Publications: Multiple papers accepted by top conferences such as NeurIPS, EMNLP, ICML; Awards: NSFC Fund (August 2025), WAIC Yunfan Rising Star Award (July 2025), Tsinghua Outstanding Doctoral Dissertation award (July 2024); Projects: PRIME (a scalable reinforcement learning method), Eurus-2-7B-PRIME model outperformed GPT-4o on advanced math benchmarks
Research Experience
Research Scientist at Shanghai AI Laboratory (Since July 2024); Member of THUNLP Lab, Tsinghua University (Until 2025)
Education
Ph.D.: Department of Computer Science and Technology, Tsinghua University, Advisor: Prof. Zhiyuan Liu (Graduated in 2025); B.S.: Mathematics and Physics, Tsinghua University (Graduated in 2019)
Background
Research Interests: LLM alignment and reinforcement learning; Previously, research on representation learning on graphs, especially graph neural networks and their application.