Junghyun Lee

I am a final-year PhD candidate at the Kim Jaechul Graduate School of AI, KAIST, where I am very fortunate to be advised by Se-Young Yun (OSI Lab) and Chulhee “Charlie” Yun (OptiML Lab). I spent the summer of 2025 as a Research Scientist Intern at Adobe Research, San Jose, working with Branislav “Brano” Kveton, Anup Rao, Subhojyoti Mukherjee, Ryan A. Rossi, Sunav Choudhary, and Alexa Siu. Before my PhD, I earned my MSc from the same school, and a BSc in Mathematical Sciences and Computer Science (double major, cum laude), also from KAIST.

My research focuses primarily on interactive machine learning (online learning, bandits, RL, active learning), “theoretical aspects” of LLMs (e.g., alignment, reasoning), optimization theory, deep learning theory, and statistical analyses of large networks with an emphasis on community detection. More broadly, I am interested in all aspects of mathematical and theoretical AI, as well as related problems in mathematics and statistics.

I enjoy organizing seminars and workshops to foster Korea’s theoretical AI community (see Organizer). Outside of research, I am an avid violinist and perform as a first violinist with various amateur orchestras, including the KAIST Orchestra (KAO), PASSIONATE Orchestra, MDOP Orchestra, KAO-S, PROJECT Starlight, and PROJECT IDEA.

Feel free to reach out if you’d like to collaborate on any of my research topics, or just to connect! (Third-person bio here.)