每周精选
近7天内社区解读较多的方向与热门关键词，适合先读一眼再决定是否深入。
以下为搜索结果。
| 标题 | arXiv | 发布时间 | 状态 |
|---|---|---|---|
|
Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
Prakhar Kaushik, Soumava Paul, Alan Yuille
cs.CV
cs.CV
cs.AI
cs.GR
|
2610.37668v1 | 2026-10-27 17:59:59 | 待赞助 |
|
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
Chaehyun Kim, Chi-Pin Huang, Jisoo Kim, Min-Hung Chen, Yu-Chiang Frank Wang, Seungryong Kim, Fu-En Yang
cs.RO
cs.RO
cs.AI
cs.CV
|
2610.37666v1 | 2026-10-27 17:59:52 | 待赞助 |
|
An EVM-Cosmos Bridge for Atomic, Semantic-Preserving Transfer of Environmental Tokens
Sebastian Pandolfi, Guzmán Llambías, Laura González
cs.SE
cs.SE
|
2610.37663v1 | 2026-10-27 17:59:30 | 待赞助 |
|
Can Discrete Tokens Serve as Semantically Lossless Representations of Visual Signals?
Jialv Zou, Xiaotong Li, Zhengrong Yue, Xu Huang, Yaxin Luo, Wenhao Yan, Haodong Li, Wenyu Liu, Xinggang Wang
cs.CV
cs.CV
|
2610.37662v1 | 2026-10-27 17:59:22 | 待赞助 |
|
When Should We Intervene at Test Time?
Jiahao Zhang, Xinling Wen, Liangliang Li, Yu Chen
cs.LG
cs.LG
|
2610.37658v1 | 2026-10-27 17:58:53 | 待赞助 |
|
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
Igor Shilov, Xiaoxue Yang, Alexander Panfilov, Evgenii Kortukov, Matthieu Meeus, Peter Romov, Wojciech Samek, Jonas Geiping, Yves-Alexandre de Montjoye
cs.LG
cs.LG
cs.CL
cs.CR
|
2610.37657v1 | 2026-10-27 17:58:52 | 待赞助 |
|
Attention as Lattice Gauge Theory: Relations Interact Only Through Wilson Loops
Aakash Sarkar, Ananya Mukherjee, Motoshige Sato
cs.LG
cs.LG
cs.AI
physics.comp-ph
|
2610.37656v1 | 2026-10-27 17:58:48 | 待赞助 |
|
KPPax: preprocess differentiable kinetic ODE for machine learning in atmospheric chemistry
Wenqing Peng, Michael Boy, Zhi-Song Liu
cs.AI
cs.AI
|
2610.37655v1 | 2026-10-27 17:58:40 | 待赞助 |
|
Pushing Dexterity and Safety for In-Hand Object Pose Reaching That Works Remarkably Well
Ian Chuang, Hiya Shah, Vamsi Chilamkur, Iman Soltani, Claire Tomlin
cs.RO
cs.RO
cs.LG
eess.SY
|
2610.37652v1 | 2026-10-27 17:58:20 | 待赞助 |
|
GEPA-Curator: Curated Learning for Self Improving Agents
Zack Yu, Nicholas Lee, Minjae Lee, Lakshya Agarwal, Luca Manolache, Wonjun Kang, Matei Zaharia, Michael W. Mahoney, Kurt Keutzer, Sehoon Kim, Amir Gholami
cs.CL
cs.CL
|
2610.37651v1 | 2026-10-27 17:58:11 | 待赞助 |
|
Can LLMs Uncover Hidden Physical Laws through Free Exploration?
Zhen Yang, Wen Wang, Xander Xu, Ying-Cong Chen
cs.CL
cs.CL
cs.AI
cs.MA
|
2610.37649v1 | 2026-10-27 17:57:00 | 待赞助 |
|
Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis
Andrew Szot, Samira Abnar, Omar Attia, Abbas Kazerouni, Michael Kirchhof, Cheng-Yu Hsieh, Raviteja Vemulapalli, Alexander Toshev
cs.LG
cs.LG
|
2610.37648v1 | 2026-10-27 17:56:46 | 待赞助 |
|
MuonGS: Pretraining LLMs with Relaxed Weight-Norm Control
Athanasios Glentis, Dawei Li, Mingyi Hong
cs.LG
cs.LG
cs.AI
math.OC
|
2610.37647v1 | 2026-10-27 17:56:40 | 待赞助 |
|
Multi-State Linear Attention with Generalized Second-Order Routing
Hee Seung Hwang, Sanghyuk Chun, Xindi Wu, Olga Russakovsky, Zhiwei Deng
cs.CL
cs.CL
|
2610.37645v1 | 2026-10-27 17:55:49 | 待赞助 |
|
Metacognitive Decoding: Efficient Inference for Diffusion Language Agents
Mingyu Zhao, Shuhang Lin, Ligong Han, Xiaojing Yu, Zhenting Wang, Yifei Pang, Yang Zhou, Dimitris N. Metaxas
cs.CL
cs.CL
|
2610.37642v1 | 2026-10-27 17:55:24 | 待赞助 |
|
Partially Edited Audio: Generation, Defense, and Open Problems
Lin Zhang, You Zhang, Nicholas Evans, Xin Wang, David Harwath, Abhinav Dhall, Bowen Shi, Chengzhe Sun, Siwei Lyu, Sanjeev Khudanpur
cs.SD
cs.SD
eess.AS
|
2610.37640v1 | 2026-10-27 17:54:42 | 待赞助 |
|
UPP$^{\text{cc}}$ is Not Closed Under Intersection
Mark Bun, Mandar Juvekar
cs.CC
cs.CC
|
2610.37634v1 | 2026-10-27 17:54:01 | 待赞助 |
|
Classical Verification of Quantum Computation Beyond the Polynomial Hierarchy
Atul Mantri
quant-ph
quant-ph
cs.CC
cs.CR
|
2610.37635v1 | 2026-10-27 17:54:01 | 待赞助 |
|
Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence
Siyoon Jin, Dahyun Chung, Honggyu An, Sangbeom Lim, Wonjin Nam, Jaewoo Jung, WonJun Moon, Seungryong Kim
cs.CV
cs.CV
|
2610.37633v1 | 2026-10-27 17:53:34 | 待赞助 |
|
What Improves During Pretraining? Tracking Knowledge Acquisition with Point-in-Time Models
Chang Su, Bin Wu, Emine Yilmaz, Yao Lu
cs.AI
cs.AI
|
2610.37631v1 | 2026-10-27 17:52:38 | 待赞助 |