| 1 | LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers | Minsoo Cheong, Sungjoo Yoo | cs.LG | 2026-11-03 |
| 2 | Universal Hardness From Masking Channels | Parikshit Gopalan, Manoj Prabhakaran, Pranay Tankala | cs.LG | 2026-11-03 |
| 3 | Fusing Earth observation embeddings and spaceborne terrain with meteorological forcing for flood peak depth prediction from high-water marks | Wen Zhou, Shaowen Wang, Upmanu Lall +2 | cs.LG | 2026-11-03 |
| #4 | Multi-Objective Generative Optimization via Expected Hypervolume Fine-Tuning | Juan Guevara, Riccardo De Santi, Andreas Krause +1 | cs.LG | 2026-11-03 |
| #5 | Diffusion Plug-in Priors for Self-Supervised Ultrasound Video Restoration | Chu Chen, Mingduo He, Yining Li +7 | cs.CV | 2026-11-03 |
| #6 | Empirical Bayes Flow Matching for Continuous Cryo-EM Heterogeneity | Daniel Aibinder, Azmi Haider, Dan Rosenbaum | cs.LG | 2026-11-03 |
| #7 | Basin2Vec: Learning Basin-Centric Embeddings for Scalable Hydrological Modeling | Muhammad Talha, Xiaofeng Liu, Yuan Yang +2 | cs.LG | 2026-11-03 |
| #8 | Asynchronous Robot Policies | Sombit Dey, Luc Van Gool, Danda Pani Paudel | cs.RO | 2026-11-03 |
| #9 | Distributed Linear Bandits for Freshness-Aware Preprocessing in MEC-Enabled Digital Twin Networks | Mariam Yahya, Setareh Maghsudi | cs.DC | 2026-11-03 |
| #10 | Do Agentic Policies Need to Look at Every Step? Geometric Abstraction for Reasoning and Action | Yihang Liu, Yiming Chen, Mingzhe Zheng | cs.RO | 2026-11-03 |
| #11 | Learning Where to Look: Observation Policy Optimization for Thinking with Images | Junfeng Wang, Jiawei Liu, Yongchao Xu +5 | cs.CV | 2026-11-03 |
| #12 | PROSE: Preservation-Constrained Selective Editing for Guilty Bias in Legal Judgment Prediction | Yimeng Wang, Zeyuan Tian, Xinyu Wang +5 | cs.CL | 2026-11-03 |
| #13 | Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling | Kling Team, Dong Chen, Jialu Chen +50 | cs.CV | 2026-11-03 |
| #14 | Attending to Memory Writes Reduces Seed Variability in Recurrent Length Generalization | Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung | cs.LG | 2026-11-03 |
| #15 | DLER: Dual-Logit Experience Replay for Online Continual Learning | Huiwei Lin, Shanshan Feng, Kong Aik Lee | cs.LG | 2026-11-03 |
| #16 | HTCE: Homeomorphism-inspired Topological Cross-Scene Experience Canonicalization and Reuse for Object Navigation | Xiaoran Xu, Yupeng Wu, Tianyu Xue +4 | cs.AI | 2026-11-03 |
| #17 | ReSI-Math: Exploring Recoverable Capability Frontiers for Efficient Reasoning Improvement | Yao Cui, Zhen Yang, Yuandong Wang +3 | cs.CL | 2026-11-03 |
| #18 | Kierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks | Andrew Semenov, Svyatoslav Dorofeev | cs.AI | 2026-11-03 |
| #19 | Non-Interfering Asymmetric AdamW Updates for Constrained Exploration of Equifinality in Hybrid Models | Ekaterina Gikalo, Zavud Baghirov, Christian Reimers +3 | cs.LG | 2026-11-03 |
| #20 | SPOD: Recovering Suppressed Temporal Evidence in Video-LLMs via Single-Pass Orthogonal Decomposition | Yangguang Lin, Quan Fang, Xiaoyan Liu +1 | cs.CV | 2026-11-03 |
| #21 | Cycle WAM: Coupling Action and Video through Cycle Consistency | Qinglin Yang, Jiepeng Wang, Yuxing Huang +5 | cs.CV | 2026-11-03 |
| #22 | One-shot Distributed Learning via Weighted Averaging with Server-side Information | Pavle Tepavčević, Dušan Jakovetić, Miloš Savić | stat.ML | 2026-11-03 |
| #23 | Feature-Based and Deep Learning Methods for Astronomical Light Curve Classification | V. Baymakanov, Kh. Khamitov, A. Raimova +7 | cs.LG | 2026-11-03 |
| #24 | Self-Privileged Fine-Tuning | Yangrong Hu, Xueyu Zhou, Yue Wu +1 | cs.LG | 2026-11-03 |
| #25 | Gradient-Guided Orientation Learning for Weakly Supervised Oriented Object Detection | Junyong Jang, Juheon Park, Minyoung Jeon +1 | cs.CV | 2026-11-03 |
| #26 | Sparse-View 3D Coronary Reconstruction from Vessel Segmentations Using a Diffusion Prior | Tianyuan Wang, Kenan Niu, Stefano Stramigioli | eess.IV | 2026-11-03 |
| #27 | Can Network Models of Science Do Without Pluralist Agents? | Jonas Hallgren, David Hyland, Mahault Albarracin | cs.MA | 2026-11-03 |
| #28 | BtsPruner: Role-Aware Visual Token Pruning for Large Vision-Language Models | Zihao Qi, Zhibo Zhang, Miaoxin Zhang +2 | cs.CV | 2026-11-03 |
| #29 | Spatial Memory for AR Glasses: Hierarchical Visual Acquisition and Source-Linked Recall | Tianxing Zhu, Dan Huang | cs.AI | 2026-11-03 |
| #30 | Hybrid Particle-Voxel Dynamics for Multimodal 3D World Simulation | Jimmy Wang, Yifan Chou, Kaifeng Zhang +5 | cs.RO | 2026-11-03 |
| #31 | CogniLife: Continuous Cognitive Distillation for Deployed Multi-Expert Agent Marketplaces | Xuwei Tan, Jingchun Huang, Ming Cai +12 | cs.AI | 2026-11-03 |
| #32 | TEMPO: Time Series Understanding via Discrete Tokenization | Riccardo Maggioni | cs.CL | 2026-11-03 |
| #33 | Large Language Model-Assisted Adaptive Heuristic Search for Agile Earth Observation Satellite Scheduling | He Wang, Yeye Liu, Ruijie Li +5 | cs.AI | 2026-11-03 |
| #34 | The Min-Max theory of language behavior | Hiram Ring | cs.CL | 2026-11-03 |
| #35 | Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs | Junhyeong Park, Wook Jung, Taeyoung Kim +2 | cs.AI | 2026-11-03 |
| #36 | Beyond Fine-Tuning: Evaluating Prompt Engineering and Prompt Tuning for Roman Urdu Hate Speech Detection | Toneema Zubair, Muhammad Junaid Asif, Faisal Kamiran +2 | cs.AI | 2026-11-03 |
| #37 | Patching the Protocol: A Taxonomy of Pre-Registration Repairs in LLM-Proposer Experiments | Peter Chen, Ni Zhang, Siyuan Zhang | cs.AI | 2026-11-03 |
| #38 | Anchor: Augmented Cross-Layer Recurrent State for Long-Context Retrieval in Test-Time Training | Vimal William, Yuanzhe Li, Danella Zhao +1 | cs.LG | 2026-11-03 |
| #39 | OSGR: Observation-Support Graph Reasoning for Earth Observation Question Answering | Dazhou Yu, Zerong Wang, Riyang Bao +3 | cs.AI | 2026-11-03 |
| #40 | GroundSeek-CXR: Retrospective Evaluation-Guided Active Observation Framework for Multi-Label Chest Radiography Diagnosis | Yihang Fu, Xinyu Liu, Qing Xu +2 | cs.CV | 2026-11-03 |
| #41 | P-SER: Physical Consistency-Constrained Scattering Expandable Representation for Class-Incremental HRRP Target Recognition | Fangyi Wang, Peng Zhao, Haipeng Wang | cs.CV | 2026-11-03 |
| #42 | AceAction-5M: Hierarchical Goals for Generalist Action Learning Across 3D Game Worlds | Kailing Li, Ruoxuan Zhang, Zheyuan Zhou +5 | cs.AI | 2026-11-03 |
| #43 | DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds? | Yang Chen, Bin Wen, Danyang Peng +3 | cs.AI | 2026-11-03 |
| #44 | Mamba3R: Fixed-Capacity Selective State Memory for Long-Sequence 3D Reconstruction | Zhenxiang Xiong, Tianchen Deng, Nailin Wang +3 | cs.CV | 2026-11-03 |
| #45 | When the Consumer Is an Agent: Execution-Grounded Service-Level Agreements | Michal Orzechowski, Renata G. Slota, Jacek Kitowski | cs.DC | 2026-11-03 |
| #46 | ReconDreamer#: Self-Evolving Closed-Loop Synergy of Reconstruction and Generation for Dynamic Driving Scenes | Songling Liu, Guosheng Zhao, Xiaofeng Wang +5 | cs.CV | 2026-11-03 |
| #47 | On the Feature Evolution of Temporal Difference Learning | Shangzhe Li, Dechen Zhang, Difan Zou +1 | cs.LG | 2026-11-03 |
| #48 | COSMIO: A Benchmark for Cross-Survey Modality Imputation | Dichang Zhang, Yixuan Shao, Jiaqi Deng +8 | astro-ph.IM | 2026-11-03 |
| #49 | ScrambleMark: Zero-Query Watermark-Agnostic Black-Box Evasion of Modern Speech Watermarking | Binhao Ma, Weikang Ding, Hanqing Guo +5 | cs.CR | 2026-11-03 |
| #50 | ScaleTraj: Scale-Decomposed Human Trajectory Generation | Yulin Zeng, Yiheng Zhao, Jun Yan +1 | cs.LG | 2026-11-03 |