| 1 | Learning Collective Dynamics with Differentiable Gaussian Representations | Jianxiang Ma, Mingfu Zhang, Xiaocui Yang +3 | cs.LG | 2026-09-23 |
| 2 | Complementary Roles of Activation and Parametric Memory in Few-Shot Learning | Miaohe Niu, Runsong Zhao, Xinyu Liu +5 | cs.CL | 2026-09-23 |
| 3 | Beyond Poetry: Can Large Language Models Generate Classical Arabic Maqamat? | AbdulRahman A. Morsy, Aya Zirikly | cs.CL | 2026-09-23 |
| #4 | Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification | Ilán Carretero, Pablo Meseguer, Rocío del Amor +1 | cs.CV | 2026-09-23 |
| #5 | From Alignment to Fusion in 3D Vision-Language | Xueqi Qiu, Xingyu Miao, Jingjing Deng +3 | cs.CV | 2026-09-23 |
| #6 | From Change Captions to Change Detection: Semantic-Appearance Agreement Framework for Remote Sensing Change Detection | Yuan Qian, Jie Ma | cs.CV | 2026-09-23 |
| #7 | Two Global Crops Suffice: Locating Semantic Emergence in DINO-Style Self-Supervised Learning | Basavaraj Sunagad, Artur Jesslen, Adam Kortylewski | cs.CV | 2026-09-23 |
| #8 | How Sensitive Are LLM Leaderboard Claims to Hidden Model Selection? | Chen Yang, Xianyang Zhang, Jun Chen | stat.ML | 2026-09-23 |
| #9 | Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs | Haitong Jiang, Chunlin Liu, Yile Wang +1 | cs.CL | 2026-09-23 |
| #10 | AstraLOD3: Zero-shot multimodal agentic reconstruction of LOD3 building models | Bryan G. Pantoja-Rosero | cs.CV | 2026-09-23 |
| #11 | Evaluating Open-Weight LLMs for Turkish Domain Documents Under Retrieval and Hardware Constraints | Imtiaz Ul Hassan, Öykü Akbulut, Onur Kaya +4 | cs.CL | 2026-09-23 |
| #12 | Controlled Attribute-Specific Summarization of Interrogative Dialogues | A Aditya Bhardwaj, Arjit Singh Arora, Md Shad Akhtar | cs.CL | 2026-09-23 |
| #13 | Risk-Controlled KV-Cache Eviction: From Memory Budgets to Risk Targets | Beomgu Kang, SoJin Yun, Hojoon Kim +1 | cs.CL | 2026-09-23 |
| #14 | Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding | Fan Zhang, Yankai Chen, Zhuohan Xie +11 | cs.CL | 2026-09-23 |
| #15 | RoadOcc Learns When to Persist, Transport, or Refresh Memory for Roadside Occupancy Prediction | Xiaokai Bai, Lei Yang, Songkai Wang +3 | cs.CV | 2026-09-23 |
| #16 | The Path Matters: Evaluating Small Language Models Beyond Answer Accuracy in KGQA | Eduin E. Hernandez, Sergio A. Diaz, Luis F. Garcia +2 | cs.CL | 2026-09-23 |
| #17 | InGuard: Towards Generalized Inner Guardrail for Safe Text-to-Image Generation | Zeyu Wang, Xiaodan Li, Zhiwen Li +2 | cs.CV | 2026-09-23 |
| #18 | Can Jev Judge Radiology Reports? Evaluating a System One Model for Clinical Factuality | Jiaju Huang, Hao Yang, Xinyu Ma +6 | cs.CL | 2026-09-23 |
| #19 | When Visual Quality Misleads: Intent Recognition under Rendered Avatar Distortions | Ning-Hsuan Chang, Kai-Siang Ma, Yu-Chih Chen | cs.MM | 2026-09-23 |
| #20 | M3D-Net: Hierarchical Coordination of Spatial Context, Feature Reuse, and Differential Attention for Mammography Classification | Zheng Yu, Xinhang Li, Jiabao Gao +2 | cs.CV | 2026-09-23 |
| #21 | Not What You Meant: Can LLMs Follow a Specified Negation Semantics? | Qiming Bao, Agnieszka Mensfelt, Michael J. Witbrock +1 | cs.AI | 2026-09-23 |
| #22 | DeltaS: Reading the Gated Linear Attention State for KV Cache Eviction in Streaming Video | Taeyoun Kwon, Seungjin Kim, Hyeonyu Kim +1 | cs.CV | 2026-09-23 |
| #23 | Beyond Balanced Accuracy: A Resolution and Parity-Controlled Benchmark for Vision-Language and Vision-Only Defect Assessment in UAV Power-Line Inspection | Linghao Zhang, Siyu Xiang, Junwei Kuang +1 | cs.CV | 2026-09-23 |
| #24 | AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task | Mo El-Haj, Saad Ezzini, Shadi Abudalfa +3 | cs.CL | 2026-09-23 |
| #25 | MORSE: Multi-Context Ordering via Reverse Scoring for Evidence-Preserving Compression | Ke Wan, Yifan Wang, Liheng Lai +1 | cs.CL | 2026-09-23 |
| #26 | Cross-Lingual Legal QA for Vietnamese Labour Law: Retrieval, Translation, and Verifier-Guided Correction | Nguyen Minh Chi, Mo El-Haj, Nguyen Ha Thanh +2 | cs.CL | 2026-09-23 |
| #27 | Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models | Ke Wan, Chen Chen | cs.CL | 2026-09-23 |
| #28 | Guides That Cause Actions: An Offline Study of Guide-Action Mutual Reinforcement in Multimodal Web Agents | Chengguang Gan, Yunhao Liang, QingHao Zhang +1 | cs.CL | 2026-09-23 |
| #29 | Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression | Mingxuan Wang, Fei Luo, Bo Wang +6 | cs.AI | 2026-09-23 |
| #30 | Multi-View Fusion for Encrypted C2 Detection: A Leakage-Controlled Measurement Study of Evaluation Pitfalls | Hoang-Huy Nguyen-Huu, Van-Tri Phan, Khuong Nguyen-An | cs.CR | 2026-09-23 |
| #31 | NGN: Learning Neural Network Size as a Differentiable Count | Lixing Li | cs.LG | 2026-09-23 |
| #32 | CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments | Yuxuan Li, Will Epperson, Wesley Deng +1 | cs.AI | 2026-09-23 |
| #33 | What Converges in the Platonic Representation Hypothesis? Structure over Geometry | Junwon You, Mihyun Jang, Sangwoo Mo +1 | cs.LG | 2026-09-23 |
| #34 | The Risk-Sensitive Schrödinger Bridge: Is Not a KL Projection | Hamidreza Behjoo | cs.IT | 2026-09-23 |
| #35 | A Scaling Study for fMRI Foundation Models | Wenhao Ye, Xuanye Pan, Junfeng Xia +3 | cs.LG | 2026-09-23 |
| #36 | Scaling of Capability and Efficiency at Inference Time in Large Reasoning Models | Moritz Laber, Zohair Shafi, Germans Savcisens +5 | cs.LG | 2026-09-22 |
| #37 | Does Graph Structure Earn Its Place in Microservice Root-Cause Analysis? A Controlled Study on RCAEval, and What the Benchmark Was Really Measuring | Imad Buljić | cs.SE | 2026-09-22 |
| #38 | Math Reasoning in LLMs is Organized by Approach, Not Topic | Sajad Goudarzi, Samaneh Zamanifard, Moloud Nasiri +1 | cs.AI | 2026-09-22 |
| #39 | ContraVis: Evidence-Grounded Visual Analytics for Contradiction Review in Legal Contracts | Luis Sante, Paula Lima, Mariana Rocha +1 | cs.HC | 2026-09-22 |
| #40 | When Learned Context Planning Fails to Beat Strong Retrieval: A Controlled Study of Planning, Routing, and Reranking for Long-Context QA | Yingrui Li, Han Chen | cs.CL | 2026-09-22 |
| #41 | COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference | Norah Alballa, Wenxuan Zhang, Salma Kharrat +4 | cs.CL | 2026-09-22 |
| #42 | SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue | Haobo Zheng, Tan Tang, Yan Chen +2 | cs.CL | 2026-09-22 |
| #43 | A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem | Laizhen Li, Xuan Wang, Peicheng Zhao +4 | cs.CR | 2026-09-22 |
| #44 | EquivSVA: A Formally Verified Dataset of Behavioral Assertions Across Equivalent RTL Implementations | FNU Aditi | cs.LG | 2026-09-22 |
| #45 | Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen | Om Nepal, Sushant Aryal, Oluseyi Olukola +1 | cs.SE | 2026-09-22 |
| #46 | Does AI Save Time on Product Design? A Randomized Controlled Experiment of AI Prompt-to-Design Workflows | Remy Stewart, Olabode Anise, Andrew Hogan +1 | cs.HC | 2026-09-22 |
| #47 | DIFTA-3D: Depth-Consistent Instance-Level Feature Transfer and Adaptation of DINOv3 for 3D Detection | Linman Wang, ZiFei Zhang, Chunran Zheng +2 | cs.CV | 2026-09-22 |
| #48 | A Spectral Theory of Grokking: Weight Decay induces Feature Learning | Lenz Pracher, Pascal de Jong, Oskar Lieshaus +2 | cs.LG | 2026-09-22 |
| #49 | The Delegation Blind Spot: Auditing Product Decisions from Agent Choices | Shivam Gupta | cs.AI | 2026-09-22 |
| #50 | A Data-Interventional Framework for Auditing Privacy and Fairness in Generative Medical Imaging | Mischa Dombrowski, Bernhard Kainz | cs.CV | 2026-09-22 |