# Research Papers — 2026-04 · bundle page 145 of 233

> Full-text markdown of papers #7201–7250 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/145
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/144.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/146.md)

### Machine Learning-Based Detection of MCP Attacks

Authors: Tobias Mattsson, Samuel Nyberg, Anton Borg, Ricardo Britto
Published: 2026-04-12
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2604.10534v1

The Model Context Protocol (MCP) is a new and emerging technology that extends the functionality of large language models, improving workflows but also exposing users to a new attack surface. Several studies have highlighted related security flaws, but MCP attack detection remains underexplored. To address this research gap, this study develops and evaluates a range of supervised machine learning approaches, including both traditional and deep-learning models. We evaluated the systems on the detection of malicious MCP tool descriptions in two scenarios: (1) a binary classification task distinguishing malicious from benign tools, and (2) a multiclass classification task identifying the attack type while separating benign from malicious tools. In addition to the machine learning models, we compared a rule-based approach that serves as a baseline. The results indicate that several of the developed models achieved 100\% F1-score on the binary classification task. In the multiclass scenario, the SVC and BERT models performed best, achieving F1 scores of 90.56\% and 88.33\%, respectively. Confusion matrices were also used to visualize the full distribution of predictions often missed by traditional metrics, providing additional insight for selecting the best-fitting solution in real-world scenarios. This study presents an addition to the MCP defence area, showing that machine learning models can perform exceptionally well in separating malicious and benign data points. To apply the solution in a live environment, a middleware was developed to classify which MCP tools are safe to use before execution, and block the ones that are not safe. Furthermore, the study shows that these models can outperform traditional rule-based solutions currently in use in the field.

---

### VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructions

Authors: Hung-Ting Su, Ting-Jun Wang, Jia-Fong Yeh, Min Sun, Winston H. Hsu
Published: 2026-04-12
Categories: cs.RO, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2604.10533v2

Conventional Vision-and-Language Navigation (VLN) benchmarks assume instructions are feasible and the referenced target exists, leaving agents ill-equipped to handle false-premise goals. We introduce VLN-NF, a benchmark with false-premise instructions where the target is absent from the specified room and agents must navigate, gather evidence through in-room exploration, and explicitly output NOT-FOUND. VLN-NF is constructed via a scalable pipeline that rewrites VLN instructions using an LLM and verifies target absence with a VLM, producing plausible yet factually incorrect goals. We further propose REV-SPL to jointly evaluate room reaching, exploration coverage, and decision correctness. To address this challenge, we present ROAM, a two-stage hybrid that combines supervised room-level navigation with LLM/VLM-driven in-room exploration guided by a free-space clearance prior. ROAM achieves the best REV-SPL among compared methods, while baselines often under-explore and terminate prematurely under unreliable instructions. VLN-NF project page can be found at https://vln-nf.github.io/.

---

### The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results

Authors: Jingkai Wang, Jue Gong, Zheng Chen, Kai Liu, Jiatong Li, Yulun Zhang, Radu Timofte, Jiachen Tu, Yaokun Shi, Guoyi Xu, Yaoxin Jiang, Jiajia Liu et al.
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10532v2

This paper provides a review of the NTIRE 2026 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes. The challenge focuses on generating natural and realistic outputs while maintaining identity consistency. Its goal is to advance state-of-the-art solutions for perceptual quality and realism, without imposing constraints on computational resources or training data. Performance is evaluated using a weighted image quality assessment (IQA) score and employs the AdaFace model as an identity checker. The competition attracted 96 registrants, with 10 teams submitting valid models; ultimately, 9 teams achieved valid scores in the final ranking. This collaborative effort advances the performance of real-world face restoration while offering an in-depth overview of the latest trends in the field.

---

### PepBenchmark: A Standardized Benchmark for Peptide Machine Learning

Authors: Jiahui Zhang, Rouyi Wang, Kuangqi Zhou, Tianshu Xiao, Lingyan Zhu, Yaosen Min, Yang Wang
Published: 2026-04-12
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.10531v1

Peptide therapeutics are widely regarded as the "third generation" of drugs, yet progress in peptide Machine Learning (ML) are hindered by the absence of standardized benchmarks. Here we present PepBenchmark, which unifies datasets, preprocessing, and evaluation protocols for peptide drug discovery. PepBenchmark comprises three components: (1) PepBenchData, a well-curated collection comprising 29 canonical-peptide and 6 non-canonical-peptide datasets across 7 groups, systematically covering key aspects of peptide drug development, representing, to the best of our knowledge, the most comprehensive AI-ready dataset resource to date; (2) PepBenchPipeline, a standardized preprocessing pipeline that ensures consistent dataset cleaning, construction, splitting, and feature transformation, mitigating quality issues common in ad hoc pipelines; and (3) PepBenchLeaderboard, a unified evaluation protocol and leaderboard with strong baselines across 4 major methodological families: Fingerprint-based, GNN-based, PLM-based, and SMILES-based models. Together, PepBenchmark provides the first standardized and comparable foundation for peptide drug discovery, facilitating methodological advances and translation into real-world applications. The data and code are publicly available at https://github.com/ZGCI-AI4S-Pep/PepBenchmark/.

---

### Towards an Appropriate Level of Reliance on AI: A Preliminary Reliance-Control Framework for AI in Software Engineering

Authors: Samuel Ferino, Rashina Hoda, John Grundy, Christoph Treude
Published: 2026-04-12
Categories: cs.SE, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2604.10530v1

How software developers interact with Artificial Intelligence (AI)-powered tools, including Large Language Models (LLMs), plays a vital role in how these AI-powered tools impact them. While overreliance on AI may lead to long-term negative consequences (e.g., atrophy of critical thinking skills); underreliance might deprive software developers of potential gains in productivity and quality. Based on twenty-two interviews with software developers on using LLMs for software development, we propose a preliminary reliance-control framework where the level of control can be used as a way to identify AI overreliance and underreliance. We also use it to recommend future research to further explore the different control levels supported by the current and emergent LLM-driven tools. Our paper contributes to the emerging discourse on AI overreliance and provides an understanding of the appropriate degree of reliance as essential to developers making the most of these powerful technologies. Our findings can help practitioners, educators, and policymakers promote responsible and effective use of AI tools.

---

### AI Patents in the United States and China: Measurement, Organization, and Knowledge Flows

Authors: Hanming Fang, Xian Gu, Hanyin Yan, Wu Zhu
Published: 2026-04-12
Categories: econ.GN, cs.AI, cs.CL, q-fin.GN
arXiv: https://arxiv.org/abs/2604.10529v1

We develop a high-precision classifier to measure artificial intelligence (AI) patents by fine-tuning PatentSBERTa on manually labeled data from the USPTO's AI Patent Dataset. Our classifier substantially improves the existing USPTO approach, achieving 97.0% precision, 91.3% recall, and a 94.0% F1 score, and it generalizes well to Chinese patents based on citation and lexical validation. Applying it to granted U.S. patents (1976-2023) and Chinese patents (2010-2023), we document rapid growth in AI patenting in both countries and broad convergence in AI patenting intensity and subfield composition, even as China surpasses the United States in recent annual patent counts. The organization of AI innovation nevertheless differs sharply: U.S. AI patenting is concentrated among large private incumbents and established hubs, whereas Chinese AI patenting is more geographically diffuse and institutionally diverse, with larger roles for universities and state-owned enterprises. For listed firms, AI patents command a robust market-value premium in both countries. Cross-border citations show continued technological interdependence rather than decoupling, with Chinese AI inventors relying more heavily on U.S. frontier knowledge than vice versa.

---

### BareBones: Benchmarking Zero-Shot Geometric Comprehension in VLMs

Authors: Aaditya Baranwal, Vishal Yadav, Abhishek Rajora
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10528v5

While Vision-Language Models (VLMs) demonstrate remarkable zero-shot recognition capabilities across a diverse spectrum of multimodal tasks, it yet remains an open question whether these architectures genuinely comprehend geometric structure or merely exploit RGB textures and contextual priors as statistical shortcuts. Existing evaluations fail to isolate this mechanism, conflating semantic reasoning with texture mapping and relying on imprecise annotations that inadvertently leak environmental cues. To address this gap, we introduce $\textbf{BareBones}$, a zero-shot benchmark designed to stress-test pure geometric shape comprehension. We curate pixel-level silhouettes of geometrically distinct classes across six datasets: five established segmentation sources (ImageNet-S, DIS5K, ThinObject5K, PASCAL VOC, CUB-200) and our novel flagship collection, WTP-Bench, establishing a noise-free geometric taxonomy. WTP-Bench is an extreme, fine-grained visual puzzle that forces models to identify inter-class geometric concepts from boundary contours alone. Our evaluation of 26 state-of-the-art proprietary and open-weight VLMs (eg. GPT-4.1, Gemini, Claude Sonnet 4.5, LLaVA) reveals a consistent, severe performance collapse under RGB deprivation, a phenomenon we term the $\textit{Texture Bias Cliff}$. By documenting universal structural blindspots, BareBones establishes a rigorous yardstick for genuine geometric grounding. Project Page: https://eternal-f1ame.github.io/WTP-Bench/

---

### STORM: End-to-End Referring Multi-Object Tracking in Videos

Authors: Zijia Lu, Jingru Yi, Jue Wang, Yuxiao Chen, Junwen Chen, Xinyu Li, Davide Modolo
Published: 2026-04-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.10527v1

Referring multi-object tracking (RMOT) is a task of associating all the objects in a video that semantically match with given textual queries or referring expressions. Existing RMOT approaches decompose object grounding and tracking into separated modules and exhibit limited performance due to the scarcity of training videos, ambiguous annotations, and restricted domains. In this work, we introduce STORM, an end-to-end MLLM that jointly performs grounding and tracking within a unified framework, eliminating external detectors and enabling coherent reasoning over appearance, motion, and language. To improve data efficiency, we propose a task-composition learning (TCL) strategy that decomposes RMOT into image grounding and object tracking, allowing STORM to leverage data-rich sub-tasks and learn structured spatial--temporal reasoning. We further construct STORM-Bench, a new RMOT dataset with accurate trajectories and diverse, unambiguous referring expressions generated through a bottom-up annotation pipeline. Extensive experiments show that STORM achieves state-of-the-art performance on image grounding, single-object tracking, and RMOT benchmarks, demonstrating strong generalization and robust spatial--temporal grounding in complex real-world scenarios. STORM-Bench is released at https://github.com/amazon-science/storm-referring-multi-object-grounding.

---

### FGML-DG: Feynman-Inspired Cognitive Science Paradigm for Cross-Domain Medical Image Segmentation

Authors: Yucheng Song, Chenxi Li, Haokang Ding, Zhining Liao, Zhifang Liao
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10524v1

In medical image segmentation across multiple modalities (e.g., MRI, CT, etc.) and heterogeneous data sources (e.g., different hospitals and devices), Domain Generalization (DG) remains a critical challenge in AI-driven healthcare. This challenge primarily arises from domain shifts, imaging variations, and patient diversity, which often lead to degraded model performance in unseen domains. To address these limitations, we identify key issues in existing methods, including insufficient simplification of complex style features, inadequate reuse of domain knowledge, and a lack of feedback-driven optimization. To tackle these problems, inspired by Feynman's learning techniques in educational psychology, this paper introduces a cognitive science-inspired meta-learning paradigm for medical image domain generalization segmentation. We propose, for the first time, a cognitive-inspired Feynman-Guided Meta-Learning framework for medical image domain generalization segmentation (FGML-DG), which mimics human cognitive learning processes to enhance model learning and knowledge transfer. Specifically, we first leverage the 'concept understanding' principle from Feynman's learning method to simplify complex features across domains into style information statistics, achieving precise style feature alignment. Second, we design a meta-style memory and recall method (MetaStyle) to emulate the human memory system's utilization of past knowledge. Finally, we incorporate a Feedback-Driven Re-Training strategy (FDRT), which mimics Feynman's emphasis on targeted relearning, enabling the model to dynamically adjust learning focus based on prediction errors. Experimental results demonstrate that our method outperforms other existing domain generalization approaches on two challenging medical image domain generalization tasks.

---

### ReFEree: Reference-Free and Fine-Grained Method for Evaluating Factual Consistency in Real-World Code Summarization

Authors: Suyoung Bae, CheolWon Na, Jaehoon Lee, Yumin Lee, YunSeok Choi, Jee-Hyong Lee
Published: 2026-04-12
Categories: cs.CL, cs.AI, cs.PL
arXiv: https://arxiv.org/abs/2604.10520v1

As Large Language Models (LLMs) have become capable of generating long and descriptive code summaries, accurate and reliable evaluation of factual consistency has become a critical challenge. However, previous evaluation methods are primarily designed for short summaries of isolated code snippets. Consequently, they struggle to provide fine-grained evaluation of multi-sentence functionalities and fail to accurately assess dependency context commonly found in real-world code summaries. To address this, we propose ReFEree, a reference-free and fine-grained method for evaluating factual consistency in real-world code summaries. We define factual inconsistency criteria specific to code summaries and evaluate them at the segment level using these criteria along with dependency information. These segment-level results are then aggregated into a fine-grained score. We construct a code summarization benchmark with human-annotated factual consistency labels. The evaluation results demonstrate that ReFEree achieves the highest correlation with human judgment among 13 baselines, improving 15-18% over the previous state-of-the-art. Our code and data are available at https://github.com/bsy99615/ReFEree.git.

---

### From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum Learning

Authors: Xiaoda Yang, Yuxiang Liu, Shenzhou Gao, Can Wang, Jingyang Xue, Lixin Yang, Yao Mu, Tao Jin, Shuicheng Yan, Zhimeng Zhang, Zhou Zhao
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10517v1

Modern vision-language models achieve strong performance in static perception, but remain limited in the complex spatiotemporal reasoning required for embodied, egocentric tasks. A major source of failure is their reliance on temporal priors learned from passive video data, which often leads to spatiotemporal hallucinations and poor generalization in dynamic environments. To address this, we present EgoTSR, a curriculum-based framework for learning task-oriented spatiotemporal reasoning. EgoTSR is built on the premise that embodied reasoning should evolve from explicit spatial understanding to internalized task-state assessment and finally to long-horizon planning. To support this paradigm, we construct EgoTSR-Data, a large-scale dataset comprising 46 million samples organized into three stages: Chain-of-Thought (CoT) supervision, weakly supervised tagging, and long-horizon sequences. Extensive experiments demonstrate that EgoTSR effectively eliminates chronological biases, achieving 92.4% accuracy on long-horizon logical reasoning tasks while maintaining high fine-grained perceptual precision, significantly outperforming existing open-source and closed-source state-of-the-art models.

---

### Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data Reasoning

Authors: Xinyi Huang
Published: 2026-04-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.10516v3

Selecting the right knowledge is critical when using large language models (LLMs) to solve domain-specific data analysis tasks. However, most retrieval-augmented approaches rely primarily on lexical or embedding similarity, which is often a weak proxy for the task-critical knowledge needed for multi-step reasoning. In many such tasks, the relevant knowledge is not merely textually related to the query, but is instead grounded in executable code and the dependency structure through which computations are carried out. To address this mismatch, we propose SGKR (Structure-Grounded Knowledge Retrieval), a retrieval framework that organizes domain knowledge with a graph induced by function-call dependencies. Given a question, SGKR extracts semantic input and output tags, identifies dependency paths connecting them, and constructs a task-relevant subgraph. The associated knowledge and corresponding function implementations are then assembled as a structured context for LLM-based code generation. Experiments on multi-step data analysis benchmarks show that SGKR consistently improves solution correctness over no-retrieval and similarity-based retrieval baselines for both vanilla LLMs and coding agents.

---

### Data-Efficient Surgical Phase Segmentation in Small-Incision Cataract Surgery: A Controlled Study of Vision Foundation Models

Authors: Lincoln Spencer, Song Wang, Chen Chen
Published: 2026-04-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.10514v1

Surgical phase segmentation is central to computer-assisted surgery, yet robust models remain difficult to develop when labeled surgical videos are scarce. We study data-efficient phase segmentation for manual small-incision cataract surgery (SICS) through a controlled comparison of visual representations. To isolate representation quality, we pair each visual encoder with the same temporal model (MS-TCN++) under identical training and evaluation settings on SICS-155 (19 phases). We compare supervised encoders (ResNet-50, I3D) against large self-supervised foundation models (DINOv3, V-JEPA2), and use a cached-feature pipeline that decouples expensive visual encoding from lightweight temporal learning. Foundation-model features improve segmentation performance in this setup, with DINOv3 ViT-7B achieving the best overall results (83.4% accuracy, 87.0 edit score). We further examine cataract-domain transfer using unlabeled videos and lightweight adaptation, and analyze when it helps or hurts. Overall, the study indicates strong transferability of modern vision foundation models to surgical workflow understanding and provides practical guidance for low-label medical video settings. The project website is available at: https://sl2005.github.io/DataEfficient-sics-phase-seg/

---

### Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts

Authors: Yuval David, Fabiana Fournier, Lior Limonad, Hadar Mulian
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10513v2

Ambiguity is an inherent property of natural-language agent specifications. When a system prompt leaves behaviour underdetermined, identical inputs follow divergent execution paths and produce inconsistent outcomes. The standard remedy is prompt optimisation: propose candidate prompts, run the agent to score them, and keep the best. This loop pays for the agent twice: once to generate candidates and again to rank them. On a tool-using agent whose rollouts cost dollars and minutes, the ranking cost dominates and budget-constrained optimisers routinely fail to find improvements. We present Semantic Feature Analysis (SFA), a pipeline that repairs agent specifications without running any search. SFA reads execution traces the agent has already produced, clusters the outputs of each workflow node, decomposes them into semantic feature classes using an extended subject-verb-object schema, ranks those features by their contribution to outcome separation using a decision tree, and injects the surviving features as corrective statements into the affected node's system prompt. Because it never ranks candidate prompts, it never spends a rollout on selection. We evaluate SFA against five prompt optimisers (GEPA, MIPROv2, SIMBA, BootstrapFewShot with random search, InferRules) and a single-reflection control, budget-matched in dollars at three budget levels across four benchmarks (IF-Bench, HotpotQA, HoVer, and GAIA). SFA consistently improves over the unmodified agent across benchmarks and budget levels, with the largest gains where rollouts are most expensive. On GAIA, where budget-constrained optimisers cannot afford to score even one candidate, SFA improves accuracy while other arms return their seed unchanged.

---

### Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis

Authors: Roi Ben-Gigi, Yuval David, Fabiana Fournier, Lior Limonad, Dany Moshkovich, Hadar Mulian, Segev Shlomov
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10513v1

AI agent development relies heavily on natural language prompting to define agents' tasks, knowledge, and goals. These prompts are interpreted by Large Language Models (LLMs), which govern agent behavior. Consequently, agentic performance is susceptible to variability arising from imprecise or ambiguous prompt formulations. Identifying and correcting such issues requires examining not only the agent's code, but also the internal system prompts generated throughout its execution lifecycle, as reflected in execution logs. In this work, we introduce an analytics pipeline implemented as part of the Agent Mentor open-source library that monitors and incrementally adapts the system prompts defining another agent's behavior. The pipeline improves performance by systematically injecting corrective instructions into the agent's knowledge. We describe its underlying mechanism, with particular emphasis on identifying semantic features associated with undesired behaviors and using them to derive corrective statements. We evaluate the proposed pipeline across three exemplar agent configurations and benchmark tasks using repeated execution runs to assess effectiveness. These experiments provide an initial exploration of automating such a mentoring pipeline within future agentic governance frameworks. Overall, the approach demonstrates consistent and measurable accuracy improvements across diverse configurations, particularly in settings dominated by specification ambiguity. For reproducibility, we released our code as open source under the Agent Mentor library.

---

### FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation

Authors: Chenhan Jiang, Yu Chen, Qingwen Zhang, Jifei Song, Songcen Xu, Dit-Yan Yeung, Jiankang Deng
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10512v1

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are typically sparse and discrete. Conversely, synthetic data scales but suffers from a domain gap and often lacks realistic semantics. We introduce FreeScale, a novel framework that leverages the power of scene reconstruction to transform limited real-world image sequences into a scalable source of high-quality training data. Our key insight is that an imperfect reconstructed scene serves as a rich geometric proxy, but naively sampling from it amplifies artifacts. To this end, we propose a certainty-aware free-view sampling strategy identifying novel viewpoints that are both semantically meaningful and minimally affected by reconstruction errors. We demonstrate FreeScale's effectiveness by scaling up the training of feedforward NVS models, achieving a notable gain of 2.7 dB in PSNR on challenging out-of-distribution benchmarks. Furthermore, we show that the generated data can actively enhance per-scene 3D Gaussian Splatting optimization, leading to consistent improvements across multiple datasets. Our work provides a practical and powerful data generation engine to overcome a fundamental bottleneck in 3D vision. Project page: https://mvp-ai-lab.github.io/FreeScale.

---

### Thinking Fast, Thinking Wrong: Intuitiveness Modulates LLM Counterfactual Reasoning in Policy Evaluation

Authors: Yanjie He
Published: 2026-04-12
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.10511v2

Large language models (LLMs) are increasingly used for causal and counterfactual reasoning, yet their reliability in real-world policy evaluation remains underexplored. We construct a benchmark of 40 empirical policy evaluation cases drawn from economics and social science, each grounded in peer-reviewed evidence and classified by intuitiveness -- whether the empirical finding aligns with (obvious), is unclear relative to (ambiguous), or contradicts (counter-intuitive) common prior expectations. We evaluate four frontier LLMs across five prompting strategies with 8,000 experimental trials and analyze the results using mixed-effects logistic regression. Our findings reveal three key results: (1) a chain-of-thought (CoT) paradox, where chain-of-thought prompting dramatically improves performance on obvious cases but this benefit is substantially attenuated on counter-intuitive ones (interaction OR = 0.278, $p < 0.001$); (2) intuitiveness as the dominant factor, with case-level variance exceeding that of model choice or prompting strategy (ICC = 0.671); and (3) a knowledge-reasoning dissociation, where citation-based familiarity is unrelated to accuracy ($p = 0.84$), suggesting models possess relevant knowledge but fail to reason with it when findings contradict intuition. We frame these results through the lens of dual-process theory (System 1 vs. System 2) and argue that current LLMs' "slow thinking" achieves only partial inhibition of intuitive priors -- producing the form of deliberative reasoning without fully delivering its substance.

---

### How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks

Authors: Johin Johny Arimbur
Published: 2026-04-12
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2604.10508v1

Large language models frequently fail to produce correct code on their first attempt, yet most benchmarks evaluate them in a single-shot setting. We investigate iterative self-repair (feeding execution errors back to the model for correction) across seven models spanning three families and both open-weight and proprietary providers: Llama 3.1 8B, Llama 3.3 70B, Llama 4 Scout (MoE, 16 experts), Llama 4 Maverick (MoE, 128 experts), Qwen3 32B, Gemini 2.5 Flash, and Gemini 2.5 Pro. On HumanEval (164 problems) and MBPP Sanitized (257 problems) with up to five attempts, self-repair universally improves pass rates: +4.9 to +17.1 pp on HumanEval and +16.0 to +30.0 pp on MBPP. Gemini 2.5 Flash achieves the highest final pass rates (96.3% HumanEval, 93.8% MBPP). Most gains concentrate in the first two rounds.Error-type analysis shows assertion errors (logical mistakes) are the hardest to repair at ~45%, while syntax and name errors are repaired at substantially higher rates, connecting to broader findings on the limits of LLM self-correction. Prior work found that weaker models fail at self-repair or require fine-tuning; we show that modern instruction-tuned models succeed with prompting alone, even at 8B scale. We also provide the first comparison of dense and MoE architectures for self-repair, and extend the repair-vs-resampling tradeoff analysis to modern models. A prompt ablation reveals chain-of-thought repair yields up to +5.5 pp additional self-repair gain (measured as improvement in repair delta) over minimal prompting for capable models.

---

### Beyond Compliance: A Resistance-Informed Motivation Reasoning Framework for Challenging Psychological Client Simulation

Authors: Danni Liu, Bo Liu, Yuxin Hu, Hantao Zhao, Yan Liu, Ding Ding, Jiahui Jin, Jiuxin Cao
Published: 2026-04-12
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2604.10507v1

Psychological client simulators have emerged as a scalable solution for training and evaluating counselor trainees and psychological LLMs. Yet existing simulators exhibit unrealistic over-compliance, leaving counselors underprepared for the challenging behaviors common in real-world practice. To bridge this gap, we present ResistClient, which systematically models challenging client behaviors grounded in Client Resistance Theory by integrating external behaviors with underlying motivational mechanisms. To this end, we propose Resistance-Informed Motivation Reasoning (RIMR), a two-stage training framework. First, RIMR mitigates compliance bias via supervised fine-tuning on RPC, a large-scale resistance-oriented psychological conversation dataset covering diverse client profiles. Second, beyond surface-level response imitation, RIMR models psychologically coherent motivation reasoning before response generation, jointly optimizing motivation authenticity and response consistency via process-supervised reinforcement learning. Extensive automatic and expert evaluations show that ResistClient substantially outperforms existing simulators in challenge fidelity, behavioral plausibility, and reasoning coherence. Moreover, ResistClient facilities evaluation of psychological LLMs under challenging conditions, offering new optimization directions for mental health dialogue systems.

---

### A Progressive Training Strategy for Embodied Vision-Language Models to Mitigate Spatio-Temporal Hallucinations

Authors: Xiaoda Yang, Shuai Yang, Can Wang, Jingyang Xue, Menglan Tang, Checheng Yu, Xunzhe Zhou, Sashuai Zhou, Tao Jin, Lixin Yang, Xiangyu Yue, Zhou Zhao
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10506v2

Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "multi-image reasoning hallucination", where a large performance drop between forward and reverse temporal queries reveals a dependence on superficial shortcuts instead of state-based understanding. To mitigate this, we first develop a new Chain-of-Thought (CoT) dataset that decomposes intricate reasoning into detailed spatiotemporal steps and definitive judgments. Building on this, we present a progressive training framework: it initiates with supervised pre-training on our CoT dataset to instill logical structures, followed by fine-tuning with scalable weakly-labeled data for broader generalization. Our experiments demonstrate that this approach not only improves backbone accuracy but also reduces the forward-backward performance gap from over 70% to only 6.53%. This shows that the method strengthens dynamic reasoning and reduces the inherent temporal biases of current VLMs.

---

### A Progressive Training Strategy for Vision-Language Models to Counteract Spatio-Temporal Hallucinations in Embodied Reasoning

Authors: Xiaoda Yang, Shuai Yang, Can Wang, Jingyang Xue, Menglan Tang, Checheng Yu, Xunzhe Zhou, Sashuai Zhou, Tao Jin, Lixin Yang, Xiangyu Yue, Zhou Zhao
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10506v1

Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "multi-image reasoning hallucination", where a massive performance drop between forward and reverse temporal queries reveals a dependence on superficial shortcuts instead of genuine causal understanding. To mitigate this, we first develop a new Chain-of-Thought (CoT) dataset that decomposes intricate reasoning into detailed spatiotemporal steps and definitive judgments. Building on this, we present a progressive training framework: it initiates with supervised pre-training on our CoT dataset to instill logical structures, followed by fine-tuning with scalable weakly-labeled data for broader generalization. Our experiments demonstrate that this approach not only improves backbone accuracy but also slashes the forward-backward performance gap from over 70\% to only 6.53\%. This confirms the method's ability to develop authentic dynamic reasoning and reduce the inherent temporal biases of current VLMs.

---

### Cooperation in Human and Machine Agents: Promise Theory Considerations

Authors: M. Burgess
Published: 2026-04-12
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2604.10505v1

Agent based systems are more common than we may think. A Promise Theory perspective on cooperation, in systems of human-machine agents, offers a unified perspective on organization and functional design with semi-automated efforts, in terms of the abstract properties of autonomous agents, This applies to human efforts, hardware systems, software, and artificial intelligence, with and without management. One may ask how does a reasoning system of components keep to an intended purpose? As the agent paradigm is now being revived, in connection with artificial intelligence agents, I revisit established principles of agent cooperation, as applied to humans, machines, and their mutual interactions. Promise Theory represents the fundamentals of signalling, comprehension, trust, risk, and feedback between agents, and offers some lessons about success and failure.

---

### CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation

Authors: Bingzhe Wu, Haotian Lu, Yuchen Mou
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10504v1

Current large language models (LLMs), even those explicitly trained for reasoning, often struggle with ambiguous content moderation cases due to misleading "decision shortcuts" embedded in context. Inspired by cognitive psychology insights into expert moderation, we introduce \caro (Chain-of-Analogy Reasoning Optimization), a novel two-stage training framework to induce robust analogical reasoning in LLMs. First, \caro bootstraps analogical reasoning chains via retrieval-augmented generation (RAG) on moderation data and performs supervised fine-tuning (SFT). Second, we propose a customized direct preference optimization (DPO) approach to reinforce analogical reasoning behaviors explicitly. Unlike static retrieval methods, \caro dynamically generates tailored analogical references during inference, effectively mitigating harmful decision shortcuts. Extensive experiments demonstrate that \caro substantially outperforms state-of-the-art reasoning models (DeepSeek R1, QwQ), specialized moderation models (LLaMA Guard), and advanced fine-tuning and retrieval-augmented methods, achieving an average F1 score improvement of 24.9\% on challenging ambiguous moderation benchmarks.

---

### Cross-Cultural Bias in Mel-Scale Representations: Evidence and Alternatives from Speech and Music

Authors: Shivam Chauhan, Ajay Pundhir
Published: 2026-04-12
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2604.10503v1

Modern audio systems universally employ mel-scale representations derived from 1940s Western psychoacoustic studies, potentially encoding cultural biases that create systematic performance disparities. We present a comprehensive evaluation of cross-cultural bias in audio front-ends, comparing mel-scale features with learnable alternatives (LEAF, SincNet) and psychoacoustic variants (ERB, Bark, CQT) across speech recognition (11 languages), music analysis (6 collections), and European acoustic scene classification (10 European cities). Our controlled experiments isolate front-end contributions while holding architecture and training protocols minimal and constant. Results demonstrate that mel-scale features yield 31.2% WER for tonal languages compared to 18.7% for non-tonal languages (12.5% gap), and show 15.7% F1 degradation between Western and non-Western music. Alternative representations significantly reduce these disparities: LEAF reduces the speech gap by 34% through adaptive frequency allocation, CQT achieves 52% reduction in music performance gaps, and ERB-scale filtering cuts disparities by 31% with only 1% computational overhead. We also release FairAudioBench, enabling cross-cultural evaluation, and demonstrate that adaptive frequency decomposition offers practical paths toward equitable audio processing. These findings reveal how foundational signal processing choices propagate bias, providing crucial guidance for developing inclusive audio systems.

---

### CHAIRO: Contextual Hierarchical Analogical Induction and Reasoning Optimization for LLMs

Authors: Haotian Lu, Yuchen Mou, Bingzhe Wu
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10502v1

Content moderation in online platforms faces persistent challenges due to the evolving complexity of user-generated content and the limitations of traditional rule-based and machine learning approaches. While recent advances in large language models (LLMs) have enabled more sophisticated moderation via direct prompting or fine-tuning, these approaches often exhibit limited generalization, interpretability, and adaptability to unseen or ambiguous cases. In this work, we propose a novel moderation framework that leverages analogical examples to enhance rule induction and decision reliability. Our approach integrates end-to-end optimization of analogical retrieval, rule generation, and moderation classification, enabling the dynamic adaptation of moderation rules to diverse content scenarios. Through comprehensive experiments, we demonstrate that our method significantly outperforms both rule-injected fine-tuning baselines and multi-stage static RAG pipelines in terms of moderation accuracy and rule quality. Further evaluations, including human assessments and external model generalization tests, confirm that our framework produces rules with better clarity, interpretability, and applicability. These findings show that analogical example-driven methods can advance robust, explainable, and generalizable content moderation in real-world applications.

---

### Visual Enhanced Depth Scaling for Multimodal Latent Reasoning

Authors: Yudong Han, Yong Wang, Zaiquan Yang, Zhen Qu, Liyuan Pan, Xiangxiang Chu
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10500v5

Multimodal latent reasoning has emerged as a promising paradigm that replaces explicit Chain-of-Thought (CoT) decoding with implicit feature propagation, simultaneously enhancing representation informativeness and reducing inference latency. By analyzing token-level gradient dynamics during latent training, we reveal two critical observations: (1) visual tokens exhibit significantly smaller gradient norms than their textual counterparts due to inherent language bias, resulting in systematic visual under-optimization; and (2) semantically simple tokens converge rapidly, whereas complex tokens exhibit persistent gradient instability constrained by fixed architectural depths. To address these limitations, we propose a visual replay module and routing depth scaling to collaboratively enhance visual perception and refine complicated latents for deeper contextual reasoning. The former module leverages causal self-attention to estimate token saliency, reinforcing fine-grained grounding through spatially-coherent constraints. Complementarily, the latter mechanism adaptively allocates additional reasoning steps to complex tokens, enabling deeper contextual refinement. Guided by a curriculum strategy that progressively internalizes explicit CoT into compact latent representations, our framework achieves state-of-the-art performance across diverse benchmarks while delivering substantial inference speedups over explicit CoT baselines.

---

### FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learning

Authors: Tao Liu, Xuehe Wang
Published: 2026-04-12
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2604.10499v1

Federated learning has become a popular paradigm for privacy protection and edge-based machine learning. However, defending against differential attacks and devising incentive strategies remain significant bottlenecks in this field. Despite recent works on privacy-aware incentive mechanism design for federated learning, few of them consider both data volume and noise level. In this paper, we propose a novel federated learning system called FEDBUD, which combines privacy and economic concerns together by considering the joint influence of data volume and noise level on incentive strategy determination. In this system, the cloud server controls monetary payments to edge nodes, while edge nodes control data volume and noise level that potentially impact the model performance of the cloud server. To determine the mutually optimal strategies for both sides, we model FEDBUD as a two-stage Stackelberg Game and derive the Nash Equilibrium using the mean-field estimator and virtual queue. Experimental results on real-world datasets demonstrate the outstanding performance of FEDBUD.

---

### CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts

Authors: Xiangyang Yin, Xingyu Liu, Tianhua Xia, Bo Bao, Vithursan Thangarasa, Valavan Manohararajah, Eric Sather, Sai Qian Zhang
Published: 2026-04-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.10496v2

Outliers have emerged as a fundamental bottleneck in preserving accuracy for low-precision large models, particularly within Mixture-of-Experts (MoE) architectures that are increasingly central to large-scale language modeling. Under post-training quantization (PTQ), these outliers induce substantial quantization errors, leading to severe accuracy degradation. While recent rotation-based smoothing techniques alleviate the problem by redistributing outlier magnitudes, residual errors remain and continue to impede reliable low-precision deployment. In this work, we tackle this challenge by introducing CodeQuant, a unified quantization-and-clustering scheme that contains smoothing activation outliers via learnable rotation and absorbing weight outliers into fine-tuned cluster centroids for MoE. This design reduces the influence of extreme values by fitting them within cluster centroids, thereby lowering quantization error while maintaining expressive capacity. Coupled with a dedicated kernel design for GPU and CPU, CodeQuant achieves up to $4.15\times$ speedup while delivering significantly higher accuracy than state-of-the-art quantization approaches across diverse MoE models. Our results highlight CodeQuant as a promising direction for efficient and accurate deployment of MoE-based large language models under low-precision constraints. Our code is available at https://github.com/SAI-Lab-NYU/CodeQuant.

---

### CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts

Authors: Xiangyang Yin, Xingyu Liu, Tianhua Xia, Bo Bao, Vithursan Thangarasa, Valavan Manohararajah, Eric Sather, Sai Qian Zhang
Published: 2026-04-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.10496v1

Outliers have emerged as a fundamental bottleneck in preserving accuracy for low-precision large models, particularly within Mixture-of-Experts (MoE) architectures that are increasingly central to large-scale language modeling. Under post-training quantization (PTQ), these outliers induce substantial quantization errors, leading to severe accuracy degradation. While recent rotation-based smoothing techniques alleviate the problem by redistributing outlier magnitudes, residual errors remain and continue to impede reliable low-precision deployment. In this work, we tackle this challenge by introducing \textit{CodeQuant}, a unified quantization-and-clustering scheme that contains smoothing activation outliers via learnable rotation and absorbing weight outliers into fine-tuned cluster centroids for MoE. This design reduces the influence of extreme values by fitting them within cluster centroids, thereby lowering quantization error while maintaining expressive capacity. Coupled with a dedicated kernel design for GPU and CPU, CodeQuant achieves up to $4.15\times$ speedup while delivering significantly higher accuracy than state-of-the-art quantization approaches across diverse MoE models. Our results highlight CodeQuant as a promising direction for efficient and accurate deployment of MoE-based large language models under low-precision constraints. Our code is available at https://github.com/SAI-Lab-NYU/CodeQuant.

---

### Why Don't You Know? Evaluating the Impact of Uncertainty Sources on Uncertainty Quantification in LLMs

Authors: Maiya Goloburda, Roman Vashurin, Fedor Chernogorskii, Nurkhan Laiyk, Daniil Orel, Preslav Nakov, Maxim Panov
Published: 2026-04-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.10495v2

As Large Language Models (LLMs) are increasingly deployed in real-world applications, reliable uncertainty quantification (UQ) becomes critical for safe and effective use. Most existing UQ approaches for language models aim to produce a single confidence score -- for example, estimating the probability that a model's answer is correct. However, uncertainty in natural language tasks arises from multiple distinct sources, including model knowledge gaps, output variability, and input ambiguity, which have different implications for system behavior and user interaction. In this work, we study how the source of uncertainty impacts the behavior and effectiveness of existing UQ methods. To enable controlled analysis, we introduce a new dataset that explicitly categorizes uncertainty sources, allowing systematic evaluation of UQ performance under each condition. Our experiments reveal that while many UQ methods perform well when uncertainty stems solely from model knowledge limitations, their performance degrades or becomes misleading when other sources are introduced. These findings highlight the need for uncertainty-aware methods that explicitly account for the source of uncertainty in large language models.

---

### UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation

Authors: Haopeng Chen, Yihao Ai, Kabeen Kim, Robby T. Tan, Yixin Chen, Bo Wang
Published: 2026-04-12
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.10485v1

Low-visibility scenarios, such as low-light conditions, pose significant challenges to human pose estimation due to the scarcity of annotated low-light datasets and the loss of visual information under poor illumination. Recent domain adaptation techniques attempt to utilize well-lit labels by augmenting well-lit images to mimic low-light conditions. But handcrafted augmentations oversimplify noise patterns, while learning-based methods often fail to preserve high-frequency low-light characteristics, producing unrealistic images that lead pose models to generalize poorly to real low-light scenes. Moreover, recent pose estimators rely on image cues through image-to-keypoint cross-attention, but these cues become unreliable under low-light conditions. To address these issues, we propose Unsupervised Domain Adaptation for Pose Estimation (UDAPose), a novel framework that synthesizes low-light images and dynamically fuses visual cues with pose priors for improved pose estimation. Specifically, our synthesis method incorporates a Direct-Current-based High-Pass Filter (DHF) and a Low-light Characteristics Injection Module (LCIM) to inject high-frequency details from input low-light images, overcoming rigidity or the detail loss in existing approaches. Furthermore, we introduce a Dynamic Control of Attention (DCA) module that adaptively balances image cues with learned pose priors in the Transformer architecture. Experiments show that UDAPose outperforms state-of-the-art methods, with notable AP gains of 10.1 (56.4%) on the ExLPose-test hard set (LL-H) and 7.4 (31.4%) in cross-dataset validation on EHPT-XC. Code: https://github.com/Vision-and-Multimodal-Intelligence-Lab/UDAPose

---

### PatchRecall: Patch-Driven Retrieval for Automated Program Repair

Authors: Mahir Labib Dihan, Faria Binta Awal, Md. Ishrak Ahsan
Published: 2026-04-12
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2604.10481v1

Retrieving the correct set of files from a large codebase is a crucial step in Automated Program Repair (APR). High recall is necessary to ensure that the relevant files are included, but simply increasing the number of retrieved files introduces noise and degrades efficiency. To address this tradeoff, we propose PatchRecall, a hybrid retrieval approach that balances recall with conciseness. Our method combines two complementary strategies: (1) codebase retrieval, where the current issue description is matched against the codebase to surface potentially relevant files, and (2) history-based retrieval, where similar past issues are leveraged to identify edited files as candidate targets. Candidate files from both strategies are merged and reranked to produce the final retrieval set. Experiments on SWE-Bench demonstrate that PatchRecall achieves higher recall without significantly increasing retrieved file count, enabling more effective APR.

---

### Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs

Authors: Yu Li, Xiaoran Shang, Qizhi Pei, Yun Zhu, Xin Gao, Honglin Lin, Zhanping Zhong, Zhuoshi Pan, Zheng Liu, Xiaoyang Wang, Conghui He, Dahua Lin et al.
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10480v1

Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs), yet datasets are often treated as isolated artifacts, overlooking the systemic connections that underlie their evolution. To disentangle these complex relationships, we introduce the concept of \textbf{data lineage} to the LLM ecosystem and propose an automated multi-agent framework to reconstruct the evolutionary graph of dataset development. Through large-scale lineage analysis, we characterize domain-specific structural patterns, such as vertical refinement in math-oriented datasets and horizontal aggregation in general-domain corpora. Moreover, we uncover pervasive systemic issues, including \textit{structural redundancy} induced by implicit dataset intersections and the \textit{propagation of benchmark contamination} along lineage paths. To demonstrate the practical value of lineage analysis for data construction, we leverage the reconstructed lineage graph to create a \textit{lineage-aware diversity-oriented dataset}. By anchoring instruction sampling at upstream root sources, this approach mitigates downstream homogenization and hidden redundancy, yielding a more diverse post-training corpus. We further highlight lineage-centric analysis as an efficient and robust topological alternative to sample-level dataset comparison for large-scale data ecosystems. By grounding data construction in explicit lineage structures, our work advances post-training data curation toward a more systematic and controllable paradigm.

---

### PEMAND: Persona-Enriched Multi-Agent Negotiation for Household Decision-Making

Authors: Yuran Sun, Mustafa Sameen, Yaotian Zhang, Rongguan Gu, Mrunal Vibhute, Chia-yu Wu, Yuanyuan Lei, Xilei Zhao
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10475v2

Modeling household-level decisions is central to many real-world applications, including trip planning, residential mobility and migration, disaster management, etc. Existing studies primarily rely on classical machine learning models with limited predictive capacity, while recent LLM-based approaches have yet to incorporate behavioral theory or intra-household interaction dynamics, both of which are essential for modeling realistic household decisions. To address these limitations, we propose Persona-Enriched Multi-Agent Negotiation for household Decision-making (PEMAND), a novel LLM-based framework that integrates behavioral theory into individualized, household-aware persona modeling and simulates household-level decision-making through structured multi-agent negotiation. Specifically, PEMAND transforms static sociodemographic attributes into coherent narrative profiles that explicitly encode household-level attitudes, subjective norms, and perceived behavioral controls, following our proposed Household-Aware Chain-of-Planned-Behavior (HA-CoPB) framework. Building on these theory-grounded personas, PEMAND captures real-world household decision negotiation via a structured two-phase multi-agent conversation framework with a novel persona-alignment control mechanism. Evaluated on national and regional household decision datasets across two major domains, including travel behavior and residential mobility, PEMAND consistently outperforms state-of-the-art benchmarks.

---

### From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation

Authors: Mingfei Lu, Yi Zhang, Mengjia Wu, Yue Feng
Published: 2026-04-12
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.10470v1

Legal consultation question answering (Legal CQA) presents unique challenges compared to traditional legal QA tasks, including the scarcity of high-quality training data, complex task composition, and strong contextual dependencies. To address these, we construct JurisCQAD, a large-scale dataset of over 43,000 real-world Chinese legal queries annotated with expert-validated positive and negative responses, and design a structured task decomposition that converts each query into a legal element graph integrating entities, events, intents, and legal issues. We further propose JurisMA, a modular multi-agent framework supporting dynamic routing, statutory grounding, and stylistic optimization. Combined with the element graph, the framework enables strong context-aware reasoning, effectively capturing dependencies across legal facts, norms, and procedural logic. Trained on JurisCQAD and evaluated on a refined LawBench, our system significantly outperforms both general-purpose and legal-domain LLMs across multiple lexical and semantic metrics, demonstrating the benefits of interpretable decomposition and modular collaboration in Legal CQA.

---

### Exact Finite-Sample Variance Decomposition of Subagging: A Spectral Filtering Perspective

Authors: Ye Su, Mingrui Ye, Yining Wang, Jipeng Guo, Yong Liu
Published: 2026-04-12
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.10469v1

Standard resampling ratios (e.g., $α\approx 0.632$) are widely used as default baselines in ensemble learning for three decades. However, how these ratios interact with a base learner's intrinsic functional complexity in finite samples lacks a exact mathematical characterization. We leverage the Hoeffding-ANOVA decomposition to derive the first exact, finite-sample variance decomposition for subagging, applicable to any symmetric base learner without requiring asymptotic limits or smoothness assumptions. We establish that subagging operates as a deterministic low-pass spectral filter: it preserves low-order structural signals while attenuating $c$-th order interaction variance by a geometric factor approaching $α^c$. This decoupling reveals why default baselines often under-regularize high-capacity interpolators, which instead require smaller $α$ to exponentially suppress spurious high-order noise. To operationalize these insights, we propose a complexity-guided adaptive subsampling algorithm, empirically demonstrating that dynamically calibrating $α$ to the learner's complexity spectrum consistently improves generalization over static baselines.

---

### ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos

Authors: Arjun Somayazulu, Kristen Grauman
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10466v2

Visual feedback is critical for motor skill acquisition in sports and rehabilitation, and psychological studies show that observing near-perfect versions of one's own performance accelerates learning more effectively than watching expert demonstrations alone. We propose to enable such personalized feedback by automatically editing a person's motion to reflect higher skill. Existing motion editing approaches are poorly suited for this setting because they assume paired input-output data -- rare and expensive to curate for skill-driven tasks -- and explicit edit guidance at inference. We introduce ExpertEdit, a framework for skill-driven motion editing trained exclusively on unpaired expert video demonstrations. ExpertEdit learns an expert motion prior with a masked language modeling objective that infills masked motion spans with expert-level refinements. At inference, novice motion is masked at skill-critical moments and projected into the learned expert manifold, producing localized skill improvements without paired supervision or manual edit guidance. Across eight diverse techniques and three sports from Ego-Exo4D and Karate Kyokushin, ExpertEdit outperforms state-of-the-art supervised motion editing methods on multiple metrics of motion realism and expert quality. Project page: https://vision.cs.utexas.edu/projects/expert_edit/ .

---

### ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos

Authors: Arjun Somayazulu, Kristen Grauman
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10466v1

Visual feedback is critical for motor skill acquisition in sports and rehabilitation, and psychological studies show that observing near-perfect versions of one's own performance accelerates learning more effectively than watching expert demonstrations alone. We propose to enable such personalized feedback by automatically editing a person's motion to reflect higher skill. Existing motion editing approaches are poorly suited for this setting because they assume paired input-output data -- rare and expensive to curate for skill-driven tasks -- and explicit edit guidance at inference. We introduce ExpertEdit, a framework for skill-driven motion editing trained exclusively on unpaired expert video demonstrations. ExpertEdit learns an expert motion prior with a masked language modeling objective that infills masked motion spans with expert-level refinements. At inference, novice motion is masked at skill-critical moments and projected into the learned expert manifold, producing localized skill improvements without paired supervision or manual edit guidance. Across eight diverse techniques and three sports from Ego-Exo4D and Karate Kyokushin, ExpertEdit outperforms state-of-the-art supervised motion editing methods on multiple metrics of motion realism and expert quality. Project page: https://vision.cs.utexas.edu/projects/expert_edit/ .

---

### Rethinking the Diffusion Model from a Langevin Perspective

Authors: Candi Zheng, Yuan Lan
Published: 2026-04-12
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2604.10465v1

Diffusion models are often introduced from multiple perspectives, such as VAEs, score matching, or flow matching, accompanied by dense and technically demanding mathematics that can be difficult for beginners to grasp. One classic question is: how does the reverse process invert the forward process to generate data from pure noise? This article systematically organizes the diffusion model from a fresh Langevin perspective, offering a simpler, clearer, and more intuitive answer. We also address the following questions: how can ODE-based and SDE-based diffusion models be unified under a single framework? Why are diffusion models theoretically superior to ordinary VAEs? Why is flow matching not fundamentally simpler than denoising or score matching, but equivalent under maximum-likelihood? We demonstrate that the Langevin perspective offers clear and straightforward answers to these questions, bridging existing interpretations of diffusion models, showing how different formulations can be converted into one another within a common framework, and offering pedagogical value for both learners and experienced researchers seeking deeper intuition.

---

### Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection

Authors: Xinlei Guan, David Arosemena, Tejaswi Dhandu, Kuan Huang, Meng Xu, Miles Q. Li, Bingyu Shen, Ruiyang Qin, Umamaheswara Rao Tida, Boyang Li
Published: 2026-04-12
Categories: cs.CV, cs.AI, cs.CR, cs.ET
arXiv: https://arxiv.org/abs/2604.10460v1

The rapid growth of generative AI has introduced new challenges in content moderation and digital forensics. In particular, benign AI-generated images can be paired with harmful or misleading text, creating difficult-to-detect misuse. This contextual misuse undermines the traditional moderation framework and complicates attribution, as synthetic images typically lack persistent metadata or device signatures. We introduce a steganography enabled attribution framework that embeds cryptographically signed identifiers into images at creation time and uses multimodal harmful content detection as a trigger for attribution verification. Our system evaluates five watermarking methods across spatial, frequency, and wavelet domains. It also integrates a CLIP-based fusion model for multimodal harmful-content detection. Experiments demonstrate that spread-spectrum watermarking, especially in the wavelet domain, provides strong robustness under blur distortions, and our multimodal fusion detector achieves an AUC-ROC of 0.99, enabling reliable cross-modal attribution verification. These components form an end-to-end forensic pipeline that enables reliable tracing of harmful deployments of AI-generated imagery, supporting accountability in modern synthetic media environments. Our code is available at GitHub: https://github.com/bli1/steganography

---

### Dynamic Adaptive Attention and Supervised Contrastive Learning: A Novel Hybrid Framework for Text Sentiment Classification

Authors: Qingyang Li
Published: 2026-04-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.10459v1

The exponential growth of user-generated movie reviews on digital platforms has made accurate text sentiment classification a cornerstone task in natural language processing. Traditional models, including standard BERT and recurrent architectures, frequently struggle to capture long-distance semantic dependencies and resolve ambiguous emotional expressions in lengthy review texts. This paper proposes a novel hybrid framework that seamlessly integrates dynamic adaptive multi-head attention with supervised contrastive learning into a BERT-based Transformer encoder. The dynamic adaptive attention module employs a global context pooling vector to dynamically regulate the contribution of each attention head, thereby focusing on critical sentiment-bearing tokens while suppressing noise. Simultaneously, the supervised contrastive learning branch enforces tighter intra-class compactness and larger inter-class separation in the embedding space. Extensive experiments on the IMDB dataset demonstrate that the proposed model achieves competitive performance with an accuracy of 94.67\%, outperforming strong baselines by 1.5--2.5 percentage points. The framework is lightweight, efficient, and readily extensible to other text classification tasks.

---

### Towards Green Wearable Computing: A Physics-Aware Spiking Neural Network for Energy-Efficient IMU-based Human Activity Recognition

Authors: Naichuan Zheng, Hailun Xia, Zepeng Sun, Weiyi Li, Yinzhe Zhou
Published: 2026-04-12
Categories: cs.LG, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2604.10458v2

Wearable IMU-based Human Activity Recognition (HAR) relies heavily on Deep Neural Networks (DNNs), which are burdened by immense computational and buffering demands. Their power-hungry floating-point operations and rigid requirement to process complete temporal windows severely cripple battery-constrained edge devices. While Spiking Neural Networks (SNNs) offer extreme event-driven energy efficiency, standard architectures struggle with complex biomechanical topologies and temporal gradient degradation. To bridge this gap, we propose the Physics-Aware Spiking Neural Network (PAS-Net), a fully multiplier-free architecture explicitly tailored for Green HAR. Spatially, an adaptive symmetric topology mixer enforces human-joint physical constraints. Temporally, an $O(1)$-memory causal neuromodulator yields context-aware dynamic threshold neurons, adapting actively to non-stationary movement rhythms. Furthermore, we leverage a temporal spike error objective to unlock a flexible early-exit mechanism for continuous IMU streams. Evaluated across seven diverse datasets, PAS-Net achieves state-of-the-art accuracy while replacing dense operations with sparse 0.1 pJ integer accumulations. Crucially, its confidence-driven early-exit capability drastically reduces dynamic energy consumption by up to 98\%. PAS-Net establishes a robust, ultra-low-power neuromorphic standard for always-on wearable sensing. The source code and pre-trained models are publicly available at https://github.com/zhengnaichuan2022/PAS-Net.git.

---

### A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation

Authors: Peixuan Zhang, Chang Zhou, Ziyuan Zhang, Hualuo Liu, Chunjie Zhang, Jingqi Liu, Xiaohui Zhou, Xi Chen, Shuchen Weng, Si Li, Boxin Shi
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10456v1

The surging demand for adapting long-form cinematic content into short videos has motivated the need for versatile automatic video compilation systems. However, existing compilation methods are limited to predefined tasks, and the community lacks a comprehensive benchmark to evaluate the cinematic compilation. To address this, we introduce CineBench, the first benchmark for instruction-driven cinematic video compilation, featuring diverse user instructions and high-quality ground-truth compilations annotated by professional editors. To overcome contextual collapse and temporal fragmentation, we present CineAgents, a multi-agent system that reformulates cinematic video compilation into ``design-and-compose'' paradigm. CineAgents performs script reverse-engineering to construct a hierarchical narrative memory to provide multi-level context and employs an iterative narrative planning process that refines a creative blueprint into a final compiled script. Extensive experiments demonstrate that CineAgents significantly outperforms existing methods, generating compilations with superior narrative coherence and logical coherence.

---

### EviCare: Enhancing Diagnosis Prediction with Deep Model-Guided Evidence for In-Context Reasoning

Authors: Hengyu Zhang, Xuyun Zhang, Pengxiang Zhan, Linhao Luo, Hang Lv, Yanchao Tan, Shirui Pan, Carl Yang
Published: 2026-04-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.10455v1

Recent advances in large language models (LLMs) have enabled promising progress in diagnosis prediction from electronic health records (EHRs). However, existing LLM-based approaches tend to overfit to historically observed diagnoses, often overlooking novel yet clinically important conditions that are critical for early intervention. To address this, we propose EviCare, an in-context reasoning framework that integrates deep model guidance into LLM-based diagnosis prediction. Rather than prompting LLMs directly with raw EHR inputs, EviCare performs (1) deep model inference for candidate selection, (2) evidential prioritization for set-based EHRs, and (3) relational evidence construction for novel diagnosis prediction. These signals are then composed into an adaptive in-context prompt to guide LLM reasoning in an accurate and interpretable manner. Extensive experiments on two real-world EHR benchmarks (MIMIC-III and MIMIC-IV) demonstrate that EviCare achieves significant performance gains, which consistently outperforms both LLM-only and deep model-only baselines by an average of 20.65\% across precision and accuracy metrics. The improvements are particularly notable in challenging novel diagnosis prediction, yielding average improvements of 30.97\%.

---

### AIM-Bench: Benchmarking and Improving Affective Image Manipulation via Fine-Grained Hierarchical Control

Authors: Shi Chen, Xuecheng Wu, Heli Sun, Yunyun Shi, Xinyi Yin, Fengjian Xue, Jinheng Xie, Dingkang Yang, Hao Wang, Junxiao Xue, Liang He
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10454v1

Affective Image Manipulation (AIM) aims to evoke specific emotions through targeted editing. Current image editing benchmarks primarily focus on object-level modifications in general scenarios, lacking the fine-grained granularity to capture affective dimensions. To bridge this gap, we introduce the first benchmark designed for AIM termed AIM-Bench. This benchmark is built upon a dual-path affective modeling scheme that integrates the Mikels emotion taxonomy with the Valence-Arousal-Dominance framework, enabling high-level semantic and fine-grained continuous manipulation. Through a hierarchical human-in-the-loop workflow, we finally curate 800 high-quality samples covering 8 emotional categories and 5 editing types. To effectively assess performance, we also design a composite evaluation suite combining rule-based and model-based metrics to holistically assess instruction consistency, aesthetics, and emotional expressiveness. Extensive evaluations reveal that current editing models face significant challenges, most notably a prevalent positivity bias, which stemming from inherent imbalances in training data distribution. To tackle this, we propose a scalable data engine utilizing an inverse repainting strategy to construct AIM-40k, a balanced instruction-tuning dataset comprising 40k samples. Concretely, we enhance raw affective images via generative redrawing to establish high-fidelity ground truths, and synthesize input images with divergent emotions and paired precise instructions. Fine-tuning a baseline model on AIM-40k yields a 9.15% relative improvement in overall performance, demonstrating the effectiveness of our AIM-40k. Our data and related code will be made open soon.

---

### NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning

Authors: Yanyi Su, Hongshuai Wang, Zhifeng Gao, Jun Cheng
Published: 2026-04-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.10452v2

Olfaction lies at the intersection of chemical structure, neural encoding, and linguistic perception, yet existing representation methods fail to fully capture this pathway. Current approaches typically model only isolated segments of the olfactory pathway, overlooking the complete chain from molecule to receptors to linguistic descriptions. Such fragmentation yields learned embeddings that lack both biological grounding and semantic interpretability. We propose NOSE (Neural Olfactory-Semantic Embedding), a representation learning framework that aligns three modalities along the olfactory pathway: molecular structure, receptor sequence, and natural language description. Rather than simply fusing these signals, we decouple their contributions via orthogonal constraints, preserving the unique encoded information of each modality. To address the sparsity of olfactory language, we introduce a weak positive sample strategy to calibrate semantic similarity, preventing erroneous repulsion of similar odors in the feature space. Extensive experiments demonstrate that NOSE achieves state-of-the-art (SOTA) performance and excellent zero-shot generalization, confirming the strong alignment between its representation space and human olfactory intuition.Code and data are available at https://github.com/Xianyusyy/NOSE

---

### Parameter Efficient Fine-tuning for Domain-specific Gastrointestinal Disease Recognition

Authors: Sanjaya Poudel, Nikita Kunwor, Raj Simkhada, Mustafa Munir, Manish Dhakal, Khem Poudel
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10451v1

Despite recent advancements in the field of medical image analysis with the use of pretrained foundation models, the issue of distribution shifts between cross-source images largely remains adamant. To circumvent that issue, investigators generally train a separate model for each source. However, this method becomes expensive when we fully fine-tune pretrained large models for a single dataset, as we must store multiple copies of those models. Thus, in this work, we propose using a low-rank adaptation (LoRA) module for fine-tuning downstream classification tasks. LoRAs learn lightweight task-specific low-rank matrices that perturb pretrained weights to optimize those downstream tasks. For gastrointestinal tract diseases, they exhibit significantly better results than end-to-end finetuning with improved parameter efficiency. Code is available at: github.com/sanjay931/peft-gi-recognition.

---

### Instruction Data Selection via Answer Divergence

Authors: Bo Li, Mingda Wang, Shikun Zhang, Wei Ye
Published: 2026-04-12
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.10448v2

Instruction tuning relies on large instruction-response corpora whose quality and composition strongly affect downstream performance. We propose Answer Divergence-Guided Selection (ADG), which selects instruction data based on the geometric structure of multi-sample outputs. ADG draws several high-temperature generations per instruction, maps responses into an embedding space, and computes an output divergence score that jointly encodes dispersion magnitude and shape anisotropy. High scores correspond to instructions whose answers are both far apart and multi-modal, rather than clustered paraphrases along a single direction. Across two backbones and three public instruction pools, fine-tuning on only 10K ADG-selected examples consistently outperforms strong selectors on six benchmarks spanning reasoning, knowledge, and coding. Analyses further show that both dispersion magnitude and shape anisotropy are necessary, supporting answer divergence as a practical signal for instruction data selection. Code and appendix are included in the supplementary materials.

---

### ReContraster: Making Your Posters Stand Out with Regional Contrast

Authors: Peixuan Zhang, Zijian Jia, Ziqi Cai, Shuchen Weng, Si Li, Boxin Shi
Published: 2026-04-12
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.10442v1

Effective poster design requires rapidly capturing attention and clearly conveying messages. Inspired by the ``contrast effects'' principle, we propose ReContraster, the first training-free model to leverage regional contrast to make posters stand out. By emulating the cognitive behaviors of a poster designer, ReContraster introduces the compositional multi-agent system to identify elements, organize layout, and evaluate generated poster candidates. To further ensure harmonious transitions across region boundaries, ReContraster integrates the hybrid denoising strategy during the diffusion process. We additionally contribute a new benchmark dataset for comprehensive evaluation. Seven quantitative metrics and four user studies confirm its superiority over relevant state-of-the-art methods, producing visually striking and aesthetically appealing posters.

---

### VeriSim: A Configurable Framework for Stress-Testing Medical AI Under Patient Communication Noise

Authors: Sina Mansouri, Mohit Marvania, Vibhavari Ashok Shihorkar, Han Ngoc Tran, Kazhal Shafiei, Mehrdad Fazli, Yikuan Li, Ziwei Zhu
Published: 2026-04-12
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.10441v2

Medical large language models are typically evaluated on idealized patient cases that do not reflect how real patients communicate. We introduce VeriSim, a patient simulation framework that injects controllable noise along six clinically grounded communication dimensions while substantially preserving each patient's medical record. Truth adherence is supported by a verifier that extracts atomic claims from each candidate utterance and judges them against a UMLS-grounded vector index built with BioLORD embeddings, using the retrieved atoms' structured clinical metadata (e.g., drug class, anatomical site, treats-condition relations) rather than surface-text similarity alone. Across seven open-weight LLMs, realistic noise reduces diagnostic accuracy by 15-25 percentage points and increases conversation length by 34-55%; the 7-8B models degrade 1.4x more than 70B+ models. A board-certified physician and a licensed nurse rate VeriSim's conversations highly on truth, realism, clinical utility, and noise fidelity (inter-annotator agreement >= 0.80 across all dimensions), and an LLM-as-judge closely tracks their ratings, enabling scalable evaluation. We release VeriSim as an open-source framework for rigorous stress-testing of clinical AI: https://github.com/mohitmarvania/VeriSim

---