大模型推理能力

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs

Li Li, Ziyi Wang, Yongliang Wu, Jianfei Cai, Xu Yang

机构 * School of Computer Science & Engineering, Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（计算机科学与工程学院，新一代人工智能技术及其交叉应用关键实验室（东南大学），教育部，中国） ； Data Science & AI Department at Faculty of IT, Monash University, Australia（信息学院数据科学与人工智能部门，墨尔本大学，澳大利亚） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；CoT(title,abstract)；chain-of-thought(abstract)；分类 cs.CL

Comments 22 pages, 7 figures

ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation

Siao Tang, Xinyin Ma, Gongfan Fang, Xinchao Wang

机构 * National University of Singapore（新加坡国立大学） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.CL、cs.AI

Comments Compare with more baselines, add more in-depth analysis, and re-evaluate the GPQA-D benchmark. Codes are available at https://github.com/tsa18/ConciseHint

ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis

Congzhi Zhang, Zhibin Wang, Yinchao Ma, Jiawei Peng, Yihan Wang, Qiang Zhou, Jun Song, Bo Zheng

机构 * Alibaba Group（阿里巴巴集团） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.AI

Through the Valley: Path to Effective Long CoT Training for Small Language Models

Renjie Luo, Jiaxi Li, Chen Huang, Wei Lu

机构 * Singapore University of Technology and Design（新加坡科技设计大学） ； Nanyang Technological University（南洋理工大学） 纠错

专题命中 复杂问题求解 ：CoT(title,abstract)；reasoning(abstract)；chain-of-thought(abstract)；分类 cs.CL

ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning

Yunhao Wang, Ziting Li, Shuai Chen, Tao Liu, Chao Song, Junjie Jiang, Jian Zhu, Peng Gao, Bin Qin

机构 * Xiaomi Inc.（小米公司） 纠错

专题命中 复杂问题求解 ：reasoning(title,abstract)；分类 cs.AI

BroRL: Scaling Reinforcement Learning via Broadened Exploration

Jian Hu, Mingjie Liu, Ximing Lu, Fang Wu, Zaid Harchaoui, Shizhe Diao, Yejin Choi, Pavlo Molchanov, Jun Yang, Jan Kautz, Yi Dong

机构 * NVIDIA ； Stanford University（斯坦福大学） ； University of Washington（华盛顿大学） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 16 pages, 4 figures

Graph Integrated Multimodal Concept Bottleneck Model

Jiakai Lin, Jinchang Zhang, Guoyu Lu

机构 * Intelligent Vision and Sensing (IVS) Lab at SUNY Binghamton（智能视觉与感知实验室（IVS）位于纽约州立大学布法罗分校） 纠错

专题命中 复杂问题求解 ：reasoning(abstract)