PhD student at The Ohio State University, advised by Zhihui Zhu.
B.Eng. from UESTC, advised by Zhao Kang and Hao Dong.
I study the representations and training dynamics of large language models,
with an eye toward mechanistic interpretability.
Happy to chat about interpretability and LLM research — email me.
Project cards are regenerated daily from public GitHub data by a GitHub Action; styling adapted from github-stats-extended.