full-shot RLVR trained with 1K target-domain samples. --- ### Brain-Inspired Capture: Evidence-Driven Neuromimetic Perceptual Simulation for Visual Decoding Authors: Feixue Shao, Guangze Shi, Xueyu Liu, Yongfei Wu, Mingqiang Wei, Jianan Zhang, Jianbo Lu, Guiying Yan, Weihua Yang Published: 2026-04-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.17927v1 Visual decoding of neurophysiological signals is a critical challenge for brain-computer interfaces (BCIs) and computational neuroscience. However, current approaches are often constrained by the systematic and stochastic gaps between neural and visual modalities, largely neglecting the intrinsic computational mechanisms of the Human Visual System (HVS). To address this, we propose Brain-Inspired Capture (BI-Cap), a neuromimetic perceptual simulation paradigm that aligns these modalities by emulating HVS processing. Specifically, we construct a neuromimetic pipeline comprising four biologically plausible dynamic and static transformations, coupled with Mutual Information (MI)-guided dynamic blur regulation to simulate adaptive visual processing. Furthermore, to mitigate the inherent non-stationarity of neural activity, we introduce an evidence-driven latent space representation. This formulation explicitly models uncertainty, thereby ensuring robust neural embeddings. Extensive evaluations on zero-shot brain-to-image retrieval across two public benchmarks demonstrate that BI-Cap substantially outperforms state-of-the-art methods, achieving relative gains of 9.2\% and 8.0\%, respectively. We have released the source code on GitHub through the link https://github.com/flysnow1024/BI-Cap. --- ### Prompting Foundation Models for Zero-Shot Ship Instance Segmentation in SAR Imagery Authors: Islam Mansour, Francescopaolo Sica, Michael Schmitt Published: 2026-04-20 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.17920v1 Synthetic Aperture Radar (SAR) plays a critical role in maritime surveillance, yet deep learning for SAR analysis is limited by the lack of pixel-level annotations. This paper explores how general-purpose vision foundation models can enable zero-shot ship instance segmentation in SAR imagery, eliminating the need for pixel-level supervision. A YOLOv11-based detector trained on open SAR datasets localizes ships via bounding boxes, which then prompt the Segment Anything Model 2 (SAM2) to produce instance masks without any mask annotations. Unlike prior SAM-based SAR approaches that rely on fine tuning or adapters, our method demonstrates that spatial constraints from a SAR-trained detector alone can effectively regularize foundation model predictions. This design partially mitigates the optical-SAR domain gap and enables downstream applications such as vessel classification, size estimation, and wake analysis. Experiments on the SSDD benchmark achieve a mean IoU of 0.637 (89% of a fully supervised baseline) with an overall ship detection rate of 89.2%, confirming a scalable, annotation-efficient pathway toward foundation-model-driven SAR image understanding. --- ### Fisher Decorator: Refining Flow Policy via a Local Transport Map Authors: Xiaoyuan Cheng, Haoyu Wang, Wenxuan Yuan, Ziyan Wang, Zonghao Chen, Li Zeng, Zhuo Sun Published: 2026-04-20 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2604.17919v2 Recent advances in flow-based offline reinforcement learning (RL) have achieved strong performance by parameterizing policies via flow matching. However, they still face critical trade-offs among expressiveness, optimality, and efficiency. In particular, existing flow policies interpret the $L_2$ regularization as an upper bound of the 2-Wasserstein distance ($W_2$), which can be problematic in offline settings. This issue stems from a fundamental geometric mismatch: the behavioral policy manifold is inherently anisotropic, whereas the $L_2$ (or upper bound of $W_2$) regularization is isotropic and density-insensitive, leading to systematically misaligned optimization directions. To address this, we revisit offline RL from a geometric perspective and show that policy refinement can be formulated as a local transport map: an initial flow policy augmented by a residual displacement. By analyzing the induced density transformation, we derive a local quadratic approximation of the KL-constrained objective governed by the Fisher information matrix, enabling a tractable anisotropic optimization formulation. By leveraging the score function embedded in the flow velocity, we obtain a corresponding quadratic constraint for efficient optimization. Our results reveal that the optimality gap in prior methods arises from their isotropic approximation. In contrast, our framework achieves a controllable approximation error within a provable neighborhood of the optimal solution. Extensive experiments demonstrate state-of-the-art performance across diverse offline RL benchmarks. See project page: https://github.com/ARC0127/Fisher-Decorator. --- ### OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models Authors: Yiwei Zhang, Xuesong Chen, Jin Gao, Hanshi Wang, Fudong Ge, Weiming Hu, Shaoshuai Shi, Zhipeng Zhang Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17915v1 Vision-Language Models(VLMs) excel at autoregressive text generation, yet end-to-end autonomous driving requires multi-task learning with structured outputs and heterogeneous decoding behaviors, such as autoregressive language generation, parallel object detection and trajectory regression. To accommodate these differences, existing systems typically introduce separate or cascaded decoders, resulting in architectural fragmentation and limited backbone reuse. In this work, we present a unified autonomous driving framework built upon a pretrained VLM, where heterogeneous decoding behaviors are reconciled within a single transformer decoder. We demonstrate that pretrained VLM attention exhibits strong transferability beyond pure language modeling. By organizing visual and structured query tokens within a single causal decoder, structured queries can naturally condition on visual context through the original attention mechanism. Textual and structured outputs share a common attention backbone, enabling stable joint optimization across heterogeneous tasks. Trajectory planning is realized within the same causal LLM decoder by introducing structured trajectory queries. This unified formulation enables planning to share the pretrained attention backbone with images and perception tokens. Extensive experiments on end-to-end autonomous driving benchmarks demonstrate state-of-the-art performance, including 0.28 L2 and 0.18 collision rate on nuScenes open-loop evaluation and competitive results (86.8 PDMS) on NAVSIM closed-loop evaluation. The full model preserves multi-modal generation capability, while an efficient inference mode achieves approximately 40% lower latency. Code and models are available at https://github.com/Z1zyw/OneDrive --- ### Beyond Binary Contrast: Modeling Continuous Skeleton Action Spaces with Transitional Anchors Authors: Yingjie Feng, Yi Wang, Jiaze Wang, Anfeng Liu, Zhuotao Tian Published: 2026-04-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.17914v1 Self-supervised contrastive learning has emerged as a powerful paradigm for skeleton-based action recognition by enforcing consistency in the embedding space. However, existing methods rely on binary contrastive objectives that overlook the intrinsic continuity of human motion, resulting in fragmented feature clusters and rigid class boundaries. To address these limitations, we propose TranCLR, a Transitional anchor-based Contrastive Learning framework that captures the continuous geometry of the action space. Specifically, the proposed Action Transitional Anchor Construction (ATAC) explicitly models the geometric structure of transitional states to enhance the model's perception of motion continuity. Building upon these anchors, a Multi-Level Geometric Manifold Calibration (MGMC) mechanism is introduced to adaptively calibrate the action manifold across multiple levels of continuity, yielding a smoother and more discriminative representation space. Extensive experiments on the NTU RGB+D, NTU RGB+D 120 and PKU-MMD datasets demonstrate that TranCLR achieves superior accuracy and calibration performance, effectively learning continuous and uncertainty-aware skeleton representations. The code is available at https://github.com/Philchieh/TranCLR. --- ### Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought Authors: Muhammed Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga, Samet Oymak Published: 2026-04-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.17912v1 State-of-the-art reasoning models utilize long chain-of-thought (CoT) to solve increasingly complex problems using more test-time computation. In this work, we explore a long CoT setting where the model makes up to K successive attempts at solving a problem, in which each attempt is allowed to build on earlier ones after the model receives a hard verifier feedback. This motivates RL methods that can harness per-attempt rewards by carefully weighting individual attempts. We study optimizing the Verification@K reward (the model succeeds by the K-th attempt) and show that naively weighing the attempts by their pass/fail results in biased gradients. We introduce Calibrated Attempt-Level (CAL) GRPO by devising a weighing strategy to obtain unbiased gradients while maintaining small variance. Our theory reveals how incorporating per-attempt rewards influence the training and the eventual Verification@K performance. Experiments, baselines, and ablations on synthetic and real data corroborate our theory and the benefits of CAL-GRPO over vanilla GRPO as well as naive weighting. --- ### Physics-Informed Causal MDPs for Sequential Constraint Repair in Engineering Simulation Pipelines Authors: Chuhan Qiao Published: 2026-04-20 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.17910v1 Off-policy learning in constrained MDPs with large binary state spaces faces a fundamental tension: causal identification of transition dynamics requires structural assumptions, while sample-efficient policy learning requires state-space compression. We introduce PI-CMDP, a framework for CMDPs whose constraint dependencies form a layered DAG under a Lifecycle Ordering Assumption (LOA). We propose an Identify-Compress-Estimate pipeline: (i) Identify: LOA enables backdoor identification of causal edge weights for cross-layer pairs, with formal partial-identification bounds when LOA is violated; (ii) Compress: a Markov abstraction compresses state cardinality from 2^(WL) to (W+1)^L under layer-priority regularity and exchangeability; and (iii) Estimate: a physics-guided doubly-robust estimator remains unbiased and reduces the variance constant when the physics prior outperforms a learned model. We instantiate PI-CMDP on constraint repair in engineering simulation pipelines. On the TPS benchmark (4,206 episodes), PI-CMDP achieves 76.2% repair success rate with only 300 training episodes versus 70.8% for the strongest baseline (+5.4 pp), narrowing to +2.8 pp (83.4% vs. 80.6%) in the full-data regime, while substantially reducing cascade failure rates. All improvements are consistent across 5 independent seeds (paired t-test p < 0.02). ---