Published several preprints and conference papers, including 'Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge' and 'Federated Domain-Specific Knowledge Transfer on Large Language Models Using Synthetic Data,' among others, presented at conferences such as EMNLP and ACL.
Research Experience
Served as an author or co-author for multiple research projects, focusing on the safety, privacy protection, and efficient inference of large language models.
Education
Ph.D. in Computer Science and Engineering from the Hong Kong University of Science and Technology (2016-2021), supervised by Yangqiu Song; B.Eng. in Computer Science and Engineering from South China University of Technology (2012-2016).
Background
Currently an associate professor at Shien-Ming Wu School of Intelligent Engineering, South China University of Technology. My research area is natural language processing, with a focus on LLM Efficient Inference, LLM Privacy Protection, and LLM Safety.