Personal Information
I am a PhD student in the Department of Computer Science at Purdue University, advised by Ruqi Zhang. I completed my BE of computer science and technology at Tianjin University, advised by Changqing Zhang.
Research Interests
I am interested in the post-training of large language models (LLMs). Recently, I focus on the sampling efficiency of post-training algorithms. I am also widely interested in safety alignment, reward generalization, Bayesian deep learning, and data imbalance.
News
[08/20/2025] 1 short paper accepted by EMNLP 2025
[07/08/2025] 2 papers accepted by COLM 2025
[05/01/2025] 1 paper accepted by ICML 2025
[01/22/2025] 1 paper accepted by ICLR 2025
[12/23/2024] 1 paper accepted by TMLR