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。

2025-09-24 至 2025-09-24 共收录 6 信号源:cs.CL, cs.AI, cs.LG

1. 测试时计算 6 篇

2509.19284 2025-09-24 cs.LG 90%

What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

Yunzhen Feng, Julia Kempe, Cheng Zhang, Parag Jain, Anthony Hartshorn

机构 * Meta Superintelligence Labs(Meta超智能实验室) New York University(纽约大学)

专题命中 测试时计算 :reasoning(title,abstract);CoT(title,abstract);chain-of-thought(abstract);test-time compute(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.18536 2025-09-24 cs.CL cs.AI 81%

CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs

Jin Young Kim, Ji Won Yoon

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

Comments Published as a main conference paper at EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.19003 2025-09-24 cs.CV 78%

Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards

Honghao Chen, Xingzhou Lou, Xiaokun Feng, Kaiqi Huang, Xinlong Wang

机构 * Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) Beijing Academy of Artificial Intelligence(北京人工智能研究院)

专题命中 测试时计算 :reasoning(title,abstract)

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.13255 2025-09-24 cs.CL cs.AI cs.IR cs.LG cs.MM 67%

Automating Steering for Safe Multimodal Large Language Models

Lyucheng Wu, Mengru Wang, Ziwen Xu, Tri Cao, Nay Oo, Bryan Hooi, Shumin Deng

机构 * Zhejiang University(浙江大学) Zhejiang University - Ant Group Joint Lab of Knowledge Graph(浙江大学-蚂蚁集团知识图谱联合实验室) National University of Singapore, NUS-NCS Joint Lab(新加坡国立大学NUS-NCS联合实验室)

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

Comments EMNLP 2025 Main Conference. 23 pages (8+ for main); 25 figures; 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15044 2025-09-24 cs.CL 57%

Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner

Bolian Li, Yanran Wu, Xinyu Luo, Ruqi Zhang

机构 * Department of Computer Science, Purdue University(计算机科学系,普渡大学)

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

Comments EMNLP 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.04130 2025-09-24 cs.CV 50%

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs

Jindong Jiang, Xiuyu Li, Zhijian Liu, Muyang Li, Guo Chen, Zhiqi Li, De-An Huang, Guilin Liu, Zhiding Yu, Kurt Keutzer, Sungjin Ahn, Jan Kautz, Hongxu Yin, Yao Lu, Song Han, Wonmin Byeon

机构 * NVIDIA(英伟达) Rutgers University(罗格斯大学) UC Berkeley(加州大学伯克利分校) MIT(麻省理工学院) Nanjing University(南京大学) KAIST(韩国科学技术院)

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