Published over 20 papers, with 9 first-authored (including first-student and co-first) papers, mainly in top-tier venues such as JMLR, TPAMI, NeurIPS, ICML, AAAI, etc. Some notable publications include 'SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models' and 'Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs'.
Research Experience
Conducting research work in the LAMDA group, involved in multiple research projects.
Background
Currently a third-year Ph.D. student at the School of Artificial Intelligence, Nanjing University, and a member of the LAMDA Group led by Professor Zhi-Hua Zhou. Research interests include Machine Learning and Online Optimization Theory, now focusing on Large Language Models (LLM), especially multimodality, reasoning, and its optimization theory.