arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

2025-10-17 至 2025-10-17 共收录 7 信号源:cs.CL, cs.AI, cs.LG

1. 测试时计算 7 篇

2510.14901 2025-10-17 cs.LG cs.AI cs.CL 85%

Reasoning with Sampling: Your Base Model is Smarter Than You Think

Aayush Karan, Yilun Du

机构 * Harvard University(哈佛大学)

专题命中 测试时计算 :reasoning(title,abstract);verifier(abstract);分类 cs.CL、cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14942 2025-10-17 cs.AI 79%

GroundedPRM: Tree-Guided and Fidelity-Aware Process Reward Modeling for Step-Level Reasoning

Yao Zhang, Yu Wu, Haowei Zhang, Weiguo Li, Haokun Chen, Jingpei Wu, Guohao Li, Zhen Han, Volker Tresp

专题命中 测试时计算 :reasoning(title,abstract);分类 cs.AI

Comments 25 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14943 2025-10-17 cs.CL cs.AI cs.LG 75%

LaSeR: Reinforcement Learning with Last-Token Self-Rewarding

Wenkai Yang, Weijie Liu, Ruobing Xie, Yiju Guo, Lulu Wu, Saiyong Yang, Yankai Lin

机构 * Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学耿丽人工智能学院) LLM Department, Tencent(腾讯机器学习部)

专题命中 测试时计算 :reasoning(abstract);verifier(abstract);分类 cs.CL、cs.AI、cs.LG

Comments Work in progress. Github repo: https://github.com/RUCBM/LaSeR

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14913 2025-10-17 cs.AI cs.CL cs.LG 67%

Budget-aware Test-time Scaling via Discriminative Verification

Kyle Montgomery, Sijun Tan, Yuqi Chen, Siyuan Zhuang, Tianjun Zhang, Raluca Ada Popa, Chenguang Wang

机构 * UC Santa Cruz(加州大学圣克ruz分校) UC Berkeley(加州大学伯克利分校)

专题命中 测试时计算 :reasoning(abstract);分类 cs.CL、cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14853 2025-10-17 cs.CL 57%

Rewiring Experts on the Fly:Continuous Rerouting for Better Online Adaptation in Mixture-of-Expert models

Guinan Su, Yanwu Yang, Li Shen, Lu Yin, Shiwei Liu, Jonas Geiping

机构 * Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) ELLIS Institute Tübingen(图宾根ELLIS研究所) Tübingen AI Center(图宾根人工智能中心) University of Tübingen(图宾根大学) Sun Yat-sen University(中山大学) University of Surrey(萨里大学)

专题命中 测试时计算 :reasoning(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14624 2025-10-17 cs.CV 50%

Efficient Video Sampling: Pruning Temporally Redundant Tokens for Faster VLM Inference

Natan Bagrov, Eugene Khvedchenia, Borys Tymchenko, Shay Aharon, Lior Kadoch, Tomer Keren, Ofri Masad, Yonatan Geifman, Ran Zilberstein, Tuomas Rintamaki, Matthieu Le, Andrew Tao

机构 * NVIDIA

专题命中 测试时计算 :reasoning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.11070 2025-10-17 cs.CV 50%

Falcon: A Remote Sensing Vision-Language Foundation Model (Technical Report)

Kelu Yao, Nuo Xu, Rong Yang, Yingying Xu, Zhuoyan Gao, Titinunt Kitrungrotsakul, Yi Ren, Pu Zhang, Jin Wang, Ning Wei, Chao Li

机构 * Research Center for Space Computing System, ZhejiangLab, Hangzhou, China(空间计算系统研究中心,浙江实验室,杭州,中国)

专题命中 测试时计算 :reasoning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏