SimpleRL-Zoo and B-STaR: Improving reasoning performance and efficiency through reinforcement learning
Date:
Invited talk on SimpleRL-Zoo and B-STaR: Improving reasoning performance and efficiency through reinforcement learning.
Weihao Zeng
PhD student at HKUST CSE, focusing on LLM post-training
- Hong Kong
- HKUST
- Google Scholar
- GitHub
- X (formerly Twitter)
- Zhihu