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。

2025-10-08 至 2025-10-08 共收录 5 篇信号源：cs.CL, cs.AI, cs.LG

1. 测试时计算 5 篇

2509.23250 2025-10-08 cs.AI cs.CV 83%

Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned

Brandon Ong, Tej Deep Pala, Vernon Toh, William Chandra Tjhi, Soujanya Poria

机构 * AI Singapore（AI新加坡）； Nanyang Technological University（南洋理工大学）

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

2505.17242 2025-10-08 cs.LG cs.AI 79%

Optimal Policy Minimum Bayesian Risk

Ramón Fernandez Astudillo, Md Arafat Sultan, Aashka Trivedi, Yousef El-Kurdi, Tahira Naseem, Radu Florian, Salim Roukos

专题命中测试时计算：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.AI、cs.LG

2510.05251 2025-10-08 cs.CL cs.LG 62%

Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning

Chenghao Yang, Lin Gui, Chenxiao Yang, Victor Veitch, Lizhu Zhang, Zhuokai Zhao

机构 * Department of Computer Science, University of Chicago（芝加哥大学计算机科学系）； Department of Statistics, University of Chicago（芝加哥大学统计系）； Toyota Technological Insitute at Chicago（芝加哥丰田技术研究所）； Data Science Institute, University of Chicago（芝加哥大学数据科学研究所）； Meta AI

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

Comments Codebase: https://github.com/yangalan123/EAD-RLVR

2510.06040 2025-10-08 cs.CV cs.AI 57%

VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization

Xinye Cao, Hongcan Guo, Jiawen Qian, Guoshun Nan, Chao Wang, Yuqi Pan, Tianhao Hou, Xiaojuan Wang, Yutong Gao

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）； Minzu University of China（民族大学）

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

Comments Accepted by ICCV 2025

2510.05421 2025-10-08 cs.LG 57%

Draft, Verify, and Improve: Toward Training-Aware Speculative Decoding

Shrenik Bhansali, Larry Heck

机构 * Georgia Institute of Technology（佐治亚理工学院）

专题命中测试时计算：verifier(abstract)；分类 cs.LG