Multiple papers accepted in top conferences such as NeurIPS 2025, ICLR 2025, and EMNLP 2024; received the President Award of the Chinese Academy of Sciences (highest honor) and National Scholarship; team won first place in the AgentSociety Challenge @ WWW 2025; research work SimPER adopted by LG AI Research as the core training algorithm for their EXAONE Deep series LLMs.
Research Experience
Currently pursuing a Ph.D. at the State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, working on various research projects across the domains of graph, vision, and language, focusing on generalization, alignment, and agent systems.
Education
Ph.D. Candidate at the State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, advised by Prof. Xueqi Cheng and Assoc. Prof. Bingbing Xu.
Background
Research interests: Building Trustworthy AI that performs reliably and ethically for social good and human well-being. Specific research areas include Machine Learning Generalization, Large Language Model Alignment, and Agent System Reasoning and Planning.