| 1 | Let CSP Be Your ANCHOR: Adaptive Crystal Search over Frozen Structure Priors | Emma Lei Hovmand, Jonas Elsborg, Melih Kandemir +1 | cond-mat.mtrl-sci | 2026-09-27 |
| 2 | Agent Safety From Within: Detecting Harmful Trajectories from LLM Internal States | Difan Jiao, Ashton Anderson | cs.AI | 2026-09-27 |
| 3 | BudgetVerify: Budget-Tiered Verification for Financial QA | Janet Jenq, Hongda Shen | cs.AI | 2026-09-27 |
| #4 | Large Language Models Substantially Compress Well-Being Inequality but Largely Preserve Its Socioeconomic Structure | Nattavudh Powdthavee | cs.AI | 2026-09-27 |
| #5 | LLM sequential decision making under uncertainty in biochemical domains | Mattias Akke, Soojung Yang, Jurgis Ruža +2 | cs.AI | 2026-09-27 |
| #6 | QureRadEmbed: Structuring Radiological Similarity through Attribute and Reasoning Supervision | Janhavi Prabhu, Sahil, Shivam Ashok Shukla +1 | cs.AI | 2026-09-27 |
| #7 | Structure-Mapping-Guided Self-Explanation for Learning Mathematical Procedures | Shinhaeng Lee, Christopher J. MacLellan, Daniel Weitekamp | cs.AI | 2026-09-27 |
| #8 | The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration | Jin Cui, Xinyue Long, Boran Zhao +2 | cs.AI | 2026-09-27 |
| #9 | Modular Discovery of General Game-Playing Algorithms with Large Language Models | Zun Li, John Schultz, Marc Lanctot +1 | cs.AI | 2026-09-27 |
| #10 | Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring | Zhixiang Zhang, Zesen Liu, Wai Ip Lai +2 | cs.AI | 2026-09-27 |
| #11 | Ceiling of a Task: When Can a Transformer Succeed Without Its Chain of Thought? | Jiashu He, Jinxuan Fan, Xiao Xiao +2 | cs.AI | 2026-09-27 |
| #12 | On Device Agentic Operation Caches -- Classifier-Centric NL-to-Action Generation | Moghis Fereidouni, Anthony Arnold, Sumit Gulwani +2 | cs.AI | 2026-09-27 |
| #13 | LiteEvo: Automated, Cost-Efficient Harness Evolution for Generalization to Unseen Tasks | Euntae Choi, Sumin Song, Sungjoo Yoo | cs.AI | 2026-09-27 |
| #14 | Not Too Hard, Not Too Easy: Learning from Intermediate States for LLM Structured Reasoning | Hongbo Chen, Guohua Lu, Ting Dang +1 | cs.AI | 2026-09-27 |
| #15 | SeOPD: Self-Evolving LLMs via Online Policy Distillation from Self-Generated Chain-of-Thought | Xiaoshu Chen, Xiangyu Wong, Sihang Zhou +2 | cs.AI | 2026-09-27 |
| #16 | Unlocking Latent Personalization in LLMs | Wei Chen, Guanghui Zhu, Zhongliang Cai +1 | cs.AI | 2026-09-27 |
| #17 | Are Benchmarks Reliable? Toward Structural Diagnosis via Sample-Level Capability Boundaries | Haiquan Hu, Yuzhu Liang, Weicheng Tang +3 | cs.AI | 2026-09-27 |
| #18 | WorldAgent: Verification-Guided Agentic Physical World Construction | Caoliwen Wang, Mengdi Wang, Yige Chen +13 | cs.AI | 2026-09-27 |
| #19 | CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents | Song-Li Wu, Jingyi Wang, Zhaocheng Du +2 | cs.AI | 2026-09-27 |
| #20 | ActiveMem: Dynamic Latent Memory Trees for Long-Horizon Agents | Song-Li Wu, Jingyi Wang, Zhaocheng Du +1 | cs.AI | 2026-09-27 |
| #21 | CORTEX: A Verified Experience Layer for Generalist Agents | Garapati Keerthana, Manik Gupta | cs.AI | 2026-09-27 |
| #22 | LSTMem: Hierarchical Long Short-Term Online Memory for Large Language Models | Xianglong Shi, Ruijie Yang, Sirui Zhao +4 | cs.AI | 2026-09-27 |
| #23 | Structured Sparse Memory for Recurrent Reasoning | Zixuan Zhao, Samuel Wheeler, Neil Getty +3 | cs.AI | 2026-09-27 |
| #24 | Next Thoughts Are Distributions: Generative Autoregressive Reasoning in the Latent Space | Yang Li, Yi Wang, Shiyuan Huang +3 | cs.AI | 2026-09-27 |
| #25 | ChronoFlow: Hierarchical Flow Matching for Irregular Time Series Generation | Changhun Kim, Sunguk Jang, Jeongjun Lee +5 | cs.AI | 2026-09-27 |
| #26 | Multi-Dimensional Comparative Scale Construction for Efficient Personalized Subjective Judgment in High-Traffic Applications | Xianglong Shi, Shifeng Liu, Sirui Zhao +2 | cs.AI | 2026-09-27 |
| #27 | RINI: Seeing the Prior Is Not Enough | Hongyi Du, Tianyi Zhang, Heng Wang +7 | cs.AI | 2026-09-27 |
| #28 | Feedback Makes Perfect: A Closed-Loop Framework for NL-to-STL Translation | Bowen Ye, Xiang Yin | cs.AI | 2026-09-27 |
| #29 | Learning to Sell: Reinforcement Learning for Strategic Large Language Model Agents in Multi-Product Markets | Shuze Daniel Liu, Claire Chen, Jiuqi Wang +1 | cs.AI | 2026-09-27 |
| #30 | TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces | Dehai Min, Daoan Zhang, Yiming Zeng +13 | cs.AI | 2026-09-27 |
| #31 | The Error You See Is Not the Error You Made: Progression-aware Reasoning Origin for Reasoning Error Localization | Yiguo Wang, Ziyuan Yang, Yi Zou +3 | cs.AI | 2026-09-27 |
| #32 | PhysAlign: A Benchmark for Evidence-Grounded Role Alignment in Multimodal Physics Reasoning | Kecheng Liang, Haoyang Liu, Zexin Chen +5 | cs.AI | 2026-09-27 |
| #33 | Agentic Multi-Turn Reasoning: A Fairness Approach | Thanh-Dat Truong, Sankalp Pandey, Hugh Churchill +3 | cs.AI | 2026-09-27 |
| #34 | ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces | Jerry Wang, Haibo Jin, Xiaopeng Yuan +2 | cs.AI | 2026-09-27 |
| #35 | Naturalness-guided Manifold Flow Matching for Sign Language Production | Jiayi He, Shengeng Tang, Sisi You +3 | cs.AI | 2026-09-27 |
| #36 | QuPID: Quantum Parameter-Efficient Input-Dependent Retrieval Adaptation for Medical RAG | Hyojun Ahn, Emily Jimin Roh, Soohyun Park +3 | cs.AI | 2026-09-27 |
| #37 | Unmask the State: When Does State Adaptation Matter for Masked Diffusion Language Models | Injin Kong, Sunghwan Choi, Yohan Jo | cs.AI | 2026-09-27 |
| #38 | Long-Horizon Analog Design Bench: Benchmarking Agents on Hours-Long Analog and Mixed-Signal Circuit Design Tasks | Analog Design Bench Team | cs.AI | 2026-09-27 |
| #39 | DISCERN: Can AI Agents Work Like Scientists and Guide Discovery? | Nan Huang, Mario Tapia-Pacheco, Kun Zhou +4 | cs.AI | 2026-09-27 |
| #40 | DrafTS: Time-Aware Decomposition with Residual Correction for Time Series Modeling | Yiqiu Liu, Siru Zhong, Zhiguang Wang +2 | cs.AI | 2026-09-27 |
| #41 | Cross-modal Translation via Conditional Latent Denoising for Video Deepfake Detection | Xinzhe Li, Youzhi Tu, Kong Aik Lee | cs.AI | 2026-09-27 |
| #42 | CoViST: Visual Token Compression via Composable States | Qi Zhang, Xiandong Meng, Ronggang Wang +1 | cs.AI | 2026-09-27 |
| #43 | COEVO: Co-Evolving Context and Parameters for Recursive Self-Improvement | Siwei Chen, Xinping Bao, Xinyu Cai +3 | cs.AI | 2026-09-27 |
| #44 | MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses | Xuanjun Chen, Hua-Hsuan Chen, Wei-Chung Lu +3 | cs.AI | 2026-09-27 |
| #45 | Temporal Graph Learning of Wearable Actigraphy and Sleep Traces for Modelling Adolescent Crystallized Intelligence | Md. Tanvir Rahman, Nabil Anan Orka, Asaduzzaman Khan +1 | cs.AI | 2026-09-27 |
| #46 | APEX: An Extensible Model for Agent-Assisted Production Scheduling | Felix J. Grumbach, Stefan Görlitz | cs.AI | 2026-09-27 |
| #47 | Raven: The Harness of Harnesses for Composable Agentic Intelligence | EverMind AI | cs.AI | 2026-09-27 |
| #48 | MAC-Net: A Multi-Task Deep Learning Framework for Modeling Cognitive Function From Task-Based fMRI | Md. Tanvir Rahman, Nabil Anan Orka, Asaduzzaman Khan +1 | cs.AI | 2026-09-27 |
| #49 | What Shared Prefixes Hide: Trajectory Dropout for On-Policy Distillation | Zzizhuo Lin, Quanling Liu, Yi Yang +1 | cs.AI | 2026-09-27 |
| #50 | When Does the Concept of "Dog" Emerge in an Audio LLM? | Zhe Wang, Shiqi Liu, Ruiyun Zhong +2 | cs.AI | 2026-09-27 |
| #51 | LiveOption: Evaluating LLM Agents in Structured Option Trading with Nonlinear Payoffs | Haochen Luo, Yifan Li, Binh Minh An +4 | cs.AI | 2026-09-27 |
| #52 | Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs | Yirui Liu, Ruoling Qi, Xuaner Wu +6 | cs.AI | 2026-09-27 |
| #53 | Federated Multi-Modal Human Activity Recognition using Multi-Agent Reinforcement Learning | Debasmita Dey, Tanmay Sen, Himel Mallick | cs.AI | 2026-09-27 |
| #54 | RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse | Ruoling Qi, Yirui Liu, Xuaner Wu +5 | cs.AI | 2026-09-27 |
| #55 | When Evidence Changes the Subject: Subject-Typed Claim Licensing for Learned Routing | Jian Chen, Zixuan Yuan | cs.AI | 2026-09-27 |
| #56 | What Happens During Autonomous Deep Research After the User Steps Away? | Yimin Liu, Yijia Zhang, Yanmin Li +4 | cs.AI | 2026-09-27 |
| #57 | PPG-LM: A Photoplethysmography-Language Model with Multi-Level Clinical Alignment | Xiaoda Wang, Minxiao Wang, Maxwell A Xu +10 | cs.AI | 2026-09-27 |
| #58 | EverMine: Dissecting the Self-Evolution of Research Capabilities in Long-Horizon Alpha Research | Siyuan Li, Jiangfeng Zhang, Rui Yao +3 | cs.AI | 2026-09-27 |
| #59 | Reasoning on the Simplex: Geometric Fixed-Point Models | Talgat Daulbaev, Ilya Glazkov, Maxim Rakhuba +1 | cs.AI | 2026-09-27 |
| #60 | OSCC: Certified Observation-Safe Coupling Optimization for Gradient-Noise Control in Imperfect-Information Learning | Miaobo Hu, Shuhao Hu, Xiaobo Guo +5 | cs.AI | 2026-09-27 |
| #61 | Dr. Free: You Don't Need Difficulty Rewards for Self-Evolving Search Agents | Zhipeng Qian, Zihan Liang, Yufei Ma +10 | cs.AI | 2026-09-27 |
| #62 | OpenFC: Learning Verification Policies towards Open-Search Fact Checking | Xinming Wang, Kaixiang Qiu, Yansong Lin +5 | cs.AI | 2026-09-27 |
| #63 | JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization | Kaicheng Yang, Kaisen Yang, Chunyu Liu +8 | cs.AI | 2026-09-27 |
| #64 | Supervision Recovery for Time Series Anomaly Detection via Context-Anchored Pairing | Yifei Gao, Tian Lan, Yimeng Lu +5 | cs.AI | 2026-09-27 |
| #65 | EAT: Expert Account Tracker for Efficient MoE Inference | Yuexian Li, Yifei Yang, Zouying Cao +1 | cs.AI | 2026-09-27 |
| #66 | ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environments | Shengbin Yue, Hongru Wang, Siyuan Wang +3 | cs.AI | 2026-09-27 |
| #67 | Trajectory Unlearning on LLM-based Agents | Yingdan Shi, Ren Wang | cs.AI | 2026-09-27 |
| #68 | Scalable and Data-Driven Decision Support in the Maintenance, Repair, and Overhaul Process | Houkun Zhu, Helena Ebel, Dominik Scheinert +3 | cs.AI | 2026-09-27 |
| #69 | Probe to Act: Elevating Browser-Use Agent via Active Visual Probing | Keliang Li, Heng Wang, Chen Hu +3 | cs.AI | 2026-09-27 |
| #70 | AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents | Tianzhuo Yang, Zirui Mi, Yantao Huang +4 | cs.AI | 2026-09-27 |
| #71 | Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification | Miaobo Hu, Shuhao Hu, Xiaobo Guo +5 | cs.AI | 2026-09-27 |
| #72 | CompoWorld: Compositional Environment Scaling for General Agents | Xiao-Wen Yang, Weiyi Xu, Wen Da +9 | cs.AI | 2026-09-27 |
| #73 | RSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games | Miaobo Hu, Shuhao Hu, Xiaobo Guo +5 | cs.AI | 2026-09-27 |
| #74 | Auditing Agent Actions through Query-Conditioned Attribution | Yifan Liu, Praveen Venkateswaran, Abdulhamid Adebayo +1 | cs.AI | 2026-09-27 |
| #75 | SWE-Game: Can Coding Agents Build the Games We Want? | Xiaoyu Chen, Lai Wei, Jin Wang +8 | cs.AI | 2026-09-27 |
| #76 | TopoMamba: A Load-Support Relation-Guided Multi-Directional State-Space Model for Topology Optimization | Bin Lou, Yuxuan Cheng, Huaizhi Zong +2 | cs.AI | 2026-09-27 |
| #77 | One Latent, Many Tokens: Jointly Learning Compressed Embeddings for Efficient Language Diffusion | Yulin Yuan, Ying Zhang, Xiangming Meng | cs.AI | 2026-09-27 |
| #78 | SpecRead: A Benchmark for Measuring Whether Language Models Understand Hardware Specifications | Feilian Huang | cs.AI | 2026-09-27 |
| #79 | Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse | Futa Waseda, Shuhei Kurita, Isao Echizen | cs.AI | 2026-09-27 |
| #80 | BIRD: Distilling Decision Boundaries into Rationales for MLLM Adaptation | Anglin Liu, Yanlin Wu, Ruichao Chen +6 | cs.AI | 2026-09-27 |
| #81 | Self-Designed Evaluators and Warm Memory for Long-Horizon Agents | Saeid Asgari, Emre Kiciman, Leonardo de Oliveira Nunes +1 | cs.AI | 2026-09-27 |
| #82 | Robust Biomolecular Complex Design Across Protein Conformational Landscapes | Qingyuan Zeng, Zongqi Xu, Anglin Liu +7 | cs.AI | 2026-09-27 |
| #83 | HTN Planning as a Coordination Layer for Multi-Server MCP Tool Orchestration | Eliott Jacopin, Éric Jacopin, Koichi Takahashi | cs.AI | 2026-09-27 |
| #84 | Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents | Weiyi Xu, Xiaowen Yang, Wen Da +7 | cs.AI | 2026-09-27 |
| #85 | Learning Strategies to Break Judges | Guruprerana Shabadi, Aaditya Naik, Rajeev Alur +1 | cs.AI | 2026-09-27 |
| #86 | Evidence-Inference Reconstruction: When The Evidence Is Recalled But The Reasoning Goes Wrong | Megan Diehl, Ser-Nam Lim | cs.AI | 2026-09-27 |
| #87 | Is your uncertainty map wrong, or is its target? Exact diagnostics for the Tweedie diagonal, and a gradient-free alternative | Vicent Ribas, Anna Oliveras Tous | cs.AI | 2026-09-27 |
| #88 | Dual-Vocabulary Language Model for Cross-Tokenizer Distillation | Kedi Chen, Chen Lin, Yutao Sun +1 | cs.AI | 2026-09-27 |
| #89 | Vestrum: Improving Agent Harnesses by Adapting Their Verification, Structure and Memory | Jayant Parashar, Eugene F. Douglass, William C. Bastian +1 | cs.AI | 2026-09-27 |
| #90 | Laya as a Typed Probabilistic Assessor: An Independent Reproduction and a Preregistered Study of Calibration and Selective Escalation | Gowthamkumar Nandakishore | cs.AI | 2026-09-27 |
| #91 | How code helps different tasks? A decompositional lens on LLM post-training | Zheng Yu, Yiwei Li, Yishen Chen +4 | cs.AI | 2026-09-27 |
| #92 | R$^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution | Mingda Zhang, Qiang Huang, Yanjin Li +4 | cs.AI | 2026-09-27 |
| #93 | When Successful Strategies Fail: Adaptation to Environmental Novelty in Terminal Agents | Janvijay Singh, Vaishnavi Shrivastava, Dilek Hakkani-Tur +2 | cs.AI | 2026-09-27 |
| #94 | Curating Merchant-Matching Training Data with Two Confidence-Gated Local LLM Judges | Donghao Huang, Jinling Pei, Zhaoxia Wang | cs.AI | 2026-09-27 |
| #95 | When Consent Outlives Context: Residual Authority Replay in Long-Lived Agents | Zhihao Zhang, Chao Wang, Rujia Li +3 | cs.AI | 2026-09-27 |
| #96 | HyperMCTS: Hypergraph-Augmented MCTS for Long-Horizon LLM Agents | Tingsong Xiao, Nithish Balachandar Moudhgalya, Chandrayee Basu +5 | cs.AI | 2026-09-27 |
| #97 | Designing Reliable LLM-as-a-Judge Measurement Systems for Multi-Turn Business Agents | Kaiwen Luo, Ming Gao | cs.AI | 2026-09-27 |
| #98 | EHRAdapt: Adapting Pretrained Language Models to Electronic Health Records with Semantic Priors for Rare Clinical Events | Andre R Goncalves, Vincent Liu, Priyadip Ray | cs.AI | 2026-09-27 |
| #99 | A Computer Vision Approach to Visual Fraud Detection in Phishing Websites Using YOLOv8 | Basil Sajid Shaikh, Hajar Homayouni | cs.AI | 2026-09-27 |
| #100 | Jev in Medicine: A Benchmark Evaluation. Preliminary Results | Alfredo Madrid-García, Beatriz Merino-Barbancho | cs.AI | 2026-09-27 |
| #101 | MorphAtt: A Neuromorphic Accelerator for Efficient Multi-Head Attention Processing in Spiking Vision Transformers | Rachmad Vidya Wicaksana Putra, Amirhesam Jafari Rad, Muhammad Shafique | cs.AR | 2026-09-27 |
| #102 | Modelling non-linear aeroelastic loads in long-span bridges with extreme learning machines | Gledson Rodrigo Tondo, Samir Chawdhury, Sergio Andres Castro Giraldo +1 | cs.CE | 2026-09-27 |
| #103 | Learning Transferable Reaction Mechanisms from Visual Chemical Knowledge | Yujian Yuan, Jiaxin Xu, Xin Cai +4 | cs.CE | 2026-09-27 |
| #104 | Adapting neural operators for mechanics decisions under changing operating conditions | Prashant K. Jha, Koffi Enakoutsa, Ian Galloway +1 | cs.CE | 2026-09-27 |
| #105 | Improving the Diversity of LLM Outputs without a Trade-off | Ryoma Sato | cs.CL | 2026-09-27 |
| #106 | Pinned and Still Unstable: Within-Judge Verdict Variance and the Noise Floor of LLM-as-Judge Leaderboards | Krishna Chytanya Ayyagari | cs.CL | 2026-09-27 |
| #107 | Reading Too Much into Context: Passive Exposure Can Steer LLM Decisions | Yuxiang Zheng, Lin Tian, Marian-Andrei Rizoiu | cs.CL | 2026-09-27 |
| #108 | OneSign: Unifying Sign Language Understanding Tasks with One Model | Shiwei Gan, Yafeng Yin, Xiao Liu +3 | cs.CL | 2026-09-27 |
| #109 | MedRouter: Demystifying Knowledge Differences Across Medical LLMs for Routing-Based Reasoning | Lang Cao, Binghang Lu, Yuhao Shen +1 | cs.CL | 2026-09-27 |
| #110 | Classifying Dominant Temporal Orientation without Pretrained Text Embeddings: A Novel Morphosyntactic Inventory Vector Approach | Jonathan Cleveland, Peter S. Bearman | cs.CL | 2026-09-27 |
| #111 | Knowing Is Not Choosing: What Explicit Verification Adds Beyond Generative Preference | Yilong Li, Chengpo Yan, Aayan Arish +1 | cs.CL | 2026-09-27 |
| #112 | CAME: Company-Aware Evidence-Memory Experts for Interpretable Quarter-Ahead Revenue Forecasting | Ya-Wen Wu, Meng-Fen Chiang, Kuang-Da Wang +1 | cs.CL | 2026-09-27 |
| #113 | Generalization Dynamics of LM Pre-training | Jiaxin Wen, Zhengxuan Wu, Dawn Song +1 | cs.CL | 2026-09-27 |
| #114 | Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction? | Yuyang Zhao, Xuan Liu, HaoYang Shangm Haojian Jin | cs.CL | 2026-09-27 |
| #115 | Scoring the Wrong Question: Readout Failures in Constrained-Option Evaluation | Jiaxuan Guo, Kejia Zhang, Shuo Xin +3 | cs.CL | 2026-09-27 |
| #116 | Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall | Sanjay Govindan, Yang Song, Maurice Pagnucco | cs.CL | 2026-09-27 |
| #117 | Turning Speech Language Models into Multilingual Listeners | Tolúlopé Ògúnrèmí, Dan Jurafsky, Chris Manning +2 | cs.CL | 2026-09-27 |
| #118 | Beyond Calibration: Do a Typed-Decision Model's Probabilities Obey the Probability Axioms? | Keyi Li, Yihao He, Quanyi Li | cs.CL | 2026-09-27 |
| #119 | CoLMbo-SV: A Grounded Language Model for Explainable Speaker Verification | Massa Baali, Sarthak Bisht, Ziyue Qiu +3 | cs.CL | 2026-09-27 |
| #120 | Beyond Memory Construction: Rethinking Memory Access for LLM-based Conversational Agents | Donghua Cai, Yongheng Deng, Yifei Wang +2 | cs.CL | 2026-09-27 |
| #121 | The Text Beside the Image: Detection, Utility and Leakage for Trustworthy Multimodal Medical Data and Beyond | Andreas Maier, Monica Hinrichs-Mayer, Franziska Weber +4 | cs.CL | 2026-09-27 |
| #122 | Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models | Yadong Xi, Rongsheng Zhang, Tangjie Lv +2 | cs.CL | 2026-09-27 |
| #123 | BaatCheet: A Multilingual Corpus for Dialogue Translation in Indian Languages | Priyanka Dasari, Yuvrajsinh D. Bodana, Vandan Mujadia +3 | cs.CL | 2026-09-27 |
| #124 | Hesitation-Aware On-Policy Distillation for Diffusion Language Models | Jianguo Huang, Lipeng Wan, Yanchen Deng +1 | cs.CL | 2026-09-27 |
| #125 | CertMark: Distortion-Free Multi-Bit Watermarking with Certified Decoding | Paweł Batorski, Przemysław Spurek, Paul Swoboda | cs.CL | 2026-09-27 |
| #126 | Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training | Xinyu Che, Hang Yan, Yanchen Liu +5 | cs.CL | 2026-09-27 |
| #127 | CHI: A Composite Hallucination Index Unifying Entity, Relation, and Quantity Dimensions for Summarization Evaluation | Praveenkumar Katwe, Rakesh Chandra Balabantaray, Kali Prasad Vittala | cs.CL | 2026-09-27 |
| #128 | Language Discrimination Improves Linguistic Learning in Multilingual Speech Models | Maureen de Seyssel, Jie Chi, Zakaria Aldeneh | cs.CL | 2026-09-27 |
| #129 | NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents | Xu Liu, WenZhang Wei, Jun Cao +4 | cs.CL | 2026-09-27 |
| #130 | From Position Risks to Block Survival: Faster Generation for Diffusion Language Models | Siwei Chen, Yuxiang Wan, Yifan Yu +1 | cs.CL | 2026-09-27 |
| #131 | Preserving Morphemes: Morphology-Guided Pre-Tokenization for Nepali | Kalash Shrestha, Nikhil Pradhan | cs.CL | 2026-09-27 |
| #132 | Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation | Yuhao Sun, Binrui Wu, Zhuoer Xu +5 | cs.CL | 2026-09-27 |
| #133 | Grounding Memory Summarization in Utility Intent | Zhenyu Lei, Mingjia Shi, Xingbo Fu +3 | cs.CL | 2026-09-27 |
| #134 | TeacherGRPO: Closing the Capacity Gap in Reasoning Distillation via Teacher Alignment | Zhenyu Lei, Zihan Chen, Yaochen Zhu +5 | cs.CL | 2026-09-27 |
| #135 | MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation | Ruihong Zeng, Jonathan Tonglet, Preslav Nakov +1 | cs.CL | 2026-09-27 |
| #136 | Context Spanning: A Communication Framework for Full-Duplex Speech Models and External LLM Backends | Seonghyeon Go, Yongwoo Kim, Hyeonjin Cha +1 | cs.CL | 2026-09-27 |
| #137 | Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features | Cunchun Li, Haonan He, Yifan Gao +4 | cs.CL | 2026-09-27 |
| #138 | GSM: Efficient Language Modeling with Shared Global State | Yunao Zheng, Bin Wen, Xiaojie Wang +12 | cs.CL | 2026-09-27 |
| #139 | DISCO: Distributed Long Context Scaling with Grounding-Reasoning Disaggregation | Guanzheng Chen, Viet Dac Lai, Subhojyoti Mukherjee +5 | cs.CL | 2026-09-27 |
| #140 | LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems | Liron Soffer, Ravid Shwartz-Ziv, Chen Shani | cs.CL | 2026-09-27 |
| #141 | E-CONAN (Entailment, CONtradition And Neutral) Diagnostics Dataset Investigating Linguistic Phenomena in Arabic Natural Language Understanding | Khloud AL Jallad, Nada Ghneim, Ghaida Rebdawi | cs.CL | 2026-09-27 |
| #142 | ManiEdit: Sequential Unstructured Knowledge Editing for Language Models from a Manifold Perspective | Rui Liu, Chenheng Zhang, Haoxuan Li +1 | cs.CL | 2026-09-27 |
| #143 | Jev Matches 7B Language Models for Speech-Neuroprosthesis Rescoring | Gabriele Cinà | cs.CL | 2026-09-27 |
| #144 | Quizzing the Translation: A Prover-Grounded Evaluation Metric for NL$\rightarrow$FOL | Pu Suo, Ali Emami | cs.CL | 2026-09-27 |
| #145 | Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails | Gert Lek, Abele Malan, Chaoyi Zhu +3 | cs.CL | 2026-09-27 |
| #146 | Learning to Learn from Context: Synthetic Training from Perturbed Public Documents | Haoyi Wu, Yang Xiao, Yusong Sun +4 | cs.CL | 2026-09-27 |
| #147 | Tsubame: Tree Replay for Diffusion-Based Speculative Decoding | Yepeng Weng, Qiao Hu, Takehisa Yairi | cs.CL | 2026-09-27 |
| #148 | One Model Is Not a Crowd: Multi-LLM and Aspect-Conditioned Diverse Comment Generation | Nafis Irtiza Tripto, Delvin Ce Zhang, Mahjabin Nahar +1 | cs.CL | 2026-09-27 |
| #149 | Closing the Cross-Dialect Gap: Query Plans as a Portable Interface in Text-to-SQL | Corentin Royer, Robin Oester, Yotam Perlitz +3 | cs.CL | 2026-09-27 |
| #150 | Reset Is Not Recovery: Evaluating Recoverability from False Conversational Context via Sycophancy Hysteresis | Adi Shnaidman | cs.CL | 2026-09-27 |
| #151 | When Do Agents Help? Embedding, LLM and Agentic Alignment of Classical Texts and Their Translations | Máté Metzger | cs.CL | 2026-09-27 |
| #152 | Understanding Confabulation and Rethinking Reconstruction in Activation Explanations | Gert Lek, Zixuan Xia, Pin-Yu Chen +1 | cs.CL | 2026-09-27 |
| #153 | From Granular Revision Operations to Meaningful Revision Units: Evaluating LLMs for Revision Boundary Detection | Yu Tian, Andrew Potter, Katerina Christhilf +4 | cs.CL | 2026-09-27 |
| #154 | Shared Experience, Separate Learning: Companion Confidence Calibration for LLMs | Shiyu Ni, Keping Bi, Jiafeng Guo +4 | cs.CL | 2026-09-27 |
| #155 | Yorùbá in Unicode: An Overview of a Problem | Kólá Túbòsún | cs.CL | 2026-09-27 |
| #156 | The Effects of Incremental Instruction Delivery on Language-Model Creative Writing | Anshuman Singh, Abrar Eyasir, Haseeb Yaqoob +1 | cs.CL | 2026-09-27 |
| #157 | Positions Are Not Facts: The Mismatch Between KV Caches and Memory | Changhai Zhou, Yuhua Zhou, Shiyang Zhang +5 | cs.CL | 2026-09-27 |
| #158 | LA-CPD: Local-Evidence-Aware Change-Point Detection for Human-LLM Authorship Segmentation | Qing Yang, Zhenyu Mao, Zixiang Luo +5 | cs.CL | 2026-09-27 |
| #159 | In-Context Adaptation of Encoder-Decoder Models in Speech Recognition | Yen Meng, Sharon Goldwater, Hao Tang | cs.CL | 2026-09-27 |
| #160 | Lost with a Map: Conversational State and Behavioral Reliability in Language Models | Atahan Dokme, Larry Heck | cs.CL | 2026-09-27 |
| #161 | LLMs learn different forms of metacognition when trained to predict their own accuracy | Nicolas Yax, Stefano Palminteri, Pierre-Yves Oudeyer | cs.CL | 2026-09-27 |
| #162 | Faster Block-Diffusion Serving with Distribution-Free Risk Guarantees | Jungseob Lee, Dongyub Jude Lee, Chanjun Park +2 | cs.CL | 2026-09-27 |
| #163 | NSV-Shift: A Contrastive Benchmark for Non-Speech Vocalization Understanding and Response Adaptation in Speech-to-Speech Models | Ziwei Chen | cs.CL | 2026-09-27 |
| #164 | SlopBench: How Well Can We Rank Language Models by Slop? A Multi-Domain Benchmark of Repetitive AI Writing | Dhruv Roongta, Harsha Gaddipati, Anh Tuan Huynh | cs.CL | 2026-09-27 |
| #165 | Quantization Error Is Spectrally Flat: A Single Random Probe Is a Calibrated, Data-Free Sensitivity Estimator, with Application to Budget-Targeted Mixed-Precision Quantization | I Kennedy, T Kennedy | cs.CL | 2026-09-27 |
| #166 | Simple Diffusion Language Models Are More Effective Few-Step Generators Than Reported | Hasan Amin, Ming Yin, Rajiv Khanna | cs.CL | 2026-09-27 |
| #167 | On the Token Value Inequality in Efficient Reasoning | Runjia Zeng, Hang Hua, Yiyang Liu +5 | cs.CL | 2026-09-27 |
| #168 | Do System One Decisions Add Up? A Study of Probabilistic Coherence | Saman Sarker Joy | cs.CL | 2026-09-27 |
| #169 | Beyond Solo and Consistency: Vindicating Multi-Agent Debate via Conditional Progressive Pruning | Ruosong Ye, Caiqi Zhang, Jiahao Li +9 | cs.CL | 2026-09-27 |
| #170 | High-Level Text Preprocessing for Semantic Similarity Analysis of Discursive Texts: A Framework and Empirical Demonstration | Mehmet Murat Albayrakoglu, Mehmet Nafiz Aydin | cs.CL | 2026-09-27 |
| #171 | Opera: A Verbal Critic Framework for Long-horizon Coding Agents | Kai Mei, Zhiyuan Hu, Yutong Dai +7 | cs.CL | 2026-09-27 |
| #172 | RewardExplainer: Learning Reward Model Explanations from Counterfactual Preference Feedback | Jingyi He, Nier Wu, Shuang Liu +3 | cs.CL | 2026-09-27 |
| #173 | Faithful Activation Verbalization: Reducing Hallucinations in LLM Representation Interpretation | Haiyan Zhao, Zirui Hei, Wei Shi +3 | cs.CL | 2026-09-27 |
| #174 | API Secrets Should Never Become Tokens in the LLM's Vocabulary: A Threat Analysis of API Credential Handling in LLM Agent Systems and an Empirical Evaluation of a Vault-Mediated Execution Boundary | Patrick Kenney, Hadi Ahmadi, Denis Lusson +2 | cs.CR | 2026-09-27 |
| #175 | Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation | Yixuan Liu | cs.CR | 2026-09-27 |
| #176 | HESP: Separating What to Probe from When to Stop in Local LLM Alert-Triage Agents | Zhuowen Liu, Zhixuan Wang | cs.CR | 2026-09-27 |
| #177 | The Price of Peeking: Anytime-Valid Leakage Detection on ML-KEM EM Traces | Georgios Feretzakis, Alexandros Papaspyridis | cs.CR | 2026-09-27 |
| #178 | COGNIT-Guard: Calibrated Standalone Direct-Decision Guardrails with Heterogeneous CPU-NPU Confidence Cascading under Explicit Latency and False-Positive Constraints | Hao Chen | cs.CR | 2026-09-27 |
| #179 | SecProbe: Adaptive Evaluation of Coding Agents on Cybersecurity Vulnerabilities | Xiaonan Luo, Yue Huang, Kehan Guo +9 | cs.CR | 2026-09-27 |
| #180 | The Privacy Fallacy of Crowdsourced Fine-Tuning: Extracting Proprietary Data via Topic-Based Poisoning | Sae Furukawa, Alina Oprea | cs.CR | 2026-09-27 |
| #181 | NutriVision: Ingredient-Conditioned Fusion and Prediction for Single-Image Food Nutrition Estimation | Aman Kumar, Avinash Anand, Chaitanya Lakhchaura +5 | cs.CV | 2026-09-27 |
| #182 | Parameter-Efficient 3D Segmentation of Liver and Liver tumors: Depthwise factorization Scales Better Than Dense Convolution with Spatial Dimensionality | Adham M. Alkhadrawi, Mohammed A. B. Mahmoud | cs.CV | 2026-09-27 |
| #183 | SemReward-VL: Semantic Reward-Guided Video-Language Adaptation for Developmental Behavior Assessment | De Jiang, Shuo Zhang, Kehong Yuan +1 | cs.CV | 2026-09-27 |
| #184 | dKFD: Phase-Structured Evidence Allocation for Fixed-Budget Localized Event Understanding | Aditya Bagri, Ashutosh Kumar, Chaitanya Lakhchaura +3 | cs.CV | 2026-09-27 |
| #185 | QSCP: Beyond Class-Name Prompts for Query-Guided Semantic Change Parsing | Yuan Qian, Jie Ma | cs.CV | 2026-09-27 |
| #186 | Query, Align, and Distill: Navigation-Aware Cross-Modal Interaction for Efficient Vision-and-Language Navigation | Zhihao Chen, Yiyuan Ge, Ziyang Wang +2 | cs.CV | 2026-09-27 |
| #187 | Octree-based Video Representation | Rungui Zhou, Chuanzhi Zhou, Yuk-Kit Hou +1 | cs.CV | 2026-09-27 |
| #188 | Toward Comprehensive 3D Grounding: Orientation Grounding through Vision-Language Models | Tuo Liang, Disheng Liu, Nengbo Wang +2 | cs.CV | 2026-09-27 |
| #189 | Train Together or Merge Later? Unifying VLA Experts via a Shared Action Interface | Zhizhen Zhang, Yuxia Fu, Zijian Wang +2 | cs.CV | 2026-09-27 |
| #190 | DroneWAM: Efficient World Action Model for Drone Visual Navigation | Liang Yao, Fan Liu, Hongbo Lu +5 | cs.CV | 2026-09-27 |
| #191 | FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs | David Restrepo, Chenwei Wu, Luis Filipe Nakayama +4 | cs.CV | 2026-09-27 |
| #192 | FloodDiffusion 2: Efficient and Path Controllable Streaming Motion Generation | Yiyi Cai, Yuhan Wu, Kunhang Li +6 | cs.CV | 2026-09-27 |
| #193 | ABO-Med: Accelerated Bilevel Optimization for Few-Shot Medical Image Classification | Ruoxuan Shi, Sheng Yang, Zhengxing Su +2 | cs.CV | 2026-09-27 |
| #194 | Can Protein-Derived Knowledge Improve Pathology Foundation Models? | Di Zhang, Zhangpeng Gong, Jiashuai Liu +10 | cs.CV | 2026-09-27 |
| #195 | FocusDrive: Reasoning with Visual Focus for Autonomous Driving | Zhiyuan Liu, Zehong Ke, Yuanxin Tian +7 | cs.CV | 2026-09-27 |
| #196 | ReAL: Accelerating Flow Matching through Segment Advancement with Shared Lookahead | Xuanhua Yin, Chuanzhi Xu, Haoxian Zhou +2 | cs.CV | 2026-09-27 |
| #197 | Structured Residual Connectivity Matters for Diffusion Transformers | Yuhe Liu, Xinyin Ma, Gongfan Fang +2 | cs.CV | 2026-09-27 |
| #198 | Background Gradients Shape Memorization in Flow Matching | Xuanhua Yin, Boyu Wei, Shuyi Zhang +3 | cs.CV | 2026-09-27 |
| #199 | RepFlow: Reciprocal Supervision Improves Generation and Representation in Flow Models | Weili Zeng, Feng Tian, Shengqi Liu +1 | cs.CV | 2026-09-27 |
| #200 | Scope-WM: Scoped Computation for Efficient Visual World Models | Chunzheng Li, Zesheng Jia, Hongda Zhang +4 | cs.CV | 2026-09-27 |
| #201 | AevaScenes: An FMCW LiDAR Dataset and Benchmark for Long-Range Perception | Gautham Narayan Narasimhan, Heethesh Vhavle, Kumar Bhargav Viswanatha +2 | cs.CV | 2026-09-27 |
| #202 | PARSEE-VAD: Efficient Training-Free Online Video Anomaly Detection via Proposition-Aware Reasoning and Streaming Evidence Escalation | Ji Wang, Shuangqing Zhang, Guo-Sen Xie +1 | cs.CV | 2026-09-27 |
| #203 | VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis | Kangjie Chen, Xiangyu Li, Dongbin Zhang +12 | cs.CV | 2026-09-27 |
| #204 | EngIntervene: Benchmarking Multimodal Engineering State Understanding and Design Intervention Reasoning | Jinchang Zhang, Yingda Tao, Jiakai Lin +1 | cs.CV | 2026-09-27 |
| #205 | VehDyn: A Driving World Model Benchmark for Vehicle Dynamics | Tianyi Wang, Wangsheng Du, Jiazhou Chen +12 | cs.CV | 2026-09-27 |
| #206 | InfoEdit: Probing Global Layout Reasoning in Infographic Editing | Cheng Yang, Chufan Shi, Huijuan Wang +6 | cs.CV | 2026-09-27 |
| #207 | Informative Viewpoint Selection for Episodic-Memory Embodied Question Answering using Omnidirectional Images | Kaname Kitamura, Asako Kanezaki | cs.CV | 2026-09-27 |
| #208 | Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents | Fuyao Zhang, Xuan Wang, Zherui Li +3 | cs.CV | 2026-09-27 |
| #209 | LoopTrack: A Simple Baseline for Parameter-Efficient Transformer Tracking | Liang Peng, Chenxiao Li, Libo Zhang +2 | cs.CV | 2026-09-27 |
| #210 | PIC-UIE: Predicting Image-Adaptive Corrections for Lightweight Underwater Image Enhancement | Cunhao Zhu, Dongliang Xu, Xiangtao Kong +3 | cs.CV | 2026-09-27 |
| #211 | VisionHOPE: Visual Backbones as Self-Modifying Learning Systems | Siran Peng, Tianshuo Zhang, Tianyu Fu +8 | cs.CV | 2026-09-27 |
| #212 | FeCoSplat: Feedback-Guided Compression for Feed-Forward 3D Gaussian Splatting | Yuxuan Li, Yihang Chen, Yufeng Zhang +2 | cs.CV | 2026-09-27 |
| #213 | OPERA: A Unified Omnimodal Progressive Spatio-Temporal Reasoning Agent for Referring Video Segmentation | Jingchen Ni, Yuji Wang, Shannan Yan +3 | cs.CV | 2026-09-27 |
| #214 | ReLoc: Rethinking Scene Coordinate Regression Architecture for Robust Outdoor LiDAR-based Localization | Heejoon Moon, Yurim Cho, Je Hyeong Hong | cs.CV | 2026-09-27 |
| #215 | Focus and Supplement: Dual-Enhanced Vision Transformer for Multi-Class Anomaly Classification | Xurui Li, Enjie Xu, Chenzhou Li +4 | cs.CV | 2026-09-27 |
| #216 | When Does Geometric View Synthesis Help Wine Label Retrieval? A Public One-Shot Benchmark Across Self-Supervised and Vision-Language Backbones | Yueh-Cheng Huang | cs.CV | 2026-09-27 |
| #217 | PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers | Yutong Wang, Xingtong Ge, Enhuai Liu +4 | cs.CV | 2026-09-27 |
| #218 | SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation | Jiali Chen, Zhengteng Lin, Zuqi Wang +6 | cs.CV | 2026-09-27 |
| #219 | Groupwise Selective State-Space Filtering for Accurate and Streaming Action Boundary Detection | Mustafa Bora Çelik | cs.CV | 2026-09-27 |
| #220 | VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings | Peixi Wu, Mingzhou Jiang, Feipeng Ma +11 | cs.CV | 2026-09-27 |
| #221 | Resolving State-Representation Mismatch: State-Space Visual Reasoning for Open-Loop VLA Planning | Junhao Xiao, Haoxiang Zhao, Menghao Fang +8 | cs.CV | 2026-09-27 |
| #222 | TTRSD: Test-Time Reinforcement Learning with Self-Distillation for Vision-Language Models | Shuning Wang, Zhiheng Wu, Xun Zhou +8 | cs.CV | 2026-09-27 |
| #223 | TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining | Shih-Ying Yeh, Daniel Z. Kaplan, Xuehai Wang +3 | cs.CV | 2026-09-27 |
| #224 | TC-ADA: One-Shot Active Domain Adaptation for Semantic Segmentation | Weihao Yan, Yeqiang Qian, Yueyuan Li +3 | cs.CV | 2026-09-27 |
| #225 | Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure | Hong Xi Tae, Jiaming Zhang, Wenwen He +2 | cs.CV | 2026-09-27 |
| #226 | A Visual Classification Dataset and Model Evaluation for Historical Manuscript Illustrations | Yoav Evron, Michal Bar-Asher Siegal, Michael Fire | cs.CV | 2026-09-27 |
| #227 | Native Association: Confidence-Aware Human Perception in the Wild with a Foundation VLM | Igal Dmitriev, Ofir Liba | cs.CV | 2026-09-27 |
| #228 | SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera | Shriram Damodaran, Soumyaratna Debnath, Cheston Tan +1 | cs.CV | 2026-09-27 |
| #229 | Printability-Constrained Adversarial Decals for Near-Nadir Aerial Perception: Measured Ink Gamuts, Nested Realism Constraints, and a Physical-World Bound | Sandesh Shrestha, K. T. Yasas Mahima, Asanka G. Perera | cs.CV | 2026-09-27 |
| #230 | SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding | Xiangqi Li, Libo Huang, Jiarui Zhao +4 | cs.CV | 2026-09-27 |
| #231 | Anatomy-Structured Hierarchical MIL for Weakly-Supervised Thoracic Disease Detection in Chest X-rays | Jeongin Kim, Sohyun Ahn, Seo Young Kang +6 | cs.CV | 2026-09-27 |
| #232 | In-Token Learning for High-Fidelity Image Restoration via Diffusion Transformers | Xingfu Yi, Xiaoxue Yu | cs.CV | 2026-09-27 |
| #233 | PGL-3D: Towards Progressive Geometric Learning for 3D Visual Query Localization | Liang Peng, Shizhuo Mu, Bohan Tan +6 | cs.CV | 2026-09-27 |
| #234 | ForeFly: A Dual-Horizon World Action Model for Aerial Vision-Language Navigation | Kunhui Wang, Xintong Zhang, Junyu Gao +1 | cs.CV | 2026-09-27 |
| #235 | Fill2SR: Repurposing Inpainting Diffusion Transformers for Real-World Super-Resolution | Xingfu Yi, Xiaoxue Yu | cs.CV | 2026-09-27 |
| #236 | IVT-Guard: All-in-One Reasoning Model for AI-Generated Content Detection | Hongwei Niu, Yunpeng Luo, Hanjun Li +6 | cs.CV | 2026-09-27 |
| #237 | LoopLUT: 3D Lookup Tables with Progressive Region Refinement for Real-Time 4K Image Enhancement | Yang Ye, Jiajun Ma, Chen Wu +5 | cs.CV | 2026-09-27 |
| #238 | ViCoR: Reliable Molecular Structure Extraction via Spatially Aligned Verification and Executable Revision | Yujian Yuan, Xin Cai, Yufan Chen +5 | cs.CV | 2026-09-27 |
| #239 | Anguinus Sculpturae: Compositional Synthesis of Peak-Enhancement Breast DCE-MRI Scans | Benjamin Hamm, Nico Albert Disch, Maximilian Rokuss +3 | cs.CV | 2026-09-27 |
| #240 | SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning | Yang Cao, Jiaxin Zhang, Dave Zhenyu Chen +4 | cs.CV | 2026-09-27 |
| #241 | StoryEngine: A State-Grounded Agentic Framework for Video Storytelling | Yingrui Wang, Zeqing Wang, Yeying Jin | cs.CV | 2026-09-27 |
| #242 | Learning Multimodal Embeddings with Evidence-Aligned Readout | Zirong Chen, Fuda Ye, Enjun Du +8 | cs.CV | 2026-09-27 |
| #243 | When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling | Ping Guo, Zhiqi Huang, Xinran Li | cs.CV | 2026-09-27 |
| #244 | MAD-Guard: Controlled Study of Autoregressive Generation versus Direct Decision Interfaces for Closed Multimodal Forensic Tasks | Hao Chen | cs.CV | 2026-09-27 |
| #245 | Resource-Aware Parameter-Efficient Model Adaptation for Onboard High-Dimensional Data | Qiyang Zhang, Xinhao Li, Lei Shi +4 | cs.CV | 2026-09-27 |
| #246 | Seeing and Solving Are Not Enough for Vision-Language Models | Ziheng Wang, Mingxuan Xie, Yilin Liu +3 | cs.CV | 2026-09-27 |
| #247 | Prompt-Anchored Residual Adaptation for Biomedical Vision-Language Models | Jingxuan Kang, Qianying Yue, Che Liu +1 | cs.CV | 2026-09-27 |
| #248 | Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptation | Xuan Qi, Yi Wei, Daniele Berardini +2 | cs.CV | 2026-09-27 |
| #249 | GeoShrink: Accelerating Diffusion Transformers with Two Lines of Code | Haosen Li, Wenshuo Chen, Shaofeng Liang +3 | cs.CV | 2026-09-27 |
| #250 | Constrained Edit Fields for Training-Free Flow Editing | Jingxuan Kang, Yinsong Wang, Che Liu +1 | cs.CV | 2026-09-27 |
| #251 | ENet-GP: Unified Document Image Restoration | Sujal Burad, Aakanksha, A. N. Rajagopalan +1 | cs.CV | 2026-09-27 |
| #252 | M3-Score: Fidelity, Memorization and Coverage as Separate Axes for Evaluating Generative Radiology Image Models | Sathiyamohan Nishankar, Pubudu Sanjeewani, Asanka Perera | cs.CV | 2026-09-27 |
| #253 | Eyes on the Road: A Naturalistic Comparison of MTW Rider Gaze in Urban Indian Traffic | Prerak Srivastava, Bhaiya Vaibhaw Kumar, Kavita Vemuri | cs.CV | 2026-09-27 |
| #254 | Augmenting Visual Anomaly Detection with Automated Interpretability | Antonio De Santis, Arsenio Leo, Marco Brambilla | cs.CV | 2026-09-27 |
| #255 | One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs | Sen Nie, Jie Zhang, Zhongqi Wang +2 | cs.CV | 2026-09-27 |
| #256 | CLIMB-flow: Coupled Linear Inverse posterior sampling via Multiscale-Based flow | Zeqiu Yu, Ruizhi Yuan, Mathews Jacob | cs.CV | 2026-09-27 |
| #257 | ReDrive: Shaping Representations with World Modeling for End-to-End Driving | Yueting Zhu, Shaoyu Chen, Yuehao Song +4 | cs.CV | 2026-09-27 |
| #258 | Program-Verified Self-Evolution for Vision-Language Models | Ahmed Heakl, Sungik Choi, Moontae Lee +1 | cs.CV | 2026-09-27 |
| #259 | Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers | Tongtong Liang, Siqi Kou, Ziqiao Xi +6 | cs.CV | 2026-09-27 |
| #260 | Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction | Kaito Shiku, Kazuya Nishimura, Yasuhiro Kojima +1 | cs.CV | 2026-09-27 |
| #261 | Video, Ergo Genero: Unifying Video Tasks via Spatiotemporal Analogy | Chia-Hsiang Kao, Belinda Zeng, Bharath Hariharan +1 | cs.CV | 2026-09-27 |
| #262 | Test-Time Generalized Category Discovery | Shambhavi Mishra, Omprakash Chakraborty, Julio Silva-Rodriguez +3 | cs.CV | 2026-09-27 |
| #263 | Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors | Ge Gao, Siyue Teng, Chanqgi Wang +5 | cs.CV | 2026-09-27 |
| #264 | A Multi-Dataset Benchmark of YOLO-Based Weed Detection in Precision Agriculture | Hristina Zdraveska, Vlatko Spasev, Ivica Dimitrovski +2 | cs.CV | 2026-09-27 |
| #265 | UnfoldCRF: Structured Mask Refinement with Image-Conditioned Latent Regions | Chunming He, Rihan Zhang, Lei Xu +5 | cs.CV | 2026-09-27 |
| #266 | MetaSampling: Making Frame Samplers Efficient for Long-Video Question Answering | Ashim Dahal, Bikramjit Banerjee | cs.CV | 2026-09-27 |
| #267 | Position Aware Layer Queries for Test Time Training in Vision Language Models | Rajat Modi, Priyank Pathak, Xin Liang +1 | cs.CV | 2026-09-27 |
| #268 | Re:Cognize -- Open-Set Comic Character Re-Identification | Aaditya Baranwal, Madhav Kataria, Yogesh S Rawat +1 | cs.CV | 2026-09-27 |
| #269 | 3D Point Tracking with State Space Models | Masahiro Ogawa, Qi An, Atsushi Yamashita | cs.CV | 2026-09-27 |
| #270 | Greenpixie's AI Token Methodology: Assessing the Energy, Water and $\mathrm{CO_2\text{-}eq}$ Impact of AI Tokens for Open and Closed Weight Models | Joshua Horswill, Ross Hunter, Matt Clifford +1 | cs.CY | 2026-09-27 |
| #271 | Robust Hierarchical Structures for Agentic Document Analysis | Ruiying Ma, Yiming Lin, Aditya G. Parameswaran | cs.DB | 2026-09-27 |
| #272 | OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading | Jingyuan Xiao, Jiayue Wang, Yitao Hu +7 | cs.DC | 2026-09-27 |
| #273 | EfficientAgent: What Makes KV Cache Offloading Work for Concurrent Agents? | Kunming Shao, Jierun Chen, Jiangnan Yu +7 | cs.DC | 2026-09-27 |
| #274 | Validating Memory-Optimal Transformer Kernels on Real Hardware: From Formal Derivation to Measured Performance Across Two HPC Clusters | Lenore M. Mullin, Gaetan Hains | cs.DC | 2026-09-27 |
| #275 | Geometry-Adaptive Mechanisms for Private Synthetic Data | Raoof Zare Moayedi, Amir R. Asadi, Mohammad Hossein Yassaee +1 | cs.DS | 2026-09-27 |
| #276 | When Privacy Moves ML-Mediated Decisions On Device: Information and Incentive Misalignment in Auctions | Dipankar Sarkar | cs.GT | 2026-09-27 |
| #277 | ParallelPilot: Supporting Coordination and Monitoring in Parallel AI Coding | Tao Long, Weili Shi, Hussein Mozannar +2 | cs.HC | 2026-09-27 |
| #278 | DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration | Yupeng Xie, Zhenyang Wang, Liangwei Wang +3 | cs.HC | 2026-09-27 |
| #279 | EEG-Fusion: Failure-Informed Source-Free Expert Routing for Robust Motor Imagery EEG Decoding | Abdul Basit, Saim Rehman, Muhammad Shafique | cs.HC | 2026-09-27 |
| #280 | ThinkNet: Compact Architecture Selection and Validation-Gated Ensembles for Subject-Independent MI-EEG Decoding | Abdul Basit, Saim Rehman, Muhammad Shafique | cs.HC | 2026-09-27 |
| #281 | Inspire: Benchmarking Scientific Literature Search for Open Research Problems | Jianrong Ding, Zhengyan Shi, Jianyuan Zhong +5 | cs.IR | 2026-09-27 |
| #282 | From PDF to Evidence: Structure-Aware Retrieval for Clinical Practice Guidelines | Xingyu Lin, Dehui Du | cs.IR | 2026-09-27 |
| #283 | Non-Adaptive Learning of Sparse Erdős--Rényi Graphs via Affine Splitting | Hoang Ta | cs.IT | 2026-09-27 |
| #284 | SymNetPro: LOS-Aware Directional Multi-Transmitter Localization from Sparse Radio Observations | Lyuzhou Ye, Heng Fan, Yan Huang | cs.IT | 2026-09-27 |
| #285 | Balancing Early Performance Sacrifices with Long-Term Gains: Scaling Learning-Rate Warmup Duration Across Training Horizons | Kristi Topollai, Anna Choromanska | cs.LG | 2026-09-27 |
| #286 | Cost-free Spectral Estimation for Adaptive Newton--Schulz in Matrix Optimizers | Kristi Topollai, Anna Choromanska | cs.LG | 2026-09-27 |
| #287 | DevelopmentODE: Structured Neural ODEs for Early Brain Development Dynamics Across a Decade | Kaiqiao Han, Haitao Chen, Bryan Quah +5 | cs.LG | 2026-09-27 |
| #288 | SketchSSM: Write to the Full State, Read from a Compact Sketch | Omin Kwon, JoongWon Shin, Minseo Kim +3 | cs.LG | 2026-09-27 |
| #289 | Deep Learning Techniques for Phoneme Recognition in Italian Children' s Speech | Nicola Barbaro, Cristina Gena, Francesco Petriglia +3 | cs.LG | 2026-09-27 |
| #290 | Zero-Storage Procedural Neural Synthesis via Boundary Dynamics: Formal Verification in Lean 4 and Bare-Metal Gauntlet Validation | Volkan Dağlı, Zerrin Dağlı, Dağhan Dağlı | cs.LG | 2026-09-27 |
| #291 | Algorithmic Harms Associated with Generative Model-Augmented Recommendation Systems | Christine Herlihy, Xumei Xi, Shloka Desai +2 | cs.LG | 2026-09-27 |
| #292 | KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation | Changxin Ke, Rui Zhang, Zixiang Fang +8 | cs.LG | 2026-09-27 |
| #293 | The limits of exactness: On the failure of automatic differentiation in physics-informed machine learning | Ameya D. Jagtap | cs.LG | 2026-09-27 |
| #294 | From Constitutions to Control: Interpretable Rewards for Aligning Language Models | Johann D. Gaebler, Calvin Isley, Max Lamparth +2 | cs.LG | 2026-09-27 |
| #295 | Geometry-Aware Operator Families for Structured Representation Learning | Zuyuan Zhang, Fei Xu Yu, Tian Lan | cs.LG | 2026-09-27 |
| #296 | How Linear Attention Remembers | Kichang Lee, JaeYeon Park, Songkuk Kim +1 | cs.LG | 2026-09-27 |
| #297 | CARVE: Breaking Data Barriers in Chip Placement by Harnessing Reusable Expertise | Jiefu Zhang, Haixiang Sun, Yang Xu +2 | cs.LG | 2026-09-27 |
| #298 | D-JEPA: Design-Recoverable JEPA Representation with Swappable Physics Decoders | Nitin Nagesh Kulkarni, Aashwin Anand Mishra, Yin Yu +1 | cs.LG | 2026-09-27 |
| #299 | Simulation-Free Learning of GP-SDEs from Irregular Observations | Zhidi Lin, Yuhao Liu, Ying Li +2 | cs.LG | 2026-09-27 |
| #300 | ECG-Scroll: A Long-Horizon, Streaming Benchmark and Agent Environment for Interpretation of Ambulatory Electrocardiograms | Haitao Li, Chenglin Li, Zhengyao Ding +3 | cs.LG | 2026-09-27 |
| #301 | Mycelium: A Generalizable Cross-Grid Multi-Task Model for Electrical Distribution Systems | Zhengyang Wei, Shourya Bose, Helgi Hilmarsson +2 | cs.LG | 2026-09-27 |
| #302 | Save Your Saturated Data: Learning Beyond Reward Saturation in Group-Based RL | Ziyuan Yang, Yike Wang, Shangbin Feng +1 | cs.LG | 2026-09-27 |
| #303 | Policy Plasticity Matters in Offline-to-Online Reinforcement Learning: Refitting Offline Policies for Online Adaptation | Yuheng Huang, Yunpeng Qing, Yixiao Chi +2 | cs.LG | 2026-09-27 |
| #304 | Flow-Matching-Based Protein Structure Tokenizer Made Efficient and Easy | Zhe Zhang, Yikai Zhang, Jiangtao Feng +3 | cs.LG | 2026-09-27 |
| #305 | ILP-BO: Integer Linear Programming-Based Black-Box Optimization | Hyakka Nakada, Shu Tanaka | cs.LG | 2026-09-27 |
| #306 | Leaky Students: Membership Inference against On-Policy Distillation | Zhexi Lu, Mingzhi Zhu, Stacy Patterson +1 | cs.LG | 2026-09-27 |
| #307 | Beyond the Training Horizon: Mechanisms and Limits of Length Generalization in Looped Transformers | Jia Liang, Xi Jin, Liangming Pan | cs.LG | 2026-09-27 |
| #308 | CFLoRA: Federated Fine-tuning of LLMs with Complementary Factors for Error-free Aggregation | Yanan Ma, Qiyuan Chen, Zihan Fang +2 | cs.LG | 2026-09-27 |
| #309 | Convergence of Practical Muon | Haonan Wang, Yu Wu, Minghui Liwang +2 | cs.LG | 2026-09-27 |
| #310 | Downstream-Aware Context Selection for Online In-Context Reinforcement Learning | Ruihan A. Li, Shangtong Zhang, Rohan Chandra | cs.LG | 2026-09-27 |
| #311 | When Does Backpropagating Through Policy Memory Matter? Physical Credit, Optimizer Updates, and Observability | Xingjian Li, Yi Han, Jianhua Z. Huang | cs.LG | 2026-09-27 |
| #312 | Perturb-and-Solve: Efficient Learned-Operator Conditioning for Latent Diffusion Inverse Problems | Abduragim Shtanchaev, Arip Asadulaev, Luiza Labazanova +3 | cs.LG | 2026-09-27 |
| #313 | When an Evaluation Rule Writes Training Labels: Measuring Human-Reference Forgiveness in NAVSIM | Jiaxuan Guo, Jingxin Yang, Jiaqi Ye +4 | cs.LG | 2026-09-27 |
| #314 | AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits | Lu Wei, Yufeng Wang, Chenfeng Cao +2 | cs.LG | 2026-09-27 |
| #315 | Apparent Compression, Real Stability: The Intrinsic Dimension of Learning a Quantum Wavefunction | Lu Wei, Yufeng Wang, Chenfeng Cao +1 | cs.LG | 2026-09-27 |
| #316 | Orthogonal Witness Control for Muon Optimization via Sigmoid Spectral Reshaping | Dat Phi Van, Ngo Vu Minh, Tuc Nguyen +3 | cs.LG | 2026-09-27 |
| #317 | Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning | Safaeid Hossain Arib, Rabeya Akter, Ismam Nur Swapnil +3 | cs.LG | 2026-09-27 |
| #318 | SMORE: Stability-Promoting Mesh-Agnostic Model Reduction for Time-Dependent PDEs | Yangyuan Li, Weichao Li, Shaowu Pan | cs.LG | 2026-09-27 |
| #319 | When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning | Steven Y. Feng, Noah D. Goodman, Michael C. Frank +3 | cs.LG | 2026-09-27 |
| #320 | RMB: Reward Model Boosting Mitigates Reward Hacking | Jiabin Fan, Dezhi Ye, Yongchang Hao +1 | cs.LG | 2026-09-27 |
| #321 | MTLiquid: Enabling Efficient Multi-Task Learning using Liquid Neural Networks for Lightweight Healthcare Monitoring Systems | Rachmad Vidya Wicaksana Putra, Fahad Abdul Rauf, Muhammad Shafique | cs.LG | 2026-09-27 |
| #322 | The Price of Locality: Why Forward-Forward Underperforms Backpropagation? | Zhaoxian Wu, Haichuan Liu, Tianyi Chen | cs.LG | 2026-09-27 |
| #323 | Minimax-Optimality of Posterior Sampling for Reinforcement Learning | Taewon Goo, Kihyuk Hong | cs.LG | 2026-09-27 |
| #324 | Feedback-Robust AI for Patient Knowledge Graphs | Mohammed Sameer Syed | cs.LG | 2026-09-27 |
| #325 | BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions | Thanina Hamitouch, Khadidja Henni, Abdelkrim Arie +3 | cs.LG | 2026-09-27 |
| #326 | Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts | Cheng Peng, Ruixi Luo, Zhi Chen +1 | cs.LG | 2026-09-27 |
| #327 | GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences | Abdul Monaf Chowdhury, MD Sameer Iqbal Chowdhury, Shifat E Arman +1 | cs.LG | 2026-09-27 |
| #328 | Towards Identifiable Representations under Misspecified Structure | Yuke Li, Yujia Zheng, Ziyi Chen +2 | cs.LG | 2026-09-27 |
| #329 | Domain Generalization under Sampling Pattern Shifts in Irregular Time Series | Changhun Kim, Joohyung Lee, Kwanhyung Lee +3 | cs.LG | 2026-09-27 |
| #330 | Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs | Fansheng Zhang, Shengran Guo, Zexiao Wang +3 | cs.LG | 2026-09-27 |
| #331 | BITS: Rethinking Fair and Comprehensive Evaluation for Irregular Time Series Forecasting | Kangjia Yan, Linfeng Wang, Tianen Shen +7 | cs.LG | 2026-09-27 |
| #332 | ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models | Zhongjian Zhang, Xiao Wang, Busheng Zhang +5 | cs.LG | 2026-09-27 |
| #333 | When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression | Haeyong Kang, Chang D. Yoo | cs.LG | 2026-09-27 |
| #334 | Beyond Conservatism: Recoverability-Conditioned Exploration for Model-Based Imitation Learning | Xuanlin Chen, Ziyue Wang, Xunlan Zhou +3 | cs.LG | 2026-09-27 |
| #335 | Safe Score Matching: Diffusion Policies with Hamilton-Jacobi Reachability for Online Safe Reinforcement Learning | Boyang Li, Matthew Kim, Sylvia Lee Herbert | cs.LG | 2026-09-27 |
| #336 | RAEGL: Risk-Aware Evidence-Gated Learning for Selective Contextual Routing under Temporal Shift | Yifan Guo | cs.LG | 2026-09-27 |
| #337 | CalibHyper: Chance-Corrected Relational Hypergraphs for Few-Shot Molecular Property Prediction | Linyu Li, Zhi Jin, Yuanpeng He +7 | cs.LG | 2026-09-27 |
| #338 | MultiEcho: An Experimental Science of Learned Worlds | Meng Zhu, Airui Zhang | cs.LG | 2026-09-27 |
| #339 | KoopCell: Koopman-Based Generative Model for Learning Single-Cell Dynamics from Distribution Snapshots | Wanfeng Lu, Yutong Zhang, Keyi Zhou +3 | cs.LG | 2026-09-27 |
| #340 | How Much Imprecision is Enough Imprecision in my Classifier? A Practical Elicitation Procedure | Victor F. Lopes de Souza, Sébastien Destercke, Abdelhak Imoussaten | cs.LG | 2026-09-27 |
| #341 | The Selection Rule Decides the Winner: A Pre-Registered Audit of Open-Set Graph Anomaly Detection | Farhan Shahriyar Hossain, Taufikur Rahman Fuad, Md Abrar Jahin +1 | cs.LG | 2026-09-27 |
| #342 | TNF based Spectral Embedding for Effective Application of Supervised Machine Learning Techniques in Automobile Insurance Fraud Detection | Rohan Yashraj Gupta, Lalith Srikanth Chintalapati, Satya Sai Mudigonda +2 | cs.LG | 2026-09-27 |
| #343 | Optimal Transport Dropout for Structured Predictive Uncertainty | Giacomo Lorenzon, Francesco Regazzoni | cs.LG | 2026-09-27 |
| #344 | From Grey-Box to Green-Box: When can Physics-Informed Machine Learning Reduce Carbon Footprints in Structural Health Monitoring? | Daisy R. Bradley, Nathan A. Hinchliffe, Daniel J. Pitchforth +2 | cs.LG | 2026-09-27 |
| #345 | Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents | Mingju Chen, Can Lv, Jinrong Liu +3 | cs.LG | 2026-09-27 |
| #346 | AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networks | Sirui Li, Pietro Liò b, Xinsheng Li +2 | cs.LG | 2026-09-27 |
| #347 | Decoupling Token Roles in Autoregressive Pretraining | Suqin Yuan, Runqi Lin, Kevin Qinghong Lin +4 | cs.LG | 2026-09-27 |
| #348 | StarBOA: Real-Time Mamba State-Space Unrolling for Sparse Radar Micro-Doppler in ISAC Networks | Mustafa Bora Çelik, Ceren Çelik, Orhan Gazi | cs.LG | 2026-09-27 |
| #349 | FoldAttention: Declared-Reference Softmax for Fast Decode and Deterministic Backward | Sriman Achanta | cs.LG | 2026-09-27 |
| #350 | Investigating the Effect of k-NN Preprocessing on Developing Graph Neural Networks: A Fairness-Based Perspective | Nikolaos Zafeiropoulos, Emmanouil Mavrikos, George E. Tsekouras | cs.LG | 2026-09-27 |
| #351 | A Light Bilevel Refinement Aligns Self-Supervised Representations for Stronger Task-Specific Learning | Gustav Wagner Zakarias, Zheng-Hua Tan | cs.LG | 2026-09-27 |
| #352 | MoGround: Measuring and Mitigating Modality Distraction in Vision-Language Models | Luca Zhou, Bo Zhao, Rose Yu +2 | cs.LG | 2026-09-27 |
| #353 | SchemaMem: Schema-Indexed Recurrent Memory for Delayed State Retrieval | Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung | cs.LG | 2026-09-27 |
| #354 | SMAT: Simple and Efficient Merge-Aware Training | Yanggan Gu, Yuanyi Wang, Zhen Li +5 | cs.LG | 2026-09-27 |
| #355 | Elucidating the Design Space of Regression-based Diffusion Reinforcement Learning | Toyota Li, David Zhao, Alan Zhao | cs.LG | 2026-09-27 |
| #356 | A Free Knob: Decoupling Calibration and Predictive Skill in Threshold-Based Evaluation | Md Tanveer Hossain Munim, Bijoy Ahmed Saiem, Al-Amin Sany +1 | cs.LG | 2026-09-27 |
| #357 | A Cheap Verifier is Good Enough: LLM Post-training is Robust to Erroneous Rewards | Andreas Plesner, Curtis Northcutt, Francisco Guzmán +1 | cs.LG | 2026-09-27 |
| #358 | Geometric Identification in Predict-Then-Optimize Learning | Jiaxiao Xu, Changhong Mou, Keji Liu +2 | cs.LG | 2026-09-27 |
| #359 | How Synthetic Labels Improve Conformal Prediction: A Perspective on Conditional Coverage | Qianyi Chen, Bo Li | cs.LG | 2026-09-27 |
| #360 | What masking geometry works best for EEG foundation models? | Pierre Guetschel, Bruno Aristimunha, Yassine El Ouahidi +3 | cs.LG | 2026-09-27 |
| #361 | Predicting Block-Coordinate Performance via Cross-Curvature | Shengkun Zhu, Jinshan Zeng, Zhiqiang Kou +2 | cs.LG | 2026-09-27 |
| #362 | Chameleon: Dynamic Format Adapter for Efficient Diffusion | Arnab Sanyal, Sandeep Chinchali | cs.LG | 2026-09-27 |
| #363 | Hamiltonian JEPA: Action-Conditioned World Models with an Inherited Control State | Tamim Zoabi, Ameen Ali, Lior Wolf | cs.LG | 2026-09-27 |
| #364 | The cost of useful natural gradient updates | Subhransu S. Bhattacharjee, Dylan Campbell, Rahul Shome | cs.LG | 2026-09-27 |
| #365 | Pulseflow: PPG Counterfactual Generation Via Latent Transport | Hung Manh Pham, Dong Ma, Bin Zhu +1 | cs.LG | 2026-09-27 |
| #366 | Source Anchoring for Physical Consistency in Flow Matching Models | Giulia Romoli, Filippo Ruffini, Paolo Soda | cs.LG | 2026-09-27 |
| #367 | SLP-ProbHard: Probabilistic Hard-Constrained Learning via Structural Latent Parameterization | Wondesen Teshome Bekele, Marco D'Oria | cs.LG | 2026-09-27 |
| #368 | LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation | Jie Wang, Yanbo Sun, Zheng Yan +2 | cs.LG | 2026-09-27 |
| #369 | Discovering Symmetries in Neural Network Parameter Spaces | Bo Zhao, Nima Dehmamy, Robin Walters +1 | cs.LG | 2026-09-27 |
| #370 | Does Execution Require Target KV Fidelity? A Mixed-Fidelity KV Runtime for LLM Serving | Jiantong Jiang, Yue Yang, Peiyu Yang +1 | cs.LG | 2026-09-27 |
| #371 | TerMeZO: Ternary Sparse Zeroth-Order Optimization for Fine-tuning BitNet Models at the Edge | Houssem Sifaou, Prabodh Katti, Bipin Rajendran +1 | cs.LG | 2026-09-27 |
| #372 | Fine Until Fine-Tuned: Repeated Solutions Make Reasoning Fragile | Ely Sheikh | cs.LG | 2026-09-27 |
| #373 | GraphSelect for Budgeted Representation Selection in Multimodal Graph Inference | Xu Wang, Xunkai Li, Yinlin Zhu +1 | cs.LG | 2026-09-27 |
| #374 | OOD Generalization as a Bifurcation Problem | Nguyen-Thanh-Luong Doan, Quang-Vu Nguyen, Tang-Phu-Quy Le +1 | cs.LG | 2026-09-27 |
| #375 | MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning | Brandon Gary Kaplowitz, Osaze James Obahor, Christian Schroeder de Witt | cs.LG | 2026-09-27 |
| #376 | Correct then Forecast: Observer State-Space Models for Time Series Forecasting | Alexis-Raja Brachet, Guillaume Clavier--Frémond, Abdelhakim Ziani +2 | cs.LG | 2026-09-27 |
| #377 | HiLoRe: What to Store, Compress, or Recompute for Efficient GRPO Training | Xinrui Chen, Mengyang Li, Ou Wu +1 | cs.LG | 2026-09-27 |
| #378 | Compressing Value Predictions for Learning-Augmented Metrical Task Systems | Sizhe Li, Yecheng Li, Kun He | cs.LG | 2026-09-27 |
| #379 | Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel Acceleration | Shangzhen Zhu, Muyan Hu, Tomasz Kozlowski | cs.LG | 2026-09-27 |
| #380 | TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs | Zihan Lin, Xiaohan Wang, Jie Cao +4 | cs.LG | 2026-09-27 |
| #381 | Pretraining Transformers with Quantized Softmax in Attention | Shangzhen Zhu, Muyan Hu, Tomasz Kozlowski | cs.LG | 2026-09-27 |
| #382 | Short-Length Code Designs for Integrated Sensing and Communications: A Deep Learning Approach | Muah Kim, Shuangyang Li, Tayyebeh Jahani-Nezhad +2 | cs.LG | 2026-09-27 |
| #383 | Hierarchical Response Preservation for Continual Adaptation of Zero-Shot Graph-Text Models | Haopeng Zhang, Yuhan Wang, Yubing Su +4 | cs.LG | 2026-09-27 |
| #384 | You Only Edit Once: Incentivizing In-Context Capability of LLMs via Local Demonstration Refinement | Jiarong Wen, Qi Wang, Yun Qu +8 | cs.LG | 2026-09-27 |
| #385 | Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss | Yi Ren, Wenlong Deng, Guanzhe Hong +2 | cs.LG | 2026-09-27 |
| #386 | Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning | Chenlong Yin, Xiaolong Jin, Wei Zou +2 | cs.LG | 2026-09-27 |
| #387 | Quantifying Behavioral Tails in Black-Box Language Models | Elsayed Eshra, Ali Al-Lawati, Dongwon Lee +1 | cs.LG | 2026-09-27 |
| #388 | SafeMol: Dual-Modality Safety Alignment for Molecular Multimodal Models | Xinmiao Wang, Ruijie Wang, Menghui Wang +5 | cs.LG | 2026-09-27 |
| #389 | From Distributions to Stochastic Processes: Neural Approximation of Measure-Valued Maps | Yichen Wang, Ziyi Wang, Wenlian Lu +5 | cs.LG | 2026-09-27 |
| #390 | FuseAlign: Forced Alignment in the Wild | Mithilesh Vaidya, Stephen Bailey, Sumukh Badam +2 | cs.LG | 2026-09-27 |
| #391 | Towards Eliminating Catastrophic Forgetting in the Curriculum Learning of Math Reasoning Tasks | Zengyan Yang, Yangyang Wu, Kai Huang +3 | cs.LG | 2026-09-27 |
| #392 | Scalable Attribution and Control of Model Behavior During Training | Sleem Abdelghafar | cs.LG | 2026-09-27 |
| #393 | Reachability is not enough: Diagnosing long-range behavior in GNNs | Filippo Maria Bianchi | cs.LG | 2026-09-27 |
| #394 | Benign Overfitting for General Norms and Distributions | Daniel Barzilai, Ohad Shamir | cs.LG | 2026-09-27 |
| #395 | T-MoXAI: A Hierarchical Explainability Framework for Temporal Multimodal Data | Ali Inha, Mo Vali, Saaliha Vali +2 | cs.LG | 2026-09-27 |
| #396 | Dynamic Kuramoto-Hodge Operators for PDEs on Complex Geometries and Topologies | Xiang Li, Yue Song | cs.LG | 2026-09-27 |
| #397 | Geometric Inductive Biases for Semi-Supervised Equalization: The Constellation-Aware Transformer | Avi Caciularu | cs.LG | 2026-09-27 |
| #398 | A Spectral Theory of Compositional Learning | Hugo Rydel | cs.LG | 2026-09-27 |
| #399 | DuoOPD: Learning from Joint Teacher-Student Outcomes for Multi-Task On-Policy Distillation | Ao Yu, Weibo Gao, Heng Zhou +6 | cs.LG | 2026-09-27 |
| #400 | Theory Guided and Interpretable Neural Operator Design for Partial Differential Equation Learning | Zeyuan Song, Zheyu Jiang | cs.LG | 2026-09-27 |
| #401 | BOReFT: Manifold Steering of Language Models for Black-box Optimization | Dhruv Agarwal, Rico Angell, Kavitha Srinivas +4 | cs.LG | 2026-09-27 |
| #402 | ALDER: Discovering the Laws of a World by Acting in It | Teng Cao, Yu Deng, Quentin Delfosse +1 | cs.LG | 2026-09-27 |
| #403 | PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention | Kunming Shao, Jierun Chen, Yanli Wang +4 | cs.LG | 2026-09-27 |
| #404 | Task-Aware Discretization of Differentiable Logic Gate Networks | Thore Gerlach | cs.LG | 2026-09-27 |
| #405 | ResDiffFRG: Residual Diffusion for Multiple Appropriate Facial Reaction Generation | Shizhe Liu, Jiayan Gu, Xiangyu Kong +1 | cs.LG | 2026-09-27 |
| #406 | Collaborative Synthetic Data for Privacy-Preserving Financial Fraud Detection Across Organizational Silos | Simeon Allmendinger, Domenique Zipperling, Burhanettin Bahadir Kibar +1 | cs.LG | 2026-09-27 |
| #407 | Oracle-Efficient Online Classification with Stochastic Inputs and Adversarial Outputs | Gon Buzaglo, Elad Hazan | cs.LG | 2026-09-27 |
| #408 | StatD2GAN: When Calibration Masks Generator Quality in Held-Out Evaluation of Synthetic Weather Sequences | Mustafa Ozaytac, Ozge Karadag Atas | cs.LG | 2026-09-27 |
| #409 | Beyond Fixed Features: Architecture-Dependent Sensitivity to Node Representations under Heterophily | Priyanath Maji, Sidharth Gaur, Rajavinoth Paul Durai | cs.LG | 2026-09-27 |
| #410 | DEALS: Decentralized Expertise-Aware Load Serving for Multi-Agent LLM Systems | Jingjuan Huang, Wenbin Wang, Yanchuan Yin +2 | cs.LG | 2026-09-27 |
| #411 | Selecting Diverse SFT Traces Improves Post-RL Generalization | Dylan Zhang, Mingyuan Wu, Jinning Li | cs.LG | 2026-09-27 |
| #412 | Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning | Woongyeong Yeo, Minki Kang, Chanuk Lee +3 | cs.LG | 2026-09-27 |
| #413 | Do We Really Need KL Divergence for On-Policy Distillation of Large Language Models? | Wenze Lin, Jiyuan Long, Jiale Zhao +11 | cs.LG | 2026-09-27 |
| #414 | Binding Multiple Modalities via Multimodal Wasserstein Barycenter | Xiaole Tang, Jiayi Xu, Xiang Gu +2 | cs.LG | 2026-09-27 |
| #415 | Diffusion Reward Models | Xiangyang Wang, Bingxiang He, Zeyuan Liu +12 | cs.LG | 2026-09-27 |
| #416 | MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception | Yuhao Li, Louie Hong Yao, Tianyi Shi +4 | cs.LG | 2026-09-27 |
| #417 | dOPT: Differentiating Conic Optimization via Geometric Reduction | Fengyu Yang, Connor W. Magoon, Tyler Watts +1 | cs.LG | 2026-09-27 |
| #418 | ChemOPD: Multi-Teacher On-Policy Distillation for Multi-Task Chemical Reasoning | Yaoyao Xu, Xinjian Zhao, Xiaozhuang Song +2 | cs.LG | 2026-09-27 |
| #419 | QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents | Weiqi Wang, Yuxin Zhou, Mouxiang Chen +9 | cs.LG | 2026-09-27 |
| #420 | Rethinking Contextualization by Reinterpreting Attention Head Channels | Hakaze Cho, Haolin Yang, Zhun Sun +3 | cs.LG | 2026-09-27 |
| #421 | PI-NOMT: Physics-Informed Neural Optimal Mass Transport for Brain Fluid Dynamics | Mehmet Emin Acar, Vahit Bugra Yesilkaynak, Helene Benveniste +1 | cs.LG | 2026-09-27 |
| #422 | JET: Justification Evaluation in Transformer | Shenghao Ding | cs.LG | 2026-09-27 |
| #423 | Vanilla Policy Optimization Is Both Optimal and Differentially Private for Stochastic Contextual Bandits | Idan Attias, Orin Levy, Alexander Ryabchenko +2 | cs.LG | 2026-09-27 |
| #424 | Where Activation Sparsity and KV-Cache Sparsity Cross in LLM Decoding | Jungseob Lee, Seungyoon Lee, Seongtae Hong +2 | cs.LG | 2026-09-27 |
| #425 | Augmented Feature Boosting for Multicalibration | Ira Globus-Harris, Inbal Livni Navon | cs.LG | 2026-09-27 |
| #426 | MISHAP-Bench: A Hallucination Benchmark for Large Audio-Language Models | Zhi Wen Soi, Giulio Segalini, Jian-Jia Chen +1 | cs.LG | 2026-09-27 |
| #427 | No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability | Yiyong Liu, Jun Sakuma, Michael Backes +1 | cs.LG | 2026-09-27 |
| #428 | Finite Probes Suffice: Identifiability and Universality for Weight-Space Learning | Soutrik Sarangi, Yonatan Sverdlov, Adir Dayan +2 | cs.LG | 2026-09-27 |
| #429 | On the Two Faces of Adam in Separable Linear Classification | Chen Fan, Csaba Szepesvári | cs.LG | 2026-09-27 |
| #430 | JIVE: Jacobian-Informed Volume Expansion for Diverse Generative Sampling | Guangxun Zhang, Brian Cai, Boxuan Zhang +2 | cs.LG | 2026-09-27 |
| #431 | Training Witnesses: Trusting the Training without Trusting the Trainer | Houjun Liu, Pratyusha Sharma | cs.LG | 2026-09-27 |
| #432 | Optimizing the Phi-2 Small Language Model for Real-time Chatbot Applications Using Parameter-Efficient Fine-Tuning (PEFT) with QLoRA Quantization | PhanTan Khanh Nguyen, Ashfaq Ali Shafin, Khandaker Mamun Ahmed | cs.LG | 2026-09-27 |
| #433 | Diffusion-Based Rollouts as a Stabilization Mechanism for Long-Horizon Environmental Forecasting | Marina Vicens-Miquel, Amy McGovern, Aaron J. Hill +2 | cs.LG | 2026-09-27 |
| #434 | How Strong Is the Evidence for the Artificial Hivemind? Reevaluating Evidence for the Open-Ended Homogeneity of Language Models | Rylan Schaeffer, Brando Miranda, Joshua Kazdan +2 | cs.LG | 2026-09-27 |
| #435 | Behavioral Monitoring of JEPA World Models with Jacobian Centroids | Thomas Walker, Randall Balestriero, Richard Baraniuk | cs.LG | 2026-09-27 |
| #436 | GroupMask: Layer-Adaptive Group-wise Sparsity for Semi-Structured LLM Pruning | Zhengao Li, Shuoqiu Li, Xiaofang Zhang +7 | cs.LG | 2026-09-27 |
| #437 | DynGraphAgentBench: A Benchmark for Agentic Lifecycle Control in Dynamic Graph Anomaly Detection | Yuwei Han, Lingwei Wei, Wooseong Yang +4 | cs.LG | 2026-09-27 |
| #438 | Future Information-Directed Sampling for Bayesian Nonstationary Bandits | Yichen Song, Alessio Russo, Aldo Pacchiano | cs.LG | 2026-09-27 |
| #439 | From HL to H+L-1 Parameters: A Hankel-Toeplitz Forecaster for Long-Term Time Series Forecasting | Chaoqi Zhang, Yu Wang, Haixu Tang | cs.LG | 2026-09-27 |
| #440 | ICMAPE: In-Context Multiagent Pure Exploration | Xinyi Hu, Alessio Russo, Aldo Pacchiano | cs.LG | 2026-09-27 |
| #441 | ASTRA: ADMM-Accelerated Topology Reconfiguration for Dynamic Satellite Constellations | João Norberto, Ricardo Ferreira, Cláudia Soares | cs.LG | 2026-09-27 |
| #442 | T-SNN: Temporal Simplicial Neural Network for EEG Decoding | Nikita Malik, Shubhajit Roy, Mohit Kataria +4 | cs.LG | 2026-09-27 |
| #443 | RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting | Tong Liu, Lanmiao Liu, Xiang Hu | cs.LG | 2026-09-27 |
| #444 | Fisher-Informed Recalibration for Feedback-Based On-Policy Self-Distillation of LLMs | Seohyun Lee, Dong-Jun Han, Seyyedali Hosseinalipour +1 | cs.LG | 2026-09-27 |
| #445 | When Known Physics Helps Neural PDE Models: Residual Constraints Out-Regularize Generic Priors for Nonlinear Dynamics | Zahra Farazpay, Aniruddha Bora | cs.LG | 2026-09-27 |
| #446 | LTV-CTDNet: Compositional Turning Decomposition for Short-Term Turning-Movement Forecasting | Md Atiqur Rahman Mallick, Kamrul Hasan, Robert T. White | cs.LG | 2026-09-27 |
| #447 | SR4-Fit: A Unified Interpretable Rule-Based Machine Learning Framework for Informative and Trustworthy Decision-Making | Shyam Sundar Murali Krishnan, Dean Frederick Hougen | cs.LG | 2026-09-27 |
| #448 | Structure-Adaptive Tree Field Integrators | Millend Roy, Soham Samal, Ivan Zelich +1 | cs.LG | 2026-09-27 |
| #449 | Posterior Regimes and Latent Deception: Variational Bayesian Inference in Hidden Markov Models for Sequential Fraud Detection in Financial Transactions | Joseph Uririoghene Obukofe, Anthony O'Hare, Chioma Sandra Dike | cs.LG | 2026-09-27 |
| #450 | UOPD: Uncertainty-Aware Intervention for On-Policy Distillation of Multi-Turn Agents | Wenbo Zhang, Pengcheng Xu, Weizhi Du +2 | cs.LG | 2026-09-27 |
| #451 | Protected Cores Are Not Enough: Certifying AI-Proposed Revisions of Temporal Specifications | Ruggero Lanotte | cs.LO | 2026-09-27 |
| #452 | Population Physics, Population Problems: Safety and Emergence in LLM Societies | Adrian de Wynter | cs.MA | 2026-09-27 |
| #453 | Prospective Interpretation Risk: Principled Communication Control Between LLMs | Wanrong Yang, Rehan Deen, Julian Ma +7 | cs.MA | 2026-09-27 |
| #454 | ADPTNet: Adaptive with Prescriptive Timescales Non-Linear SSM for Sequence Modelling | Matei-Ioan Stan, Oliver Rhodes | cs.NE | 2026-09-27 |
| #455 | Evolving Dexterous Robots from Scratch | Zihan Guo, Shuzhe Zhang, Muhan Li +2 | cs.RO | 2026-09-27 |
| #456 | VPTwin: Real-Sim-Real Video Prediction for Robotic Manipulation Planning | Zhenghao Xiao, Minting Pan, Nantian He +2 | cs.RO | 2026-09-27 |
| #457 | Beyond Tasks: A Vision for Reproducing an Animal-like Behavioral Substrate Using Modern Robot Learning Techniques | Samiyuru Menik, Hemadri Jayalath | cs.RO | 2026-09-27 |
| #458 | Dynamic Manipulation with World-Action Models via Counterfactual Planning | Sunwoo Park, Wonbin Lee, Seonghyun Jin +3 | cs.RO | 2026-09-27 |
| #459 | DeltaWAM: Change-Centric Visual Foresight via Delta Tokens for an Efficient World-Action Model | Tianyun Jiang, Wenrui Bao, Bingxin Xu +2 | cs.RO | 2026-09-27 |
| #460 | TAO-DA: Towards Autonomous Operation--A Dual-Arm Vision-Language-Action Model for Coordinated Manipulation | Yongsheng Zhao, Han Gao, Baoping Cheng +7 | cs.RO | 2026-09-27 |
| #461 | PORTER: Edge-Cloud Residency for Persistent 3D Scene Graph Memory | Yue Chang, Yifan Tian, Jiajing Peng +5 | cs.RO | 2026-09-27 |
| #462 | Q-WAM: 4-Bit Quantization of World Action Models with Action-Subspace Protection | Arash Akbari, Arman Akbari, Jingwu Luo +7 | cs.RO | 2026-09-27 |
| #463 | AquaWAM: A Dynamics-aware World Action Model for Underwater Embodied Agents | Cunhao Zhu, Yifeng Wang, Dongliang Xu +3 | cs.RO | 2026-09-27 |
| #464 | SocialHumanoid: Towards Expressive Humanoid Behavior via One-Step Co-Speech Motion Generation | Chengqun Yang, Tengjie Zhu, Liang Xu +10 | cs.RO | 2026-09-27 |
| #465 | Recursive Harness Distillation across Agents for Robot Manipulation | Seungyeon Kim, Junhoo Lee, Minkyu Kim +2 | cs.RO | 2026-09-27 |
| #466 | AI-Driven Collaborative Assembly Line Inspection: System Integration and Deployment Challenges | Asya Ünal, Amr Okasha, Ege Çırakman +1 | cs.RO | 2026-09-27 |
| #467 | Beyond One-Step Accuracy: State-Affine Latent Transition for Reliable Visual Planning | Boyuan Zhang, Yingjun Du, Xiantong Zhen +1 | cs.RO | 2026-09-27 |
| #468 | Demonstration-Free Success-Probability Reward Learning for Generalist Robot Policies | Duo Wu, Haifeng Wang, Rongwei Lu +6 | cs.RO | 2026-09-27 |
| #469 | CodeActionBench: Evaluating Agentic Code-as-Policy for Embodied Manipulation | Yiheng Lyu, Xueying Jiang, Wenhao Li +2 | cs.RO | 2026-09-27 |
| #470 | Achieve What You Imagined: Learning to Align Actions with Visual Plans | Yuheng Qiao, Ziran Wei, Xiaohan Wang +5 | cs.RO | 2026-09-27 |
| #471 | DeltaSeek: Toward Active Perception in Evolving Construction Environments | Sanjay Acharjee, Md Nazmus Sakib | cs.RO | 2026-09-27 |
| #472 | Robot-GST: geometry-aware spatial-temporal robot policy representation and evaluation | Sichao Liu, Zekun Wang, Lixuan Tang +6 | cs.RO | 2026-09-27 |
| #473 | ArticulateArena: A Metric for Articulated Kinematics | Yumeng He, Yongfei She, Huanyu Chen +6 | cs.RO | 2026-09-27 |
| #474 | EpiTransfer: Sparse, Training-Free Long-Range Depth Estimation from Temporal Monocular Aerial Frames | Diksha Aggarwal, Rutvik Dagadkhair, Sanjana Srivastava +2 | cs.RO | 2026-09-27 |
| #475 | Test-Time Spatial Reasoning for Robot Manipulation Using Generative Real-to-Sim | Ivan Kapelyukh, Yafei Hu, Ran Gong +6 | cs.RO | 2026-09-27 |
| #476 | ZeroBot: Learning from Scratch in Minutes with Generative Real2Sim | Ivan Kapelyukh, Xiaohan Zhang, Stephen James +2 | cs.RO | 2026-09-27 |
| #477 | Estimate, Don't Imitate: Reusing Differentiable State-Based Policies for Visuomotor Control | Denis Shcherba, Adrian Abel, Eckart Cobo-Briesewitz +3 | cs.RO | 2026-09-27 |
| #478 | LieDiscover: Adaptive Symbolic Library Construction for Explicit Open-form Symmetry Discovery | Xinxin Li, Jianming Ma, Xingyu Cui +3 | cs.SC | 2026-09-27 |
| #479 | SCISSOR: Score-Conditioned Instrument Source Separation for Orchestral Recordings | Yiheng Lu, Hao-Wen Dong | cs.SD | 2026-09-27 |
| #480 | What Survives the Codec Shift: Pooled No-Vocals Residuals for Speech Deepfake Detection | Jiajun Xu, Menglu Li, Xiao-Ping Zhang | cs.SD | 2026-09-27 |
| #481 | CORA: A Protocol for Diagnosing Boundary Robustness in Text-to-Audio Retrieval under Query Reformulations | Jae Min Woo, Kyongmin Kong, Bogyung Jeong +3 | cs.SD | 2026-09-27 |
| #482 | Mask-Induced Displacement in Audio XAI via Logit Trajectory Decomposition | Nico García-Peguinho, David Kelly, Fabrizio Smeraldi +1 | cs.SD | 2026-09-27 |
| #483 | DuraS2ST: Chain-of-Thought and Reinforcement Learning for Duration-Aligned Speech-to-Speech Translation | Yayue Deng, Dingdong Wang, Yuxuan Hu +7 | cs.SD | 2026-09-27 |
| #484 | Transformer-based Neural Beamforming for Real-Time Speech Enhancement on Smart Low-Power Hearable Devices | Luca Bompani, Marco Fariselli, Giovanni Oltrecolli +1 | cs.SD | 2026-09-27 |
| #485 | Tokens Change, Structure Endures: Spectral Watermarking for Generated Speech | Kanghwi Lee, Kyeongseok Jeong, Jeongmin Liu | cs.SD | 2026-09-27 |
| #486 | Controlling Speaking Rate in Autoregressive TTS via Activation Steering | Francesco Verdini, Antonis Asonitis, Aref Farhadipour +4 | cs.SD | 2026-09-27 |
| #487 | Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations | Cecilia Bolaños, Luciana Ferrer, Magdalena Fuentes | cs.SD | 2026-09-27 |
| #488 | What Does a Skill Actually Do? Estimands and Evaluation Validity for Tool and Skill Use in LLM Agents: A Critical Review | Shuyang Zhang | cs.SE | 2026-09-27 |
| #489 | Graph-Guided Repository Environment Construction | Jianying Pan, John Zhang, Hongyu Zhang | cs.SE | 2026-09-27 |
| #490 | RAISE: Reinforcing Access Control Policy Synthesis in LLMs via Symbolic Evaluation | Yingming Zhou, Adarsh Vatsa, William Eiers | cs.SE | 2026-09-27 |
| #491 | Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models | Eduardo Ariño de la Rubia, Szilard Pafka | cs.SE | 2026-09-27 |
| #492 | Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents | Yuanhao Li, Hongbo Wang, Xuhong Chen +2 | cs.SE | 2026-09-27 |
| #493 | Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows | Uliana Elina | cs.SE | 2026-09-27 |
| #494 | Acoustic Progress Propagation for Long-Horizon Speculative Decoding in ASR | Yuanyuan Jia, Qianqian Yang | eess.AS | 2026-09-27 |
| #495 | From Script to Drama: An Agentic Framework for Controllable Multi-Speaker Dialogue TTS | Kangxiang Xia, Xinfa Zhu, HangRui Hu +8 | eess.AS | 2026-09-27 |
| #496 | YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality | Ruibin Yuan, Jiahao Pan, Junyan Jiang +32 | eess.AS | 2026-09-27 |
| #497 | Neuron-Level Architecture Growth: A Controlled Evaluation for EEG Time-Series Decoding | Adam Mounir, Stella Douka, Arnault H. Caillet +2 | eess.SP | 2026-09-27 |
| #498 | More than 83.69% of the zeros of the Riemann zeta function are distinct | Kristian Muri Knausgård | math.NT | 2026-09-27 |
| #499 | Sharp Critical Minimax Laws and No-Learning Thresholds in Continuous-Time Adaptive Control | Chen Jia | math.OC | 2026-09-27 |
| #500 | Notes on Generative Modeling for Feedback Control and Planning | Karthik Elamvazhuthi | math.OC | 2026-09-27 |
| #501 | Local LMO is Secretly a Projection Method! | Peter Richtárik, Ammar Mahran | math.OC | 2026-09-27 |
| #502 | lapanda: A Matrix-Free Differentiable Solver for Nonconvex Constrained Optimization Layers | Yuankun Chen, Zifei Nie, Kangyu Lin +2 | math.OC | 2026-09-27 |
| #503 | Annealed Sinkhorn with Momentum: Certified Unregularized Optimal Transport in Linear Memory | Samuel J. K. Chin, Maximilian Schiffer | math.OC | 2026-09-27 |
| #504 | DCEmbed: Scalable Optimization over Neural Surrogates | Akshay Sreekumar, Nicolas Christianson, Priya L. Donti +2 | math.OC | 2026-09-27 |
| #505 | Identifying the Predictable Drift of a Semimartingale from Marginal Laws | Jakub Marecek, Enrico Biffis, Abigail Langbridge +1 | math.ST | 2026-09-27 |
| #506 | Recovering Lower-Dimensional Semialgebraic Support of a Measure from its Moments | Ruben Karapetyan, Shenyuan Ma, Ales Wodecki +1 | math.ST | 2026-09-27 |
| #507 | Multi-Aperture PPG with MAPIS: Spatial Optical and Temporal Coherence Fields | Shuguang Wang, Yuanjing Wang | physics.optics | 2026-09-27 |
| #508 | A packet-level digital hardware twin for commissioning megahertz diagnostic edge AI and plasma control system integration in tokamaks | Semin Joung, Abhilasha Dave, Luca Scomparin +6 | physics.plasm-ph | 2026-09-27 |
| #509 | Explainable Deep Learning of Resting-State Functional Connectomes Reveals Network Biomarkers of Adolescent Intelligence | Md. Tanvir Rahman, Nabil Anan Orka, Asaduzzaman Khan +1 | q-bio.NC | 2026-09-27 |
| #510 | Taming the Greeks: Option Portfolios with Inductive Biases | Wee Ling Tan, Stephen Roberts, Stefan Zohren | q-fin.PM | 2026-09-27 |
| #511 | Quantum Monte Carlo Tree Search with Fixed Confidence | Mingjie Hu, Jian-Qiang Hu, Enlu Zhou | quant-ph | 2026-09-27 |
| #512 | Terminal-Register Certification for Finite-Measurement Learning of Multiscale Quantum States | Bhvain Makwana, Kashyap Patel, Manjunath Joshi +1 | quant-ph | 2026-09-27 |
| #513 | Autonomous phase discovery | Shiyu Zhou, Yuxuan Zhang, Sebastian Wetzel +2 | quant-ph | 2026-09-27 |
| #514 | ViBR-WM: Visual Bayesian Regression for World Modeling | Jifan Li, Ning Ning | stat.ME | 2026-09-27 |
| #515 | Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction | Prasanjit Dubey, Xiaoming Huo | stat.ML | 2026-09-27 |
| #516 | Can Tabular Foundation Models Amortize Statistical Inference? | Kai Ye, Shijin Gong, Hongyi Zhou +2 | stat.ML | 2026-09-27 |
| #517 | Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks | Xiaojing Sun, Yuhan Zeng, Zihua She +1 | stat.ML | 2026-09-27 |
| #518 | Offline Policy Evaluation via Mixed Bellman Residuals and Adaptive Critic Representations | Amitakshar Biswas, Yuhan Li, Ruoqing Zhu | stat.ML | 2026-09-27 |
| #519 | Schrödinger--Föllmer Actor--Critic: Diffusion Policy Improvement with Finite-Sample Analysis | Yuling Jiao, Lican Kang, Jerry Zhijian Yang +1 | stat.ML | 2026-09-27 |
| #520 | The Statistical Benefits of Multiple Responses for Learning from Demonstrations | Chandramauli Chakraborty, Cong Ma | stat.ML | 2026-09-27 |
| #521 | Sharp training-conditional coverage for conformal prediction under covariate shift | Mehrdad Pournaderi | stat.ML | 2026-09-27 |
| #522 | Domain-Adapted Diffusion Models for Conditional Independence Testing | Yanfeng Yang, Junda Zhao, Yijie Gao +8 | stat.ML | 2026-09-27 |
| #523 | Neural Scaling Laws of Transformer Operator Network | Haoran Yan, Zhongjie Shi, Yuanzhe Xi +2 | stat.ML | 2026-09-27 |
| #524 | Calibrated Derivative-Process Sensitivity for Gaussian-Process Variable Selection | Jia Cai | stat.ML | 2026-09-27 |
| #525 | Sparsity by Default: The Theory and Practice of ARD in Gaussian Process Regression for Variable Selection | Jia Cai | stat.ML | 2026-09-27 |
| #526 | Reliable Replay through Spatial Coherence in Online Continual Learning | Haixiang Sun, Jiefu Zhang, Yinghao He +4 | stat.ML | 2026-09-27 |
| #527 | A Statistical Perspective on Knowledge Distillation: Foundations, Classical Methods, and Large Language Model Extensions | Luyang Fang, Haoran Lu, Jiazhang Cai +4 | stat.ML | 2026-09-27 |
| #528 | Weighted Spline-Expanded Networks with Distributional Balancing for Continuous Treatment Effects | Shucheng Liu, Chan Park, Guanhua Chen | stat.ML | 2026-09-27 |
| #529 | Multi-Marginal Inverse Optimal Transport for Contrastive Learning Via Explicit Anchor-Positive-Negative Coupling | Ngoc-Hai Nguyen, Thuan Nguyen, Prakash Ishwar +1 | stat.ML | 2026-09-27 |
| #530 | An Active-Bottleneck Mechanism for Weak-to-Strong Generalization | Mohammad Zeinalpour, Amir Najafi | stat.ML | 2026-09-27 |
| #531 | Two-Sample Testing for Inhomogeneous Random Graphs in Non-Integral $L_r$ Norms | Soham Dan | stat.ML | 2026-09-27 |
| #532 | HARMONIA: Interpretable Graph Learning through Mixtures of Neural Bases | Quan D. Bui, Nguyen Do, An Nguyen Dang +3 | stat.ML | 2026-09-27 |