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 |
|---|---|---|---|
|
SWE-Prime: Fewer Trajectories, Better Performance
Dewu Zheng, Ruizhe Ye, Yanlin Wang, Yang Ye, Hongyu Zhang, Ensheng Shi, Xilin Liu, Yuchi Ma, Jianxing Yu, Zibin Zheng
cs.SE
cs.SE
cs.AI
cs.CL
|
2608.27449v1 | 2026-08-27 17:58:10 | 待赞助 |
|
TTPO: Test-Time Policy Optimization
Aozhe Wang, Zhengxi Lu, Jianze Wang, Shangke Lv, Ying Liu, Weiming Lu, Jun Xiao, Yueting Zhuang, Hua Yang, Qianglong Chen, Yongliang Shen
cs.CL
cs.CL
|
2608.27448v1 | 2026-08-27 17:58:10 | 待赞助 |
|
From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench
Dewu Zheng, Yanlin Wang, Xiwen Wang, Kefeng Duan, Hongyu Zhang, Xilin Liu, Yuchi Ma, Zibin Zheng
cs.SE
cs.SE
cs.AI
cs.CL
|
2608.27442v1 | 2026-08-27 17:56:24 | 待赞助 |
|
Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
Chanho Park, Daehyeon Choi, Jihyun Lee, Minhyuk Sung
cs.CV
cs.CV
|
2608.27417v1 | 2026-08-27 17:43:58 | 待赞助 |
|
Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms
Siye Wu, Kai Yang, Yuchen Cai, Xin Xu, Peng-Yuan Wang, Jiaxuan Wang, Jiashun Liu, Jiafei Lyu, Yangkun Chen, Saiyong Yang, Yanghua Xiao
cs.CL
cs.CL
|
2608.27409v1 | 2026-08-27 17:38:04 | 待赞助 |
|
CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators
Kechen Liu, Ola Shorinwa
cs.RO
cs.RO
cs.AI
cs.CV
|
2608.27406v1 | 2026-08-27 17:35:10 | 待赞助 |
|
CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases
Sil Hamilton, Albert Yu Sun, Oscar J. Romero, Carl-Leander Henneking, David Mimno, Bishan Yang, Igor Labutov
cs.AI
cs.AI
cs.CL
cs.IR
|
2608.27391v1 | 2026-08-27 17:23:04 | 待赞助 |
|
FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference
Zekai Li, Jiaming Tang, Zhijian Liu
cs.RO
cs.RO
|
2608.27384v1 | 2026-08-27 17:19:29 | 待赞助 |
|
Embodied Scene Rearrangement Planning
Canzhi Chen, Zan Wang, Siqi Zhu, Qi Wu, Yixuan Li, Wei Liang
cs.RO
cs.RO
|
2608.27371v1 | 2026-08-27 17:08:40 | 待赞助 |
|
Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models
Frederik Berenz
cs.CV
cs.CV
cs.AI
|
2608.27367v1 | 2026-08-27 17:04:57 | 待赞助 |
|
Super-Resolution of Range-Doppler Maps: A Case Study with Chirp-Sequence Radar and Transformer
Sven Hinderer, Jonathan Riese, Zheming Yin, Bin Yang
eess.SP
eess.SP
|
2608.27354v1 | 2026-08-27 16:52:57 | 待赞助 |
|
Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO
Yunpeng Ba, Zhi Zheng, Yue Xie, Jiaqing Li, Xialiang Tong, Tao Zhong, Mingxuan Yuan, Zhichao Lu, Xuyang Wu, Zhenkun Wang
cs.LG
cs.LG
|
2608.27351v1 | 2026-08-27 16:48:39 | 待赞助 |
|
Pair-Level Essay-Scale Republication and Reuse from Fragmented Historical Text Reuse: A Workflow Study on Eighteenth-Century Books and Newspapers
Ke Shu, Kira Hinderks, Eetu Mäkelä, Mikko Tolonen
cs.CL
cs.CL
|
2608.27343v1 | 2026-08-27 16:43:27 | 待赞助 |
|
BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent Benchmarks
Jeong-Yoon Kim
cs.CL
cs.CL
cs.SE
|
2608.27334v1 | 2026-08-27 16:35:52 | 待赞助 |
|
Evidence, Calibration, and Stability: A Triadic Framework for Hypothesis Testing Under Model Uncertainty
Subir Hait
stat.ME
stat.ME
|
2608.27320v1 | 2026-08-27 16:21:03 | 待赞助 |
|
Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification
Jinghan Xu, Yikai Zhang, Aili Chen, Weiyuan Li, Jiaqing Liang, Deqing Yang
cs.AI
cs.AI
|
2608.27311v1 | 2026-08-27 16:12:23 | 待赞助 |
|
Accelerating Optical Photon Simulation in DUNE with Opticks
Ilker Parmaksiz, Aaron Higuera, Laura Paulucci, Viktor Pec, Estanislao Forino
hep-ex
hep-ex
physics.comp-ph
|
2608.27306v1 | 2026-08-27 16:08:29 | 待赞助 |
|
QuantumBoostNet: A Hybrid Classical-Quantum Architecture for Enhanced Accuracy in Cardiac Ultrasound View Identification
Mihai Udrescu-Milosav, Stefan-Alexandru Jura, Mihai Udrescu, Gerhard-Paul Diller
cs.LG
cs.LG
|
2608.27302v1 | 2026-08-27 16:06:09 | 待赞助 |
|
When Context Gets Root: Privilege Escalation in LLM Harnesses
Xingbang He, Yuanwei Chen, Yi Qian, Haiyang Wei, Ligeng Chen, Zenan Fu, Linzhang Wang, Hao Wu, Bing Mao
cs.CR
cs.CR
cs.SE
|
2608.27299v1 | 2026-08-27 16:03:57 | 待赞助 |
|
Optimal cloning of mixed states
Marco Fanizza, Dmitry Grinko, Thilo Scharnhorst, Jack Spilecki
quant-ph
quant-ph
|
2608.27298v1 | 2026-08-27 16:03:42 | 待赞助 |