PaperScope
LIVE · 2026-09-03 05:40 UTC

New Papers · 2026-08-09 239 submissions

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

#TitleAuthorsCatDate
1Clustered Attractor Manifolds and Dynamical Condensation in Self-AttentionQucheng Gao, Zuyi Yang, Xiao Chencond-mat.dis-nn2026-08-09
2Temperature-Driven Sequential Modeling for the Prediction of Annual Power Conversion Efficiency Profiles of Organic Photovoltaic Materials: Douala Case StudySteve Cabrel Teguia Kouam, Rockefeller Rockefeller, Raoult Dabou Teukam +4cond-mat.mtrl-sci2026-08-09
3LLMVisor: A Real-Time Latency Attribution Model for Multi-Tenant LLM ServingShuowei Jin, Xueshen Liu, Jiaxin Shan +4cs.AI2026-08-09
#4Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research AgentsHarshitha Kolukuluru, Reshma Ashok, Kirat Arora +7cs.AI2026-08-09
#5CAP: A Scalable Benchmark for Evaluating Cross-Site Browser Agents with Complex Actions and PerceptionZejun Xu, Taiyi Chen, Jin Li +13cs.AI2026-08-09
#6Estimating Uncertainty in Galaxy Morphology ClassificationKai Cheng, Ruoqi Wang, Qiong Luocs.AI2026-08-09
#7Forgotten History or Test-of-Time? Retrospect and Prospect on RAG from an IR PerspectiveXiaoyan Zhao, Yujie Cai, Yang Zhang +2cs.AI2026-08-09
#8TRACE-Memory: Public-Conditioned Retrieval and Utility-Aware Evidence Admission for Personalized GenerationJing Wang, Zhu Wang, Yifan Guo +2cs.AI2026-08-09
#9What Keeps Agent Skills from Being Reusable? Evidence from 138K SKILL.md FilesChi Zhang, Yimin Liu, Xinze Chen +1cs.AI2026-08-09
#10Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent HarnessesTailin Zhoucs.AI2026-08-09
#11LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMsMinhan Cho, Soyoung Park, Kihyeon Jeong +3cs.AI2026-08-09
#12Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal GenerationKaichen Zhang, Wei Huang, Keming Wu +2cs.AI2026-08-09
#13Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in ProductionCong Ming, Jingyi Chen, Bin Liu +4cs.AI2026-08-09
#14HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM GuardrailsTak Ho Alex Li, Kaijie Liu, Lik-Hang Lee +3cs.AI2026-08-09
#15TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward ModelsYidong Wang, Yan Zhan, Ziteng Feng +16cs.AI2026-08-09
#16MathShikkha: A Controlled Study of Answer-Only and Chain-of-Thought Supervision for Bangla Mathematical Reasoning in Small Language ModelsRahma Simin Ali, Jawad Hossaincs.AI2026-08-09
#17Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMsMohanad Odema, Gabrielle De Micheli, Dayin Gou +3cs.AI2026-08-09
#18Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Document UnderstandingMahbub E Sobhani, Md. Faiyaz Abdullah Sayeedi, Fahmid Hasan Chowdhury +4cs.AI2026-08-09
#19Reproducing and Stress-Testing Two Approaches to LLM Reasoning Reliability: Test-Time Probability Aggregation and Logic-Representation EditingMinhan Cho, Jimin Kweoncs.AI2026-08-09
#20Discovering Diverse Planning Policies for Multimodal Embodied Agents with Quality-Diversity OptimizationPengfei Xu, Yong Liu, Xiaoya Nan +2cs.AI2026-08-09
#21Deep probabilistic logic programming for diagnostic reasoning from incomplete information: A case study in stroke detectionFelix Weitkämper, Monchito Avila, Elizabeth Nanjala +2cs.AI2026-08-09
#22VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio InferenceWenxu Jia, Dongjie Fu, Xize Cheng +6cs.AI2026-08-09
#23FailForge: Distilling Procedural Competence from Persistent Failures into Code AgentsDongyi Lv, Fushun E, Aichen Cai +8cs.AI2026-08-09
#24SDDBMs: Soft Denoising Diffusion Bridge ModelsShiyi Qi, Kun He, Mingmou Liucs.AI2026-08-09
#25Unaccountable Delegation, Fading Skills: Mapping the Risks of Workplace AI AgentsGabriele La Malfa, Lakmal Meegahapola, Edyta Bogucka +4cs.AI2026-08-09
#26ForestBench: A Unified Graph Framework for Evaluating Multi-Agent CollaborationGuo Chen, Ziwen Li, Reed Li +4cs.AI2026-08-09
#27Walking through Discussions: A Mobile Visual Analytics System for In-Situ Group Discussion AnalysisYiping Sun, Ziyao Kang, Wei Zeng +2cs.AI2026-08-09
#28Business Arena: Benchmarking LLM Agents in a Realistic MarketplaceYijun Pan, Yukun Lian, Kunyu Shi +5cs.AI2026-08-09
#29MedCalc-R1: Knowledge-Guided Reward Framework for Medical Mathematical ReasoningHaotian Wang, Lian Yan, Xingzhi Yao +4cs.AI2026-08-09
#30UniMoMo: Expert Merging-Based MoE Acceleration for Large Recommendation ModelsLei Xin, Bin Gu, Peize Li +9cs.AI2026-08-09
#31A QUBO-Inspired Computational Framework for Airport Landside Bottleneck Diagnosis and Dynamic Dispatch OptimizationWuming Lei, Xiaobin Li, Mingyan Sun +3cs.AI2026-08-09
#32Can Open-Weight Models Compete on Financial Text Comprehension?Jan Spörercs.AI2026-08-09
#33Smart Compaction: Predicting Compaction Utility from Lakehouse Table MetadataJannic Cutura, Subash Prakashcs.AI2026-08-09
#34SkillReason: Reasoning-Enhanced Agent Skill Retrieval for Implicit User RequestsDonghong Jiang, Endian Lin, Luoping Cui +6cs.AI2026-08-09
#35The Scaffolding Matters More Than the Interface: A Controlled Comparison of MCP and CLI Tool Use Across Seven Agent Scaffoldings, Five Language Models, and One Software TaskMarc Alier Forment, María José Casañ Guerrero, Francisco José García-Peñalvo +1cs.AI2026-08-09
#36Branch2Skill: Efficient Skill Evolution Through Reasoning TreesYanwei Ren, Haotian Zhang, Likang Xiao +5cs.AI2026-08-09
#37A Structural Dynamics Graph World Model: Unified Modeling, Constrained Rollout, and Interpretable CalibrationWei Wang, Yaosen Chen, Han Yang +5cs.AI2026-08-09
#38EnergyBridge: Benchmarking Household Energy Management, User Participation, and Grid FlexibilityXudong Wu, Zeqing Wu, Jiarui Zhang +8cs.AI2026-08-09
#39PluginEval: A Diagnostic Benchmark for Fine-Grained Error Attribution in Function CallingDongjie Xu, Julius, Hanchi Dong +6cs.AI2026-08-09
#40AI Evaluation Should Measure Verification Cost, Not Correctness AloneViviana Crescitelli, Generoso Immediato, Fabio Persia +1cs.AI2026-08-09
#41FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language ModelsKaili Zheng, Kaiwen Wang, Xun Zhu +3cs.AI2026-08-09
#42Scale-to-Dialogue: Low-Burden Elicitation of Daily Premenstrual Symptom Ratings with Small Language ModelsYifan Wangcs.AI2026-08-09
#43SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic VerificationWenyao Cui, Huaping Zhang, Yongyi Huang +6cs.AI2026-08-09
#44Deferred Audio Pruning with Local Audio-Visual Dynamics for Omni-LLMsKyeongyoon Lee, Hongyeob Kim, Youngeun Kim +1cs.AI2026-08-09
#45Improving Generalization Robustness of Multimodal RLVRPengfei Zhou, Zhiwei Tang, Xiaopeng Peng +11cs.AI2026-08-09
#46Three Generations of Healthcare IT: From the Digital Record to the Computable Care ProcessAlexander Apartsin, Yehudit Apersteincs.AI2026-08-09
#47Automated Generation of Complexity-Validated Decision Scenarios Using Large Language ModelsAbdalla Doleh, Toni Somers, Ratna Babu Chinnamcs.AI2026-08-09
#48PROSLEX: A Novel Dataset for Expert-Annotated Legal Statute Prediction for Indian JudiciarySubinay Adhikary, Upal Bhattacharya, Vivek Kumar Singh +6cs.AI2026-08-09
#49Findings of the First Teaching Monster Challenge: A Benchmark of Pedagogical Content Knowledge in AI AgentsYi-Cheng Lin, Yu-Kai Guo, Szu-Chi Chen +15cs.AI2026-08-09
#50A Comprehensive Survey of Wireless Foundation Models for AI-Native 6G NetworksNaveed Khan, Besan Al Sbeihi, Maryam Alshehhi +1cs.AI2026-08-09
#51Theory-Guided Deception Detection: A RAG-Based Artificial Intelligence ExplorationDavid M. Markowitz, Timothy R. Levinecs.AI2026-08-09
#52AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research GroupsJack Stark, Srinath Saikrishnan, Vikram Seenivasan +3cs.AI2026-08-09
#53Full-bandwidth transformerXi Wang, Ziyang Cai, Zheng Zhan +5cs.AI2026-08-09
#54LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning RoutingJuncheng Dong, Ding Tong, Ishan Gupta +1cs.AI2026-08-09
#55From Manuals to Maintenance: Fine-Tuning MedGemma for Multi-Modal Imaging System Support in Low-Resource SettingsBernes Lorier Atabonfack, Zion Kongbi Nfo, Ahmed Tahiru Issah +9cs.AI2026-08-09
#56Decoding Phenotypes: A Framework for Fusing Genomic Language Models and NeuroimagingTianli Tao, Ziyang Wang, Emma Robinson +2cs.AI2026-08-09
#57Integrated Multimodal AI System for Retrieval-Augmented Reasoning, Object Sensing, and Damage AnalysisKalelo Dukuray, Israel Pina, Evan Perez +2cs.AI2026-08-09
#58Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt InjectionRahul Deivasigamani, Sayeda Faatin Alvi, Derqui Andrea +2cs.AI2026-08-09
#59Synchronized Logit Steering: Real-world SteganographyAndrew Rufail, Aadi Dash, Onir Narahari +5cs.AI2026-08-09
#60Depth-Aware Implicit Neural Representation Priors for 3D Gravity InversionLeón Suarez-Rodriguez, Paul Goyes-Peñafiel, Javier Torres-Quintero +1cs.AI2026-08-09
#61Reading is not Reasoning: Bridging the Agentic Policy Gap in Vision-Text CompressionCheng Fan, Junyi Zhou, Tingzhang Luo +5cs.AI2026-08-09
#62SeqFeed: Improving Agentic RTL Code Generation with Sequential Behavior FeedbackYuxin Du, Juxin Niu, Tao Hu +3cs.AR2026-08-09
#63Eco-SoC: A Sustainable VLSI Architecture for Energy-Proportional Artificial IntelligenceJatin Chopracs.AR2026-08-09
#64Safety Cost of Steering Vectors Is Separable and ReducibleYuxiao Li, Gjergji Kasnecics.CL2026-08-09
#65Hidden Language Consistency Phenomena in Reasoning LLMsMuhammad Ali Shafique, Kelly Marchisiocs.CL2026-08-09
#66Calling the Bluff: Detecting Ever-Shifting Harmful Chat Dialogue via Ordered Reasoning Chain RegularizationHaojie Yu, Ziyou Jiang, Junjie Wang +4cs.CL2026-08-09
#67Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database ConstructionZhuowen Liang, Zhengxuan Zhang, Jiayang Wang +2cs.CL2026-08-09
#68VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool UseJuan S. Santillanacs.CL2026-08-09
#69From Speech to Interaction: Analyzing Multimodal Systems in Cocktail-Party ScenariosThai-Binh Nguyen, Zhaolin Li, Jan Niehues +1cs.CL2026-08-09
#70OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use TrajectoriesChanghao Xiang, Shilin Zhang, Zheng Ma +8cs.CL2026-08-09
#71Mitigating Gender Bias in English to Romanian Machine TranslationIoana Grigore, Sergiu Nisioics.CL2026-08-09
#72North Africa's Missing Framework: NLP-Driven Mental Healthcare in Algeria and Implications for Low-resource SettingsMeriem Laifa, Abdallah Bengueddoudjcs.CL2026-08-09
#73Position Encoding in Transformers: From Absolute and Relative Methods to Rotary Position Embeddings and Long-Context ScalingJiguo Lics.CL2026-08-09
#74Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning ApproachTong Bao, Yi Zhao, Heng Zhang +1cs.CL2026-08-09
#75The Evolution of Mixture-of-Experts Architectures in Large Language Models: Routing, Topology, Load Balancing, and Expert ParallelismJiguo Lics.CL2026-08-09
#76LibraSpec: Dynamic Diffusion-Based Speculative Decoding via Marginal-Gain-Driven OptimizationZexun Lin, Yuan Feng, Junlin Lv +2cs.CL2026-08-09
#77Domain Agnostic Text Redaction from Natural Language Rules using Instruction TuningAravindhan Arunagiri, Ayaan Khan, Udayaadithya Avadhanam +1cs.CL2026-08-09
#78Can We Optimize the Performance-Carbon Emission Break-Even Point?: The Quest for Greener LLMsSourav Das, Tanmay Joshi, Kripabandhu Ghoshcs.CL2026-08-09
#79Multilingual Emotion Neurons in Large Audio-Language ModelsXiutian Zhao, Philipp Koehn, Björn Schuller +1cs.CL2026-08-09
#80OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI AgentsAndrea Caciolai, Pere-Lluís Huguet Cabot, Chierh Cheng +11cs.CL2026-08-09
#81Unsure but Certain: Uncovering the Representation-Confidence Gap in Diffusion Language ModelsSaurabh Yadav, Badri Narayana Patro, Vijay Srinivas Agneeswarancs.CL2026-08-09
#82Evidence-Calibrated Runtime Reconstruction for Agent Skills Across Heterogeneous Coding AgentsXueping Gaocs.CL2026-08-09
#83Instability of LLM Pre-Pretraining: It Doesn't Always Help. An Investigation on Multiple LanguagesSofiia Riazhskykh, Nam Luu, Ondřej Bojarcs.CL2026-08-09
#84IDRAAK: From Multi-Agent NLP to Few-Shot Prompting for Semantic Drift Detection in Technical RequirementsShiva Ahircs.CL2026-08-09
#85Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and RerankersYu Wang, Shengyao Zhuang, Xueguang Ma +4cs.CL2026-08-09
#86Deployable Per-Instance Multi-Layer Activation Steering for Large Language ModelsMuhammad Faishal Adly Nelwan, Alfan Farizki Wicaksonocs.CL2026-08-09
#87Explicit Boundary Markers for Subword VocabulariesSander Land, Clara Meistercs.CL2026-08-09
#88Conversation as Measurement in Clinical Encounters: Observable Phase Structure, Partially Observable Patient StateLily Chen, Ted Mau, Michael Gensheimer +3cs.CL2026-08-09
#89Position Bias in Ordinal Classification: A Systematic EvaluationYu Wang, Jeffrey Zhou, Menglin Liu +1cs.CL2026-08-09
#90Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts ServingMatteo Grellacs.CL2026-08-09
#91Investigating Multimodal Informativity under Different Partner Visibility Conditions in Video-Mediated DialogueEsam Ghaleb, Hugh Mee Wong, Kristina Kobrockcs.CL2026-08-09
#92The Deontic Gap: Large Language Models and the Modal Language of ObligationDaniel Hart, Sarah Allred, Joseph Abbas +1cs.CL2026-08-09
#93Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI AccessLier Jin, Lan Hu, Binqi Shen +2cs.CL2026-08-09
#94SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent SkillsXinze Chen, Chi Zhang, Ping Ji +1cs.CR2026-08-09
#95Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned ReflectionSihan Hou, Xinmeng Hou, Zhijun Zhang +5cs.CR2026-08-09
#96DoRF++: Spherical Representation Learning over Doppler Radiance Fields for Robust Wi-Fi SensingNavid Hasanzadeh, Shahrokh Valaeecs.CV2026-08-09
#97Anatomically Consistent Cross-Contrast Super-Resolution of Anisotropic Brain T2w MRIMengqi Shen, Haicheng Wang, Meghna Trivedi +4cs.CV2026-08-09
#98Agentic AI-powered flexible fiber-bundle endoscopy for high-resolution NIR-II fluorescence imaging in vivoYanzhao Shi, Yuanhua Liu, Sixin Xu +10cs.CV2026-08-09
#99Learning Deep Modality-Shared Self-Expressiveness for Image Clustering with Textual InformationXianghan Meng, Wei He, Zhiyuan Huang +1cs.CV2026-08-09
#100FreCast: Refining Radar Echo Intensity via Phase-Preserving Amplitude Residual Diffusion for Precipitation NowcastingHeping Fang, Zihuai Yin, Kaicheng Mao +2cs.CV2026-08-09
#101InstructionCrafter: Generating Consistent and High-Fidelity Visual InstructionsShun Okamoto, Satoshi Iizuka, Kazuhiro Fukuics.CV2026-08-09
#102RayLift: Lifting Complementary Ray-Wise Evidence with 3D Geometry Priors for Semantic Scene CompletionMeng Wang, Hongxia Yu, Wenzhe He +4cs.CV2026-08-09
#103RenderMatte: Exact-Alpha Rendering and Group-Relative Alignment for Image MattingZecheng Ren, Yafei Hu, Jianing Zhao +3cs.CV2026-08-09
#104Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report GenerationQiang Hu, Yuxuan Luo, Yingjie Guo +4cs.CV2026-08-09
#105Towards Adaptive Super-Resolution and Quality Assessment via Test-Time AdaptationAjeet Kumar Vermacs.CV2026-08-09
#106eBIRD: Event-based Intensity Image Reconstruction Using Controllable Diffusion ModelsIgnacio Bugueno-Cordova, Fabian Valderrama, Rodrigo Verschaecs.CV2026-08-09
#107A Combined Feature-Based Framework for Disguise and Spoofing Detection in Face Recognition SystemsSangiya Pararajasinghamcs.CV2026-08-09
#108ERF-GS: Reconstructing Fast Motion from Disjoint Event-RGB ViewpointsXiaoyang Bai, Zhenyang Li, Weiwei Xu +2cs.CV2026-08-09
#109Rethinking Attention Locality in Spiking TransformersZeqi Zheng, Zizheng Zhu, Yuping Yan +3cs.CV2026-08-09
#110MotionCraft: Latent World Modeling with Sparse Attention for Visual UpscalingRong Fu, Chunlei Meng, Yangchen Zeng +9cs.CV2026-08-09
#111SC-Diff: Semantically Calibrated Diffusion for Visible-to-Infrared Image TranslationJunyin Zhang, Siyu Huang, Jianxiong Ye +4cs.CV2026-08-09
#112On-Device Multi-Species Malaria Detection with Uncertainty-Calibrated Slide-Level AggregationIdaya Seidu, Ahmed Tahiru Issah, Charles B. Delahunt +1cs.CV2026-08-09
#113CDGC-Net: 3D Medical Image Segmentation with Cooperative Dual-Scale Self-Attention and Grouped Channel ModelingZheyang Jing, Qin Lu, Jianwang Li +3cs.CV2026-08-09
#114Where Is the Bee? Detecting Tiny Pollinators with a Single Collaborative-Head TransformerJunsu Kim, Seungryul Baekcs.CV2026-08-09
#115EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event StreamsZixuan Chen, Jiakai Zhang, Junhao Dong +4cs.CV2026-08-09
#116RobustDefect-LLM: Explainable and Robustness-Aware Industrial Surface Defect Classification with Decision Support and AI-Assisted ReportingNazlıcan Düşünmez, Halûk Gümüşkayacs.CV2026-08-09
#117Goal-oriented Navigation Instruction Generation with Tour Video PriorsFangdi Li, Juncheng Liao, Changxu Cheng +4cs.CV2026-08-09
#118Population-Scalable Multi-Agent World ModelingRenjie Zhao, Yuxiang Wu, Mingyu Zhang +9cs.CV2026-08-09
#119REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question AnsweringCaijun Yan, Yang Zhou, Meixing Shi +4cs.CV2026-08-09
#120VADER: Adaptive Debiasing for Hallucination Mitigation in Video Large Language ModelsDong Xing, Jiaxin Chen, Hang Yang +3cs.CV2026-08-09
#121VLZip: Unified Visual and Textual Compression for Interleaved Long-Context ModelingYuqi Zhang, Cheng Chen, Yuyu Guo +6cs.CV2026-08-09
#122Agentic Visual Reasoning in Whole-Slide Pathology Images via Active PerceptionJingyun Chen, Fengchun Liu, Linghan Cai +5cs.CV2026-08-09
#123JSGS: JPEG State-Guided Supervision for 3D Gaussian Splatting from Mixed-Quality ViewsJinhua Cui, Anhong Wang, Kai Hu +5cs.CV2026-08-09
#124Degradation-Guided Underwater Image Restoration with Task-Oriented Latent ControlXu Zhang, Xuhui Cao, Kangzhe Yuan +5cs.CV2026-08-09
#125FiRe: Fixed-Noise Refinement for Visual Counterfactual ExplanationsYan Zeng, Changlu Guo, Oskar Kristoffersen +3cs.CV2026-08-09
#126UniSpace: Unified Visual Representation and Scalable Multimodal ModelingJinbo Yan, Limeng Qiao, Jie Qin +3cs.CV2026-08-09
#127Semi-Dense Matching Uncertainty Is Not Just Local ConfidenceKhoa Hoang, Hoang-Tuan Nguyen, Huong Ninh +2cs.CV2026-08-09
#128CUPA-T2*: Covariance-Aware Uncertainty Propagation and Alignment for T2* Mapping in Accelerated MRIGideon N. L. Rouwendaal, Natascha Niessen, Hannah Eichhorn +3cs.CV2026-08-09
#129OccAnyScene: Towards Unified Indoor-Outdoor 3D Occupancy PredictionJunjie Liu, Wanshui Gan, Zitong Dai +6cs.CV2026-08-09
#130SRE-FER: Regional residual evidence learning for mitigating local evidence dilution in fine-grained facial expression recognitionJiaye Song, Ruochen Zhang, Yuliang Wang +1cs.CV2026-08-09
#131Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report GenerationJonathan Suprijadi, Raphael Stock, Moritz Langenberg +10cs.CV2026-08-09
#132High-Quality Exposure Correction with Diffusion-Based Image Generation PriorsZiwen Li, Meng Cao, Jinpu Zhang +4cs.CV2026-08-09
#133TomaMMU: A Comprehensive Multimodal Understanding Benchmark for Tomato Leaf DiseasesGia-Han Truong, Khang Nguyen Quoc, Luyl-Da Quachcs.CV2026-08-09
#134AnchorFold: A Focus-Then-Fold Framework via Recursive Attention Propagation for Efficient Multi-Vector Visual Document RetrievalHaoyu Zuo, Yibo Yan, Xin Zou +4cs.CV2026-08-09
#135IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer AttackYi Pan, Jun-Jie Huang, Tianrui Liu +3cs.CV2026-08-09
#136Parcel2Progression: An Anatomy-aware Longitudinal Framework for Alzheimer's Disease DiagnosisMadhumitha Venkatesh, Shanawaj S Madarkar, Konda Reddy Mopurics.CV2026-08-09
#137UPolarSQ: Polar Representation Learning for Optic Disc and Peripapillary Atrophy Segmentation and Quantification in Fundus PhotographsMengxian He, Yunyun sun, Ziyue Gao +3cs.CV2026-08-09
#138LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic SegmentationJinhong Zhu, Weiqi Yan, Shengchuan Zhang +1cs.CV2026-08-09
#139AdapterMoE: A Two-Stage Hard-Routing Mixture-of-Experts Architecture for Multi-Crop Disease Recognition with Calibrated Rejection and Incremental LearningPin-Hsun Huang, Shaou-Gang Miaoucs.CV2026-08-09
#140360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied AgentsKenta Watanabe, Atsuyuki Miyai, Mizuki Takenawa +2cs.CV2026-08-09
#141MRI super-resolution in ten sampling steps using a diffusion bridge modelMojtaba Safari, Hang Yu, Zach Eidex +10cs.CV2026-08-09
#142LogiShot: Logically Coherent Cross-Shot Video GenerationShuai Guo, Yuhang Yang, Zeyu Zhang +4cs.CV2026-08-09
#143Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature CodingDonghui Feng, Fengxi Zhang, Changsheng Gao +6cs.CV2026-08-09
#144SLAP: Selective Local Vision-Language Alignment for Fish Re-Identification via Partial Optimal TransportCigdem Beyan, Tonje Knutsen Sordalen, Kim Tallaksen Halvorsencs.CV2026-08-09
#145Toward Mask Annotation-Free Surgical Instrument Segmentation from Endoscopic Images Using Text-Prompted Segment Anything Model 3 (SAM3)Nakul Poudel, Richard Simon, Cristian A. Lintecs.CV2026-08-09
#146Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking PipelineDipit Saha, Shah Mohammad Abdul Mannan, Mohammad Raihan Rashid +2cs.CV2026-08-09
#147Sparse Attention to Emotion: Efficient Facial Emotion Recognition via Token ReductionAya Manel Zitouni, Aicha Zenakhri, Karim Haroun +1cs.CV2026-08-09
#148AeroReformer2: Spoken-Query Referring Segmentation for Aerial ImagesRui Li, Chenxi Duan, Haoyang Yangcs.CV2026-08-09
#149City Sentinel: A Unified AI-Based Smart Surveillance Framework for Real-Time Multi-Threat Detection Using Deep LearningHanan Syed Shabir, Noor Fatima, Safia Baloch +1cs.CV2026-08-09
#150From Recovery to Drop-off: How Action Post-training Reduces a VLM's Late-Layer Depth DecodabilityAlexander Hackett, Arnaud Denis-Remillard, Axel Cassoucs.CV2026-08-09
#151ToolVision: Learning When and How to Use Visual Tools with Capability-Aligned SupervisionDelin Mao, Chenghao Sun, Jingwei Song +2cs.CV2026-08-09
#152From Noise to Meaning: Meaningful Secret Sharing with Tamper Detection for Facial RecognitionAjnas Muhammed, Iurii Medvedev, Nuno Gonçalvescs.CV2026-08-09
#153Zero-shot 2D Grounding with Novel Affordance TypesHaomeng Zhang, Raymond A. Yehcs.CV2026-08-09
#154Can Webcam Gaze Constrain Mesa-Objectives in Driving Models? An Instrument Precision AnalysisLennox Anderson, Ahmed Boutar, Jonah Mulcrone +1cs.CV2026-08-09
#155EndoMD-SLAM: Endoscopic Gaussian Splatting SLAM under Optical Degradation with Memory and Static-Transient DecompositionNuo Chen, Kangqi Ni, Lulin Liu +5cs.CV2026-08-09
#156Topology-Aware Global-Local Mamba Networks for Palm Vein BiometricsZhengxi Wu, Felix Marattukalam, Waleed H. Abdullacs.CV2026-08-09
#157Damage Classification for 3D Point Cloud Data via 3D Data Analysis and Vision Foundation Model-based 2D ProjectionsEvan Perez, Kalelo Dukuray, Erika Ardiles-Cruz +1cs.CV2026-08-09
#158RMR-P: Road Metadata-Aware Restoration for Pavement InspectionAmir Ghorbani, Amirali K. Gostar, WeiQin Chuah +4cs.CV2026-08-09
#159Fourier Self-Supervision for Fine-Grained Generalized Category DiscoverySarah Rastegar, Mina Ghadimi Atigh, Pascal Mettes +2cs.CV2026-08-09
#160Abstracted Away: Resisting Alienation and Ungrounded Abstraction in AI Research CommunitiesVyoma Raman, Isabel O. Gallegos, Neha Srivathsacs.CY2026-08-09
#161Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit SimulationLei Shu, Ying Jiang, Kui Wu +3cs.GR2026-08-09
#162Does a Toehold Make a Bidder Bolder? Preemption and Multiplicity in Multi-Round Takeover AuctionsZain Naboulsics.GT2026-08-09
#163Kernel Methods for Refined Prophet InequalitiesPatrick Loiseau, Mathieu Molina, Vianney Perchet +2cs.GT2026-08-09
#164Human-Guided Causal Knowledge Injection for Virtual CellsPengcheng Wang, Changjian Chen, Zhuo Tang +4cs.HC2026-08-09
#165Private Etymology: Designing Relational Reuse of Shared Symbols in Long-Term Human-AI InteractionMiki Uenocs.HC2026-08-09
#166A Dynamic-Semantics Framework for Grounding Human Referring Expressions in Visual Perceptual DataJoseph Binghamcs.HC2026-08-09
#167Inductive Graph Layout with Implicit Neural FieldsBerfin Inal, Daniel Probstcs.HC2026-08-09
#168Epistemic Transfer in AI-Assisted Verification: A Framework and Evaluation ProtocolChristoph Trattnercs.HC2026-08-09
#169What Would Fix This RAG Failure? Auditing Counterfactual Response with Paired Evidence InterventionsWenzhang Ducs.IR2026-08-09
#170Exact Rank and Convex Calibration Dimension Lower Bounds for the Multi-Label F1 LossMingyuan Zhangcs.LG2026-08-09
#171Rethinking Learning-Based Influence Maximization: Simple Neural Surrogates and Native Discrete SearchYiqiao Liao, Parinaz Naghizadehcs.LG2026-08-09
#172Constrained Learning with Universally Learnable Concept ClassesHerlock SeyedAbolfazl Rahimi, Spyridon Pougkakiotis, Dionysis Kalogeriascs.LG2026-08-09
#173Optimal Learning Under Tsybakov NoiseSteve Hanneke, Hongao Wang, Mingyue Xucs.LG2026-08-09
#174FSTC-Encoder: Feature--Spatial--Temporal Correlation Learning for Generalizable RF SensingJing Wang, Zhu Wang, Changlong Cheng +2cs.LG2026-08-09
#175MGMCL: Multi-Granularity Manifold Contrastive Learning With Neural ODEs for Cross-Subject EEG Emotion RecognitionXiang Xiecs.LG2026-08-09
#176No Unique Minimizer, No Problem: On the Consistency of Robust Neural ClassifiersSubhabrata Majumdar, Anand Deo, Partha Pratim Saha +1cs.LG2026-08-09
#177Out-of-Distribution Federated Distillation with Domain-Aware ProxyJiahao Xiao, Jiangming Liucs.LG2026-08-09
#178Task-to-Model Optimization for Enterprise LLM Coding Assistants: A Data-Driven Framework for Cost-Optimal RoutingSrinivasan Manoharan, Junhua Zhao, Fangbo Tu +6cs.LG2026-08-09
#179Can Graph Learning Learn Circuits?Chester Tan, Moritz Lampert, Courtney Maynard +3cs.LG2026-08-09
#180When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMsYu Ma, Hongli Shi, Jing Li +2cs.LG2026-08-09
#181Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural NetworksOmer Yom-Tov, Avigdor Galcs.LG2026-08-09
#182Robust Reputation-Driven Crowdsourced Federated LearningMouhamed Amine Bouchiha, Gregory Blanccs.LG2026-08-09
#183When Can Fraud Operations Authorize Automation? A Decision-Support Framework for Fresh Audit Evidence and Review WorkloadJie Dengcs.LG2026-08-09
#184Multi-Agent Reinforcement Learning via Agent-Specific PreferenceNi Mu, Yao Luan, Yiqin Yang +1cs.LG2026-08-09
#185Domain-Aware Pruning: Sparsity and Domain Generalization via Regularized Probabilistic MaskingParham Sazdar, Mostafa Tavassolipour, Reshad Hosseinics.LG2026-08-09
#186Trajectory Design and Budgeted Querying for Digital Twin CalibrationVladyslava Spitkovska, Dmytro Kuzmenkocs.LG2026-08-09
#187Exact Rank-Space KL Projection for Shared-Marginal Low-Rank Factors: Application to Doubly Stochastic ClusteringEnliang Hucs.LG2026-08-09
#188Path-dependent Discrete Amortized InferenceTiago da Silva, Esmeralda S. Whitammer, Salem Lahloucs.LG2026-08-09
#189Multi-Relational Knowledge Graph Enhanced Embedding for Trajectory-User LinkingZhifeng Chu, Bin Wangcs.LG2026-08-09
#190LegoLM: Structured Weight Sharing for Large Language ModelsJoseph Binghamcs.LG2026-08-09
#191Catastrophic Forgetting in Continual Reinforcement LearningEmma Grahamcs.LG2026-08-09
#192Backward Compatibility in Tree-Based Explanations and Enhanced CART AlgorithmHirofumi Suzukics.LG2026-08-09
#193Efficient Test-Time Scaling for LLM-based Time Series ForecastingXuan-May Le, Minh-Tuan Tran, Ling Luo +3cs.LG2026-08-09
#194RippleKV: Cross-Layer KV Cache Allocation via Perturbation PropagationDongjie Xu, Kai Qian, Julius +6cs.LG2026-08-09
#195Loss-Resilient Wireless Video Token Communication over Block Fading ChannelsBingyan Xie, Yongjeong Oh, Zihan Chen +3cs.LG2026-08-09
#196Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection PressureVíctor Gallegocs.LG2026-08-09
#197PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-DistillationYangyang Feng, Zhuoyan Feng, Junlan Chencs.LG2026-08-09
#198Measuring and Reducing WebGPU Dispatch Overhead for LLM InferenceJędrzej Maczancs.LG2026-08-09
#199Memory-Efficient Activation Checkpointing with Sliding Window and Hirschberg's Algorithm for 0/1 Knapsack Solving in PyTorchJędrzej Maczancs.LG2026-08-09
#200Learning from Consensus and Disagreement: Unsupervised On-Policy Self-Distillation with Minority-Trajectory ContrastJiaxin Guo, Yanwei Yue, Xuanbo Fan +2cs.LG2026-08-09
#201Quantum-Classical Physics-Informed Kolmogorov-Arnold Networks for Solving Fuzzy Differential EquationsXiang Rao, Yuxuan Shencs.LG2026-08-09
#202Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous VehiclesPedram MohajerAnsari, Amir Salarpour, Mert D. Pesécs.LG2026-08-09
#203Hybrid Neural-Classical Correction for Frozen Time Series Foundation Models: A Comprehensive Ablation Study on High-Frequency Stock PredictionKasun Dewage, Suranadi De Silva, Shankhadeep Mondalcs.LG2026-08-09
#204The Cost of Adaptivity: Matching Lower Bounds Across Learning ProblemsIbne Farabi Shihab, Adria Binte Habibcs.LG2026-08-09
#205Beyond Routing: Decoupling Expert Dispatch and Aggregation in Sparse Mixture-of-ExpertsZongfei Lics.LG2026-08-09
#206Agentic Anomaly Detection with ORCA-Style Dynamic Inductive Bias Adaptation in Multimodal Wearable Time Series DataAnushka Roy, Jyotirmoy Singh, Shreea Bose +1cs.LG2026-08-09
#207Approximation Rates for Metaplectic Neural NetworksAhmed Abdeljawad, Marcello Carioni, Elena Corderocs.LG2026-08-09
#208DistillCache: KL-Guided Adaptive KV-Cache Eviction for Memory-Efficient LLM InferenceAsaad Althoubics.LG2026-08-09
#209Federated Attention Autoencoders with a Stochastic Aggregation Scheme for Anomaly DetectionMihailo Ilić, Miloš Savić, Vladimir Kurbalija +3cs.LG2026-08-09
#210A Domain-Structured Ensemble Framework for Perioperative Outcome Prediction Using Electronic Health Record DataShikhar Shukla, Cristina Barboics.LG2026-08-09
#211Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific MethodsXuefei Julie Wang, Hao Cui, Michael P. Brenner +1cs.LG2026-08-09
#212Gradient Under Microscope: Benchmarking Resource Utilization of Memory-Efficient Gradient Computation MethodsSarthak Mahapatra, Zihan Zhou, Khatoon Khedri +2cs.LG2026-08-09
#213Math-Vision Diagrams: A Comprehensive Benchmark for Evaluating LLM Mathematical Diagram Generation CapabilitiesHarish Kashyap, Kiran Byadarhaly, Sriram Chakaravarthy +2cs.LG2026-08-09
#214SuperNeuroMAT: An Efficient Matrix-based Simulator for Spiking Neural NetworksPrasanna Date, Kevin Zhu, Shruti Kulkarni +12cs.NE2026-08-09
#215A New Approach to Characterising Optimisation Problems Using Programmatic Representation and Complexity MeasuresMarcus Gallagher, Katherine M. Malancs.NE2026-08-09
#216Curriculum Generation under Structured Parametric Environments for Robust Navigation PoliciesPrishita Raycs.RO2026-08-09
#217RAG-Based Auto-Configuration for Industrial Fieldbus DevicesAadil Gani Ganie, Saad Ezzini, Naveed Farooz Marazics.RO2026-08-09
#218Protection Levels for Vision-Based Pose EstimationOlivia Beyer Bruvik, Romeo Valentin, Marc R. Schlichting +2cs.RO2026-08-09
#219SG-WAM: Text-Grounded and Spatial-aware Semantic Guidance for World-Action ModelsJunjie He, Junfeng Li, Zhide Zhong +9cs.RO2026-08-09
#220From Operational Design Domain to Action: A Systematic Behavioral Taxonomy for Autonomous DrivingChaitanya Shinde, Hadi Hajieghrary, Miguel Hurtadocs.RO2026-08-09
#221CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous LatentsYuqian Zhang, Yao Shi, Kexin Huang +7cs.SD2026-08-09
#222From Product Search to Preference Articulation: The Economics of Agentic CommerceLingxiu Dong, Kaiwen Luo, Fasheng Xuecon.TH2026-08-09
#223Transfer Learning-Enabled Distortion Compensation for Amplitude-Phase-Time Block Modulation-Based Nonlinear Single-Carrier Wireless CommunicationsGuoxing Duan, Min Fan, Cheng Yi +4eess.SP2026-08-09
#224End-to-End Neural Decomposition with Koopman Operators for Time-Series ForecastingDe-Yan Lu, Xugang Lu, Yu Tsao +1eess.SP2026-08-09
#225A Low-Cost IoT Device for Environmental Monitoring and Embedded Solar Forecasting with On-Device Incremental LearningErick Michel Lara Pinal, Abhinav Das, Stephan Schlütereess.SP2026-08-09
#226ML-Based Hierarchical Prediction for Practical Energy Scheduling in Dynamic NTN-WPT SystemsZhanyu Ju, Wenchi Chengeess.SY2026-08-09
#227ADEx-FNO: A Unified Ambient-Domain Framework for Fourier Neural Operators on Varying GeometriesRoberto Nuca, Giovanni Testa, Luca Galimberti +1math.NA2026-08-09
#228Halpern Iteration Achieves $\tilde{\mathcal{O}}(ε^{-1/p})$ $p$th-Order Oracle Complexity for Monotone Variational InequalitiesLesi Chen, Xinliang Zhang, Hengyu Wang +3math.OC2026-08-09
#229Deep Learning-Based Statistical Downscaling of Sea Surface Temperature Using a Residual Corrective Neural NetworkOnkar Jadhav, Tim French, Ivica Janekovic +2physics.ao-ph2026-08-09
#230Do AI Forecast Ensembles Sample the Correct Conditional Distribution?Lucas J. Howard, Elizabeth A. Barnesphysics.ao-ph2026-08-09
#231Toward CT-Equivalent Image Quality in Low-Dose Radiotherapy Planning: Conditional Diffusion-Based CBCT-to-CT Synthesis and the Impact of CBCT Input RepresentationAlzahra Altalib, Chunhui Li, Christopher Hamill Taylor +2physics.med-ph2026-08-09
#232Towards an LLM-based method for quantifying the sexual content in song lyricsIgnacio M. Sticcophysics.soc-ph2026-08-09
#233Population-Level Generative Modeling for Ranking DataZhaoyang Shistat.ME2026-08-09
#234ARC: Augmented-Rank Conformalization for Changepoint Localization --- Finite-Sample Validity and Distribution-Robust EfficiencyChenchen Peng, Mixia Wu, Qijing Yan +2stat.ML2026-08-09
#235LazyHMC: Hamiltonian Monte Carlo Simulation for Lazy, Infinite Dimensional Probabilistic ProgramsMaria-Nicoleta Crăciun, C. -H. Luke Ong, Tom Schrijvers +1stat.ML2026-08-09
#236Multi-kernel spectral clustering: Entrywise eigenvector perturbation bounds and exact recoveryZeqin Lin, Guangming Pan, Zhixiang Zhang +1stat.ML2026-08-09
#237A Distribution Mapping Approach to Counterfactually Fair Reinforcement LearningJianhan Zhang, Jitao Wang, John D. Piette +3stat.ML2026-08-09
#238A Mean-Field Framework for Inference-Time Distributional Control of Diffusion ModelsSamuel Howard, Nikolas Nüskenstat.ML2026-08-09
#239Physics-Informed Learning for Robust Acoustic Localization with Calibrated UncertaintyJennifer N. Kampe, Changwoo J. Lee, Xin Shen +5stat.ML2026-08-09

latest · arXiv announcement batches follow US Eastern weekdays