Paper 'REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing' accepted to EMNLP 2025; paper 'VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark' accepted to NeurIPS 2024; paper 'PTransIPs: Identification of phosphorylation sites enhanced by protein PLM embeddings' accepted to IEEE J-BHI; won National Second Prize at the 13th Chinese Mathematics Competition in 2023; won two Excellence Awards at the 2022 S.-T. Yau College Student Mathematics Contest.
Research Experience
Current Ph.D. student at the National Laboratory of Pattern Recognition, CASIA; former research assistant at Microsoft Research Asia, focusing on LLM Safety; former undergraduate researcher at CRIPAC-DIG, focusing on LVLM Editing.
Education
Ph.D. student at the Institute of Automation, Chinese Academy of Sciences, supervised by Prof. Tieniu Tan and Prof. Qiang Liu. Bachelor's degree in Mathematics and Applied Mathematics from Cuiying Honors College, Lanzhou University. Won two Excellence Awards at the 2022 S.-T. Yau College Student Mathematics Contest in Analysis and Partial Differential Equations and Applied and Computational Mathematics.
Background
Research interests include Large Language Models (Reasoning and Knowledge Editing) and AI for Science (Bioinformatics). Formerly a research assistant at Microsoft Research Asia.
Miscellany
Fan of Chelsea Football Club and the Los Angeles Lakers. Enjoys running and playing basketball in free time.