PaperScope
LIVE · 2026-10-30 05:40 UTC

New Papers · 2026-10-16 376 submissions

cs.CL · cs.LG · cs.AI · cs.CV daily batch

#TitleAuthorsCatDate
1Sampling the XY model with an attention-based neural networkPiotr Białas, Christian D. Morales, Tomasz Stebel +1cond-mat.dis-nn2026-10-16
2Scalable long-range machine learning interatomic potentials with electrical response for atomistic material modelingYicheng Chen, Xiaoyun Yu, Hyejeong Song +5cond-mat.mtrl-sci2026-10-16
3Between Spoilers and Guesswork: Avoiding Over-Specification in Coding BenchmarksYuanzhe Liu, Bastian Lipka, Avraham Shinnar +3cs.AI2026-10-16
#4StoBasket: Joint Upsell and Cross-Sell Optimization for Contribution MarginXin Hengcs.AI2026-10-16
#5When Can You Trust an Agent's Own Verifier? Stress-Testing Counterfactual Rationale Verification Under Search Pressure and Oracle AccessJonghyun Lee, Moonsu Kim, Sunghwan Parkcs.AI2026-10-16
#6Compression Precedes, Content Decides: Emergent Misalignment in Reward ModelsDhruv Puri, Nikhil Prakashcs.AI2026-10-16
#7World Action Critic (WAC) Model: Joint Foresight and Criticism for Policy LearningXiangteng Zhang, Haoyuan Liu, Yang Guan +7cs.AI2026-10-16
#8Evo-B&B: Behavior-Aware LLM-Guided Joint Evolution of Branching and Node Selection Policies for MILPJiayu Chen, Chentong Chen, Yuhan Liu +3cs.AI2026-10-16
#9MS-Eval: Benchmarking Sub-Agent Delegation and Orchestration in MCP-Intensive Working ScenariosBowen Ding, Qixin Wang, Lexing Ruan +4cs.AI2026-10-16
#10ShadowFPT: Backdooring Federated Prompt Tuning via Shadow TriggersKun Zhai, Teng Li, Yunhao Feng +1cs.AI2026-10-16
#11Look Back, Correct Forward: Error Feedback Calibration for Time Series ForecastingHaonan Yang, Yulin He, Zhuo Lics.AI2026-10-16
#12ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-TuningSicong Li, Qianqian Xu, Zhiyong Yang +4cs.AI2026-10-16
#13When to Forget: Risk-Controlled Context Adaptation for Long-Horizon AgentsChenle Chen, Yangbo Wei, Zhijie Zheng +6cs.AI2026-10-16
#14Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool AgentsLitong Feng, Ji Qi, Yiran Cheng +3cs.AI2026-10-16
#15Sep-Latent: Separator Tokens as Natural Compression Anchors for Implicit ReasoningYinlong Xu, Jianfeng Huang, Zhengdong Zhou +5cs.AI2026-10-16
#16Multiple Turns, Short Horizons: Measuring Effective-Horizon Compression in JailbreaksZhipeng Wei, Michael Lee, N. Benjamin Erichsoncs.AI2026-10-16
#17DiffusionRVGE: Reinforcement Learning via Regression-Based Value Gradient EstimationJiayuan Wang, Tongyao Pangcs.AI2026-10-16
#18From Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding AgentsXianglin Yang, Yechao Zhang, Jiahao Liu +4cs.AI2026-10-16
#19GOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse FoldingQi Si, Xuyang Liu, Penglei Wang +6cs.AI2026-10-16
#20Efficient CPU-GPU collaborative MoE inference via Adaptive Expert AssignmentWenhui Lv, Yunming Liao, Hongli Xu +2cs.AI2026-10-16
#21Adaptation of Computer Use Agents to New Software with User ManualsChulhoon Yoon, Kyungri Park, Jinyeong Yun +3cs.AI2026-10-16
#22Causal Value Attribution of Marketing Labels in LLM-Generated Ads: A Deconfounder ApproachDanhong You, Wei Jiang, Zhiqiang +1cs.AI2026-10-16
#23ASE: Attribution-Guided Semantic Evolution for Time Series ForecastingYuxuan Zheng, Zhaoyang Li, Purui Liu +2cs.AI2026-10-16
#24Where Research Ideation Begins: Forward-Citation Supervision for Actionable Limitation GenerationLiyang Zhao, Yong Cao, Haibin Lingcs.AI2026-10-16
#25Where Does the Performance Go? Understanding and Recovering Performance Regressions in C-to-Rust TranslationZhiqiang Yuan, Chong Wang, Zhenhao Zhou +2cs.AI2026-10-16
#26Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RLYibin Huang, Conghui Zhucs.AI2026-10-16
#27Agentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction?Shiguang Wu, Yaqing Wang, Quanming Yaocs.AI2026-10-16
#28Rethinking GRPO for Large Reasoning Model Safety AlignmentJiawei Chen, Yi Zhang, Jiawei Du +9cs.AI2026-10-16
#29WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement LearningZijun Dou, Zhen Yang, Xijun Liu +3cs.AI2026-10-16
#30LexPilot: Benchmarking the Proactive Interaction Ability of Legal LLMs with Laypeople in Chinese Civil Case ConsultationWenbin Zhang, ShangZhan Li, Bingxiang He +5cs.AI2026-10-16
#31CIIR - Class-Indexed Interface Representation LearningDoo Yon Kim, Christian Wallravencs.AI2026-10-16
#32QuAD: Quantitative Assessment via Distribution-Alignment for Qualitative Data Quality Enabled by a Content-Aware Multi-Agent SystemWenshuo Zhang, Leixian Shen, Qiqi Zhou +6cs.AI2026-10-16
#33Algorithm Modelization: Transforming Optimization Algorithms into Evolvable IntelligenceJian Yao, Zhiyao Zhang, Yichen Li +2cs.AI2026-10-16
#34LongForge: Measuring and Improving Long-Context Instruction Data via Evidence-Assertion Reasoning GraphsZiyang Chen, Junlong Jia, Xing Wu +2cs.AI2026-10-16
#35OfficeTown: Generative Organizations for Evolving Agent IntelligenceHongchen Wei, Daohong Ying, Zhi Hong +10cs.AI2026-10-16
#36FuzzInsight: Navigating the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN FuzzingVivek Vekariya, Fathiyeh Faghih, Alexander Pretschnercs.AI2026-10-16
#37Not All Test-Time Compute Is Evidence: Model-Specific Bias in LLM ReasoningMing Shen, Tianjun Yaocs.AI2026-10-16
#38Characterising and Analysing Retrieval-Augmented Generation TechniquesEmmanuel Igbekele, Olawande Daramolacs.AI2026-10-16
#39Beyond Reward Scoring: Online Multi-Agent Preference Learning for Multimodal Response GenerationZiyun Zou, Jiwoo Hong, Yifan Lu +5cs.AI2026-10-16
#40Reasoning Models Can Control Their Chains of Thought When They Tell Themselves ToUriel Dolev, Idan Schwartz, Yoav Goldbergcs.AI2026-10-16
#41Annotrace: A Workbench for Step-Level Annotation of Agent TracesArun Josephraj Arokiaraj, Chenyi Huang, Sahan Bulathwela +2cs.AI2026-10-16
#42CoTA++: Understanding the Repeat Curse in dMLLMs from an Information Flow PerspectiveQiyan Zhao, Xiaofeng Zhang, Xu-Yao Zhang +4cs.AI2026-10-16
#43Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature ResearchGihan Panapitiyacs.AI2026-10-16
#44SimOPD: Relational Knowledge Transfer for On-Policy DistillationKai Tang, Xing Zheng, Haobo Wang +6cs.AI2026-10-16
#45Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMsFabian Broszio, Michael Hoffmann, Adrian Paschkecs.AI2026-10-16
#46From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent MemoryShangze Li, Yanyu Yao, Derong Xu +2cs.AI2026-10-16
#47AgentOnto: Ontology-Guided LLM Agents for Enterprise Data AnalyticsDayan Pan, Bincheng Zuo, Xiaojian Wang +2cs.AI2026-10-16
#48Robust Function Calling for LLM Agents Under Interface DriftAniruddha Chattopadhyay, Kanishka Halder, Partha Sarathi Roycs.AI2026-10-16
#49OliO: ODE-based Linear Transition Operator for Self-Supervised Time Series ForecastingKwangryeol Park, Seulki Leecs.AI2026-10-16
#50Monitor-Validity Failures: LLM Safety Evidence Paths at Evolving Framework BoundariesJunchi Liaocs.AI2026-10-16
#51Generative Policy Improvement from Observational DataJonas Schweisthal, Dennis Frauen, Stefan Feuerriegel +1cs.AI2026-10-16
#52ScoutRoute: Efficient Mixture-of-Experts Routing Using Internal Language Model SignalsRajdeep Pandhare, Delzaan Bharuchacs.AI2026-10-16
#53GatewayBench: Unified Capability and Security Evaluation Platform for MCP GatewaysYitian Zheng, Zhaorun Chen, Haoyu Li +1cs.AI2026-10-16
#54S-GAP: Stealthy Graph Attack Primitives for Graph Large Language ModelsWenda Li, Tongya Zheng, Shunyu Liu +8cs.AI2026-10-16
#55LocalIntent: Outcome-Specific Structured Generation for Backend-Compatible Smart Building Automation with Local LLMsTianyang Liu, Jiayue Wang, Zhanhao Cheng +4cs.AI2026-10-16
#56Trapped in Your Story: Evaluating Narrative-Induced Sycophancy in Large Language ModelsRuntai Yang, Dandan Zhu, Kaiwei Zhang +1cs.AI2026-10-16
#57SkillBrowser: Selective Skill Exposure for Scalable Skill-Using AgentsJin Ye, Yifan Jiang, Lan-zhe Guocs.AI2026-10-16
#58Darwin-Claw: Environment-Adaptive Experience Consolidation for Recursively Self-Evolving AgentsMingze Yin, Xiaohan Wang, Dian Li +4cs.AI2026-10-16
#59RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent MemoryDabin Sheng, Zhe Wu, Jinming Zhao +2cs.AI2026-10-16
#60From Trajectories to Differentiated Skills: Cognitive Differentiation for Self-Improving AgentsYewei Zhao, Derong Xu, Wei Chen +6cs.AI2026-10-16
#61GEMS: Molecular Structure Elucidation as Learned Search over Isomer GraphsUtku Umur Acikalin, Yingheng Wang, Goncalo J. Gouveia +3cs.AI2026-10-16
#62OwlSight: A Panoramic Monitor for Chain-of-Thought ReasoningLewen Yan, Yanxu Zhu, Jie Zhang +1cs.AI2026-10-16
#63Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and InterpretabilityQingshi Wangcs.AI2026-10-16
#64DrugHarness: An Evolvable Agent Harness for Computational Drug DiscoveryYuxing Chen, Zhisheng Zhang, Cheng Tang +20cs.AI2026-10-16
#65FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on HopperWei Wangcs.AI2026-10-16
#66Beyond SAEs: Consistent Concept Discovery with Sparse CodingJinho Choi, Hyesu Lim, Jaegul Choo +1cs.AI2026-10-16
#67Self-Building LabsJiaru Bai, Yuchi Zhao, Han Hao +4cs.AI2026-10-16
#68AI-Driven Reproducibility and Analytical Robustness in Scientific DiscoveryShicheng Liu, Krista Opsahl-Ong, Andrew Drozdov +6cs.AI2026-10-16
#69qGAMMA: A Framework for Optimal DNN Mapping on Multi-Precision AcceleratorsLeandro Fiorin, Luigi Altamura, Cristina Silvanocs.AR2026-10-16
#70Self-Evolving Coding Agents via Harness-Policy OptimizationZhepei Wei, Wenlin Yao, Baolin Peng +5cs.CL2026-10-16
#71Prune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided PruningMohamed Shaaban, Mohamed Elmahallawycs.CL2026-10-16
#72Causal Latent Workspaces for Looped TransformersIlia Zaznovcs.CL2026-10-16
#73On the Position Bias of Large Language Models: A Comprehensive StudyYining Li, Huayang Li, Lemao Liu +1cs.CL2026-10-16
#74Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based WatermarksZewei Deng, Mohamed Seif, Liyan Xiecs.CL2026-10-16
#75Causal Edit SerializationLouis Robinsoncs.CL2026-10-16
#76The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level FallsLucas Resck, Jingyi Sun, Qianli Wang +2cs.CL2026-10-16
#77Uncertainty-Aware Budget Allocation for Efficient LLM Tree SearchJianguo Huang, Zhiyi Lyu, Fuxiang Zhang +3cs.CL2026-10-16
#78Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External DataZesheng Shi, Xue Li, Chenrui Dai +1cs.CL2026-10-16
#79NLData2Opt: Benchmarking Parameter Derivation and Prediction for Modeling Optimization Problems from Natural Language and DataLijia Liu, Kyohei Atarashi, Jiyi Li +3cs.CL2026-10-16
#80Bengali Hallucination Detection with Retrieval and Programs: A System StudyShamim Hasan, Samiya Ahmed Chowdhurycs.CL2026-10-16
#81Competence-Based Evaluation of Logical Reasoning in Large Language ModelsJize Jiang, Chengxiang Zhaics.CL2026-10-16
#82FederatedBytes: Tokenizer-Free, Byte-Level Small Language Models for Efficient Multimodal Federated LearningAli Sarabadani, Massimo Piccardi, Mehran Abolhasan +3cs.CL2026-10-16
#83Where's the Indirect Evidence? Investigating Grammatical Generalization with Influence FunctionsWilliam Dai, Zhenghao Herbert Zhou, Maya Viswanathan +1cs.CL2026-10-16
#84ASR-Style Transcript Normalization Removes Useful Pragmatic Signal for Dialogue Act ClassificationLucky Onyekwelu-Udoka, Md Shafiqul Islamcs.CL2026-10-16
#85Many Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing MechanismPrakhar Gupta, Terry Jingchen Zhang, Zhijing Jincs.CL2026-10-16
#86Beyond Surface Cues: Robust LLM-Generated Korean Text DetectionSungHo Kim, SangKeun Leecs.CL2026-10-16
#87Aligning Language Models Towards Counterfactual InvarianceBasar Demir, Emily Shen, Ksheeraj Sai Vepuri +5cs.CL2026-10-16
#88Recognizing Atari and Assessing Sente: Controlled Evaluation Tasks for Language-Based Go AgentsTaiyi Chen, Iskar Deng, Amandalynne Paulladacs.CL2026-10-16
#89What Shapes Brain Alignment of Large Language Models during Dialogue? Insights from Language Production and ComprehensionYuko Nakagi, Yuya Chiba, Yasue Kishinocs.CL2026-10-16
#90KiranaBench: Can a Language Model Run a Neighbourhood Shop?Bhuvan Arora, Ankita Karmakar, Chaitanya Jain +10cs.CL2026-10-16
#91Self-Evolving Agents Can Repair Failures but Struggle to Generalize from ThemWeixiang Zhao, Yichen Zhang, Yanyan Zhao +5cs.CL2026-10-16
#92Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs InferenceZhenxu Tian, Kebin Liu, Zhengwu Yang +8cs.CL2026-10-16
#93Controlling the Diversity-Quality Trade-Off of LLMs by Merging Models Before and After AlignmentYasuaki Sumita, Tomoharu Iwata, Toshiyuki Tanakacs.CL2026-10-16
#94Same Person, Different Advice: Auditing LLM Financial Advice with Repeated Risk-Tolerance ResponsesSoovadeep Bakshi, Apurba Bose, Aishwarya Bose +1cs.CL2026-10-16
#95ParetoChat: An LLM-Based Interface for Interactive Multi-Objective OptimizationGokhan Ceyhancs.CL2026-10-16
#96Before Retrieval Begins: Safety and Tool-Use Decisions in LLM AgentsAditya Nawal, Manit Baser, Mohan Gurusamycs.CL2026-10-16
#97Disentangling Language Effects on Tool Admission and Post-Retrieval SafetyAditya Nawal, Manit Baser, Mohan Gurusamycs.CL2026-10-16
#98Cross-Centaur: Modeling Individual Decision-Making Across Psychological Tasks with Language ModelsHikaru Asano, Hidezo Suganuma, Ryutaro Mori +1cs.CL2026-10-16
#99Explaining Chess and Go in Natural LanguageOri Press, Alexander Golubevcs.CL2026-10-16
#100Chinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-MakingQiang Yancs.CL2026-10-16
#101Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond ScalingZehui Feng, Weichuan Wang, Xiaohan Chen +2cs.CL2026-10-16
#102What LLMs Do in the Shadows: Reading Context Reliance from the Unembedding Dark SpaceAlexandra Kuleshova, Andrey Volodichev, Daria Kotova +1cs.CL2026-10-16
#103AMEND: Constraint-Guided Multi-Agent Text Detoxification with Isolated CriticsTianyu Wangcs.CL2026-10-16
#104MAS-Bai: Linguistically Informed Adaptive Multi-Agent Translation for Bowen-Script BaiJingting Zheng, Hong Ren, Yuehan Cui +2cs.CL2026-10-16
#105ReLaDrift: Recurrent Language Generation via Drifting for Test-Time ScalingYuki Otsuka, Daisuke Oba, Naoaki Okazakics.CL2026-10-16
#106MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy DistillationYuhan Sun, Jiaxin Zhao, Yongdong Luo +6cs.CL2026-10-16
#107MGE-PO: Entropy-Aware Credit Assignment for Mathematical ReasoningJihao Huang, Guangjia Chai, Zhirui Chen +9cs.CL2026-10-16
#108Think More or Read More? A Token-Budget Theory of Reasoning with Shared ContextManh Nguyen, Sunil Gupta, Hung Lecs.CL2026-10-16
#109Who Pays for Efficient Inference? Confidence-Based Small-to-Large LLM Routing Across Tasks and LanguagesMd Sabbir Hossen, Anichur Rahman, Pabon Shaha +3cs.CL2026-10-16
#110Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using AgentsFarhan Zarif, Kazi Shahid Ahmed Galib, Synthia Akter Promi +4cs.CL2026-10-16
#111Verbalising Model's Computation for Chain-of-Thought Faithfulness DetectionYujing Wang, Yulan He, Wenya Wang +1cs.CL2026-10-16
#112Inferring L1 Backgrounds from L2 English with LLM Token ProbabilitiesAhmet Yavuz Uluslu, Mark Gales, Kate Knill +1cs.CL2026-10-16
#113Language Models Learn to Improve Language ModelsMinhua Lin, Zijun Wang, Zewen Liu +7cs.CL2026-10-16
#114Sentence-Level Topic Modeling with Lexical and Contextual EvidenceFederica Granese, Serena Villata, Charles Bouveyroncs.CL2026-10-16
#115On the Tip of the Tongue: First-Token Cueing as a Behavioral Probe of Recall Failures in LLMsJaewon Sok, Jewon Yeom, Seonghyeon Park +3cs.CL2026-10-16
#116HydraLLM: Adaptive Width Slicing for Elastic Text and Vision-Language ModelsOscar Kemme, Janek Haberer, Ali Hojjat +1cs.CL2026-10-16
#117A low-dimensional dynamical basis for tongue shape controlSam Kirkham, Patrycja Strycharczukcs.CL2026-10-16
#118MuninAI: A Self-Hosted Agentic Framework for Independent Research GroupsMarkus Fischer, Jens Meiler, Matthias Elgetics.CL2026-10-16
#119Perceive, Solve, Reason: Progressive Capability Formation in Time Series-LLMsXin Qiu, Junlong Tong, Wei Zhang +1cs.CL2026-10-16
#120Truth in Contrast: Calibrated Factual Evidence from Language Model LikelihoodsPonhvoan Srey, Jason Lucas, Pittawat Taveekitworachai +2cs.CL2026-10-16
#121EduWild: How Teacher-Configured Chatbots Fail in Real-World Use and How to Fix ThemZiqi Liu, Ruiwei Xiao, Yuxuan Li +1cs.CL2026-10-16
#122ConvexLLM: Scaling Convex-Hull Speech Interfaces to General-Purpose Audio IntelligenceMing-Hao Hsu, Shujie Liu, Yuxuan Hu +4cs.CL2026-10-16
#123MARS: Memory-Aware Routing for Session-Level LLM AssistantsMinghan Wang, Jinhang Zuo, Zhongxiang Dai +2cs.CL2026-10-16
#124Analyzing Occupational Gender Bias across the LLM Training LifecycleManthan Gadhia, Alexander Hoyle, Karolina Stańczakcs.CL2026-10-16
#125SIT-Eval: Situation-Based Interactive Turn-by-Turn Evaluation of Conversational AgentsRavil Mussabayev, Saveliy Zavertyaev, Dmitriy Parpulov +1cs.CL2026-10-16
#126Trajectory-Triggered Sparse Collaborative DecodingAmit Ranjan Trivedi, Sruthikesh Surineni, Kyong Ho Lee +3cs.CL2026-10-16
#127In Human Memories. Technology, Creativity and Self-Determination: An Ethical ProposalFrancesco Vitucci, Giuseppe Silvi, Francesco Abbrescia +2cs.CL2026-10-16
#128VISTA: Steering LLMs with Latent User Values Inferred from a Few Survey AnswersYinuo Xu, Jadie Adams, Brian Hu +3cs.CL2026-10-16
#129GLOBE: Evolving Structured Agentic Memory for E-commerce Product Optimization in Generative SearchHyunseo Kim, Suil Choe, Sukkyoung So +1cs.CL2026-10-16
#130The Cognitive Cost of LLM Writing: A Reading-Time Comparison with Human TextKamer Cekini, Elisabetta Biondi, Chiara Boldrini +2cs.CL2026-10-16
#131Recognizing Study Lineage Is Not Enough: Over-Crediting Same-Trial Evidence in LLM-Based Medical VerificationMukand Krishna, Anoushka Harit, Chenghao Xiao +1cs.CL2026-10-16
#132Bridging the Language Gap in Scholarly Data II: Enhancing Gender Inference for Chinese NamesLisette Espín-Noboa, Mingrong She, Ana Maria Jaramillo +1cs.CL2026-10-16
#133The Italian lawmaking process: a unified and structured datasetMatilde Contestabile, Chiara Ferrara, Giovanni Parrillo +2cs.CL2026-10-16
#134DLite: History-free Speculative Decoding for Agentic AIJiaming Xu, Hanzhen Wang, Tianlang Zhao +7cs.CL2026-10-16
#135Steering beyond Language: Improving Multilingual Training-Free Text Embeddings via Paired-Residual Subspace RemovalAiliang Lin, Zhuoyun Li, Yusong Wang +3cs.CL2026-10-16
#136Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative DecodingChiatzen Wang, Bill Xu, Haochen Gu +1cs.CL2026-10-16
#137Beyond the Answer: Student-Conditioned Trace Construction for Reasoning DistillationShaoang Li, Yanhang Shi, Yufei Li +6cs.CL2026-10-16
#138DiscoveryRSI: Recursively Learning to Discover Valuable HypothesesJianyuan Zhong, Chenwei Wu, Zhaochen Yu +21cs.CL2026-10-16
#139Behavioral Couplings: From Formation to Behavioral Emergence in Language ModelsDongyoon Hahm, Woogyeol Jin, Dennis Wei +3cs.CL2026-10-16
#140Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM InteractionMohamed Shaaban, Mohamed Elmahallawy, Thomas E. Carrollcs.CR2026-10-16
#141SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware RetrievalHaoming Li, Dingyi Kang, Xu Hu +8cs.CR2026-10-16
#142ECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak AttackYuanwei Wu, Lingdong Huang, Yunlong Mao +3cs.CR2026-10-16
#143MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency InjectionSongping Wang, Peiyang Li, Yi Huang +5cs.CR2026-10-16
#144From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-ExploitationGabriel Hortea, Simon Pietro Romano, Juan Tapiador +1cs.CR2026-10-16
#145TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision ModelsYiqu Yang, Qiaoyuan Zheng, Yang Tian +2cs.CR2026-10-16
#146HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance RemediationManohar Vellala, Soumya Banerjee, Sandip Roy +2cs.CR2026-10-16
#147Direct Conditional Parameterization for N-Dimensional SplattingZhongpai Gao, Benjamin Planche, Van Nguyen Nguyen +5cs.CV2026-10-16
#148STRIDE: Evaluating Spatiotemporal Reasoning in Driving Edge CasesLieqi Liu, Rui gao, Jia-Chen Gu +6cs.CV2026-10-16
#149Replay Pruning and Few-Bit Integer Inference for Hardware-Efficient Speed-Sign RecognitionSe Un Park, Kyungkeon Chung, Huigeol Kim +1cs.CV2026-10-16
#150VISTA: A Multimodal Egocentric Benchmark for Goal-Oriented Perception and Assistance to Blind and Low-Vision UsersNoé Mosca, Mohamed Rayan Barhdadi, Muhammad Hamza +11cs.CV2026-10-16
#151VTrajEmbed: Aligning Text with Video Object Trajectories via Spatiotemporal EmbeddingsRuizhi Chen, Zining Fan, Yudi Guo +5cs.CV2026-10-16
#152Variational and Decomposed method for Mitigating Bimodal Bias in Robust Visual Question AnsweringYihan Zhao, Yuncheng Jiangcs.CV2026-10-16
#153HAPACT: A Benchmark For Human-Centric Physical Impact Localization in MoviesYoungrae Kim, Yejin Jang, Eunho Kim +4cs.CV2026-10-16
#154COMET: Decoupled Distillation, Routing, and Capacity Control for Task-Agnostic Continual Vision--Language LearningSeungyoon Woo, Keonhee Park, Gunhee Kimcs.CV2026-10-16
#155MaskMerge: Structure-aware Token Merging for Efficient Instance SegmentationBavesh Balaji, Letian Jiang, Alexander Wong +2cs.CV2026-10-16
#156ODSS-Net: Orthogonally Decoupled Shared-Specific Representations for Multi-Modal Object Re-IdentificationZhifeng Ma, Yuhong Feng, Chongyi Huang +2cs.CV2026-10-16
#157DICL-Qwen3VL: Decoupled Confidence Calibration for Interpretable Workwear DetectionMeng Wang, Wu Zeng, Mei Li +1cs.CV2026-10-16
#158Query-adaptive Recurrent TokenizationBavesh Balaji, Pranav Gopinath, Pouya Sadeghi +1cs.CV2026-10-16
#159ANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning BenchmarkJoel Julin, Souraja Kundu, Liza Dahiya +6cs.CV2026-10-16
#160Sink-Sparse Hybrid Attention for Efficient Inference in T2I/T2V Diffusion TransformersBingxin Xing, Yu Zhang, Jiatong Ding +2cs.CV2026-10-16
#161How Murky Before a VLM Knows It Cannot See? Accuracy, Confidence and Abstention on a Physical Visibility AxisMochamad Rizal Fauzan, Irgi Suryacs.CV2026-10-16
#162UniField++: A Unified Agentic Framework with Loop Reasoning for MRI Field-Strength EnhancementYiyang Lin, Chenhui Wang, Tianliang Yao +4cs.CV2026-10-16
#163A100: A Hybrid Vision Foundation Model for Agricultural Plant Image AnalysisMayur Pratim Das, Ajai Dubey, Aksshay Mathew P +5cs.CV2026-10-16
#164BRICE: Brain-inspired Recurrent Illusory Contour Encoder for Point Cloud CompletionYunlei Wang, Dawei Li, Xue-song Tangcs.CV2026-10-16
#165Semantic-Critical Regions for Video-to-Audio GenerationYun Fang, Wei Guo, Zhuonan Liang +2cs.CV2026-10-16
#166Frame-Consistent Feed-Forward 3D Gaussian Splatting from Sparse Unposed ImagesViruthshaan Vinasirajan, Ranga Rodrigocs.CV2026-10-16
#167TriFold: Folding irregular 3D Gaussians into structured latents for 3D Scene GenerationYun Wang, Chiyu Wang, Fan Jiang +5cs.CV2026-10-16
#168Scene-Designer: Learning Design Intelligence for Agentic 3D Scene GenerationXuanyu Liu, Hongyan Feng, Miao Pan +5cs.CV2026-10-16
#169Reliability-Consistent Appearance Modeling for RGB-Infrared Multi-Object TrackingBingyang Wang, Jiazuo Yu, Lu Zhang +3cs.CV2026-10-16
#170From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face ImagesZhiqing Guo, Lixin Jia, Luning Sun +7cs.CV2026-10-16
#171Knowledge-Guided Distributional Prompt Learning with Visual Hierarchy for Zero-Shot Anomaly DetectionJiyul Ham, Seongho Yoon, Yonggon Jung +2cs.CV2026-10-16
#172MLLM Frame Subset Ensembling for Audio-Visual Video QA and MLLM-based Reranking for Ad-hoc Video Search in TRECVID 2025Andreas Goulas, Damianos Galanopoulos, Ioannis Patras +1cs.CV2026-10-16
#173RAP: A Dataset for Paper-to-Poster Generation via Declarative Markup from Human-Crafted ExemplarsHaonan Han, Yukang Lin, Minliang Lin +7cs.CV2026-10-16
#174X-Splat: Unified Gaussian Splatting for Joint RGB and X-ray 3D ReconstructionWangze Xu, Chu Zhou, Mae Yamaguchi +4cs.CV2026-10-16
#175Kingfisher: Fast Personalized Visual Autoregressive Generation via Scale-Aware Prompt-Conditioned Scale DecompositionDinh-Khoi Vo, Akihiro Sugimoto, Minh-Triet Tran +1cs.CV2026-10-16
#176Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OODYibo Zhou, Yirong Xiangcs.CV2026-10-16
#177LonGaussian: Tracking Foundation Priors for Long-Context Feedforward Gaussian ReconstructionZhoufeng Xie, Guanjun Wu, Shuai Zhang +2cs.CV2026-10-16
#178SCALE: Improving Guidance-Free Visual Generation via Self-Contrastive Alignment for Likelihood EstimationJiwan Hur, Dong-Jae Lee, Dongyeun Lee +2cs.CV2026-10-16
#179Agentic Image Generation in the WildYifan Li, Bowen Qin, Kun Zhou +8cs.CV2026-10-16
#180Xiaomi-Lens-0 Technical ReportPei Fu, Yike Liu, Yue Sun +12cs.CV2026-10-16
#181I2V-DETACH: Source Grounding Detachment for Unauthorized Image-to-Video GenerationChanhui Lee, Yeonghwan Song, Yewon Kang +1cs.CV2026-10-16
#182FlashReFocus: Interactive Image Refocusing in SecondsChing-Heng Cheng, Chia-Ming Lee, Ming-Ching Chang +3cs.CV2026-10-16
#183Look, Reason, Draw a Region: Recursive Refinement for Spatial Context PredictionWajeeha Tahir, Anna Tegon, Lionnus Kesting +4cs.CV2026-10-16
#184CatchUp: Depth-Aware Re-Admission of Visual Tokens for Efficient Large Vision-Language ModelsEunju Park, Uiwon Hwangcs.CV2026-10-16
#185STC-MGNet: Spatial-Temporal-Channel Attention-Enhanced Multimodal Graph Network for Pedestrian Intention PredictionYuanzhe Li, Meng Wangcs.CV2026-10-16
#186UniPolar: Joint Image and Polarimetric Restoration under Compound Degradations via Physical Consistency LearningYang Jin, Guangyu Guo, Linghao Shen +1cs.CV2026-10-16
#187MOSS-Image Technical ReportMOSI. AIcs.CV2026-10-16
#188FloodVLM-Pix: Language-Guided Pixel-Level Flood UnderstandingChengyang Zhang, Zhihao Wang, Zhiyu Long +4cs.CV2026-10-16
#189LithoWorld: An Endpoint World Model for Lithography Process-Window RecoveryBotong Zhao, Fang Yu, Xinyuan Chen +1cs.CV2026-10-16
#190Can We Use Saliency Maps for the Evaluation of Generative Image Models?Eleonora Ristori, Luca Bindini, Marco Lippi +1cs.CV2026-10-16
#191GeoReason: Bridging Logical Reasoning and Spatial Fidelity in Remote Sensing SegmentationCheng Fan, Han Wu, Tingzhang Luo +3cs.CV2026-10-16
#192Momentum: Persistent Dynamics for Video World ModelsNedko Savov, Stefan Maria Ailuro, Danda Pani Paudel +3cs.CV2026-10-16
#193ShadowCast: On-the-Fly Context-Aware Shadow Augmentation for Remote Sensing Image SegmentationYechan Kim, Dongho Yoon, Jongmin Joo +2cs.CV2026-10-16
#194TriINR: Unsupervised Atmospheric Turbulence Mitigation with Triple Implicit Neural RepresentationsYuka Ogino, Rikuto Otsuka, Yuho Shoji +3cs.CV2026-10-16
#195When Evidence Vanishes: Distilling Visual-Evidence Dependency in Medical Vision-Language ModelsQizhen Lan, Yiling Ma, Ruiqi Chen +8cs.CV2026-10-16
#196TAN: A Size- and Form-Adaptive Masked-Convolution Encoder for Tissue GraphsJan Herschel, Anselm von Gladisscs.CV2026-10-16
#197PONDER: Learning to Generate in the Right OrderJulius Erbach, Dominik Narnhofer, Bernt Schiele +2cs.CV2026-10-16
#198ReVision: Reprogramming Image Generators for Dense Visual PerceptionYitong Yang, Yinglin Wang, Xuexin Liu +6cs.CV2026-10-16
#199PreciseEdit: Strong Yet Stable Semantic Transport for One-Step Image EditingJingyi Wang, Xiao Lucs.CV2026-10-16
#200PanoBench: A Panoptic Occupancy Prediction Benchmark for Autonomous DrivingYi Feng, Zizhan Guo, Junwu E +8cs.CV2026-10-16
#201Execution Before Memory: Diagnosing Memory Failures in Video World ModelsWeiyang Jin, Jiwen Yu, Sihan Xu +2cs.CV2026-10-16
#202LiveSync: Iterative Self-Training for Lip-Sync GenerationHuaishao Luo, Huan Zhang, Guanbo Bao +3cs.CV2026-10-16
#203From Adult Renal Masses to Pediatric Wilms Tumors: Evaluating Cross-Domain Generalization of Kidney Lesion Segmentation on MRISarah de Boer, Myrthe A. D. Buser, Hartmut Häntze +8cs.CV2026-10-16
#204CLEAR: Cooperative Latent Flow for Visual Counterfactual Explanations with Accurate Region PreservationYan Zeng, Changlu Guo, Oskar Kristoffersen +3cs.CV2026-10-16
#205Enhancing RAG-based Medical VQA with Gated Multimodal RepresentationsDaniela Jimenez-Pano, Hugo Jair Escalante, Delia Irazú Hernández-Faríascs.CV2026-10-16
#206SemPurify: Semantics-Aware Data Purification for Black-box Backdoor DefenseJiawei Yu, Syed Irfan Ali Meerza, Yi Wu +2cs.CV2026-10-16
#207Learning to Discriminate Scene Structures Makes Self-Supervised Depth Learning ScalableMengtan Zhang, Yuchuan Cui, Yu Ma +3cs.CV2026-10-16
#208ADA 2025: A Multimodal Dataset for Water-Deficit Stress Detection in Sugar BeetsPiper Powell, Robert Franz, Amos Smith +3cs.CV2026-10-16
#209Not Every Mention Is a Claim: Rethinking Object Hallucination Detection in Vision-Language ModelsHsin-Ling Hsu, Neeraja Kirtane, Kuan-Hao Huangcs.CV2026-10-16
#210Stereo LWIR-RGB Automatic Labeling for Low-Light Camera-Based VRU DetectionDimitrios Bouzoulas, Pyry Jäppinen, Pejman Habibiroudkenar +2cs.CV2026-10-16
#211Diversity Without Labels: Task-Agnostic Coreset Selection Across Perception and ActionJulia Hindel, Benjamin Ramtoula, Kyuhwan Yeon +4cs.CV2026-10-16
#212A Language-Informed Loss for Visual GenerationSuchir Agarwal, Keshigeyan Chandrasegaran, Ziyu Chen +4cs.CV2026-10-16
#213FlexPart: Text-Controlled Semantics-Aware 3D Part Segmentation at Flexible GranularityYiqun Zhao, Jiachen Xu, Yihao Zhi +5cs.CV2026-10-16
#214An Efficient Approach to Beetle Damage Detection of Banana Using Deep LearningMd. Mehedi Hasan Naeem, Ishtiyak Ahmmad Araf, Md. Arefin Haque Mahir +1cs.CV2026-10-16
#215PCDFusion: Proposal-Context-Detail Bayesian Rendering for Infrared-Visible Image FusionRui Liu, Lin Gu, Hesong Li +1cs.CV2026-10-16
#216Agentic Physics-Grounded Video Generation via Memory-Augmented In-Context ReasoningXikang Guan, Shaocong Yang, Yanqi Bao +6cs.CV2026-10-16
#217FedRAPP: Federated Test-Time Prompt Tuning for Vision-Language Models with Reliability-Aware Prompt PersonalizationSyed Md. Ahnaf Hasan, Md Akil Raihan Iftee, Sajib Mistry +2cs.CV2026-10-16
#218Synthetic Image Oversampling for Rare-Class Representation Learning in Deep Facial PhenotypingMiles Liao, Zhanliang Wang, Hongzhuo Chen +1cs.CV2026-10-16
#219Beyond Multi-Stage Pipelines: A Label-Correlation Ensemble for Multi-Label Retinal Fundus Disease ClassificationMd Asif Uddin, Jannatul Ferdous, Asif Islam +5cs.CV2026-10-16
#220MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image EditingHouyuan Chen, Fanzhou Wang, Xiangyu Fan +7cs.CV2026-10-16
#221A Paired RGB-Sonar Dataset for Fish Monitoring with Consumer SonarMourad Derbedrosian, Michael Hobley, Pietro Peronacs.CV2026-10-16
#222Video Diffusion Avatars: Taming Video Diffusion Models into Controllable 3D AvatarsSimon Giebenhain, Tobias Kirschstein, Liam Schoneveld +3cs.CV2026-10-16
#223The Collection of a Real-World, Large-Scale Dataset for Automated Skill Evaluation in Central Line Dressing ChangeUmmey Tanin, Shannan K. Hamlin, Hsin-Mei Chen +2cs.CV2026-10-16
#224Persistent Planar Memory for Video World ModelsYuze He, Bin Tan, Zelin Gao +4cs.CV2026-10-16
#225StopWatch: Goal Grounding for Object-goal NavigationXinhao Liu, Yunsheng Tian, Yuheng Qiu +4cs.CV2026-10-16
#226Rethinking the design space of Vanilla Pixel Diffusion TransformersSoumik Mukhopadhyay, Long Mai, Abhinav Shrivastava +1cs.CV2026-10-16
#227Learning to Correct Geometry in Generated VideosWeijie Lyu, Tiancheng Shen, Jason Li +5cs.CV2026-10-16
#228Can AI interview? Comparing AI-led to Human-led Chat InterviewsSemra Guven, Tobias Gårdhus, Andreas Bjerre-Nielsen +2cs.CY2026-10-16
#229NL2SQL with Iterative Self-RefinementAnjali Vemula, Akshat Dasulacs.DB2026-10-16
#230One Communicator, Three Vendors: Extending the MoA Predictive Theory to a Real NVIDIA+AMD+CPU MPI EnsembleLenore Mullin, Gaetan Hainscs.DC2026-10-16
#231DIFFLET: A Fast Inference Engine for Diffusion Transformer Models on AWS TrainiumBin Ma, Min Yu, Vijay Kodamalla +2cs.DC2026-10-16
#232Anytime Contracts for AI ServicesBoris Velasevic, Eden Saig, Eric Mazumdarcs.GT2026-10-16
#233Cooperation Without Adaptation: LLM Agents in a Collective-Risk DilemmaTrung-Kiet Huynh, Dao-Sy Duy-Minh, Chi-Nguyen Tran +4cs.GT2026-10-16
#234Proportionality in Ranking CompressionDaniel Halpern, Xinyu Liu, Evi Micha +2cs.GT2026-10-16
#235PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse PersonasHaoming Li, Defu Cao, Xu Hu +23cs.HC2026-10-16
#236Designing for Imperfect Prompts: A Simulation-Based Evaluation of an LLM-Based Enterprise Data Assistant Using Knowledge GraphsNiklas Wagner, Alexander Mädchecs.HC2026-10-16
#237mmPencil: Toward Writing-Style-Independent In-Air Handwriting Recognition via mmWave Radar and Large Vision-Language ModelYifan Guo, Zhu Wang, Qian Qin +6cs.HC2026-10-16
#238PresenceBench: An Exploratory Evaluation of Large Language Model Adaptation to User StatePeña Arroyo Gallego, Mauro Ruiz Moreno, Alejandro Acien +2cs.HC2026-10-16
#239Reasoning Reranking with Semantic IDs as the Sole Item RepresentationZhenwei Tang, Jintao Liu, Di Bai +2cs.IR2026-10-16
#240QD-Rec: Open-Ended Evolution of Recommendations via Quality-DiversityTakashi Ishida, Taro Makino, Issa Sugiuracs.IR2026-10-16
#241Acquisition Function-Guided Generation for Bayesian Optimization over Discrete SpacesTommaso Ancilli, Thomas Wedenig, Henry Moss +1cs.LG2026-10-16
#242Reusing Calibration Gains across Model RepresentationsXu Cao, Wenxuan Xiaocs.LG2026-10-16
#243Next Token or Vector? Learning How Far to DecodeSai Sreenivas Chintha, Chidera Biringa, Rishab Sharma +6cs.LG2026-10-16
#244Ori: Drift-Aware Streaming $k$-PCA for Very Low-Rank LLM TrainingXinyu Luo, Jincheng Zhou, Mengbo Wang +5cs.LG2026-10-16
#245Partial-Revelation Panel Forecasting: Predictive Information Gain, Allocation, and Coarsening-Consistent OperatorsBin Wen, Dai-Qiao Zhang, Tien-Ping Tancs.LG2026-10-16
#246Benchmarking and Enhancing Agentic Causal DiscoveryPingchuan Ma, Rui Ding, Shuai Wangcs.LG2026-10-16
#247Learning to Be Guided: Shaping Latent Geometry for Classifier-Free GuidanceHaoming Liu, Junhao Zhu, Shaoyi Zheng +4cs.LG2026-10-16
#248Batched Contextual Reinforcement II: Does RLVR Need Long Rollout Windows?Bangji Yang, Hongbo Ma, Ruihan Guo +3cs.LG2026-10-16
#249What Accuracy Hides In Learned Transformer ProgramsJonathan Lee, Narmeen Oozeer, Philip Quirkecs.LG2026-10-16
#250A Feature Selection Layer Approach for Multi-Class Classification on Neural NetworksJoão Pedro Silveira e Silva, Márcio Dorn, Bruno Iochins Griscics.LG2026-10-16
#251Scalable Levenberg-Marquardt Training Framework for Deep LearningXianghao Wang, Johan Barthélemy, John Taylorcs.LG2026-10-16
#252Large Diffusion Models Need More Than EMAChuyu Hu, Huanran Chen, Shitong Shao +1cs.LG2026-10-16
#253On the tradeoff between robustness and geometric accuracy in adversarial trainingRachel Morris, Ryan Murray, Kerrek Stinsoncs.LG2026-10-16
#254Towards Hyperparameter Transfer for Differentially Private OptimizationTianze Wang, Zhiqi Bu, Linjun Zhangcs.LG2026-10-16
#255TALLOP: Joint Optimization of Local Training and Communication Compression for Time-Constrained Federated LearningHonoka Anada, Yafei Ou, Shinya Takamaeda-Yamazakics.LG2026-10-16
#256A Label Noise Robust Algorithm for Graph Data using Neighborhood Label DistributionPintu Kumar, Nandyala Hemachandracs.LG2026-10-16
#257A Minimal ReLU Classifier on Non-Linearly Separable Data: Convergence and Implicit Bias at and beyond the Edge of StabilityQuan Nguyen, Robin Yadav, Param Mody +1cs.LG2026-10-16
#258"Deep lifts": Neural networks can generalize even with the dumbest optimizerSunil Madhow, Yu-Xiang Wangcs.LG2026-10-16
#259Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State DesignBenhao Huang, Chufan Shi, Junlin Chen +4cs.LG2026-10-16
#260GR-OPD: Group-Relative Sequence Credit for On-Policy DistillationYushu Wang, Renkai Yang, Jingcao Xu +4cs.LG2026-10-16
#261Path to Prior-Data Fitted Relational Models via Learned Latent Multi-table RepresentationsMohammad Sadeq Abolhasani, Viswanath Ganapathycs.LG2026-10-16
#262Where Latents Belong and How They Flow: Joint Identification of Structural RolesXintong Li, Kun Zhang, Yujia Zhengcs.LG2026-10-16
#263Towards a GraphNARX model for structural dynamicsGeorge Tsialiamanis, Keith Wordencs.LG2026-10-16
#264Domain-specific language alignment of multimodal embeddings towards explainable predictionsGabrielė Tijūnaitytė, Thijs L. van der Plas, Mohamed-Bachir Belaid +3cs.LG2026-10-16
#265LED: Improving Masked Diffusion Language Models by Lookahead EditingYuyan Zhou, Zeyuan Yang, Yuxuan Song +5cs.LG2026-10-16
#266MetaCurate: Evolving Curation Filters for High-Quality Agentic Coding DataDonghoon Kim, Seunghyuk Oh, Kevin Galim +6cs.LG2026-10-16
#267Local proxies for memory-efficient trainingWu S. Zihan, Brian A. Yuan, Guillaume Belleccs.LG2026-10-16
#268Grounded Credit Assignment in Reinforcement Learning for Multi-Turn Search AgentsQirui Liu, Hao Chen, Yi Wen +7cs.LG2026-10-16
#269Nearly Linear Private Learning of Littlestone ClassesShay Moran, Chao Yancs.LG2026-10-16
#270Structural Affinity: An Algorithm for Coherent Cage-Based Shape DesignAviraj Newatia, Shengan Yang, Hantao Zhong +1cs.LG2026-10-16
#271Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement LearningHeming Zou, Qi Wang, Yixiu Mao +7cs.LG2026-10-16
#272A Stronger Teacher Within: Strengthening MoE Models via On-Policy Bidirectional DistillationHaoyu Chen, Jun Bai, Yang Liu +2cs.LG2026-10-16
#273LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial OptimizationHironori Ohigashics.LG2026-10-16
#274Non-Parametric Optimization for Scalable Learning in Stochastic Decision ProblemsMohsen Amidzadeh, Lauri Viitasaari, Mario Di Francescocs.LG2026-10-16
#275Process Reward Modeling with Reliability- and Conservatism-Aware Bayesian BeliefZhongjian Qiao, Zhixiang Zhou, Jiafei Lyu +4cs.LG2026-10-16
#276Response-Informed Value Estimation for Cost-Aware Multi-Turn LLM RoutingHaotian Yan, Jiaqi Liu, Bingyi Jing +1cs.LG2026-10-16
#277Anisotropic Representation Dynamics in TransformersNguyen Do, My T. Thaics.LG2026-10-16
#278FLARE: Physics-Grounded Evaluation of Language-Model Agents for Feeder Restoration with Degraded ObservationsBHVSP Subrahmanyam, Neeraj Choudharycs.LG2026-10-16
#279Sample, Mix, or Verify? Allocating Test-Time Compute under Imperfect VerifiersSrinivasan Iyengarcs.LG2026-10-16
#280ADT: All-Atom Diffusion Tokenizer for 3D Molecular StructuresXuantuo Huang, Encheng Su, Aoran Wang +6cs.LG2026-10-16
#281Beyond Marginal Influence: Interaction-Aware Memory Selection for LLM AgentsBHVSP Subrahmanyam, Neeraj Choudharycs.LG2026-10-16
#282DeDiCa: A Scalable Deconfounding Discrete Causal Generative ModelKunchangtai Liang, Adrián Javaloy, Antonio Vergari +1cs.LG2026-10-16
#283Data-Efficient Classifier Pretraining Through Diffusion ModelsQinyu Li, Yee Whye Teh, Chris Holmes +1cs.LG2026-10-16
#284Untrained CNN and coefficient-space regularization for joint reconstruction in photoacoustic tomographyAlfio Bozi, Anwesa Dey, Souvik Roycs.LG2026-10-16
#285Peak-Memory Schedules You Can Trust: Exact Realization, Certified Optimality, and the Limits of Recomputation for InferenceIvan Fomin, Ivan Koryabkin, Boris Sheludkocs.LG2026-10-16
#286HiPredict: Predicting the missing HiRISE RED4 spectral channel with machine learningArdan Suphi, Ben Moseley, Gareth S Collins +2cs.LG2026-10-16
#287Minimax-optimal Scaling Laws in Ridge Regression via Transfer LearningYalda Shabanzadeh, Diyuan Wu, Marco Mondellics.LG2026-10-16
#288SETAREH Transform: A Sorting-Assisted Haar-Wavelet Sparsification Method for Approximate Inner-Product ComputationSeyed Kamaledin Setarehdancs.LG2026-10-16
#289How Finite-Rank Bottlenecks Shape the Low-Rank Adaptation LandscapeLong Nguyen-Chi, Quynh Nguyen, Thanh Nguyen-Cung +1cs.LG2026-10-16
#290RTSM: Adapting Recursive Models to Multivariate Time-Series ClassificationGeorg Tenzing, Anna Tegon, Luca Benini +1cs.LG2026-10-16
#291Forecasting Voltage Time Series under Anomalies Using a WGAN Model With Lipschitz Control and Progressive Kernel Critic StrategyNajmieh Sadat Safarabadics.LG2026-10-16
#292Contracting with an Agent under Model MismatchElif Yılmaz, Jakub Tłuczek, Victor Villin +1cs.LG2026-10-16
#293Information Estimation with Discrete DiffusionAlberto Foresti, Giulio Franzese, Pietro Michiardics.LG2026-10-16
#294Flash RNN-T: Memory-Efficient Joint Network and Transducer Loss ComputationMahmoud Ashrafcs.LG2026-10-16
#295Residual Stochastic Concept Bottleneck ModelsStephen Marcou, Mateo Espinosa Zarlenga, Sonia Laguna +3cs.LG2026-10-16
#296Bridging Compressed Communication and Local Steps via Spectral Method in Federated LearningDmitriy Bystrov, George Chirkov, Daniil Medyakov +2cs.LG2026-10-16
#297RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement LearningAlexander W. Goodall, Francesco Belardinellics.LG2026-10-16
#298Regularized free deconvolution for spectral repair of resampling distortion in high-dimensional particle filtersDeming Song, Chi-Kin Lam, Kefeng Li +3cs.LG2026-10-16
#299Predictable Scaling: Efficient Model Exploration via Scaling-Law PredictionAishwarya Wesanekar, Sheng-Tao Yang, Jiawei Zhang +20cs.LG2026-10-16
#300A Topological Signature of Learning under Noisy LabelsZhongtian Sun, Fan Mo, Prayag Tiwari +1cs.LG2026-10-16
#301Uncertainty-aware AI-enabled framework for predicting hydrogen dispersion in confined spaces to enhance operator situational awarenessNiclas Flehmig, Mary Ann Lundteigen, Shen Yincs.LG2026-10-16
#302Out of Support, Not Out of Reach: In-Context Learning with Unsupported Instructions and Composed TasksXuhan Tong, Yuchen Zeng, Jiawei Zhangcs.LG2026-10-16
#303Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree SearchQuynh Trinh, Trung Nguyen, Nam Nguyen +1cs.LG2026-10-16
#304BMuon: Budgeting Muon's Spectral Geometry for Structured CompressibilityRida Assalouh, Tom Jacobs, Rebekka Burkholz +2cs.LG2026-10-16
#305Boundary Detection for High-Dimensional Point CloudsAbigail Hickok, Valerio Galanti, Osama Al Dalahmah +1cs.LG2026-10-16
#306When Magnitude Suffices: Reconstructing Time-Domain-Gated Microwave Signals Without Phase on a Thoracic PhantomMaciej Cichoń, Patrycja Gołaś, Maksymilian Bartosik +3cs.LG2026-10-16
#307How Many, but How Sure? Class Competition as a Confidence Proxy in Multi-Class Density-Based CountingVillanelle O'Reilly, Georgios Leontidis, Marc Hanheidecs.LG2026-10-16
#308The Sign Code: The Hidden Binary Nature of Deep NetworksNiclas Göring, Shuofeng Zhang, Roi Holtzman +2cs.LG2026-10-16
#309ThetreStageAI: Multi-View Retrieval-Augmented Generation for Structured Bengali Theatre Production PlanningMd. Mehedi Hasan Naeem, Mst. Kamrunnahar Ruma, Shakila Sultana +3cs.LG2026-10-16
#310GRAFT-EEG: Gauge-Aware Physical Field Transport for Cross-Dataset Motor-Imagery EEGYing Zhou, Mengting Liucs.LG2026-10-16
#311Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal DecompositionJuho Jung, Seongjae Kang, Jinyoung Hancs.LG2026-10-16
#312Deep LLM layers expose passage-level context in EEG during silent readingIngo Marquardt, Anthilia Alchanat, Priyanka Jaincs.LG2026-10-16
#313No-Regret Language GenerationJiaxun Li, Vinod Raman, Ambuj Tewarics.LG2026-10-16
#314JAXtari: High-Throughput and Easy-to-Modify Arcade Learning EnvironmentQuentin Delfosse, Raban Emunds, Paul Seitz +5cs.LG2026-10-16
#315TriRouter: Sparse-to-Dense Electrode-Space Routing for Robust EEG Motor Imagery DecodingYing Zhou, Yaoxin, Mengting Liucs.LG2026-10-16
#316Equivalence testing and run-count design for stochastic machine-learning experimentsDmytro Knopov, Nadiya Shvaics.LG2026-10-16
#317Blitz: Accelerating the Diffusion Modules of AlphaFold3 and Boltz-2Vinay Saji Mathew, Soundar Kumara, Gretta Kellogg +1cs.LG2026-10-16
#318Tool Recommendation for Multi-Step Agents: Finding Every Tool a Task NeedsSam Partee, River Stevens, Thierry Damiba +1cs.LG2026-10-16
#319Neural Expansion: A Unified Mechanism for How Deep Neural Networks GeneralizeChashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino +2cs.LG2026-10-16
#320Escaping Parameter Space: Tight Generalization Bounds via Representation QualityNiclas Göring, Shuofeng Zhang, Branton DeMoss +1cs.LG2026-10-16
#321LagNet: Lag-Structured Operators for Long-Term Time Series ForecastingZhenan Yu, Guangxin Jiang, Jiuyun Jiang +1cs.LG2026-10-16
#322Universal Semantic Enhancement for Weakly Supervised Anomaly DetectionSiyu Zhou, Yuqin Xie, Hao Yuan +1cs.LG2026-10-16
#323Logic-Guided Graph Denoising Diffusion ModelsSamuel Cognolato, Luciano Serafini, Alessandro Sperduti +1cs.LG2026-10-16
#324Explainable Machine Learning Analysis of Temperature Effects on Mechanical Strength of Fiber-Reinforced High-Performance ConcreteJagaran Chakma, Zhiguang Zhou, Badhan Chakma +1cs.LG2026-10-16
#325Learning Personalized Memory Gating from Delayed One-Sided FeedbackKaixuan Ji, Zixiang Chen, Wenting Zhao +9cs.LG2026-10-16
#326CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement LearningTianmeng Hu, Biao Luo, Ke Lics.LG2026-10-16
#327Waiting Buys Exactly Two Moments: Endogenous Identification in Prediction-Driven AllocationRama AlHamidi, Rasul Khanbayov, Erchin Serpedin +1cs.LG2026-10-16
#328SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural NetworksKai Sun, Peibo Duan, Zhanglu Yan +3cs.NE2026-10-16
#329Preventing Data Hallucinations in Agentic AI for Optical Network TroubleshootingJeremias Dötterl, Martin Kuiperscs.NI2026-10-16
#330The Optimal Ranking Tradeoffs Between Two Ranking Scores in Two-Class ClassificationSébastien Piérard, Adrien Deliège, Marc Van Droogenbroeckcs.PF2026-10-16
#331Data-Driven Prediction of Optimal MPI Rank Placement and Node Count for Memory-Bound CFD on AMD EPYC ClustersMarcin Lawenda, Łukasz Szustak, Aleksandra Krasickacs.PF2026-10-16
#332Shape-Aware Neural Time Fields for Rigid-Body Motion and Manipulation PlanningYanming Zhou, Yuchen Liu, Ahmed H. Qureshics.RO2026-10-16
#333Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action AnchorsCarl Qi, Weijun Dong, Xiaojie Wang +8cs.RO2026-10-16
#334MambaAct: Efficient Mamba Action Experts for Flow-Matching Vision-Language-Action ModelsKhuyen Pham, Tran Nguyen Le, Edoardo Fazzari +1cs.RO2026-10-16
#335Unifying Embodied Foundation Models via a Model-to-Policy FormulationXinyi Hong, Mingyang Rencs.RO2026-10-16
#336Expand-and-Prune: Test-Time Candidate-Space Adaptation for End-to-End Autonomous DrivingFabian Schmidt, Karol Fedurko, Markus Enzweiler +1cs.RO2026-10-16
#337NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action ModelsGuodong Du, Wanyu Lincs.RO2026-10-16
#338Beyond Success Rate: Interventional Evaluation of Memory in Vision-Language-Action SystemsKeyuan Luo, Yi Xie, Wanyun Ling +3cs.RO2026-10-16
#339AWAM: Active Trajectory-Conditioned View Imagination for Robust Robot ManipulationJiawei Geng, Zhenyang Liu, Yuzheng Wu +1cs.RO2026-10-16
#340Reason-guided Human Reward Modeling for Preference-based Reinforcement LearningAnshul Nayak, Shahil Shaik, Jonathan Smereka +1cs.RO2026-10-16
#341Beyond Action Prediction: Learning Search-Free Planning in Latent SpaceGuanchen Du, Jinhao Du, Yanpeng Sun +3cs.RO2026-10-16
#342Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake DetectorsJingyi Chen, Surya Koppisettics.SD2026-10-16
#343Framing Spatial Hearing within the Free Energy Principle: A Hierarchical Model of Perceptual LearningRoberto Barumerli, Nils Meyer-Kahlen, Lorenzo Picinalics.SD2026-10-16
#344Interpreting SSL Representations for Spoof Detection: a WavLM StudyMohamed Mallat, Michele Panariello, Massimiliano Todisco +2cs.SD2026-10-16
#345Beyond the Benchmark: Conditioning, Domains and Failure Modes of Qwen3-TTSSéverin Baroudi, Yanis Labrak, Petr Motlicek +2cs.SD2026-10-16
#346VocalGrad: Evaluating Acoustic Perception in Audio Language ModelsKoki Ryu, Hitomi Yanakacs.SD2026-10-16
#347Validating LLM-generated political networks with survey-reported partisan exposureMarco Tonin, Michele Tizzoni, Bruno Lepri +1cs.SI2026-10-16
#348"You" Is Not Toxic: How LLM Labelers Rewrite the Web's Conversation LawsLiang Yue, Eric A. Vancecs.SI2026-10-16
#349Graphlet-based Decentralized Finance Transaction Method ClassificationCélestin Coquidé, Alessio Brini, Natkamon Tovanichcs.SI2026-10-16
#350Measurement-Adaptive Light-Cone Transform for Robust Non-Line-of-Sight ImagingLianfang Wang, Xueying Liu, Junnan Dong +4eess.IV2026-10-16
#351Stabilizing Illumination Conditioning in SSM-Based Low-Light Image Enhancement with Bottleneck Prompt SidecarsWei Chen Ng, Qiyi Xie, Jian Ding Tan +3eess.IV2026-10-16
#352TransNSNet: A Transformer-Enhanced Multi-Scale Adversarial Framework for CT-to-PET Image SynthesisShaojun Li, Xiaoyu Deng, Ikuo Keshieess.IV2026-10-16
#353Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress DetectionWei-Hsiang Ma, Ya-Tse Wu, Hsing-Hang Chou +1eess.SP2026-10-16
#354ECG-SDI: Single-lead Electrocardiogram Enables Continuous Sleep Depth Index Profiling and Scalable Digital Biomarkers for Sleep HealthDonglin Xie, Qingshuo Zhao, Songchi Zhou +5eess.SP2026-10-16
#355Distributed Performance Boosting through Neural Control for Plug-and-Play NetworksDanilo Saccani, Leonardo Massai, Giancarlo Ferrari-Trecateeess.SY2026-10-16
#356On the possibilities and limitations of LLM-based multi-agent systems for multi-criteria decision-making in healthcare operations managementMarco Boresta, Tommaso Giovannelli, Sepehr Namirad +1math.OC2026-10-16
#357From Flow-Box Invariants to Global Conservation Laws: Machine Learning-Assisted Detection of Singularities and Near-IntegrabilityJimmie Adriazola, Ioannis G. Kevrekidis, Panayotis G. Kevrekidis +1nlin.CD2026-10-16
#358How the elastic axis folds the transonic flutter boundary: shock energy transfer and conformally calibrated active learningAshray Saxena, Sharad Shrivastavaphysics.flu-dyn2026-10-16
#359Learning angles for quantum approximate optimizationJohannes Jakubik, Isabelle Wittmann, Zaheed Gaffoor +5quant-ph2026-10-16
#360Expressivity of IQP Feature-Map Quantum Kernels via Reproducing Kernel Hilbert SpacesValeria Repetto, Stefano Melchionna, Romina D'Aurizioquant-ph2026-10-16
#361Quality-of-Transmission Estimation in Quantum Networks: Compute, Simulate, or Learn?Anis Bekri, Amar Abane, Van Sy Mai +2quant-ph2026-10-16
#362Task-aligned spectral inductive biases in parameterized quantum circuitsFelix Frohnert, Adrián Pérez-Salinas, Sebastian Lange +3quant-ph2026-10-16
#363Conformal Policy Selection: When to Deploy AI Decisions for Targeted InterventionJunyu Cao, Ruijiang Gao, Maytal Saar-Tsechansky +1stat.ME2026-10-16
#364Causal Discovery beyond Conditional Independence: Identifiability, Algorithms, and Statistical Inference for Directed Acyclic and Cyclic GraphsYang Nistat.ME2026-10-16
#365Unit-level aggregation breaks coverage in causal foundation modelsGabe Schulman, Lucius E. J. Bynum, Yoav Waldstat.ML2026-10-16
#366Distinguishability and Recovery for a Doubly Sparse Spiked Wigner ModelIoana Dumitriu, JD Flynn, Zhichao Wangstat.ML2026-10-16
#367Information-Geometric Blind Spots of Conformal Test MartingalesJohan Hallberg Szabadvárystat.ML2026-10-16
#368The Loss or the Architecture? What Matters in Survival Analysis with Competing RisksJulie Alberge, Gaël Varoquaux, Judith Abécassisstat.ML2026-10-16
#369Towards optimal selection schedules for online active learningHugo Cui, Francesca Mignacco, Francesco Moristat.ML2026-10-16
#370Adaptive conformal prediction on the GrassmannianDimitrios Loukrezis, Zachary J. Grey, Dimitris G. Giovanisstat.ML2026-10-16
#371A general recipe for data-adaptive anytime-valid envelopes for iterative algorithmsSoham Bonnerjee, Aaditya Ramdasstat.ML2026-10-16
#372Mesoscopic learning dynamics of extensive-width neural networksShu Zhou, Jean Barbier, Sebastian Goldtstat.ML2026-10-16
#373Parametric Resonance in Primal-Dual Learning for Slowly Non-Stationary Constrained MDPsMaxime Baeldestat.ML2026-10-16
#374Task-aware Kernel Stein certificates for Rényi differential privacyLeoni Carla Wirth, Tara Trautwein, Gesine Reinertstat.ML2026-10-16
#375Learning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphereJoshua Williamson, Niall Jeffrey, Lorne Whitewaystat.ML2026-10-16
#376ENFR: Evidence Networks with Flow-Matched References for Amortized Simulation-Based Model InferenceKai Lehman, Jameson Dong, Carolina Cuesta-Lazaro +5stat.ML2026-10-16

latest · trends · arXiv announcement batches follow US Eastern weekdays