I am a Ph.D. student at KAIST Graduate School of AI, co-advised by Minjoon Seo and Seongjoon Oh. My personal page is at yunjae-won.github.io.

My research focuses on learning algorithms utilizing pairwise comparison data, such as Direct Preference Optimization (DPO). I am also interested in understanding how language models acquire and forget knowledge during optimization. My goal is to develop principled theoretical explanations of these phenomena and to improve learning algorithms based on such analyses.

Previously, I received my Bachelor’s degree in Electrical Engineering from KAIST. I have also interned at NAVER Cloud (HyperCLOVA Pre-Training Team), NAVER Place (AI Development Team), and NCSoft Speech AI Lab.