Published multiple papers in conferences such as ICML'25, ACL'25, and NAACL'25, covering topics like memory extension, e-commerce script planning, and unifying retrieval and response generation in conversations.
Research Experience
Working at Amazon Rufus team, building large language models for shopping, developing LLM scaling laws, and using these findings to determine key pre-training modeling factors, predict benchmark performance, and guide pre-training data recipes.
Education
Ph.D. in Computer Science from the Chinese University of Hong Kong, supervised by Prof. Irwin King and Prof. Michael R. Lyu.
Background
Senior Applied Scientist at Amazon Rufus team, with research interests in natural language processing and machine learning. During his PhD, he focused on teaching machines to ask and answer reading comprehension questions, covering knowledge assessment and information acquisition.
Miscellany
Offers research internship positions at Amazon for those interested in LLM pre-training. Feel free to send your CV.