I am a fifth-year Ph.D. student in the Department of Computer Science at the University of Hong Kong (HKU), supervised by Lingpeng Kong. I previously interned at Google DeepMind, ByteDance, and SambaNova Systems. In 2021, I received my Bachelor degree in the School of Computer Science and Engineering, Sun Yat-sen University, working with Qinliang Su.
Research
I develop efficient and flexible sequence models. Recently, I've focused on how language models represent inputs beyond tokenization, and how they generate outputs beyond left-to-right autoregression.
For a complete list, see Google Scholar.
* indicates equal contribution.
Beyond Tokenization
Beyond Autoregressive Models
Model Architectures
Teaching
Spring 2022 and Spring 2023: TA for COMP3314B Machine Learning
Service
Reviewer: ACL 2021, NAACL 2021, ICML 2022-2024, NeurIPS 2022-2023, etc.