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
De quem é
Shanghai Artificial Intelligence Laboratoryafiliação declarada pelos autores, segundo o OpenAlex- Shanghai Jiao Tong Universityafiliação declarada pelos autores, segundo o OpenAlex
Tsinghua Universityafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsPeking University · 12.684 citações
- Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic TasksChinese Academy of Sciences · 3.956 citações
- A Comprehensive Survey of Continual Learning: Theory, Method and ApplicationTsinghua University · 2.465 citações
- VBench: Comprehensive Benchmark Suite for Video Generative ModelsNanjing University · 2.431 citações
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific ProblemsBeihang University · 1.649 citações
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language ModelsNanjing University · 1.603 citações