Published several papers, including 'SALMON: Self-Alignment with Instructable Reward Models', 'Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision', 'Aligning Large Multimodal Models with Factually Augmented RLHF', etc. Received multiple grants and awards, such as OpenAI Superalignment Fast Grants ($100,000), Microsoft Accelerate Foundation Models Research (AFMR) Initiative ($20,000), Google PhD Fellowship in Natural Language Processing.
Research Experience
Research Scientist at OpenAI, involved in multiple research projects including OpenAI Deep Research (research lead), OpenAI Computer-Using Agent, OpenAI o3 / o4-mini, etc.
Education
Ph.D. in Computer Science from CMU; B.S. with honors in Computer Science from Peking University.
Background
Research Scientist, focusing on the alignment of large language models towards truth seeking, complex reasoning, and human values.
Miscellany
Served as a Teaching Assistant for 11-741 Machine Learning with Graphs; selected as 2023 Rising Stars in Data Science and gave a talk at the Rising Stars workshop at UChicago.