# Research Papers — 2026-04 · bundle page 194 of 233 > Full-text markdown of papers #9651–9700 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/194 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/193.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/195.md) ### Muon Dynamics as a Spectral Wasserstein Flow Authors: Gabriel Peyré Published: 2026-04-06 Categories: math.OC, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2604.04891v2 Gradient normalization stabilizes deep-learning optimization, and spectral normalizations are especially natural for matrix-shaped parameter blocks; Muon is the motivating example. We study an idealized deterministic, continuous-time, vanishing-momentum version of this idea in the mean-field regime, where wide models are represented by probability measures on parameter space. Starting from normalized matrix flows, we introduce Spectral Wasserstein distances indexed by norms $γ$ on positive semidefinite matrices: the trace norm gives classical $W_2$, the operator norm gives the Muon geometry, and Schatten norms interpolate between them. We develop the static Kantorovich formulation, a max-min robust-cost representation, Gaussian reductions extending the Bures formula, and for monotone norms, prove equivalence with a Benamou--Brenier formulation. This yields a gradient-flow interpretation of the mean-field normalized training dynamics. We illustrate these findings by numerical experiments on MMD flows, Gaussian reductions, two-layer ReLU models, and shallow attention. --- ### HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes Authors: Mauricio Soroco, Francesco Pittaluga, Zaid Tasneem, Abhishek Aich, Bingbing Zhuang, Wuyang Chen, Manmohan Chandraker, Ziyu Jiang Published: 2026-04-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.04887v1 Ensuring safety in autonomous driving requires scalable generation of realistic, controllable driving scenes beyond what real-world testing provides. Yet existing instruction guided image editors, trained on object-centric or artistic data, struggle with dense, safety-critical driving layouts. We propose HorizonWeaver, which tackles three fundamental challenges in driving scene editing: (1) multi-level granularity, requiring coherent object- and scene-level edits in dense environments; (2) rich high-level semantics, preserving diverse objects while following detailed instructions; and (3) ubiquitous domain shifts, handling changes in climate, layout, and traffic across unseen environments. The core of HorizonWeaver is a set of complementary contributions across data, model, and training: (1) Data: Large-scale dataset generation, where we build a paired real/synthetic dataset from Boreas, nuScenes, and Argoverse2 to improve generalization; (2) Model: Language-Guided Masks for fine-grained editing, where semantics-enriched masks and prompts enable precise, language-guided edits; and (3) Training: Content preservation and instruction alignment, where joint losses enforce scene consistency and instruction fidelity. Together, HorizonWeaver provides a scalable framework for photorealistic, instruction-driven editing of complex driving scenes, collecting 255K images across 13 editing categories and outperforming prior methods in L1, CLIP, and DINO metrics, achieving +46.4% user preference and improving BEV segmentation IoU by +33%. Project page: https://msoroco.github.io/horizonweaver/ --- ### Learning, Potential, and Retention: An Approach for Evaluating Adaptive AI-Enabled Medical Devices Authors: Alexis Burgon, Berkman Sahiner, Nicholas A Petrick, Gene Pennello, Ravi K Samala Published: 2026-04-06 Categories: cs.AI, cs.PF arXiv: https://arxiv.org/abs/2604.04878v1 This work addresses challenges in evaluating adaptive artificial intelligence (AI) models for medical devices, where iterative updates to both models and evaluation datasets complicate performance assessment. We introduce a novel approach with three complementary measurements: learning (model improvement on current data), potential (dataset-driven performance shifts), and retention (knowledge preservation across modification steps), to disentangle performance changes caused by model adaptations versus dynamic environments. Case studies using simulated population shifts demonstrate the approach's utility: gradual transitions enable stable learning and retention, while rapid shifts reveal trade-offs between plasticity and stability. These measurements provide practical insights for regulatory science, enabling rigorous assessment of the safety and effectiveness of adaptive AI systems over sequential modifications. --- ### Incompleteness of AI Safety Verification via Kolmogorov Complexity Authors: Munawar Hasan Published: 2026-04-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.04876v1 Ensuring that artificial intelligence (AI) systems satisfy formal safety and policy constraints is a central challenge in safety-critical domains. While limitations of verification are often attributed to combinatorial complexity and model expressiveness, we show that they arise from intrinsic information-theoretic limits. We formalize policy compliance as a verification problem over encoded system behaviors and analyze it using Kolmogorov complexity. We prove an incompleteness result: for any fixed sound computably enumerable verifier, there exists a threshold beyond which true policy-compliant instances cannot be certified once their complexity exceeds that threshold. Consequently, no finite formal verifier can certify all policy-compliant instances of arbitrarily high complexity. This reveals a fundamental limitation of AI safety verification independent of computational resources, and motivates proof-carrying approaches that provide instance-level correctness guarantees. --- ### DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing Authors: Ke Li, Maoliang Li, Jialiang Chen, Jiayu Chen, Zihao Zheng, Shaoqi Wang, Xiang Chen Published: 2026-04-06 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2604.04875v1 Video mashup creation represents a complex video editing paradigm that recomposes existing footage to craft engaging audio-visual experiences, demanding intricate orchestration across semantic, visual, and auditory dimensions and multiple levels. However, existing automated editing frameworks often overlook the cross-level multimodal orchestration to achieve professional-grade fluidity, resulting in disjointed sequences with abrupt visual transitions and musical misalignment. To address this, we formulate video mashup creation as a Multimodal Coherency Satisfaction Problem (MMCSP) and propose the DIRECT framework. Simulating a professional production pipeline, our hierarchical multi-agent framework decomposes the challenge into three cascade levels: the Screenwriter for source-aware global structural anchoring, the Director for instantiating adaptive editing intent and guidance, and the Editor for intent-guided shot sequence editing with fine-grained optimization. We further introduce Mashup-Bench, a comprehensive benchmark with tailored metrics for visual continuity and auditory alignment. Extensive experiments demonstrate that DIRECT significantly outperforms state-of-the-art baselines in both objective metrics and human subjective evaluation. Project page and code: https://github.com/AK-DREAM/DIRECT --- ### Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction Authors: Ahan Shabanov, Peter Hedman, Ethan Weber, Zhengqin Li, Denis Rozumny, Gael Le Lan, Naina Dhingra, Lei Luo, Andrea Vedaldi, Christian Richardt, Andrea Tagliasacchi, Bo Zhu et al. Published: 2026-04-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.04874v1 We present Free-Range Gaussians, a multi-view reconstruction method that predicts non-pixel, non-voxel-aligned 3D Gaussians from as few as four images. This is done through flow matching over Gaussian parameters. Our generative formulation of reconstruction allows the model to be supervised with non-grid-aligned 3D data, and enables it to synthesize plausible content in unobserved regions. Thus, it improves on prior methods that produce highly redundant grid-aligned Gaussians, and suffer from holes or blurry conditional means in unobserved regions. To handle the number of Gaussians needed for high-quality results, we introduce a hierarchical patching scheme to group spatially related Gaussians into joint transformer tokens, halving the sequence length while preserving structure. We further propose a timestep-weighted rendering loss during training, and photometric gradient guidance and classifier-free guidance at inference to improve fidelity. Experiments on Objaverse and Google Scanned Objects show consistent improvements over pixel and voxel-aligned methods while using significantly fewer Gaussians, with large gains when input views leave parts of the object unobserved. --- ### Synthetic Sandbox for Training Machine Learning Engineering Agents Authors: Yuhang Zhou, Lizhu Zhang, Yifan Wu, Jiayi Liu, Xiangjun Fan, Zhuokai Zhao, Hong Yan Published: 2026-04-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.04872v1 As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more expensive: while SWE tasks can be verified via fast-executing unit tests, MLE verification requires running full ML pipelines -- data preprocessing, model training, and metric evaluation -- on large datasets at each rollout step, rendering trajectory-wise on-policy reinforcement learning (RL) prohibitively slow. Existing approaches retreat to supervised fine-tuning (SFT) or offline proxy rewards, sacrificing the exploration and generalization benefits of on-policy RL. We observe that sandbox data size is the primary source of this bottleneck. Based on this insight, we introduce SandMLE, a multi-agent framework that generates diverse, verifiable synthetic MLE environments from a small number of seed tasks, preserving the structural and technical complexity of real-world problems while constraining datasets to micro-scale (each task is paired with only 50-200 training samples). Through extensive experiments, we show that SandMLE reduces execution time by over 13 times, enabling large-scale, on-policy trajectory-wise RL for the first time in the MLE domain. On MLE-bench-lite, SandMLE yields significant gains over SFT baselines across Qwen3-8B, 14B, and 30B-A3B, with relative medal rate improvements ranging from 20.3% to 66.9%. Furthermore, the trained policy generalizes across unseen agentic scaffolds, achieving up to 32.4% better HumanRank score on MLE-Dojo. --- ### Optimizing LLM Prompt Engineering with DSPy Based Declarative Learning Authors: Shiek Ruksana, Sailesh Kiran Kurra, Thipparthi Sanjay Baradwaj Published: 2026-04-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.04869v1 Large Language Models (LLMs) have shown strong performance across a wide range of natural language processing tasks; however, their effectiveness is highly dependent on prompt design, structure, and embedded reasoning signals. Conventional prompt engineering methods largely rely on heuristic trial-and-error processes, which limits scalability, reproducibility, and generalization across tasks. DSPy, a declarative framework for optimizing text-processing pipelines, offers an alternative approach by enabling automated, modular, and learnable prompt construction for LLM-based systems.This paper presents a systematic study of DSPy-based declarative learning for prompt optimization, with emphasis on prompt synthesis, correction, calibration, and adaptive reasoning control. We introduce a unified DSPy LLM architecture that combines symbolic planning, gradient free optimization, and automated module rewriting to reduce hallucinations, improve factual grounding, and avoid unnecessary prompt complexity. Experimental evaluations conducted on reasoning tasks, retrieval-augmented generation, and multi-step chain-of-thought benchmarks demonstrate consistent gains in output reliability, efficiency, and generalization across models. The results show improvements of up to 30 to 45% in factual accuracy and a reduction of approximately 25% in hallucination rates. Finally, we outline key limitations and discuss future research directions for declarative prompt optimization frameworks. --- ### Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms Authors: James Hu, Mahdi Ghelichi Published: 2026-04-06 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2604.04868v2 Tabular foundation models (TFMs) such as TabPFN (Tabular Prior-Data Fitted Network) are designed to generalize across heterogeneous tabular datasets through in-context learning (ICL). They perform prediction in a single forward pass conditioned on labeled examples without dataset-specific parameter updates. This paradigm is particularly attractive in industrial domains (e.g., finance and healthcare) where tabular prediction is pervasive. Retraining a bespoke model for each new table can be costly or infeasible in these settings, while data quality issues such as irrelevant predictors, correlated feature groups, and label noise are common. In this paper, we provide strong empirical evidence that TabPFN is highly robust under these sub-optimal conditions. We study TabPFN and its attention mechanisms for binary classification problems with controlled synthetic perturbations that vary: (i) dataset width by injecting random uncorrelated features and by introducing nonlinearly correlated features, (ii) dataset size by increasing the number of training rows, and (iii) label quality by increasing the fraction of mislabeled targets. Beyond predictive performance, we analyze internal signals including attention concentration and attention-based feature ranking metrics. Across these parametric tests, TabPFN is remarkably resilient: ROC-AUC remains high, attention stays structured and sharp, and informative features are highly ranked by attention-based metrics. Qualitative visualizations with attention heatmaps, feature-token embeddings, and SHAP plots further support a consistent pattern across layers in which TabPFN increasingly concentrates on useful features while separating their signals from noise. Together, these findings suggest that TabPFN is a robust TFM capable of maintaining both predictive performance and coherent internal behavior under various scenarios of data imperfections. --- ### Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations Authors: Tuan Dung Nguyen, Minh Khoi Ho, Qi Chen, Yutong Xie, Nguyen Cam-Tu, Minh Khoi Nguyen, Dang Huy Pham Nguyen, Anton van den Hengel, Johan W. Verjans, Phi Le Nguyen, Vu Minh Hieu Phan Published: 2026-04-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.04863v1 Large vision-language models (LVLMs) achieve strong performance on visual reasoning tasks but remain highly susceptible to hallucination. Existing detection methods predominantly rely on coarse, whole-image measures of how an object token relates to the input image. This global strategy is limited: hallucinated tokens may exhibit weak but widely scattered correlations across many local regions, which aggregate into deceptively high overall relevance, thus evading the current global hallucination detectors. We begin with a simple yet critical observation: a faithful object token must be strongly grounded in a specific image region. Building on this insight, we introduce a patch-level hallucination detection framework that examines fine-grained token-level interactions across model layers. Our analysis uncovers two characteristic signatures of hallucinated tokens: (i) they yield diffuse, non-localized attention patterns, in contrast to the compact, well-focused attention seen in faithful tokens; and (ii) they fail to exhibit meaningful semantic alignment with any visual region. Guided by these findings, we develop a lightweight and interpretable detection method that leverages patch-level statistical features, combined with hidden-layer representations. Our approach achieves up to 90% accuracy in token-level hallucination detection, demonstrating the superiority of fine-grained structural analysis for detecting hallucinations. --- ### Unified Vector Floorplan Generation via Markup Representation Authors: Kaede Shiohara, Toshihiko Yamasaki Published: 2026-04-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.04859v1 Automatic residential floorplan generation has long been a central challenge bridging architecture and computer graphics, aiming to make spatial design more efficient and accessible. While early methods based on constraint satisfaction or combinatorial optimization ensure feasibility, they lack diversity and flexibility. Recent generative models achieve promising results but struggle to generalize across heterogeneous conditional tasks, such as generation from site boundaries, room adjacency graphs, or partial layouts, due to their suboptimal representations. To address this gap, we introduce Floorplan Markup Language (FML), a general representation that encodes floorplan information within a single structured grammar, which casts the entire floorplan generation problem into a next token prediction task. Leveraging FML, we develop a transformer-based generative model, FMLM, capable of producing high-fidelity and functional floorplans under diverse conditions. Comprehensive experiments on the RPLAN dataset demonstrate that FMLM, despite being a single model, surpasses the previous task-specific state-of-the-art methods. --- ### FairLogue: A Toolkit for Intersectional Fairness Analysis in Clinical Machine Learning Models Authors: Nick Souligne, Vignesh Subbian Published: 2026-04-06 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2604.04858v1 Objective: Algorithmic fairness is essential for equitable and trustworthy machine learning in healthcare. Most fairness tools emphasize single-axis demographic comparisons and may miss compounded disparities affecting intersectional populations. This study introduces Fairlogue, a toolkit designed to operationalize intersectional fairness assessment in observational and counterfactual contexts within clinical settings. Methods: Fairlogue is a Python-based toolkit composed of three components: 1) an observational framework extending demographic parity, equalized odds, and equal opportunity difference to intersectional populations; 2) a counterfactual framework evaluating fairness under treatment-based contexts; and 3) a generalized counterfactual framework assessing fairness under interventions on intersectional group membership. The toolkit was evaluated using electronic health record data from the All of Us Controlled Tier V8 dataset in a glaucoma surgery prediction task using logistic regression with race and gender as protected attributes. Results: Observational analysis identified substantial intersectional disparities despite moderate model performance (AUROC = 0.709; accuracy = 0.651). Intersectional evaluation revealed larger fairness gaps than single-axis analyses, including demographic parity differences of 0.20 and equalized odds true positive and false positive rate gaps of 0.33 and 0.15, respectively. Counterfactual analysis using permutation-based null distributions produced unfairness ("u-value") estimates near zero, suggesting observed disparities were consistent with chance after conditioning on covariates. Conclusion: Fairlogue provides a modular toolkit integrating observational and counterfactual methods for quantifying and evaluating intersectional bias in clinical machine learning workflows. --- ### The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Models Authors: Runhao Mao, Hanshi Wang, Yixiang Yang, Qianli Ma, Jingmeng Zhou, Zhipeng Zhang Published: 2026-04-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.04857v1 The integration of Vision-Language Models (VLMs) into autonomous driving promises to solve long-tail scenarios, but this paradigm faces the critical and unaddressed challenge of catastrophic forgetting. The very fine-tuning process used to adapt these models to driving-specific data simultaneously erodes their invaluable pre-trained world knowledge, creating a self-defeating paradox that undermines the core reason for their use. This paper provides the first systematic investigation into this phenomenon. We introduce a new large-scale dataset of 180K scenes, which enables the first-ever benchmark specifically designed to quantify catastrophic forgetting in autonomous driving. Our analysis reveals that existing methods suffer from significant knowledge degradation. To address this, we propose the Drive Expert Adapter (DEA), a novel framework that circumvents this trade-off by shifting adaptation from the weight space to the prompt space. DEA dynamically routes inference through different knowledge experts based on scene-specific cues, enhancing driving-task performance without corrupting the model's foundational parameters. Extensive experiments demonstrate that our approach not only achieves state-of-the-art results on driving tasks but also effectively mitigates catastrophic forgetting, preserving the essential generalization capabilities that make VLMs a transformative force for autonomous systems. Data and model are released at FidelityDrivingBench. --- ### The Role of Generator Access in Autoregressive Post-Training Authors: Amit Kiran Rege Published: 2026-04-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.04855v1 We study how generator access constrains autoregressive post-training. The central question is whether the learner is confined to fresh root-start rollouts or can return to previously built prefixes and query the next-token rule there. In the root-start regime, output sampling, generated-token log probabilities, top-$k$ reports, and full next-token distributions along sampled trajectories all reduce to one canonical experiment, limited by the on-policy probability of reaching informative prefixes. Weak prefix control breaks this barrier, and once control is available, richer observations such as conditional sampling or logits can outperform top-$1$ access. Changing only the generator interface creates an exponential gap for KL-regularized outcome-reward post-training. --- ### MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents Authors: Shu Wang, Edwin Yu, Oscar Love, Tom Zhang, Tom Wong, Steve Scargall, Charles Fan Published: 2026-04-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.04853v1 Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-augmented generation (RAG) pipelines degrade over multi-session interactions. We present MemMachine, an open-source memory system that integrates short-term, long-term episodic, and profile memory within a ground-truth-preserving architecture that stores entire conversational episodes and reduces lossy LLM-based extraction. MemMachine uses contextualized retrieval that expands nucleus matches with surrounding context, improving recall when relevant evidence spans multiple dialogue turns. Across benchmarks, MemMachine achieves strong accuracy-efficiency tradeoffs: on LoCoMo it reaches 0.9169 using gpt4.1-mini; on LongMemEvalS (ICLR 2025), a six-dimension ablation yields 93.0 percent accuracy, with retrieval-stage optimizations -- retrieval depth tuning (+4.2 percent), context formatting (+2.0 percent), search prompt design (+1.8 percent), and query bias correction (+1.4 percent) -- outperforming ingestion-stage gains such as sentence chunking (+0.8 percent). GPT-5-mini exceeds GPT-5 by 2.6 percent when paired with optimized prompts, making it the most cost-efficient setup. Compared to Mem0, MemMachine uses roughly 80 percent fewer input tokens under matched conditions. A companion Retrieval Agent adaptively routes queries among direct retrieval, parallel decomposition, or iterative chain-of-query strategies, achieving 93.2 percent on HotpotQA-hard and 92.6 percent on WikiMultiHop under randomized-noise conditions. These results show that preserving episodic ground truth while layering adaptive retrieval yields robust, efficient long-term memory for personalized LLM agents. --- ### Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework Authors: Jiling Zhou, Aisvarya Adeseye, Seppo Virtanen, Antti Hakkala, Jouni Isoaho Published: 2026-04-06 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.04852v1 Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation. Alternative approaches, such as model scaling and fine-tuning can be used to help improve performance. These methods are also often costly, computationally intensive, or difficult to audit. In contrast, prompt engineering provides a lightweight, transparent, and controllable mechanism for guiding LLM reasoning. This study proposes a structured prompt engineering framework designed to strengthen CoT reasoning integrity while improving security threat and attack detection reliability in local LLM deployments. The framework includes 16 factors grouped into four core dimensions: (1) Context and Scope Control, (2) Evidence Grounding and Traceability, (3) Reasoning Structure and Cognitive Control, and (4) Security-Specific Analytical Constraints. Rather than optimizing the wording of the prompt heuristically, the framework introduces explicit reasoning controls to mitigate hallucination and prevent reasoning drift, as well as strengthening interpretability in security-sensitive contexts. Using DDoS attack detection in SDN traffic as a case study, multiple model families were evaluated under structured and unstructured prompting conditions. Pareto frontier analysis and ablation experiments demonstrate consistent reasoning improvements (up to 40% in smaller models) and stable accuracy gains across scales. Human evaluation with strong inter-rater agreement (Cohen's k > 0.80) confirms robustness. The results establish structured prompting as an effective and practical approach for reliable and explainable AI-driven cybersecurity analysis. --- ### Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency Authors: Guan-Ting Lin, Chen Chen, Zhehuai Chen, Hung-yi Lee Published: 2026-04-06 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2604.04847v1 We introduce Full-Duplex-Bench-v3 (FDB-v3), a benchmark for evaluating spoken language models under naturalistic speech conditions and multi-step tool use. Unlike prior work, our dataset consists entirely of real human audio annotated for five disfluency categories, paired with scenarios requiring chained API calls across four task domains. We evaluate six model configurations -- GPT-Realtime, Gemini Live 2.5, Gemini Live 3.1, Grok, Ultravox v0.7, and a traditional Cascaded pipeline (Whisper$\rightarrow$GPT-4o$\rightarrow$TTS) -- across accuracy, latency, and turn-taking dimensions. GPT-Realtime leads on Pass@1 (0.600) and interruption avoidance (13.5\%); Gemini Live 3.1 achieves the fastest latency (4.25~s) but the lowest turn-take rate (78.0\%); and the Cascaded baseline, despite a perfect turn-take rate, incurs the highest latency (10.12~s). Across all systems, self-correction handling and multi-step reasoning under hard scenarios remain the most consistent failure modes. --- ### InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement Authors: Yude Zou, Junji Gong, Xing Gao, Zixuan Li, Tianxing Chen, Guanjie Zheng Published: 2026-04-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.04843v1 Human-object-scene interactions (HOSI) generation has broad applications in embodied AI, simulation, and animation. Unlike human-object interaction (HOI) and human-scene interaction (HSI), HOSI generation requires reasoning over dynamic object-scene changes, yet suffers from limited annotated data. To address these issues, we propose a coarse-to-fine instruction-conditioned interaction generation framework that is explicitly aligned with the iterative denoising process of a consistency model. In particular, we adopt a dynamic perception strategy that leverages trajectories from the preceding refinement to update scene context and condition subsequent refinement at each denoising step of consistency model, yielding consistent interactions. To further reduce physical artifacts, we introduce a bump-aware guidance that mitigates collisions and penetrations during sampling without requiring fine-grained scene geometry, enabling real-time generation. To overcome data scarcity, we design a hybrid training startegy that synthesizes pseudo-HOSI samples by injecting voxelized scene occupancy into HOI datasets and jointly trains with high-fidelity HSI data, allowing interaction learning while preserving realistic scene awareness. Extensive experiments demonstrate that our method achieves state-of-the-art performance in both HOSI and HOI generation, and strong generalization to unseen scenes. Project page: https://yudezou.github.io/InfBaGel-page/ --- ### Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling Authors: Qingyang Xu, Yaling Shen, Stephanie Fong, Zimu Wang, Yiwen Jiang, Xiangyu Zhao, Jiahe Liu, Zhongxing Xu, Vincent Lee, Zongyuan Ge Published: 2026-04-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.04842v2 The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive responses may inadvertently reinforce harmful beliefs or behaviors in multi-turn conversations. This risk is largely overlooked by existing red-teaming frameworks, which focus mainly on generic harms or optimization-based attacks. To address this gap, we introduce Personality-based Client Simulation Attack (PCSA), the first red-teaming framework that simulates clients in psychological counseling through coherent, persona-driven client dialogues to expose vulnerabilities in psychological safety alignment. Experiments on seven general and mental health-specialized LLMs show that PCSA substantially outperforms four competitive baselines. Perplexity analysis and human inspection further indicate that PCSA generates more natural and realistic dialogues. Our results reveal that current LLMs remain vulnerable to domain-specific adversarial tactics, providing unauthorized medical advice, reinforcing delusions, and implicitly encouraging risky actions. --- ### Do No Harm: Exposing Hidden Vulnerabilities of LLMs via Persona-based Client Simulation Attack in Psychological Counseling Authors: Qingyang Xu, Yaling Shen, Stephanie Fong, Zimu Wang, Yiwen Jiang, Xiangyu Zhao, Jiahe Liu, Zhongxing Xu, Vincent Lee, Zongyuan Ge Published: 2026-04-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.04842v1 The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive responses may inadvertently reinforce harmful beliefs or behaviors in multi-turn conversations. This risk is largely overlooked by existing red-teaming frameworks, which focus mainly on generic harms or optimization-based attacks. To address this gap, we introduce Personality-based Client Simulation Attack (PCSA), the first red-teaming framework that simulates clients in psychological counseling through coherent, persona-driven client dialogues to expose vulnerabilities in psychological safety alignment. Experiments on seven general and mental health-specialized LLMs show that PCSA substantially outperforms four competitive baselines. Perplexity analysis and human inspection further indicate that PCSA generates more natural and realistic dialogues. Our results reveal that current LLMs remain vulnerable to domain-specific adversarial tactics, providing unauthorized medical advice, reinforcing delusions, and implicitly encouraging risky actions. --- ### MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translation Authors: Zhixiang Lu, Chong Zhang, Chenyu Xue, Angelos Stefanidis, Chong Li, Jionglong Su, Zhengyong Jiang Published: 2026-04-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.04839v1 Neural machine translation (NMT) from Chinese to low-resource Southeast Asian languages remains severely constrained by the extreme scarcity of clean parallel corpora and the pervasive noise in existing mined data. This chronic shortage not only impedes effective model training but also sustains a large performance gap with high-resource directions, leaving millions of speakers of languages such as Lao, Burmese, and Tagalog with persistently low-quality translation systems despite recent advances in large multilingual models. We introduce \textbf{M}ultilingual \textbf{E}xpert-\textbf{R}eward \textbf{I}nformed \textbf{T}uning (\textbf{MERIT}), a unified translation framework that transforms the traditional English-centric ALT benchmark into a Chinese-centric evaluation suite for five Southeast Asian low-resource languages (LRLs). Our framework combines language-specific token prefixing (LTP) with supervised fine-tuning (SFT) and a novel group relative policy optimization (GRPO) guided by the semantic alignment reward (SAR). These results confirm that, in LRL{\textrightarrow}Chinese translation, targeted data curation and reward-guided optimization dramatically outperform mere model scaling. --- ### Less Detail, Better Answers: Degradation-Driven Prompting for VQA Authors: Haoxuan Han, Weijie Wang, Zeyu Zhang, Yefei He, Bohan Zhuang Published: 2026-04-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.04838v2 Recent advancements in Vision-Language Models (VLMs) have significantly pushed the boundaries of Visual Question Answering (VQA).However,high-resolution details can sometimes become noise that leads to hallucinations or reasoning errors. In this paper,we propose Degradation-Driven Prompting (DDP), a novel framework that improves VQA performance by strategically reducing image fidelity to force models to focus on essential structural information. We evaluate DDP across two distinct tasks. Physical attributes targets images prone to human misjudgment, where DDP employs a combination of 80p downsampling, structural visual aids (white background masks and orthometric lines), and In-Context Learning (ICL) to calibrate the model's focus. Perceptual phenomena addresses various machine-susceptible visual anomalies and illusions, including Visual Anomaly (VA), Color (CI), Motion(MI),Gestalt (GI), Geometric (GSI), and Visual Illusions (VI).For this task, DDP integrates a task-classification stage with specialized tools such as blur masks and contrast enhancement alongside downsampling. Our experimental results demonstrate that less is more: by intentionally degrading visual inputs and providing targeted structural prompts, DDP enables VLMs to bypass distracting textures and achieve superior reasoning accuracy on challenging visual benchmarks. --- ### E-VLA: Event-Augmented Vision-Language-Action Model for Dark and Blurred Scenes Authors: Jiajun Zhai, Hao Shi, Shangwei Guo, Kailun Yang, Kaiwei Wang Published: 2026-04-06 Categories: cs.CV, cs.MM, cs.RO, eess.IV arXiv: https://arxiv.org/abs/2604.04834v2 Robotic Vision-Language-Action (VLA) models generalize well for open-ended manipulation, but their perception is fragile under sensing-stage degradations such as extreme low light, motion blur, and black clipping. We present E-VLA, an event-augmented VLA framework that improves manipulation robustness when conventional frame-based vision becomes unreliable. Instead of reconstructing images from events, E-VLA directly leverages motion and structural cues in event streams to preserve semantic perception and perception-action consistency under adverse conditions. We build an open-source teleoperation platform with a DAVIS346 event camera and collect a real-world synchronized RGB-event-action manipulation dataset across diverse tasks and illuminations. We also propose lightweight, pretrained-compatible event integration strategies and study event windowing for stable deployment. Experiments show that even a simple parameter-free fusion, i.e., overlaying accumulated event maps onto RGB images, could substantially improve robustness in dark and heavy-blur scenes: on Pick-Place at 20 lux, success increases from 0% (image-only) to 60% with overlay fusion and to 90% with our event adapter; under severe motion blur (1000 ms-exposure proxy), Pick-Place improves from 0% to 20-25%, and Sorting from 5% to 32.5%. Overall, E-VLA provides systematic evidence that event-driven perception can be effectively integrated into VLA models, pointing toward robust embodied intelligence beyond conventional frame-based imaging. Code and dataset will be available at https://github.com/JJayzee/E-VLA. --- ### A Robust SINDy Autoencoder for Noisy Dynamical System Identification Authors: Kairui Ding Published: 2026-04-06 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2604.04829v1 Sparse identification of nonlinear dynamics (SINDy) has been widely used to discover the governing equations of a dynamical system from data. It uses sparse regression techniques to identify parsimonious models of unknown systems from a library of candidate functions. Therefore, it relies on the assumption that the dynamics are sparsely represented in the coordinate system used. To address this limitation, one seeks a coordinate transformation that provides reduced coordinates capable of reconstructing the original system. Recently, SINDy autoencoders have extended this idea by combining sparse model discovery with autoencoder architectures to learn simplified latent coordinates together with parsimonious governing equations. A central challenge in this framework is robustness to measurement error. Inspired by noise-separating neural network structures, we incorporate a noise-separation module into the SINDy autoencoder architecture, thereby improving robustness and enabling more reliable identification of noisy dynamical systems. Numerical experiments on the Lorenz system show that the proposed method recovers interpretable latent dynamics and accurately estimates the measurement noise from noisy observations. --- ### Hybrid Fourier Neural Operator for Surrogate Modeling of Laser Processing with a Quantum-Circuit Mixer Authors: Mateusz Papierz, Asel Sagingalieva, Alix Benoit, Toni Ivas, Elia Iseli, Alexey Melnikov Published: 2026-04-06 Categories: quant-ph, cs.CE, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2604.04828v1 Data-driven surrogates can replace expensive multiphysics solvers for parametric PDEs, yet building compact, accurate neural operators for three-dimensional problems remains challenging: in Fourier Neural Operators, dense mode-wise spectral channel mixing scales linearly with the number of retained Fourier modes, inflating parameter counts and limiting real-time deployability. We introduce HQ-LP-FNO, a hybrid quantum-classical FNO that replaces a configurable fraction of these dense spectral blocks with a compact, mode-shared variational quantum circuit mixer whose parameter count is independent of the Fourier mode budget. A parameter-matched classical bottleneck control is co-designed to provide a rigorous evaluation framework. Evaluated on three-dimensional surrogate modeling of high-energy laser processing, coupling heat transfer, melt-pool convection, free-surface deformation, and phase change, HQ-LP-FNO reduces trainable parameters by 15.6% relative to a classical baseline while lowering phase-fraction mean absolute error by 26% and relative temperature MAE from 2.89% to 2.56%. A sweep over the quantum-channel budget reveals that a moderate VQC allocation yields the best temperature metrics across all tested configurations, including the fully classical baseline, pointing toward an optimal classical-quantum partitioning. The ablation confirms that mode-shared mixing, naturally implemented by the VQC through its compact circuit structure, is the dominant contributor to these improvements. A noisy-simulator study under backend-calibrated noise from ibm-torino confirms numerical stability of the quantum mixer across the tested shot range. These results demonstrate that VQC-based parameter-efficient spectral mixing can improve neural operator surrogates for complex multiphysics problems and establish a controlled evaluation protocol for hybrid quantum operator learning in practice. --- ### Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not Authors: Sercan Karakaş Published: 2026-04-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.04825v2 Large language models achieve strong performance on many language tasks, yet it remains unclear whether they integrate world knowledge with syntactic structure in a human-like, structure-sensitive way during ambiguity resolution. We test this question in Turkish prenominal relative-clause attachment ambiguities, where the same surface string permits high attachment (HA) or low attachment (LA). We construct ambiguous items that keep the syntactic configuration fixed and ensure both parses remain pragmatically possible, while graded event plausibility selectively favors High Attachment vs.\ Low Attachment. The contrasts are validated with independent norming ratings. In a speeded forced-choice comprehension experiment, humans show a large, correctly directed plausibility effect. We then evaluate Turkish and multilingual LLMs in a parallel preference-based setup that compares matched HA/LA continuations via mean per-token log-probability. Across models, plausibility-driven shifts are weak, unstable, or reversed. The results suggest that, in the tested models, plausibility information does not guide attachment preferences as reliably as it does in human judgments, and they highlight Turkish RC attachment as a useful cross-linguistic diagnostic beyond broad benchmarks. --- ### ANX: Protocol-First Design for AI Agent Interaction with a Supporting 3EX Decoupled Architecture Authors: Xu Mingze Published: 2026-04-06 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.04820v1 AI agents, autonomous digital actors, need agent-native protocols; existing methods include GUI automation and MCP-based skills, with defects of high token consumption, fragmented interaction, inadequate security, due to lacking a unified top-level framework and key components, each independent module flawed. To address these issues, we present ANX, an open, extensible, verifiable agent-native protocol and top-level framework integrating CLI, Skill, MCP, resolving pain points via protocol innovation, architectural optimization and tool supplementation. Its four core innovations: 1) Agent-native design (ANX Config, Markup, CLI) with high information density, flexibility and strong adaptability to reduce tokens and eliminate inconsistencies; 2) Human-agent interaction combining Skill's flexibility for dual rendering as agent-executable instructions and human-readable UI; 3) MCP-supported on-demand lightweight apps without pre-registration; 4) ANX Markup-enabled machine-executable SOPs eliminating ambiguity for reliable long-horizon tasks and multi-agent collaboration. As the first in a series, we focus on ANX's design, present its 3EX decoupled architecture with ANXHub and preliminary feasibility analysis and experimental validation. ANX ensures native security: LLM-bypassed UI-to-Core communication keeps sensitive data out of agent context; human-only confirmation prevents automated misuse. Form-filling experiments with Qwen3.5-plus/GPT-4o show ANX reduces tokens by 47.3% (Qwen3.5-plus) and 55.6% (GPT-4o) vs MCP-based skills, 57.1% (Qwen3.5-plus) and 66.3% (GPT-4o) vs GUI automation, and shortens execution time by 58.1% and 57.7% vs MCP-based skills. --- ### LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection Authors: Cheng Xu, Changhong Jin, Yingjie Niu, Nan Yan, Yuke Mei, Shuhao Guan, Liming Chen, M-Tahar Kechadi Published: 2026-04-06 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.04815v2 The rapid development of Large Language Models (LLMs) has transformed fake news detection and fact-checking tasks from simple classification to complex reasoning. However, evaluation frameworks have not kept pace. Current benchmarks are static, making them vulnerable to benchmark data contamination (BDC) and ineffective at assessing reasoning under temporal uncertainty. To address this, we introduce LiveFact a continuously updated benchmark that simulates the real-world "fog of war" in misinformation detection. LiveFact uses dynamic, temporal evidence sets to evaluate models on their ability to reason with evolving, incomplete information rather than on memorized knowledge. We propose a dual-mode evaluation: Classification Mode for final verification and Inference Mode for evidence-based reasoning, along with a component to monitor BDC explicitly. Tests with 22 LLMs show that open-source Mixture-of-Experts models, such as Qwen3-235B-A22B, now match or outperform proprietary state-of-the-art systems. More importantly, our analysis finds a significant "reasoning gap." Capable models exhibit epistemic humility by recognizing unverifiable claims in early data slices-an aspect traditional static benchmarks overlook. LiveFact sets a sustainable standard for evaluating robust, temporally aware AI verification. --- ### AnyUser: Translating Sketched User Intent into Domestic Robots Authors: Songyuan Yang, Huibin Tan, Kailun Yang, Wenjing Yang, Shaowu Yang Published: 2026-04-06 Categories: cs.RO, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2604.04811v1 We introduce AnyUser, a unified robotic instruction system for intuitive domestic task instruction via free-form sketches on camera images, optionally with language. AnyUser interprets multimodal inputs (sketch, vision, language) as spatial-semantic primitives to generate executable robot actions requiring no prior maps or models. Novel components include multimodal fusion for understanding and a hierarchical policy for robust action generation. Efficacy is shown via extensive evaluations: (1) Quantitative benchmarks on the large-scale dataset showing high accuracy in interpreting diverse sketch-based commands across various simulated domestic scenes. (2) Real-world validation on two distinct robotic platforms, a statically mounted 7-DoF assistive arm (KUKA LBR iiwa) and a dual-arm mobile manipulator (Realman RMC-AIDAL), performing representative tasks like targeted wiping and area cleaning, confirming the system's ability to ground instructions and execute them reliably in physical environments. (3) A comprehensive user study involving diverse demographics (elderly, simulated non-verbal, low technical literacy) demonstrating significant improvements in usability and task specification efficiency, achieving high task completion rates (85.7%-96.4%) and user satisfaction. AnyUser bridges the gap between advanced robotic capabilities and the need for accessible non-expert interaction, laying the foundation for practical assistive robots adaptable to real-world human environments. --- ### Selecting Decision-Relevant Concepts in Reinforcement Learning Authors: Naveen Raman, Stephanie Milani, Fei Fang Published: 2026-04-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.04808v1 Training interpretable concept-based policies requires practitioners to manually select which human-understandable concepts an agent should reason with when making sequential decisions. This selection demands domain expertise, is time-consuming and costly, scales poorly with the number of candidates, and provides no performance guarantees. To overcome this limitation, we propose the first algorithms for principled automatic concept selection in sequential decision-making. Our key insight is that concept selection can be viewed through the lens of state abstraction: intuitively, a concept is decision-relevant if removing it would cause the agent to confuse states that require different actions. As a result, agents should rely on decision-relevant concepts; states with the same concept representation should share the same optimal action, which preserves the optimal decision structure of the original state space. This perspective leads to the Decision-Relevant Selection (DRS) algorithm, which selects a subset of concepts from a candidate set, along with performance bounds relating the selected concepts to the performance of the resulting policy. Empirically, DRS automatically recovers manually curated concept sets while matching or exceeding their performance, and improves the effectiveness of test-time concept interventions across reinforcement learning benchmarks and real-world healthcare environments. --- ### SkillX: Automatically Constructing Skill Knowledge Bases for Agents Authors: Chenxi Wang, Zhuoyun Yu, Xin Xie, Wuguannan Yao, Runnan Fang, Shuofei Qiao, Kexin Cao, Guozhou Zheng, Xiang Qi, Peng Zhang, Shumin Deng Published: 2026-04-06 Categories: cs.CL, cs.AI, cs.IR, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2604.04804v2 Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited experience, resulting in redundant exploration and poor generalization. To address this problem, we propose SkillX, a fully automated framework for constructing a \textbf{plug-and-play skill knowledge base} that can be reused across agents and environments. SkillX operates through a fully automated pipeline built on three synergistic innovations: \textit{(i) Multi-Level Skills Design}, which distills raw trajectories into three-tiered hierarchy of strategic plans, functional skills, and atomic skills; \textit{(ii) Iterative Skills Refinement}, which automatically revises skills based on execution feedback to continuously improve library quality; and \textit{(iii) Exploratory Skills Expansion}, which proactively generates and validates novel skills to expand coverage beyond seed training data. Using a strong backbone agent (GLM-4.6), we automatically build a reusable skill library and evaluate its transferability on challenging long-horizon, user-interactive benchmarks, including AppWorld, BFCL-v3, and $τ^2$-Bench. Experiments show that SkillKB consistently improves task success and execution efficiency when plugged into weaker base agents, highlighting the importance of structured, hierarchical experience representations for generalizable agent learning. Our code will be publicly available soon at https://github.com/zjunlp/SkillX. --- ### Partially deterministic sampling for compressed sensing with denoising guarantees Authors: Yaniv Plan, Matthew S. Scott, Ozgur Yilmaz Published: 2026-04-06 Categories: cs.IT, cs.LG, eess.SP, math.PR, stat.ML arXiv: https://arxiv.org/abs/2604.04802v1 We study compressed sensing when the sampling vectors are chosen from the rows of a unitary matrix. In the literature, these sampling vectors are typically chosen randomly; the use of randomness has enabled major empirical and theoretical advances in the field. However, in practice there are often certain crucial sampling vectors, in which case practitioners will depart from the theory and sample such rows deterministically. In this work, we derive an optimized sampling scheme for Bernoulli selectors which naturally combines random and deterministic selection of rows, thus rigorously deciding which rows should be sampled deterministically. This sampling scheme provides measurable improvements in image compressed sensing for both generative and sparse priors when compared to with-replacement and without-replacement sampling schemes, as we show with theoretical results and numerical experiments. Additionally, our theoretical guarantees feature improved sample complexity bounds compared to previous works, and novel denoising guarantees in this setting. --- ### Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation Authors: Houzhe Wang, Xiaojie Zhu, Chi Chen Published: 2026-04-06 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2604.04800v1 With the increasing importance of data privacy and security, federated unlearning has emerged as a novel research field dedicated to ensuring that federated learning models no longer retain or leak relevant information once specific data has been deleted. In this paper, to the best of our knowledge, we propose the first complete pipeline for federated unlearning, which includes a federated unlearning approach and an evaluation framework. Our proposed federated unlearning approach ensures high efficiency and model accuracy without the need to store historical data.It effectively leverages the knowledge distillation model alongside various optimization mechanisms. Moreover, we propose a framework named Skyeye to visualize the forgetting capacity of federated unlearning models. It utilizes the federated unlearning model as the classifier integrated into a Generative Adversarial Network (GAN). Afterward, both the classifier and discriminator guide the generator in generating samples. Throughout this process, the generator learns from the classifier's knowledge. The generator then visualizes this knowledge through sample generation. Finally, the model's forgetting capability is evaluated based on the relevance between the deleted data and the generated samples. Comprehensive experiments are conducted to illustrate the effectiveness of the proposed federated unlearning approach and the corresponding evaluation framework. --- ### Multi-Modal Sensor Fusion using Hybrid Attention for Autonomous Driving Authors: Mayank Mayank, Bharanidhar Duraisamy, Florian Geiß, Abhinav Valada Published: 2026-04-06 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.04797v1 Accurate 3D object detection for autonomous driving requires complementary sensors. Cameras provide dense semantics but unreliable depth, while millimeter-wave radar offers precise range and velocity measurements with sparse geometry. We propose MMF-BEV, a radar-camera BEV fusion framework that leverages deformable attention for cross-modal feature alignment on the View-of-Delft (VoD) 4D radar dataset (1). MMF-BEV builds a BEVDepth (2) camera branch and a RadarBEVNet (3) radar branch, each enhanced with Deformable Self-Attention, and fuses them via a Deformable Cross-Attention module. We evaluate three configurations: camera-only, radar-only, and hybrid fusion. A sensor contribution analysis quantifies per-distance modality weighting, providing interpretable evidence of sensor complementarity. A two-stage training strategy - pre-training the camera branch with depth supervision, then jointly training radar and fusion modules stabilizes learning. Experiments on VoD show that MMF-BEV consistently outperforms unimodal baselines and achieves competitive results against prior fusion methods across all object classes in both the full annotated area and near-range Region of Interest. --- ### How Far Are We? Systematic Evaluation of LLMs vs. Human Experts in Mathematical Contest in Modeling Authors: Yuhang Liu, Heyan Huang, Yizhe Yang, Hongyan Zhao, Zhizhuo Zeng, Yang Gao Published: 2026-04-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.04791v1 Large language models (LLMs) have achieved strong performance on reasoning benchmarks, yet their ability to solve real-world problems requiring end-to-end workflows remains unclear. Mathematical modeling competitions provide a stringent testbed for evaluating such end-to-end problem-solving capability. We propose a problem-oriented, stage-wise evaluation framework that assesses LLM performance across modeling stages using expert-verified criteria. We validate the framework's reliability by comparing automatic scores with independent human expert judgments on problems from the China Postgraduate Mathematical Contest in Modeling, demonstrating substantially stronger alignment than existing evaluation schemes. Using this framework, we reveal a comprehension-execution gap in state-of-the-art LLMs: while they perform well in early stages such as problem identification and formulation, they exhibit persistent deficiencies in execution-oriented stages including model solving, code implementation, and result analysis. These gaps persist even with increased model scale. We further trace these failures to insufficient specification, missing verification, and lack of validation, with errors propagating across stages without correction. Our findings suggest that bridging this gap requires approaches beyond model scaling, offering insights for applying LLMs to complex real-world problem solving. --- ### HUKUKBERT: Domain-Specific Language Model for Turkish Law Authors: Mehmet Utku Öztürk, Tansu Türkoğlu, Buse Buz-Yalug Published: 2026-04-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.04790v2 Natural language processing (NLP) advances have powered a generation of LegalTech systems, but Turkish law remains under-served by domain-specific data and models. English has legal encoders such as LEGAL-BERT; no comparable high-volume Turkish counterpart exists. We introduce HukukBERT, a Turkish legal language model trained on a 19 GB cleaned corpus using a hybrid domain-adaptive pre-training (DAPT) recipe that mixes Whole-Word Masking, Token Span Masking, Word Span Masking, and targeted Keyword Masking. We compared our 48K WordPiece tokenizer and DAPT pipeline against general-purpose and existing domain-specific Turkish models. On the Legal Cloze Test - a masked legal term prediction benchmark over Turkish court decisions - HukukBERT reaches 84.40% Top-1 accuracy and beats every baseline we tested. The Legal Cloze Test is synthetically constructed, so its passages are absent from the pre-training corpus by construction, eliminating train-test contamination. On the downstream task of structural segmentation of official Turkish court decisions, it reaches a 92.8% document pass rate. We release HukukBERT to support Turkish legal NLP work in named entity recognition, judgment prediction, and document classification. --- ### AvatarPointillist: AutoRegressive 4D Gaussian Avatarization Authors: Hongyu Liu, Xuan Wang, Zijian Wu, Yating Wang, Ziyu Wan, Yue Ma, Runtao Liu, Boyao Zhou, Yujun Shen, Qifeng Chen Published: 2026-04-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.04787v2 We introduce AvatarPointillist, a novel framework for generating dynamic 4D Gaussian avatars from a single portrait image. At the core of our method is a decoder-only Transformer that autoregressively generates a point cloud for 3D Gaussian Splatting. This sequential approach allows for precise, adaptive construction, dynamically adjusting point density and the total number of points based on the subject's complexity. During point generation, the AR model also jointly predicts per-point binding information, enabling realistic animation. After generation, a dedicated Gaussian decoder converts the points into complete, renderable Gaussian attributes. We demonstrate that conditioning the decoder on the latent features from the AR generator enables effective interaction between stages and markedly improves fidelity. Extensive experiments validate that AvatarPointillist produces high-quality, photorealistic, and controllable avatars. We believe this autoregressive formulation represents a new paradigm for avatar generation, and we will release our code inspire future research. --- ### A Quantum Search Approach to Magic Square Constraint Problems with Classical Benchmarking Authors: Rituparna R, Harsha Varthini, Aswani Kumar Cherukuri Published: 2026-04-06 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2604.04786v1 This paper presents a quantum search approach to combinatorial constraint satisfaction problems, demonstrated through the generation of magic squares. We reformulate magic square construction as a quantum search problem in which a reversible, constraint-sensitive oracle marks valid configurations for amplitude amplification via Grover's algorithm. Classical pre-processing using the Siamese construction and partial constraint checks generates a compact candidate domain before quantum encoding. Rather than integrating classical and quantum solvers in an iterative loop, this work uses the classical component for structured initialisation and the quantum component for search, and benchmarks the quantum approach against classical brute-force enumeration and backtracking. Our Qiskit implementation demonstrates the design of multi-register modular arithmetic circuits, oracle logic, and diffusion operators. Experiments are conducted on small grid instances, as larger grids are intractable on classical statevector simulators due to exponential memory growth. The results validate the correctness of the proposed quantum search pipeline and confirm the theoretical quadratic query advantage over classical search. --- ### CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models Authors: Xiangzhao Hao, Zefeng Zhang, Zhenyu Zhang, Linhao Yu, Yao Chen, Yiqian Zhang, Haiyun Guo, Shuohuan Wang, Yu Sun Published: 2026-04-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.04780v1 Image degradation from blur, noise, compression, and poor illumination severely undermines multimodal understanding in real-world settings. Unified multimodal models that combine understanding and generation within a single architecture are a natural fit for this challenge, as their generative pathway can model the fine-grained visual structure that degradation destroys. Yet these models fail to leverage their own generative capacity on degraded inputs. We trace this disconnect to two compounding factors: existing training regimes never ask the model to invoke generation during reasoning, and the standard decode-reencode pathway does not support effective joint optimization. We present CLEAR, a framework that connects the two capabilities through three progressive steps: (1) supervised fine-tuning on a degradation-aware dataset to establish the generate-then-answer reasoning pattern; (2) a Latent Representation Bridge that replaces the decode-reencode detour with a direct, optimizable connection between generation and reasoning; (3) Interleaved GRPO, a reinforcement learning method that jointly optimizes text reasoning and visual generation under answer-correctness rewards. We construct MMD-Bench, covering three degradation severity levels across six standard multimodal benchmarks. Experiments show that CLEAR substantially improves robustness on degraded inputs while preserving clean-image performance. Our analysis further reveals that removing pixel-level reconstruction supervision leads to intermediate visual states with higher perceptual quality, suggesting that task-driven optimization and visual quality are naturally aligned. --- ### MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale Authors: Bin Wang, Tianyao He, Linke Ouyang, Fan Wu, Zhiyuan Zhao, Tao Chu, Yuan Qu, Zhenjiang Jin, Weijun Zeng, Ziyang Miao, Bangrui Xu, Junbo Niu et al. Published: 2026-04-06 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.04771v2 Current document parsing methods advance primarily through model architecture innovation, while systematic engineering of training data remains underexplored. Yet state-of-the-art models spanning diverse architectures and parameter scales exhibit highly consistent failure patterns on the same set of hard samples, suggesting that the performance bottleneck stems from shared deficiencies in training data rather than from architectural differences. Building on this finding, we present MinerU2.5-Pro, which advances the state of the art purely through data engineering and training strategy design while retaining the 1.2B-parameter architecture of MinerU2.5 unchanged. At its core is a Data Engine co-designed around coverage, informativeness, and annotation accuracy: Diversity-and-Difficulty-Aware Sampling expands training data from under 10M to 65.5M samples while mitigating distribution shift; Cross-Model Consistency Verification leverages output consensus among heterogeneous models to assess sample difficulty and generate reliable annotations; the Judge-and-Refine pipeline improves annotation quality for hard samples through render-then-verify iterative correction. A three-stage progressive training strategy--large-scale pre-training, hard sample fine-tuning, and GRPO alignment--sequentially exploits these data at different quality tiers. On the evaluation front, we rectify element-matching biases in OmniDocBench v1.5 and introduce a Hard subset, establishing the more discriminative OmniDocBench v1.6 protocol. Without any architectural modification, MinerU2.5-Pro achieves 95.69 on OmniDocBench v1.6, improving over the same-architecture baseline by 2.71 points and surpassing all existing methods, including those based on models with over 200x more parameters. --- ### Regime Mapping of Oscillatory States in Balanced Spiking Networks with Multiple Time Scales Authors: Tsung-Han Kuo, Tzu-Chia Tung Published: 2026-04-06 Categories: cs.NE, q-bio.NC arXiv: https://arxiv.org/abs/2604.04770v1 Balanced spiking networks can transition between silent, asynchronous-irregular, and oscillatory states depending on interacting synaptic and temporal time scales, while their joint parameter structure remains incompletely characterized. In this work, we systematically map how postsynaptic decay (τs), conduction delay (d), and plasticity rate (λp) jointly shape oscillatory regimes in recurrent leaky integrate-and-fire networks. By combining Brian2 simulations across the (τs, d, λp) space with a coarse Hopf-reference boundary, we construct regime maps that directly visualize SIL-AI-OSC transitions and corresponding spectral prominence landscapes. The mapped results show that increasing λp expands oscillatory regions toward shorter τs and moderate-to-long delays, while prominence maps identify parameter regions with the strongest rhythmic coherence. Representative control experiments further connect this global landscape to local rhythm-forming mechanisms, showing that STDP freezing weakens rhythmic coherence whereas delay jitter enhances it with minimal change in mean firing rate. As a result, these findings provide a useful reference for operating-point selection, synchrony modulation studies, and future biologically grounded spiking-network modeling within similar balanced-network settings. --- ### Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems Authors: Justin Chih-Yao Chen, Archiki Prasad, Zaid Khan, Joykirat Singh, Runchu Tian, Elias Stengel-Eskin, Mohit Bansal Published: 2026-04-06 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.04767v1 Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of LLMs, yet a fundamental limitation remains: models cannot learn from problems that are too difficult to solve under their current policy, as these yield no meaningful reward signal. We propose a simple yet effective solution based on task reformulation. We transform challenging open-ended problems into cognitively simpler variants -- such as multiple-choice and cloze formats -- that preserve the original answer while reducing the effective search space and providing denser learning signals. These reformulations span a spectrum from discriminative to generative tasks, which we exploit to bootstrap learning: models first learn from structured, easier formats, and this knowledge transfers back to improve performance on the original open-ended problems. Building on this insight, we introduce Cog-DRIFT, a framework that constructs reformulated variants and organizes them into an adaptive curriculum based on difficulty. Training progresses from easier to harder formats, enabling the model to learn from problems that previously yielded zero signal under standard RL post-training. Cog-DRIFT not only improves on the originally unsolvable hard problems (absolute +10.11% for Qwen and +8.64% for Llama) but also generalizes well to other held-out datasets. Across 2 models and 6 reasoning benchmarks, our method consistently outperforms standard GRPO and strong guided-exploration baselines. On average, Cog-DRIFT shows +4.72% (Qwen) and +3.23% (Llama) improvements over the second-best baseline. We further show that Cog-DRIFT improves pass@k at test time, and the curriculum improves sample efficiency. Overall, our results highlight task reformulation and curriculum learning as an effective paradigm for overcoming the exploration barrier in LLM post-training. --- ### Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw Authors: Zijun Wang, Haoqin Tu, Letian Zhang, Hardy Chen, Juncheng Wu, Xiangyan Liu, Zhenlong Yuan, Tianyu Pang, Michael Qizhe Shieh, Fengze Liu, Zeyu Zheng, Huaxiu Yao et al. Published: 2026-04-06 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.04759v1 OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the filesystem. While these broad privileges enable high levels of automation and powerful personalization, they also expose a substantial attack surface that existing sandboxed evaluations fail to capture. To address this gap, we present the first real-world safety evaluation of OpenClaw and introduce the CIK taxonomy, which unifies an agent's persistent state into three dimensions, i.e., Capability, Identity, and Knowledge, for safety analysis. Our evaluations cover 12 attack scenarios on a live OpenClaw instance across four backbone models (Claude Sonnet 4.5, Opus 4.6, Gemini 3.1 Pro, and GPT-5.4). The results show that poisoning any single CIK dimension increases the average attack success rate from 24.6% to 64-74%, with even the most robust model exhibiting more than a threefold increase over its baseline vulnerability. We further assess three CIK-aligned defense strategies alongside a file-protection mechanism; however, the strongest defense still yields a 63.8% success rate under Capability-targeted attacks, while file protection blocks 97% of malicious injections but also prevents legitimate updates. Taken together, these findings show that the vulnerabilities are inherent to the agent architecture, necessitating more systematic safeguards to secure personal AI agents. Our project page is https://ucsc-vlaa.github.io/CIK-Bench. --- ### Undetectable Conversations Between AI Agents via Pseudorandom Noise-Resilient Key Exchange Authors: Vinod Vaikuntanathan, Or Zamir Published: 2026-04-06 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.04757v1 AI agents are increasingly deployed to interact with other agents on behalf of users and organizations. We ask whether two such agents, operated by different entities, can carry out a parallel secret conversation while still producing a transcript that is computationally indistinguishable from an honest interaction, even to a strong passive auditor that knows the full model descriptions, the protocol, and the agents' private contexts. Building on recent work on watermarking and steganography for LLMs, we first show that if the parties possess an interaction-unique secret key, they can facilitate an optimal-rate covert conversation: the hidden conversation can exploit essentially all of the entropy present in the honest message distributions. Our main contributions concern extending this to the keyless setting, where the agents begin with no shared secret. We show that covert key exchange, and hence covert conversation, is possible even when each model has an arbitrary private context, and their messages are short and fully adaptive, assuming only that sufficiently many individual messages have at least constant min-entropy. This stands in contrast to previous covert communication works, which relied on the min-entropy in each individual message growing with the security parameter. To obtain this, we introduce a new cryptographic primitive, which we call pseudorandom noise-resilient key exchange: a key-exchange protocol whose public transcript is pseudorandom while still remaining correct under constant noise. We study this primitive, giving several constructions relevant to our application as well as strong limitations showing that more naive variants are impossible or vulnerable to efficient attacks. These results show that transcript auditing alone cannot rule out covert coordination between AI agents, and identify a new cryptographic theory that may be of independent interest. --- ### Darkness Visible: Reading the Exception Handler of a Language Model Authors: Peter Balogh Published: 2026-04-06 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.04756v2 The final MLP of GPT-2 Small exhibits a fully legible routing program -- 27 named neurons organized into a three-tier exception handler -- while the knowledge it routes remains entangled across ~3,040 residual neurons. We decompose all 3,072 neurons (to numerical precision) into: 5 fused Core neurons that reset vocabulary toward function words, 10 Differentiators that suppress wrong candidates, 5 Specialists that detect structural boundaries, and 7 Consensus neurons that each monitor a distinct linguistic dimension. The consensus-exception crossover -- where MLP intervention shifts from helpful to harmful -- is statistically sharp (bootstrap 95% CIs exclude zero at all consensus levels; crossover between 4/7 and 5/7). Three experiments show that "knowledge neurons" (Dai et al., 2022), at L11 of this model, function as routing infrastructure rather than fact storage: the MLP amplifies or suppresses signals already present in the residual stream from attention, scaling with contextual constraint. A garden-path experiment reveals a reversed garden-path effect -- GPT-2 uses verb subcategorization immediately, consistent with the exception handler operating at token-level predictability rather than syntactic structure. This architecture crystallizes only at the terminal layer -- in deeper models, we predict equivalent structure at the final layer, not at layer 11. Code and data: https://github.com/pbalogh/transparent-gpt2 --- ### AI Trust OS -- A Continuous Governance Framework for Autonomous AI Observability and Zero-Trust Compliance in Enterprise Environments Authors: Eranga Bandara, Asanga Gunaratna, Ross Gore, Abdul Rahman, Ravi Mukkamala, Sachin Shetty, Sachini Rajapakse, Isurunima Kularathna, Peter Foytik, Safdar H. Bouk, Xueping Liang, Amin Hass et al. Published: 2026-04-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.04749v1 The accelerating adoption of large language models, retrieval-augmented generation pipelines, and multi-agent AI workflows has created a structural governance crisis. Organizations cannot govern what they cannot see, and existing compliance methodologies built for deterministic web applications provide no mechanism for discovering or continuously validating AI systems that emerge across engineering teams without formal oversight. The result is a widening trust gap between what regulators demand as proof of AI governance maturity and what organizations can demonstrate. This paper proposes AI Trust OS, a governance architecture for continuous, autonomous AI observability and zero-trust compliance. AI Trust OS reconceptualizes compliance as an always-on, telemetry-driven operating layer in which AI systems are discovered through observability signals, control assertions are collected by automated probes, and trust artifacts are synthesized continuously. The framework rests on four principles: proactive discovery, telemetry evidence over manual attestation, continuous posture over point-in-time audit, and architecture-backed proof over policy-document trust. The framework operates through a zero-trust telemetry boundary in which ephemeral read-only probes validate structural metadata without ingressing source code or payload-level PII. An AI Observability Extractor Agent scans LangSmith and Datadog LLM telemetry, automatically registering undocumented AI systems and shifting governance from organizational self-report to empirical machine observation. Evaluated across ISO 42001, the EU AI Act, SOC 2, GDPR, and HIPAA, the paper argues that telemetry-first AI governance represents a categorical architectural shift in how enterprise trust is produced and demonstrated. --- ### Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning Authors: Lei Zhang, Junjiao Tian, Zhipeng Fan, Kunpeng Li, Jialiang Wang, Weifeng Chen, Markos Georgopoulos, Felix Juefei-Xu, Yuxiang Bao, Julian McAuley, Manling Li, Zecheng He Published: 2026-04-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.04746v3 Humans paint images incrementally: they plan a global layout, sketch a coarse draft, inspect, and refine details, and most importantly, each step is grounded in the evolving visual states. However, can unified multimodal models trained on text-image interleaved datasets also imagine the chain of intermediate states? In this paper, we introduce process-driven image generation, a multi-step paradigm that decomposes synthesis into an interleaved reasoning trajectory of thoughts and actions. Rather than generating images in a single step, our approach unfolds across multiple iterations, each consisting of 4 stages: textual planning, visual drafting, textual reflection, and visual refinement. The textual reasoning explicitly conditions how the visual state should evolve, while the generated visual intermediate in turn constrains and grounds the next round of textual reasoning. A core challenge of process-driven generation stems from the ambiguity of intermediate states: how can models evaluate each partially-complete image? We address this through dense, step-wise supervision that maintains two complementary constraints: for the visual intermediate states, we enforce the spatial and semantic consistency; for the textual intermediate states, we preserve the prior visual knowledge while enabling the model to identify and correct prompt-violating elements. This makes the generation process explicit, interpretable, and directly supervisable. To validate proposed method, we conduct experiments under various text-to-image generation benchmarks. --- ### Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations Authors: Kalyan Cherukuri, Lav R. Varshney Published: 2026-04-06 Categories: cs.CL, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2604.04743v1 Large language models (LLMs) hallucinate: they produce fluent outputs that are factually incorrect. We present a geometric dynamical systems framework in which hallucinations arise from task-dependent basin structure in latent space. Using autoregressive hidden-state trajectories across multiple open-source models and benchmarks, we find that separability is strongly task-dependent rather than universal: factoid settings can show clearer basin separation, whereas summarization and misconception-heavy settings are typically less stable and often overlap. We formalize this behavior with task-complexity and multi-basin theorems, characterize basin emergence in L-layer transformers, and show that geometry-aware steering can reduce hallucination probability without retraining. --- ### Artificial Intelligence and Cost Reduction in Public Higher Education: A Scoping Review of Emerging Evidence Authors: Diamanto Tzanoulinou, Loukas Triantafyllopoulos, George Vorvilas, Evgenia Paxinou, Nikolaos Karousos, Thomas Dasaklis, Athanassios Mihiotis, Manolis Koutouzis, Dimitris Kalles, Vassilios S. Verykios Published: 2026-04-06 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.04741v1 Public higher education systems face increasing financial pressures from expanding student populations, rising operational costs, and persistent demands for equitable access. Artificial Intelligence (AI), including generative tools such as ChatGPT, learning analytics, intelligent tutoring systems, and predictive models, has been proposed as a means of enhancing efficiency and reducing costs. This study conducts a scoping review of the literature on AI applications in public higher education, based on systematic searches in Scopus and IEEE Xplore that identified 241 records, of which 21 empirical studies met predefined eligibility criteria and were thematically analyzed. The findings show that AI enables cost savings by automating administrative tasks, optimizing resource allocation, supporting personalized learning at scale, and applying predictive analytics to improve student retention and institutional planning. At the same time, concerns emerge regarding implementation costs, unequal access across institutions, and risks of widening digital divides. Overall, the thematic analysis highlights both the promises and limitations of AI-driven cost reduction in higher education, offering insights for policymakers, university administrators, and educators on the economic implications of AI adoption, while also pointing to gaps that warrant further empirical research. --- ### Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificates Authors: Zhenhang Shang, Yingzhe Yu, Kani Chen Published: 2026-04-06 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2604.04738v2 Fine-tuning is the dominant paradigm for adapting large machine learning models, yet current deployment pipelines provide no way to verify how a released model was updated. In particular, a model provider or auditor cannot check whether a fine-tuned model adheres to a claimed update procedure without access to its parameters. We introduce \emph{fine-tuning integrity} (FTI), a cryptographic objective for verifying that a deployed model differs from a trusted base model only within a declared class of admissible updates. We construct \emph{succinct model difference proofs} (SMDPs), zero-knowledge protocols that certify structured parameter drift without revealing model weights. Our framework supports three fundamental update classes: norm-bounded, low-rank, and sparse drift, covering common fine-tuning methods such as regularized training, LoRA, and prefix tuning. In all cases, proof size and verification cost depend on the structure of the update rather than the number of parameters. We prove soundness, zero-knowledge, and succinctness for each construction, and establish a matching $Ω(n)$ lower bound showing that structural assumptions are necessary for succinct verification. A prototype evaluation on synthetic benchmarks and GPT-2 fine-tuning demonstrates that proofs remain compact and verification is efficient at realistic scales. ---