Yihao Xue

I am a final-year PhD candidate in the Computer Science Department at UCLA, advised by Professor Baharan Mirzasoleiman. Prior to this, I completed my undergraduate studies at Shanghai Jiao Tong University.

My research focuses on understanding and improving the reliability of machine learning systems, specifically examining whether models behave as intended under imperfect conditions (e.g., imperfect supervision and imperfect training environments). I study these challenges across different training paradigms, including supervised learning, self-supervised learning, and language models.

I am a recipient of the OpenAI Superalignment Grant.