Research Scientist at Apple MLR, focused on building efficient and scalable foundation models for sequence modeling, with methods that improve applications across various domains including real-time chat agents, LLM post-training, and knowledge & retrieval grounded LLMs.
I completed my PhD in Computer Science at the University of Waterloo, with a dissertation titled "Novel Methods for Natural Language Modeling and Pretraining", under the supervision of Professor Ming Li. Prior to my doctoral studies, I obtained a Master's degree from the Chinese Academy of Sciences, where I began my NLP research journey under the mentorship of Professor Chengqing Zong.
Building toward fast, streamable speech for low-latency voice agents.
Self-improvement, test-time scaling, and cross-modal alignment.
Grounding LLM generation in external knowledge and curated data.
Preprint, 2026
ACL 2026
IEEE ASRU 2025 (Best Demo)
*equal contribution
ACL 2024
EMNLP 2024
COLING 2024
*equal contribution
ACL 2024 Workshop (KnowLLM)
*equal contribution
Dissertation: Novel Methods for Natural Language Modeling and Pretraining
Findings of EMNLP 2022