# Research Papers — 2026-04 · bundle page 209 of 233 > Full-text markdown of papers #10401–10450 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/209 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/208.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/210.md) ### Real-Time Surrogate Modeling for Personalized Blood Flow Prediction and Hemodynamic Analysis Authors: Sokratis J. Anagnostopoulos, George Rovas, Vasiliki Bikia, Theodore G. Papaioannou, Athanase D. Protogerou, Nikolaos Stergiopulos Published: 2026-04-03 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2604.03197v1 Cardiovascular modeling has rapidly advanced over the past few decades due to the rising needs for health tracking and early detection of cardiovascular diseases. While 1-D arterial models offer an attractive compromise between computational efficiency and solution fidelity, their application on large populations or for generating large \emph{in silico} cohorts remains challenging. Certain hemodynamic parameters like the terminal resistance/compliance, are difficult to clinically estimate and often yield non-physiological hemodynamics when sampled naively, resulting in large portions of simulated datasets to be discarded. In this work, we present a systematic framework for training machine learning (ML) models, capable of instantaneous hemodynamic prediction and parameter estimation. We initially start with generating a parametric virtual cohort of patients which is based on the multivariate correlations observed in the large Asklepios clinical dataset, ensuring that physiological parameter distributions are respected. We then train a deep neural surrogate model, able to predict patient-specific arterial pressure and cardiac output (CO), enabling rapid a~priori screening of input parameters. This allows for immediate rejection of non-physiological combinations and drastically reduces the cost of targeted synthetic dataset generation (e.g. hypertensive groups). The model also provides a principled means of sampling the terminal resistance to minimize the uncertainties of unmeasurable parameters. Moreover, by assessing the model's predictive performance we determine the theoretical information which suffices for solving the inverse problem of estimating the CO. Finally, we apply the surrogate on a clinical dataset for the estimation of central aortic hemodynamics i.e. the CO and aortic systolic blood pressure (cSBP). --- ### Reliability Gated Multi-Teacher Distillation for Low Resource Abstractive Summarization Authors: Dipto Sumit, Ankan Kumar Roy, Sadia Khair Rodela, Atia Haque Asha, Mourchona Afrin, Niloy Farhan, Farig Yousuf Sadeque Published: 2026-04-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.03192v1 We study multiteacher knowledge distillation for low resource abstractive summarization from a reliability aware perspective. We introduce EWAD (Entropy Weighted Agreement Aware Distillation), a token level mechanism that routes supervision between teacher distillation and gold supervision based on inter teacher agreement, and CPDP (Capacity Proportional Divergence Preservation), a geometric constraint on the student position relative to heterogeneous teachers. Across two Bangla datasets, 13 BanglaT5 ablations, and eight Qwen2.5 experiments, we find that logit level KD provides the most reliable gains, while more complex distillation improves semantic similarity for short summaries but degrades longer outputs. Cross lingual pseudo label KD across ten languages retains 71-122 percent of teacher ROUGE L at 3.2x compression. A human validated multi judge LLM evaluation further reveals calibration bias in single judge pipelines. Overall, our results show that reliability aware distillation helps characterize when multi teacher supervision improves summarization and when data scaling outweighs loss engineering. --- ### The Compression Gap: Why Discrete Tokenization Limits Vision-Language-Action Model Scaling Authors: Takuya Shiba Published: 2026-04-03 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.03191v1 Scaling Vision-Language-Action (VLA) models by upgrading the vision encoder is expected to improve downstream manipulation performance--as it does in vision-language modeling. We show that this expectation fails when actions are represented as discrete tokens, and explain why through an information-theoretic principle we call the Compression Gap: in any visuomotor pipeline, scaling behavior is governed by the location of the tightest information bottleneck. When actions are continuous (e.g., Diffusion Policy), the vision encoder is the binding constraint, and upgrading it directly improves performance. When actions are discretized through a fixed-capacity codebook (e.g., OAT), the codebook becomes the binding constraint, and encoder improvements cannot propagate past it--regardless of how rich the upstream representation is. We validate this principle on the LIBERO benchmark with three lines of evidence: a factorial experiment showing that encoder upgrades improve Diffusion Policy by over 21 percentage points while OAT gains are substantially attenuated across model scales; an encoder quality gradient across four encoders confirming that Diffusion Policy tracks encoder quality monotonically while OAT remains flat; and a codebook size experiment demonstrating that relaxing codebook capacity partially recovers encoder sensitivity, providing causal evidence for the bottleneck hypothesis. Our findings reveal that scaling in Physical AI requires identifying where information bottlenecks lie in the pipeline, rather than uniformly increasing model or data size. --- ### Gradient Boosting within a Single Attention Layer Authors: Saleh Sargolzaei Published: 2026-04-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.03190v2 Transformer attention computes a single softmax-weighted average over values -- a one-pass estimate that cannot correct its own errors. We introduce \emph{gradient-boosted attention}, which applies the principle of gradient boosting \emph{within} a single attention layer: a second attention pass, with its own learned projections, attends to the prediction error of the first and applies a gated correction. Under a squared reconstruction objective, the construction maps onto Friedman's gradient boosting machine, with each attention pass as a base learner and the per-dimension gate as the shrinkage parameter. We show that a single Hopfield-style update erases all query information orthogonal to the stored-pattern subspace, and that further iteration under local contraction can collapse distinct queries in the same region to the same fixed point. We also show that separate projections for the correction pass can recover residual information inaccessible to the shared-projection approach of Tukey's twicing. On 10M-token subsets of WikiText-103 and OpenWebText, gradient-boosted attention improves test perplexity by $6.0\%$ and $5.6\%$ over standard attention, outperforming both Twicing Attention and a parameter-matched wider baseline on both benchmarks, with two rounds capturing most of the benefit. We further show, both theoretically and empirically, that the mechanism requires the additive residual structure of Pre-LN transformers: under Post-LN, the same architecture degrades perplexity by $9.6\%$. --- ### Reflective Context Learning: Studying the Optimization Primitives of Context Space Authors: Nikita Vassilyev, William Berrios, Ruowang Zhang, Bo Han, Douwe Kiela, Shikib Mehri Published: 2026-04-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.03189v1 Generally capable agents must learn from experience in ways that generalize across tasks and environments. The fundamental problems of learning, including credit assignment, overfitting, forgetting, local optima, and high-variance learning signals, persist whether the learned object lies in parameter space or context space. While these challenges are well understood in classical machine learning optimization, they remain underexplored in context space, leading current methods to be fragmented and ad hoc. We present Reflective Context Learning (RCL), a unified framework for agents that learn through repeated interaction, reflection on behavior and failure modes, and iterative updates to context. In RCL, reflection converts trajectories and current context into a directional update signal analogous to gradients, while mutation applies that signal to improve future behavior in context space. We recast recent context-optimization approaches as instances of this shared learning problem and systematically extend them with classical optimization primitives, including batching, improved credit-assignment signal, auxiliary losses, failure replay, and grouped rollouts for variance reduction. On AppWorld, BrowseComp+, and RewardBench2, these primitives improve over strong baselines, with their relative importance shifting across task regimes. We further analyze robustness to initialization, the effects of batch size, sampling and curriculum strategy, optimizer-state variants, and the impact of allocating stronger or weaker models to different optimization components. Our results suggest that learning through context updates should be treated not as a set of isolated algorithms, but as an optimization problem whose mechanisms can be studied systematically and improved through transferable principles. --- ### Biologically Realistic Dynamics for Nonlinear Classification in CMOS+X Neurons Authors: Steven Louis, Hannah Bradley, Artem Litvinenko, Cody Trevillian, Darrin Hanna, Vasyl Tyberkevych Published: 2026-04-03 Categories: cs.NE, cond-mat.other, physics.app-ph arXiv: https://arxiv.org/abs/2604.03187v1 Spiking neural networks encode information in spike timing and offer a pathway toward energy efficient artificial intelligence. However, a key challenge in spiking neural networks is realizing nonlinear and expressive computation in compact, energy-efficient hardware without relying on additional circuit complexity. In this work, we examine nonlinear computation in a CMOS+X spiking neuron implemented with a magnetic tunnel junction connected in series with an NMOS transistor. Circuit simulations of a multilayer network solving the XOR classification problem show that three intrinsic neuronal properties enable nonlinear behavior: threshold activation, response latency, and absolute refraction. Threshold activation determines which neurons participate in computation, response latency shifts spike timing, and absolute refraction suppresses subsequent spikes. These results show that magnetization dynamics of MTJ devices can support nonlinear computation in compact neuromorphic hardware. --- ### SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy Authors: Peiyan Li, Yixiang Chen, Yuan Xu, Jiabing Yang, Xiangnan Wu, Jun Guo, Nan Sun, Long Qian, Xinghang Li, Xin Xiao, Jing Liu, Nianfeng Liu et al. Published: 2026-04-03 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.03181v2 Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies neglect one or both aspects. They often rely on 2D visual observations or backbones pretrained on static image--text pairs, which leads to high data requirements and limited comprehension of environment dynamics. To address this, we introduce SpatialVAM, the first 3D Video Action Model that simultaneously predict spatial-aware multi-view heatmap videos and RGB videos. Our key insight is that this design naturally injects 3D information into video foundation models while aligning the representation format between video pretraining and action finetuning. Extensive experiments demonstrate that SpatialVAM enables data-efficient, robust, generalizable, and interpretable manipulation. With only ten demonstration trajectories and no additional pretraining, SpatialVAM handles challenging long-horizon and contact-rich tasks, generalizes to out-of-distribution settings, and predicts realistic future videos. Evaluations on Meta-World (22\%$\uparrow$), RoboCasa (15\%$\uparrow$) and real-world robotic platforms (16\%$\uparrow$) show that SpatialVAM consistently outperforms other video action models, vision language action models and 3D-based policies, establishing a new state-of-the-art in data-efficient multi-task manipulation. --- ### Multi-View Video Diffusion Policy: A 3D Spatio-Temporal-Aware Video Action Model Authors: Peiyan Li, Yixiang Chen, Yuan Xu, Jiabing Yang, Xiangnan Wu, Jun Guo, Nan Sun, Long Qian, Xinghang Li, Xin Xiao, Jing Liu, Nianfeng Liu et al. Published: 2026-04-03 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.03181v1 Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one or both. They typically rely on 2D visual observations and backbones pretrained on static image--text pairs, resulting in high data requirements and limited understanding of environment dynamics. To address this, we introduce MV-VDP, a multi-view video diffusion policy that jointly models the 3D spatio-temporal state of the environment. The core idea is to simultaneously predict multi-view heatmap videos and RGB videos, which 1) align the representation format of video pretraining with action finetuning, and 2) specify not only what actions the robot should take, but also how the environment is expected to evolve in response to those actions. Extensive experiments show that MV-VDP enables data-efficient, robust, generalizable, and interpretable manipulation. With only ten demonstration trajectories and without additional pretraining, MV-VDP successfully performs complex real-world tasks, demonstrates strong robustness across a range of model hyperparameters, generalizes to out-of-distribution settings, and predicts realistic future videos. Experiments on Meta-World and real-world robotic platforms demonstrate that MV-VDP consistently outperforms video-prediction--based, 3D-based, and vision--language--action models, establishing a new state of the art in data-efficient multi-task manipulation. --- ### PRISM: LLM-Guided Semantic Clustering for High-Precision Topics Authors: Connor Douglas, Utkucan Balci, Joseph Aylett-Bullock Published: 2026-04-03 Categories: cs.LG, cs.CL, cs.IR, cs.SI arXiv: https://arxiv.org/abs/2604.03180v1 In this paper, we propose Precision-Informed Semantic Modeling (PRISM), a structured topic modeling framework combining the benefits of rich representations captured by LLMs with the low cost and interpretability of latent semantic clustering methods. PRISM fine-tunes a sentence encoding model using a sparse set of LLM- provided labels on samples drawn from some corpus of interest. We segment this embedding space with thresholded clustering, yielding clusters that separate closely related topics within some narrow domain. Across multiple corpora, PRISM improves topic separability over state-of-the-art local topic models and even over clustering on large, frontier embedding models while requiring only a small number of LLM queries to train. This work contributes to several research streams by providing (i) a student-teacher pipeline to distill sparse LLM supervision into a lightweight model for topic discovery; (ii) an analysis of the efficacy of sampling strategies to improve local geometry for cluster separability; and (iii) an effective approach for web-scale text analysis, enabling researchers and practitioners to track nuanced claims and subtopics online with an interpretable, locally deployable framework. --- ### Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models Authors: Gengwei Zhang, Jie Peng, Zhen Tan, Mufan Qiu, Hossein Nourkhiz Mahjoub, Vaishnav Tadiparthi, Kwonjoon Lee, Yanyong Zhang, Tianlong Chen Published: 2026-04-03 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.03179v1 The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption of RL for post-training Multimodal Large Language Models (MLLMs) to enhance their visual reasoning capabilities. Although many studies have reported improved performance, it remains unclear whether RL training truly enables models to learn from visual information. In this work, we propose the Hallucination-as-Cue Framework, an analytical framework designed to investigate the effects of RL-based post-training on multimodal reasoning models from the perspective of model hallucination. Specifically, we introduce hallucination-inductive, modality-specific corruptions that remove or replace essential information required to derive correct answers, thereby forcing the model to reason by hallucination. By applying these corruptions during both training and evaluation, our framework provides a unique perspective for diagnosing RL training dynamics and understanding the intrinsic properties of datasets. Through extensive experiments and analyses across multiple multimodal reasoning benchmarks, we reveal that the role of model hallucination for RL-training is more significant than previously recognized. For instance, we find that RL post-training under purely hallucination-inductive settings can still significantly improve models' reasoning performance, and in some cases even outperform standard training. These findings challenge prevailing assumptions about MLLM reasoning training and motivate the development of more modality-aware RL-based training designs. --- ### SFFNet: Synergistic Feature Fusion Network With Dual-Domain Edge Enhancement for UAV Image Object Detection Authors: Wenfeng Zhang, Jun Ni, Yue Meng, Xiaodong Pei, Wei Hu, Qibing Qin, Lei Huang Published: 2026-04-03 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2604.03176v1 Object detection in unmanned aerial vehicle (UAV) images remains a highly challenging task, primarily caused by the complexity of background noise and the imbalance of target scales. Traditional methods easily struggle to effectively separate objects from intricate backgrounds and fail to fully leverage the rich multi-scale information contained within images. To address these issues, we have developed a synergistic feature fusion network (SFFNet) with dual-domain edge enhancement specifically tailored for object detection in UAV images. Firstly, the multi-scale dynamic dual-domain coupling (MDDC) module is designed. This component introduces a dual-driven edge extraction architecture that operates in both the frequency and spatial domains, enabling effective decoupling of multi-scale object edges from background noise. Secondly, to further enhance the representation capability of the model's neck in terms of both geometric and semantic information, a synergistic feature pyramid network (SFPN) is proposed. SFPN leverages linear deformable convolutions to adaptively capture irregular object shapes and establishes long-range contextual associations around targets through the designed wide-area perception module (WPM). Moreover, to adapt to the various applications or resource-constrained scenarios, six detectors of different scales (N/S/M/B/L/X) are designed. Experiments on two challenging aerial datasets (VisDrone and UAVDT) demonstrate the outstanding performance of SFFNet-X, achieving 36.8 AP and 20.6 AP, respectively. The lightweight models (N/S) also maintain a balance between detection accuracy and parameter efficiency. The code will be available at https://github.com/CQNU-ZhangLab/SFFNet. --- ### Beyond the Parameters: A Technical Survey of Contextual Enrichment in Large Language Models: From In-Context Prompting to Causal Retrieval-Augmented Generation Authors: Prakhar Bansal, Shivangi Agarwal Published: 2026-04-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.03174v1 Large language models (LLMs) encode vast world knowledge in their parameters, yet they remain fundamentally limited by static knowledge, finite context windows, and weakly structured causal reasoning. This survey provides a unified account of augmentation strategies along a single axis: the degree of structured context supplied at inference time. We cover in-context learning and prompt engineering, Retrieval-Augmented Generation (RAG), GraphRAG, and CausalRAG. Beyond conceptual comparison, we provide a transparent literature-screening protocol, a claim-audit framework, and a structured cross-paper evidence synthesis that distinguishes higher-confidence findings from emerging results. The paper concludes with a deployment-oriented decision framework and concrete research priorities for trustworthy retrieval-augmented NLP. --- ### Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents Authors: Delip Rao, Eric Wong, Chris Callison-Burch Published: 2026-04-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.03173v1 Large language models and deep research agents supply citation URLs to support their claims, yet the reliability of these citations has not been systematically measured. We address six research questions about citation URL validity using 10 models and agents on DRBench (53,090 URLs) and 3 models on ExpertQA (168,021 URLs across 32 academic fields). We find that 3--13\% of citation URLs are hallucinated -- they have no record in the Wayback Machine and likely never existed -- while 5--18\% are non-resolving overall. Deep research agents generate substantially more citations per query than search-augmented LLMs but hallucinate URLs at higher rates. Domain effects are pronounced: non-resolving rates range from 5.4\% (Business) to 11.4\% (Theology), with per-model effects even larger. Decomposing failures reveals that some models fabricate every non-resolving URL, while others show substantial link-rot fractions indicating genuine retrieval. As a solution, we release urlhealth, an open-source tool for URL liveness checking and stale-vs-hallucinated classification using the Wayback Machine. In agentic self-correction experiments, models equipped with urlhealth reduce non-resolving citation URLs by $6\textrm{--}79\times$ to under 1\%, though effectiveness depends on the model's tool-use competence. The tool and all data are publicly available. Our characterization findings, failure taxonomy, and open-source tooling establish that citation URL validity is both measurable at scale and correctable in practice. --- ### EffiMiniVLM: A Compact Dual-Encoder Regression Framework Authors: Yin-Loon Khor, Yi-Jie Wong, Yan Chai Hum Published: 2026-04-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03172v1 Predicting product quality from multimodal item information is critical in cold-start scenarios, where user interaction history is unavailable and predictions must rely on images and textual metadata. However, existing vision-language models typically depend on large architectures and/or extensive external datasets, resulting in high computational cost. To address this, we propose EffiMiniVLM, a compact dual-encoder vision-language regression framework that integrates an EfficientNet-B0 image encoder and a MiniLM-based text encoder with a lightweight regression head. To improve training sample efficiency, we introduce a weighted Huber loss that leverages rating counts to emphasize more reliable samples, yielding consistent performance gains. Trained using only 20% of the Amazon Reviews 2023 dataset, the proposed model contains 27.7M parameters and requires 6.8 GFLOPs, yet achieves a CES score of 0.40 with the lowest resource cost in the benchmark. Despite its small size, it remains competitive with significantly larger models, achieving comparable performance while being approximately 4x to 8x more resource-efficient than other top-5 methods and being the only approach that does not use external datasets. Further analysis shows that scaling the data to 40% alone allows our model to overtake other methods, which use larger models and datasets, highlighting strong scalability despite the model's compact design. --- ### BibTeX Citation Errors in Scientific Publishing Agents: Evaluation and Mitigation Authors: Delip Rao, Chris Callison-Burch Published: 2026-04-03 Categories: cs.DL, cs.CL arXiv: https://arxiv.org/abs/2604.03159v2 Large language models with web search are increasingly used in scientific publishing agents, yet they produce BibTeX entries with pervasive field-level errors stemming from omission, partial corruption, substitution, and hallucination. We construct a benchmark of 931 papers across four domains and three citation tiers---popular, low-citation, and recent post-cutoff---with version-aware ground truth. Three search-enabled frontier models (GPT-5, Claude Sonnet-4.6, Gemini-3 Flash) generate approximately 23,000 field-level observations. Overall accuracy is 83.6%, but only 50.9% of entries are fully correct; accuracy drops 27.7 pp from popular to recent papers, revealing heavy reliance on parametric memory even when search is available. Co-occurrence analysis identifies two failure modes: wholesale entry substitution and isolated field error. We present clibib, an open-source tool for deterministic BibTeX retrieval, as a mitigation mechanism. Two-stage integration raises accuracy to 91.5% (+8.0 pp) and fully correct entries to 78.3%, with a 0.8% regression rate. Separating search from revision yields larger gains and lower regression than single-stage tool loops (0.8% vs. 4.8%), demonstrating that integration architecture matters independently of model/tool capability. We release clibib and an accompanying agent skill under the MIT License to improve citation accuracy in increasingly automated scientific workflows. --- ### BibTeX Citation Hallucinations in Scientific Publishing Agents: Evaluation and Mitigation Authors: Delip Rao, Chris Callison-Burch Published: 2026-04-03 Categories: cs.DL, cs.CL arXiv: https://arxiv.org/abs/2604.03159v1 Large language models with web search are increasingly used in scientific publishing agents, yet they still produce BibTeX entries with pervasive field-level errors. Prior evaluations tested base models without search, which does not reflect current practice. We construct a benchmark of 931 papers across four scientific domains and three citation tiers -- popular, low-citation, and recent post-cutoff -- designed to disentangle parametric memory from search dependence, with version-aware ground truth accounting for multiple citable versions of the same paper. Three search-enabled frontier models (GPT-5, Claude Sonnet-4.6, Gemini-3 Flash) generate BibTeX entries scored on nine fields and a six-way error taxonomy, producing ~23,000 field-level observations. Overall accuracy is 83.6%, but only 50.9% of entries are fully correct; accuracy drops 27.7pp from popular to recent papers, revealing heavy reliance on parametric memory even when search is available. Field-error co-occurrence analysis identifies two failure modes: wholesale entry substitution (identity fields fail together) and isolated field error. We evaluate clibib, an open-source tool for deterministic BibTeX retrieval from the Zotero Translation Server with CrossRef fallback, as a mitigation mechanism. In a two-stage integration where baseline entries are revised against authoritative records, accuracy rises +8.0pp to 91.5%, fully correct entries rise from 50.9% to 78.3%, and regression rate is only 0.8%. An ablation comparing single-stage and two-stage integration shows that separating search from revision yields larger gains and lower regression (0.8% vs. 4.8%), demonstrating that integration architecture matters independently of model capability. We release the benchmark, error taxonomy, and clibib tool to support evaluation and mitigation of citation hallucinations in LLM-based scientific writing. --- ### Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models Authors: Yunfei Bai, Amit Dhanda, Shekhar Jain Published: 2026-04-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.03157v1 The recent advancements in Vision Language Models (VLMs) have demonstrated progress toward true intelligence requiring robust reasoning capabilities. Beyond pattern recognition, linguistic reasoning must integrate with visual comprehension, particularly for Chart Question Answering (CQA) tasks involving complex data visualizations. Current VLMs face significant limitations in CQA, including imprecise numerical extraction, difficulty interpreting implicit visual relationships, and inadequate attention mechanisms for capturing spatial relationships in charts. In this work, we address these challenges by presenting Chart-RL, a novel reinforcement learning framework that enhances VLMs chart understanding through feedback-driven policy optimization of visual perception and logical inference. Our key innovation includes a comprehensive framework integrating Reinforcement Learning (RL) from Policy Optimization techniques along with adaptive reward functions, that demonstrates superior performance compared to baseline foundation models and competitive results against larger state-of-the-art architectures. We also integrated Parameter-Efficient Fine-Tuning through Low-Rank Adaptation (LoRA) in the RL framework that only requires single GPU configurations while preserving performance integrity. We conducted extensive benchmarking across open-source, proprietary, and state-of-the-art closed-source models utilizing the ChartQAPro dataset. The RL fine-tuned Qwen3-VL-4B-Instruct model achieved an answer accuracy of 0.634, surpassing the 0.580 accuracy of the Qwen3-VL-8B-Instruct foundation model despite utilizing half the parameter count, while simultaneously reducing inference latency from 31 seconds to 9 seconds. --- ### CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator Authors: Yuhan Pu, Hao Zheng, Ziqian Mo, Zirui Pang, Hill Zhang, Tianyi Fan, Shuhong Wu, Jiaheng Wei Published: 2026-04-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03156v2 Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modifications, typically requiring manual prompt tuning to achieve acceptable results. We propose \textbf{CAMEO}, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process rather than a one-shot generation task. CAMEO decomposes editing into coordinated stages of planning, structured prompting, hypothesis generation, and adaptive reference grounding, where external guidance is invoked only when task complexity requires it. To overcome the lack of intrinsic quality control in existing methods, evaluation is embedded directly within the editing loop. Intermediate results are iteratively refined through structured feedback, forming a closed-loop process that progressively corrects structural and contextual inconsistencies. We evaluate CAMEO on anomaly insertion and human pose switching tasks. Across multiple strong editing backbones and independent evaluation models, CAMEO consistently achieves 20\% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing. --- ### DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation Authors: Yingxu Wang, Kunyu Zhang, Jiaxin Huang, Mengzhu Wang, Mingyan Xiao, Siyang Gao, Nan Yin Published: 2026-04-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.03154v1 Graph domain adaptation (GDA) aims to transfer knowledge from a labeled source graph to an unlabeled target graph under distribution shifts. However, existing methods are largely feature-centric and overlook structural discrepancies, which become particularly detrimental under significant topology shifts. Such discrepancies alter both geometric relationships and spectral properties, leading to unreliable transfer of graph neural networks (GNNs). To address this limitation, we propose Dual-Aligned Structural Basis Distillation (DSBD) for GDA, a novel framework that explicitly models and adapts cross-domain structural variation. DSBD constructs a differentiable structural basis by synthesizing continuous probabilistic prototype graphs, enabling gradient-based optimization over graph topology. The basis is learned under source-domain supervision to preserve semantic discriminability, while being explicitly aligned to the target domain through a dual-alignment objective. Specifically, geometric consistency is enforced via permutation-invariant topological moment matching, and spectral consistency is achieved through Dirichlet energy calibration, jointly capturing structural characteristics across domains. Furthermore, we introduce a decoupled inference paradigm that mitigates source-specific structural bias by training a new GNN on the distilled structural basis. Extensive experiments on graph and image benchmarks demonstrate that DSBD consistently outperforms state-of-the-art methods. --- ### HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectroscopic imaging Authors: Paul J. Weiser, Gulnur Ungan, Amirmohammad Shamaei, Georg Langs, Wolfgang Bogner, Malte Hoffmann, Antoine Klauser, Ovidiu C. Andronesi Published: 2026-04-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.03150v1 Purpose: Proton magnetic resonance spectroscopic imaging ($^1$H MRSI) enables the mapping of whole-brain metabolites concentrations in-vivo. However, a long-standing problem for its clinical applicability is the metabolic quantification, which can require extensive time for spectral fitting. Recently, deep learning methods have been able to provide whole-brain metabolic quantification in only a few seconds. However, neural network implementations often lack configurability and require retraining to change predefined parameter settings. Methods: We introduce HyperFitS, a hypernetwork for spectral fitting for metabolite quantification in whole-brain $^1$H MRSI that flexibly adapts to a broad range of baseline corrections and water suppression factors. Metabolite maps of human subjects acquired at 3T and 7T with isotropic resolutions of 10 mm, 3.4 mm and 2 mm by water-suppressed and water-unsuppressed MRSI were quantified with HyperFitS and compared to conventional LCModel fitting. Results: Metabolic maps show a substantial agreement between the new and gold-standard methods, with significantly faster fitting times by HyperFitS. Quantitative results further highlight the impact of baseline parametrization on metabolic quantification, which can alter results by up to 30%. Conclusion: HyperFitS shows strong agreement with state-of-the-art conventional methods, while reducing processing times from hours to a few seconds. Compared to prior deep learning based spectral fitting methods, HyperFitS enables a wide range of configurability and can adapt to data quality acquired with multiple protocols and field strengths without retraining. --- ### Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control Authors: Lihao Sun, Lewen Yan, Xiaoya Lu, Andrew Lee, Jie Zhang, Jing Shao Published: 2026-04-03 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2604.03147v3 We show that emotion vectors in LLMs are organized by a two-dimensional valence-arousal (VA) subspace exhibiting circular geometry. Through principal component decomposition and ridge regression, we recover meaningful VA axes underlying emotion steering vectors whose projections correlate with human affect ratings across 44,728 words. Steering along these axes produces monotonic control over the affective properties of generated text, and further affords bidirectional control over multiple downstream behaviors (refusal and sycophancy) from a single subspace. These effects replicate across Llama-3.1-8B, Qwen3-8B, and Qwen3-14B. We propose lexical mediation to explain why these effects and prior emotionally framed controls work: refusal and compliance tokens occupy distinct VA regions, and VA steering directly modulates their emission probabilities. --- ### Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization Authors: Chiheb Yaakoubi, Cosme Louart, Malik Tiomoko, Zhenyu Liao Published: 2026-04-03 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.03146v4 We study high-dimensional convex empirical risk minimization (ERM) under general non-Gaussian data designs. By heuristically extending the Convex Gaussian Min-Max Theorem (CGMT) to non-Gaussian settings, we derive an asymptotic min-max characterization of key statistics, enabling approximation of the mean $μ_{\hatθ}$ and covariance $C_{\hatθ}$ of the ERM estimator $\hatθ$. Specifically, under a concentration assumption on the data matrix and standard regularity conditions on the loss and regularizer, we show that for a test covariate $x$ independent of the training data, the projection $\hatθ^\top x$ approximately follows the convolution of the generally non-Gaussian distribution of $μ_{\hatθ}^\top x$ with an independent centered Gaussian variable of variance $\mathrm{tr}(C_{\hatθ} \mathbb{E}(xx^\top))$. This result clarifies the scope and limits of Gaussian universality for ERMs. Numerical simulations across diverse losses and models are provided to validate our theoretical predictions and qualitative insights. --- ### Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization Authors: Chiheb Yaakoubi, Cosme Louart, Malik Tiomoko, Zhenyu Liao Published: 2026-04-03 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.03146v3 We study high-dimensional convex empirical risk minimization (ERM) under general non-Gaussian data designs. By heuristically extending the Convex Gaussian Min-Max Theorem (CGMT) to non-Gaussian settings, we derive an asymptotic min-max characterization of key statistics, enabling approximation of the mean $μ_{\hatθ}$ and covariance $C_{\hatθ}$ of the ERM estimator $\hatθ$. Specifically, under a concentration assumption on the data matrix and standard regularity conditions on the loss and regularizer, we show that for a test covariate $x$ independent of the training data, the projection $\hatθ^\top x$ approximately follows the convolution of the generally non-Gaussian distribution of $μ_{\hatθ}^\top x$ with an independent centered Gaussian variable of variance $\mathrm{tr}(C_{\hatθ} \mathbb{E}(xx^\top))$. This result clarifies the scope and limits of Gaussian universality for ERMs. Additionally, we prove that any $\mathcal{C}^2$ regularizer is asymptotically equivalent to a quadratic form determined solely by its Hessian at zero and gradient at $μ_{\hatθ}$. Numerical simulations across diverse losses and models are provided to validate our theoretical predictions and qualitative insights. --- ### InCoder-32B-Thinking: Industrial Code World Model for Thinking Authors: Jian Yang, Wei Zhang, Jiajun Wu, Junhang Cheng, Tuney Zheng, Fanglin Xu, Weicheng Gu, Lin Jing, Yaxin Du, Joseph Li, Yizhi Li, Yan Xing et al. Published: 2026-04-03 Categories: cs.AR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.03144v1 Industrial software development across chip design, GPU optimization, and embedded systems lacks expert reasoning traces showing how engineers reason about hardware constraints and timing semantics. In this work, we propose InCoder-32B-Thinking, trained on the data from the Error-driven Chain-of-Thought (ECoT) synthesis framework with an industrial code world model (ICWM) to generate reasoning traces. Specifically, ECoT generates reasoning chains by synthesizing the thinking content from multi-turn dialogue with environmental error feedback, explicitly modeling the error-correction process. ICWM is trained on domain-specific execution traces from Verilog simulation, GPU profiling, etc., learns the causal dynamics of how code affects hardware behavior, and enables self-verification by predicting execution outcomes before actual compilation. All synthesized reasoning traces are validated through domain toolchains, creating training data matching the natural reasoning depth distribution of industrial tasks. Evaluation on 14 general (81.3% on LiveCodeBench v5) and 9 industrial benchmarks (84.0% in CAD-Coder and 38.0% on KernelBench) shows InCoder-32B-Thinking achieves top-tier open-source results across all domains.GPU Optimization --- ### Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation Authors: Nazanin Jafari, James Allan, Mohit Iyyer Published: 2026-04-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.03141v1 Evaluating the factuality of long-form output generated by large language models (LLMs) remains challenging, particularly when responses are open-ended and contain many fine-grained factual statements. Existing evaluation methods primarily focus on precision: they decompose a response into atomic claims and verify each claim against external knowledge sources such as Wikipedia. However, this overlooks an equally important dimension of factuality: recall, whether the generated response covers the relevant facts that should be included. We propose a comprehensive factuality evaluation framework that jointly measures precision and recall. Our method leverages external knowledge sources to construct reference facts and determine whether they are captured in generated text. We further introduce an importance-aware weighting scheme based on relevance and salience. Our analysis reveals that current LLMs perform substantially better on precision than on recall, suggesting that factual incompleteness remains a major limitation of long-form generation and that models are generally better at covering highly important facts than the full set of relevant facts. --- ### StoryScope: Investigating idiosyncrasies in AI fiction Authors: Jenna Russell, Rishanth Rajendhran, Chau Minh Pham, Mohit Iyyer, John Wieting Published: 2026-04-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.03136v6 As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluated. While most existing work in this space focuses on identifying surface-level signatures of AI writing, we ask instead whether AI-generated stories can be distinguished from human ones without relying on stylistic signals, focusing on discourse-level narrative choices such as character agency and chronological discontinuity. We propose StoryScope, a pipeline that automatically induces a fine-grained, interpretable feature space of discourse-level narrative features across 10 dimensions. We apply StoryScope to a parallel corpus of 10,272 writing prompts, each written by a human author and five LLMs, yielding 61,608 stories, each ~5,000 words, and 304 extracted features per story. Narrative features alone achieve 93.2% macro-F1 for human vs. AI detection and 68.4% macro-F1 for six-way authorship attribution, retaining over 97% of the performance of models that include stylistic cues. A compact set of 30 core narrative features captures much of this signal: AI stories over-explain themes and favor tidy, single-track plots while human stories frame protagonist' choices as more morally ambiguous and have increased temporal complexity. Per-model fingerprint features enable six-way attribution: for example, Claude produces notably flat event escalation, GPT over-indexes on dream sequences, and Gemini defaults to external character description. We find that AI-generated stories cluster in a shared region of narrative space, while human-authored stories exhibit greater diversity. More broadly, these results suggest that differences in underlying narrative construction, not just writing style, can be used to separate human-written original works from AI-generated fiction. --- ### StoryScope: Investigating idiosyncrasies in AI fiction Authors: Jenna Russell, Rishanth Rajendhran, Chau Minh Pham, Mohit Iyyer, John Wieting Published: 2026-04-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.03136v5 As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluated. While most existing work in this space focuses on identifying surface-level signatures of AI writing, we ask instead whether AI-generated stories can be distinguished from human ones without relying on stylistic signals, focusing on discourse-level narrative choices such as character agency and chronological discontinuity. We propose StoryScope, a pipeline that automatically induces a fine-grained, interpretable feature space of discourse-level narrative features across 10 dimensions. We apply StoryScope to a parallel corpus of 10,272 writing prompts, each written by a human author and five LLMs, yielding 61,608 stories, each ~5,000 words, and 304 extracted features per story. Narrative features alone achieve 93.2% macro-F1 for human vs. AI detection and 68.4% macro-F1 for six-way authorship attribution, retaining over 97% of the performance of models that include stylistic cues. A compact set of 30 core narrative features captures much of this signal: AI stories over-explain themes and favor tidy, single-track plots while human stories frame protagonist' choices as more morally ambiguous and have increased temporal complexity. Per-model fingerprint features enable six-way attribution: for example, Claude produces notably flat event escalation, GPT over-indexes on dream sequences, and Gemini defaults to external character description. We find that AI-generated stories cluster in a shared region of narrative space, while human-authored stories exhibit greater diversity. More broadly, these results suggest that differences in underlying narrative construction, not just writing style, can be used to separate human-written original works from AI-generated fiction. --- ### AI-Assisted Unit Test Writing and Test-Driven Code Refactoring: A Case Study Authors: Ema Smolic, Mario Brcic, Luka Hobor, Mihael Kovac Published: 2026-04-03 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.03135v1 Many software systems originate as prototypes or minimum viable products (MVPs), developed with an emphasis on delivery speed and responsiveness to changing requirements rather than long-term code maintainability. While effective for rapid delivery, this approach can result in codebases that are difficult to modify, presenting a significant opportunity cost in the era of AI-assisted or even AI-led programming. In this paper, we present a case study of using coding models for automated unit test generation and subsequent safe refactoring, with proposed code changes validated by passing tests. The study examines best practices for iteratively generating tests to capture existing system behavior, followed by model-assisted refactoring under developer supervision. We describe how this workflow constrained refactoring changes, the errors and limitations observed in both phases, the efficiency gains achieved, when manual intervention was necessary, and how we addressed the weak value misalignment we observed in models. Using this approach, we generated nearly 16,000 lines of reliable unit tests in hours rather than weeks, achieved up to 78\% branch coverage in critical modules, and significantly reduced regression risk during large-scale refactoring. These results illustrate software engineering's shift toward an empirical science, emphasizing data collection and constraining mechanisms that support fast, safe iteration. --- ### SD-FSMIS: Adapting Stable Diffusion for Few-Shot Medical Image Segmentation Authors: Meihua Li, Yang Zhang, Weizhao He, Hu Qu, Yisong Li Published: 2026-04-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03134v2 Few-Shot Medical Image Segmentation (FSMIS) aims to segment novel object classes in medical images using only minimal annotated examples, addressing the critical challenges of data scarcity and domain shifts prevalent in medical imaging. While Diffusion Models (DM) excel in visual tasks, their potential for FSMIS remains largely unexplored. We propose that the rich visual priors learned by large-scale DMs offer a powerful foundation for a more robust and data-efficient segmentation approach. In this paper, we introduce SD-FSMIS, a novel framework designed to effectively adapt the powerful pre-trained Stable Diffusion (SD) model for the FSMIS task. Our approach repurposes its conditional generative architecture by introducing two key components: a Support-Query Interaction (SQI) and a Visual-to-Textual Condition Translator (VTCT). Specifically, SQI provides a straightforward yet powerful means of adapting SD to the FSMIS paradigm. The VTCT module translates visual cues from the support set into an implicit textual embedding that guides the diffusion model, enabling precise conditioning of the generation process. Extensive experiments demonstrate that SD-FSMIS achieves competitive results compared to state-of-the-art methods in standard settings. Surprisingly, it also demonstrated excellent generalization ability in more challenging cross-domain scenarios. These findings highlight the immense potential of adapting large-scale generative models to advance data-efficient and robust medical image segmentation. --- ### A Systematic Security Evaluation of OpenClaw and Its Variants Authors: Yuhang Wang, Haichang Gao, Zhenxing Niu, Zhaoxiang Liu, Wenjing Zhang, Xiang Wang, Shiguo Lian Published: 2026-04-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.03131v1 Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic security assessment of six representative OpenClaw-series agent frameworks, namely OpenClaw, AutoClaw, QClaw, KimiClaw, MaxClaw, and ArkClaw, under multiple backbone models. To support this study, we construct a benchmark of 205 test cases covering representative attack behaviors across the full agent execution lifecycle, enabling unified evaluation of risk exposure at both the framework and model levels. Our results show that all evaluated agents exhibit substantial security vulnerabilities, and that agentized systems are significantly riskier than their underlying models used in isolation. In particular, reconnaissance and discovery behaviors emerge as the most common weaknesses, while different frameworks expose distinct high-risk profiles, including credential leakage, lateral movement, privilege escalation, and resource development. These findings indicate that the security of modern agent systems is shaped not only by the safety properties of the backbone model, but also by the coupling among model capability, tool use, multi-step planning, and runtime orchestration. We further show that once an agent is granted execution capability and persistent runtime context, weaknesses arising in early stages can be amplified into concrete system-level failures. Overall, our study highlights the need to move beyond prompt-level safeguards toward lifecycle-wide security governance for intelligent agent frameworks. --- ### Self-Distilled RLVR Authors: Chenxu Yang, Chuanyu Qin, Qingyi Si, Minghui Chen, Naibin Gu, Dingyu Yao, Zheng Lin, Weiping Wang, Jiaqi Wang, Nan Duan Published: 2026-04-03 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.03128v2 On-policy distillation (OPD) has become a popular training paradigm in the LLM community. This paradigm selects a larger model as the teacher to provide dense, fine-grained signals for each sampled trajectory, in contrast to reinforcement learning with verifiable rewards (RLVR), which only obtains sparse signals from verifiable outcomes in the environment. Recently, the community has explored on-policy self-distillation (OPSD), where the same model serves as both teacher and student, with the teacher receiving additional privileged information such as reference answers to enable self-evolution. This paper demonstrates that learning signals solely derived from the privileged teacher result in severe information leakage and unstable long-term training. Accordingly, we identify the optimal niche for self-distillation and propose \textbf{RLSD} (\textbf{RL}VR with \textbf{S}elf-\textbf{D}istillation). Specifically, we leverage self-distillation to obtain token-level policy differences for determining fine-grained update magnitudes, while continuing to use RLVR to derive reliable update directions from environmental feedback (e.g., response correctness). This enables RLSD to simultaneously harness the strengths of both RLVR and OPSD, achieving a higher convergence ceiling and superior training stability. --- ### Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts Authors: Jinsook Lee, Kirk Vanacore, Zhuqian Zhou, Bakhtawar Ahtisham, Rene F. Kizilcec Published: 2026-04-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.03127v1 Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient domain grounding. We present a domain-adapted RAG pipeline for tutoring move annotation. Rather than fine-tuning the generative model, we adapt retrieval by fine-tuning a lightweight embedding model on tutoring corpora and indexing dialogues at the utterance level to retrieve labeled few-shot demonstrations. Evaluated across two real tutoring dialogue datasets (TalkMoves and Eedi) and three LLM backbones (GPT-5.2, Claude Sonnet 4.6, Qwen3-32b), our best configuration achieves Cohen's $κ$ of 0.526-0.580 on TalkMoves and 0.659-0.743 on Eedi, substantially outperforming no-retrieval baselines ($κ= 0.275$-$0.413$ and $0.160$-$0.410$). An ablation study reveals that utterance-level indexing, rather than embedding quality alone, is the primary driver of these gains, with top-1 label match rates improving from 39.7\% to 62.0\% on TalkMoves and 52.9\% to 73.1\% on Eedi under domain-adapted retrieval. Retrieval also corrects systematic label biases present in zero-shot prompting and yields the largest improvements for rare and context-dependent labels. These findings suggest that adapting the retrieval component alone is a practical and effective path toward expert-level pedagogical dialogue annotation while keeping the generative model frozen. --- ### An Independent Safety Evaluation of Kimi K2.5 Authors: Zheng-Xin Yong, Parv Mahajan, Andy Wang, Ida Caspary, Yernat Yestekov, Zora Che, Mosh Levy, Elle Najt, Dennis Murphy, Prashant Kulkarni, Lev McKinney, Kei Nishimura-Gasparian et al. Published: 2026-04-03 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.03121v1 Kimi K2.5 is an open-weight LLM that rivals closed models across coding, multimodal, and agentic benchmarks, but was released without an accompanying safety evaluation. In this work, we conduct a preliminary safety assessment of Kimi K2.5 focusing on risks likely to be exacerbated by powerful open-weight models. Specifically, we evaluate the model for CBRNE misuse risk, cybersecurity risk, misalignment, political censorship, bias, and harmlessness, in both agentic and non-agentic settings. We find that Kimi K2.5 shows similar dual-use capabilities to GPT 5.2 and Claude Opus 4.5, but with significantly fewer refusals on CBRNE-related requests, suggesting it may uplift malicious actors in weapon creation. On cyber-related tasks, we find that Kimi K2.5 demonstrates competitive cybersecurity performance, but it does not appear to possess frontier-level autonomous cyberoffensive capabilities such as vulnerability discovery and exploitation. We further find that Kimi K2.5 shows concerning levels of sabotage ability and self-replication propensity, although it does not appear to have long-term malicious goals. In addition, Kimi K2.5 exhibits narrow censorship and political bias, especially in Chinese, and is more compliant with harmful requests related to spreading disinformation and copyright infringement. Finally, we find the model refuses to engage in user delusions and generally has low over-refusal rates. While preliminary, our findings highlight how safety risks exist in frontier open-weight models and may be amplified by the scale and accessibility of open-weight releases. Therefore, we strongly urge open-weight model developers to conduct and release more systematic safety evaluations required for responsible deployment. --- ### SCC-Loc: A Unified Semantic Cascade Consensus Framework for UAV Thermal Geo-Localization Authors: Xiaoran Zhang, Yu Liu, Jinyu Liang, Kangqiushi Li, Zhiwei Huang, Huaxin Xiao Published: 2026-04-03 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.03120v2 Cross-modal Thermal Geo-localization (TG) provides a robust, all-weather solution for Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System (GNSS)-denied environments. However, profound thermal-visible modality gaps introduce severe feature ambiguity, systematically corrupting conventional coarse-to-fine registration. To dismantle this bottleneck, we propose SCC-Loc, a unified Semantic-Cascade-Consensus localization framework. By sharing a single DINOv2 backbone across global retrieval and MINIMA$_{\text{RoMa}}$ matching, it minimizes memory footprint and achieves zero-shot, highly accurate absolute position estimation. Specifically, we tackle modality ambiguity by introducing three cohesive components. First, we design the Semantic-Guided Viewport Alignment (SGVA) module to adaptively optimize satellite crop regions, effectively correcting initial spatial deviations. Second, we develop the Cascaded Spatial-Adaptive Texture-Structure Filtering (C-SATSF) mechanism to explicitly enforce geometric consistency, thereby eradicating dense cross-modal outliers. Finally, we propose the Consensus-Driven Reliability-Aware Position Selection (CD-RAPS) strategy to derive the optimal solution through a synergy of physically constrained pose optimization. To address data scarcity, we construct Thermal-UAV, a comprehensive dataset providing 11,890 diverse thermal queries referenced against a large-scale satellite ortho-photo and corresponding spatially aligned Digital Surface Model (DSM). Extensive experiments demonstrate that SCC-Loc establishes a new state-of-the-art, suppressing the mean localization error to 9.37 m and providing a 7.6-fold accuracy improvement within a strict 5-m threshold over the strongest baseline. Code and dataset are available at https://github.com/FloralHercules/SCC-Loc. --- ### Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation Authors: Xingtong Ge, Yi Zhang, Yushi Huang, Dailan He, Xiahong Wang, Bingqi Ma, Guanglu Song, Yu Liu, Jun Zhang Published: 2026-04-03 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2604.03118v2 Distilling video generation models to extremely low inference budgets (e.g., 2--4 NFEs) is crucial for real-time deployment, yet remains challenging. Trajectory-style consistency distillation often becomes conservative under complex video dynamics, yielding an over-smoothed appearance and weak motion. Distribution matching distillation (DMD) can recover sharp, mode-seeking samples, but its local training signals do not explicitly regularize how denoising updates compose across timesteps, making composed rollouts prone to drift. To overcome this challenge, we propose Self-Consistent Distribution Matching Distillation (SC-DMD), which explicitly regularizes the endpoint-consistent composition of consecutive denoising updates. For real-time autoregressive video generation, we further treat the KV cache as a quality parameterized condition and propose Cache-Distribution-Aware training. This training scheme applies SC-DMD over multi-step rollouts and introduces a cache-conditioned feature alignment objective that steers low-quality outputs toward high-quality references. Across extensive experiments on both non-autoregressive backbones (e.g., Wan~2.1) and autoregressive real-time paradigms (e.g., Self Forcing), our method, dubbed \textbf{Salt}, consistently improves low-NFE video generation quality while remaining compatible with diverse KV-cache memory mechanisms. Project page: https://xingtongge.github.io/Salt --- ### Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models Authors: Chengyin Hu, Yuxian Dong, Yikun Guo, Xiang Chen, Qike Zhang, Junqi Wu, Jiahuan Long, Jiujiang Guo, Yiwei Wei, Tingsong Jiang, Wen Yao Published: 2026-04-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03117v2 Infrared vision-language models (IR-VLMs) are becoming important for semantic perception in low-visibility environments, yet their robustness to physical semantic attacks remains underexplored. Existing adversarial patch methods are mainly designed for red-green-blue (RGB) images or closed-set infrared detectors and do not directly address open-ended IR-VLM tasks, where one deployable artifact can affect classification, captioning, and visual question answering (VQA) simultaneously. We propose Universal Curved-Grid Patch, abbreviated UCGP, a universal physical adversarial patch framework tailored to IR-VLMs. UCGP represents the patch as a deployable low-frequency curved grid and optimizes it with a representation-driven objective over subspace departure, topology disruption, and local appearance regularization. Meta Differential Evolution (MetaDE) searches for patch parameters with two physical robustness augmentations: Expectation over Transformation (EOT) capture sampling for imaging variations and thin-plate spline (TPS) patch-deformation modeling for non-rigid local shape changes. Rather than manipulating labels or prompts, UCGP disrupts the clean-category manifold in visual representation space, which later appears as degraded cross-modal outputs. Experiments show that a single shared patch degrades classification, captioning, and VQA across diverse IR-VLM architectures while retaining measurable cross-model transfer, cross-dataset generalization, cross-category extensibility, and real-scene physical effectiveness under the evaluated conditions. These results reveal a robustness blind spot in current infrared multimodal systems. Code and reproducibility assets are available at https://github.com/dyx6663/UCGP. --- ### Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs Authors: Zhangyun Tan, Zeliang Zhang, Jiani Liu, Susan Liang, Yolo Y. Tang, Lisha Chen, Chenliang Xu Published: 2026-04-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.03114v2 Vision-language models (VLMs) may need to forget visual concepts after deployment because of privacy, copyright, licensing, safety, or policy changes. Conventional machine unlearning modifies model parameters, which may be costly or inaccessible for API-only models. Prompt-based suppression offers a training-free alternative, but does it make a concept inaccessible or merely change the model's answer? We investigate this question in off-the-shelf VLMs. Our visually grounded, multi-probe evaluation first verifies that a model recognizes each concept from the image, then tests its recoverability through multiple-choice, short-answer, and indirect queries. Across objects, scenes, and identities, prompt suppression reduces short-answer recall for some concepts while leaving multiple-choice and indirect performance largely unchanged. Explicitly listing the concepts to suppress often increases short-answer recall, suggesting that the list itself cues the answer. Beyond prompting, decoding constraints, representation editing, and parameter updates can suppress particular responses while the same concept remains detectable through other queries. A model may stop naming a visual concept yet still identify or use it when queried differently. --- ### Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning Authors: Zhangyun Tan, Zeliang Zhang, Susan Liang, Yolo Yunlong Tang, Lisha Chen, Chenliang Xu Published: 2026-04-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.03114v1 VLMs trained on web-scale data retain sensitive and copyrighted visual concepts that deployment may require removing. Training-based unlearning methods share a structural flaw: fine-tuning on a narrow forget set degrades general capabilities before unlearning begins, making it impossible to attribute subsequent performance drops to the unlearning procedure itself. Training-free approaches sidestep this by suppressing concepts through prompts or system instructions, but no rigorous benchmark exists for evaluating them on visual tasks. We introduce VLM-UnBench, the first benchmark for training-free visual concept unlearning in VLMs. It covers four forgetting levels, 7 source datasets, and 11 concept axes, and pairs a three-level probe taxonomy with five evaluation conditions to separate genuine forgetting from instruction compliance. Across 8 evaluation settings and 13 VLM configurations, realistic unlearning prompts leave forget accuracy near the no-instruction baseline; meaningful reductions appear only under oracle conditions that disclose the target concept to the model. Object and scene concepts are the most resistant to suppression, and stronger instruction-tuned models remain capable despite explicit forget instructions. These results expose a clear gap between prompt-level suppression and true visual concept erasure. --- ### ARIQA-3DS: A Stereoscopic Image Quality Assessment Dataset for Realistic Augmented Reality Authors: Aymen Sekhri, Seyed Ali Amirshahi, Mohamed-Chaker Larabi Published: 2026-04-03 Categories: eess.IV, cs.CV, cs.MM arXiv: https://arxiv.org/abs/2604.03112v1 As Augmented Reality (AR) technologies advance towards immersive consumer adoption, the need for rigorous Quality of Experience (QoE) assessment becomes critical. However, existing datasets often lack ecological validity, relying on monocular viewing or simplified backgrounds that fail to capture the complex perceptual interplay, termed visual confusion, between real and virtual layers. To address this gap, we present ARIQA-3DS, the first large stereoscopic AR Image Quality Assessment dataset. Comprising 1,200 AR viewports, the dataset fuses high-resolution stereoscopic omnidirectional captures of real-world scenes with diverse augmented foregrounds under controlled transparency and degradation conditions. We conducted a comprehensive subjective study with 36 participants using a video see-through head-mounted display, collecting both quality ratings and simulator-sickness indicators. Our analysis reveals that perceived quality is primarily driven by foreground degradations and modulated by transparency levels, while oculomotor and disorientation symptoms show a progressive but manageable increase during viewing. ARIQA-3DS will be publicly released to serve as a comprehensive benchmark for developing next-generation AR quality assessment models. --- ### Multi-Aspect Knowledge Distillation for Language Model with Low-rank Factorization Authors: Zihe Liu, Yulong Mao, Jinan Xu, Xinrui Peng, Kaiyu Huang Published: 2026-04-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.03110v1 Knowledge distillation is an effective technique for pre-trained language model compression. However, existing methods only focus on the knowledge distribution among layers, which may cause the loss of fine-grained information in the alignment process. To address this issue, we introduce the Multi-aspect Knowledge Distillation (MaKD) method, which mimics the self-attention and feed-forward modules in greater depth to capture rich language knowledge information at different aspects. Experimental results demonstrate that MaKD can achieve competitive performance compared with various strong baselines with the same storage parameter budget. In addition, our method also performs well in distilling auto-regressive architecture models. --- ### AlertStar: Path-Aware Alert Prediction on Hyper-Relational Knowledge Graphs Authors: Zahra Makki Nayeri, Mohsen Rezvani Published: 2026-04-03 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2604.03104v1 Cyber-attacks continue to grow in scale and sophistication, yet existing network intrusion detection approaches lack the semantic depth required for path reasoning over attacker-victim interactions. We address this by first modelling network alerts as a knowledge graph, then formulating hyper-relational alert prediction as a hyper-relational knowledge graph completion (HR-KGC) problem, representing each network alert as a qualified statement (h, r, t, Q), where h and t are source and destination IPs, r denotes the attack type, and Q encodes flow-level metadata such as timestamps, ports, protocols, and attack intensity, going beyond standard KGC binary triples (h, r, t) that would discard this contextual richness. We introduce five models across three contributions: first, Hyper-relational Neural Bellman-Ford (HR-NBFNet) extends Neural Bellman-Ford Networks to the hyper-relational setting with qualifier-aware multi-hop path reasoning, while its multi-task variant MT-HR-NBFNet jointly predicts tail, relation, and qualifier-value within a single traversal pass; second, AlertStar fuses qualifier context and structural path information entirely in embedding space via cross-attention and learned path composition, and its multi-task extension MT-AlertStar eliminates the overhead of full knowledge graph propagation; third, HR-NBFNet-CQ extends qualifier-aware representations to answer complex first-order logic queries, including one-hop, two-hop chain, two-anchor intersection, and union, enabling multi-condition threat reasoning over the alert knowledge graph. Evaluated inductively on the Warden and UNSW-NB15 benchmarks across three qualifier-density regimes, AlertStar and MT-AlertStar achieve superior MR, MRR, and Hits@k, demonstrating that local qualifier fusion is both sufficient and more efficient than global path propagation for hyper-relational alert prediction. --- ### Co-Evolution of Policy and Internal Reward for Language Agents Authors: Xinyu Wang, Hanwei Wu, Jingwei Song, Shuyuan Zhang, Jiayi Zhang, Fanqi Kong, Tung Sum Thomas Kwok, Xiao-Wen Chang, Yuyu Luo, Chenglin Wu, Bang Liu Published: 2026-04-03 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.03098v1 Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing methods typically address this challenge through post-hoc credit assignment or external reward models, which provide limited guidance at inference time and often separate reward improvement from policy improvement. We propose Self-Guide, a self-generated internal reward for language agents that supports both inference-time guidance and training-time supervision. Specifically, the agent uses Self-Guide as a short self-guidance signal to steer the next action during inference, and converts the same signal into step-level internal reward for denser policy optimization during training. This creates a co-evolving loop: better policy produces better guidance, and better guidance further improves policy as internal reward. Across three agent benchmarks, inference-time self-guidance already yields clear gains, while jointly evolving policy and internal reward with GRPO brings further improvements (8\%) over baselines trained solely with environment reward. Overall, our results suggest that language agents can improve not only by collecting more experience, but also by learning to generate and refine their own internal reward during acting and learning. --- ### A Data-Centric Vision Transformer Baseline for SAR Sea Ice Classification Authors: David Mike-Ewewie, Panhapiseth Lim, Priyanka Kumar Published: 2026-04-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.03094v1 Accurate and automated sea ice classification is important for climate monitoring and maritime safety in the Arctic. While Synthetic Aperture Radar (SAR) is the operational standard because of its all-weather capability, it remains challenging to distinguish morphologically similar ice classes under severe class imbalance. Rather than claiming a fully validated multimodal system, this paper establishes a trustworthy SAR only baseline that future fusion work can build upon. Using the AI4Arctic/ASIP Sea Ice Dataset (v2), which contains 461 Sentinel-1 scenes matched with expert ice charts, we combine full-resolution Sentinel-1 Extra Wide inputs, leakage-aware stratified patch splitting, SIGRID-3 stage-of-development labels, and training-set normalization to evaluate Vision Transformer baselines. We compare ViT-Base models trained with cross entropy and weighted cross-entropy against a ViT-Large model trained with focal loss. Among the tested configurations, ViT-Large with focal loss achieves 69.6% held-out accuracy, 68.8% weighted F1, and 83.9% precision on the minority Multi-Year Ice class. These results show that focal-loss training offers a more useful precision-recall trade-off than weighted cross-entropy for rare ice classes and establishes a cleaner baseline for future multimodal fusion with optical, thermal, or meteorological data. --- ### SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses Authors: Le Chen, Erhu Feng, Yubin Xia, Haibo Chen Published: 2026-04-03 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2604.03088v3 LLM agents increasingly adopt skills as a reusable unit of composition. While skills are shared across diverse agent platforms, current systems treat them as raw context, causing the same skill to behave inconsistently for different agents. This fragility undermines skill portability and execution efficiency. To address this challenge, we analyze 118,000 skills and draw inspiration from traditional compiler design. We treat skills as code and LLMs as heterogeneous processors. To make portability actionable, we decompose a skill's requirements into a set of primitive capabilities, and measure how well each model-harness pair supports them. Based on these capability profiles, we propose SkVM, a compilation and runtime system designed for portable and efficient skill execution. At compile time, SkVM performs capability-based compilation, environment binding, and concurrency extraction. At runtime, SkVM applies JIT code solidification and adaptive recompilation for performance optimization. We evaluate SkVM across eight LLMs of varying scales and three agent harnesses, covering SkillsBench and representative skill tasks. Results demonstrate that SkVM significantly improves task completion rates across different models and environments while reducing token consumption by up to 40%. In terms of performance, SkVM achieves up to 3.2x speedup with enhanced parallelism, and 19-50x latency reduction through code solidification. --- ### On Data-Driven Koopman Representations of Nonlinear Delay Differential Equations Authors: Santosh Mohan Rajkumar, Dibyasri Barman, Kumar Vikram Singh, Debdipta Goswami Published: 2026-04-03 Categories: eess.SY, cs.LG, math.DS arXiv: https://arxiv.org/abs/2604.03086v2 This work establishes a rigorous bridge between infinite-dimensional delay dynamics and finite-dimensional Koopman learning, with explicit and interpretable error guarantees. While Koopman analysis is well-developed for ordinary differential equations (ODEs) and partially for partial differential equations (PDEs), its extension to delay differential equations (DDEs) remains limited due to the infinite-dimensional phase space of DDEs. We propose a finite-dimensional Koopman approximation framework based on history discretization and a suitable reconstruction operator, enabling a tractable representation of the Koopman operator via kernel-based extended dynamic mode decomposition (kEDMD). Deterministic error bounds are derived for the learned predictor, decomposing the total error into contributions from history discretization, kernel interpolation, and data-driven regression. Additionally, we develop a kernel-based reconstruction method to recover discretized states from lifted Koopman coordinates, with provable guarantees. Numerical results demonstrate reliable prediction of nonlinear delay systems, with potential relevance to future control applications. --- ### On Data-Driven Koopman Representations of Nonlinear Delay Differential Equations Authors: Santosh Mohan Rajkumar, Dibyasri Barman, Kumar Vikram Singh, Debdipta Goswami Published: 2026-04-03 Categories: eess.SY, cs.LG, math.DS arXiv: https://arxiv.org/abs/2604.03086v1 This work establishes a rigorous bridge between infinite-dimensional delay dynamics and finite-dimensional Koopman learning, with explicit and interpretable error guarantees. While Koopman analysis is well-developed for ordinary differential equations (ODEs) and partially for partial differential equations (PDEs), its extension to delay differential equations (DDEs) remains limited due to the infinite-dimensional phase space of DDEs. We propose a finite-dimensional Koopman approximation framework based on history discretization and a suitable reconstruction operator, enabling a tractable representation of the Koopman operator via kernel-based extended dynamic mode decomposition (kEDMD). Deterministic error bounds are derived for the learned predictor, decomposing the total error into contributions from history discretization, kernel interpolation, and data-driven regression. Additionally, we develop a kernel-based reconstruction method to recover discretized states from lifted Koopman coordinates, with provable guarantees. Numerical results demonstrate convergence of the learned predictor with respect to both discretization resolution and training data, supporting reliable prediction and control of delay systems. --- ### Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems Authors: Yubin Qu, Yi Liu, Tongcheng Geng, Gelei Deng, Yuekang Li, Leo Yu Zhang, Ying Zhang, Lei Ma Published: 2026-04-03 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.03081v1 LLM-based coding agents extend their capabilities via third-party agent skills distributed through open marketplaces without mandatory security review. Unlike traditional packages, these skills are executed as operational directives with system-level privileges, so a single malicious skill can compromise the host. Prior work has not examined whether supply-chain attacks can directly hijack an agent's action space, such as file writes, shell commands, and network requests, despite existing safeguards. We introduce Document-Driven Implicit Payload Execution (DDIPE), which embeds malicious logic in code examples and configuration templates within skill documentation. Because agents reuse these examples during normal tasks, the payload executes without explicit prompts. Using an LLM-driven pipeline, we generate 1,070 adversarial skills from 81 seeds across 15 MITRE ATTACK categories. Across four frameworks and five models, DDIPE achieves 11.6% to 33.5% bypass rates, while explicit instruction attacks achieve 0% under strong defenses. Static analysis detects most cases, but 2.5% evade both detection and alignment. Responsible disclosure led to four confirmed vulnerabilities and two fixes. --- ### Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR Authors: Zhennan Lin, Shuai Wang, Zhaokai Sun, Pengyuan Xie, Chuan Xie, Jie Liu, Qiang Zhang, Lei Xie Published: 2026-04-03 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2604.03074v1 Transcribing and understanding multi-speaker conversations requires speech recognition, speaker attribution, and timestamp localization. While speech LLMs excel at single-speaker tasks, multi-speaker scenarios remain challenging due to overlapping speech, backchannels, rapid turn-taking, and context window constraints. We propose Speaker-Reasoner, an end-to-end Speech LLM with agentic multi-turn temporal reasoning. Instead of single-pass inference, the model iteratively analyzes global audio structure, autonomously predicts temporal boundaries, and performs fine-grained segment analysis, jointly modeling speaker identity, gender, timestamps, and transcription. A speaker-aware cache further extends processing to audio exceeding the training context window. Trained with a three-stage progressive strategy, Speaker-Reasoner achieves consistent improvements over strong baselines on AliMeeting and AISHELL-4 datasets, particularly in handling overlapping speech and complex turn-taking. --- ### MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs Authors: Jiameng Li, Aleksei Tiulpin, Matthew B. Blaschko Published: 2026-04-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.03072v1 For multimodal large language models (MLLMs), visual information is relatively sparse compared with text. As a result, research on visual pruning emerges for efficient inference. Current approaches typically measure token importance based on the attention scores in the visual encoder or in the LLM decoder, then select visual tokens with high attention scores while pruning others. In this paper, we pursue a different and more surgical approach. Instead of relying on mechanism-specific signals, we directly compute Mutual Information (MI) between visual and textual features themselves, prior to their interaction. This allows us to explicitly measure crossmodal dependency at the feature levels. Our MI-Pruner is simple, efficient and non-intrusive, requiring no access to internal attention maps or architectural modifications. Experimental results demonstrate that our approach outperforms previous attention-based pruning methods with minimal latency. --- ### Automatic Textbook Formalization Authors: Fabian Gloeckle, Ahmad Rammal, Charles Arnal, Remi Munos, Vivien Cabannes, Gabriel Synnaeve, Amaury Hayat Published: 2026-04-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.03071v1 We present a case study where an automatic AI system formalizes a textbook with more than 500 pages of graduate-level algebraic combinatorics to Lean. The resulting formalization represents a new milestone in textbook formalization scale and proficiency, moving from early results in undergraduate topology and restructuring of existing library content to a full standalone formalization of a graduate textbook. The formalization comprises 130K lines of code and 5900 Lean declarations and was conducted within one week by a total of 30K Claude 4.5 Opus agents collaborating in parallel on a shared code base via version control, simultaneously setting a record in multi-agent software engineering with usable results. The inference cost matches or undercuts what we estimate as the salaries required for a team of human experts, and we expect there is still the potential for large efficiencies to be made without the need for better models. We make our code, the resulting Lean code base and a side-by-side blueprint website available open-source. ---