Short Bio
Hello!👋 I am a senior undergraduate student from University of Science and Technology of China and currently work as a research intern at MSR Asia, under the supervision of Furu Wei and the mentorship of Nan Yang, Liang Wang. My research interest mainly lies in:
- LLM Reasoning: Train reasoning models with long-thinking capabilities, similar to OpenAI-o1 and DeepSeek-R1, or enhance model reasoning abilities through alternative methods such as hidden CoT. Meanwhile, investigate the inference scaling laws of reasoning.
- AI Alignment: Explore the application of different RLHF and RL algorithms across various scenarios.
- Agent: Build web agents or something similar.
I am always eager for discussions and collaborations! Feel free to email me!
Education
News
Publications
