Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, Gao Huang
Who it is from
Shanghai Artificial Intelligence Laboratoryaffiliation declared by the authors, according to OpenAlex- Shanghai Jiao Tong Universityaffiliation declared by the authors, according to OpenAlex
Tsinghua Universityaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsPeking University · 12,684 citations
- Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic TasksChinese Academy of Sciences · 3,956 citations
- A Comprehensive Survey of Continual Learning: Theory, Method and ApplicationTsinghua University · 2,465 citations
- VBench: Comprehensive Benchmark Suite for Video Generative ModelsNanjing University · 2,431 citations
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific ProblemsBeihang University · 1,649 citations
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language ModelsNanjing University · 1,603 citations