Junghyun Lee is a third-year PhD student at the Kim Jaechul Graduate School of AI, KAIST, jointly advised by Professors Se-Young Yun (OSI Lab) and Chulhee "Charlie" Yun (OptiML Lab). His research primarily focuses on mathematical and theoretical AI, with a strong emphasis on interactive machine learning (bandits, RL, active learning) and the statistical analysis of large networks, especially community detection. His theoretical interests also extend to probability and deep learning theory. Recently, he has been exploring problems related to LLMs such as alignment (RLHF, preference learning), reasoning, test-time scaling, and more. He spent the summer of 2025 as a research scientist intern at Adobe Research, San Jose, working with Branislav "Brano" Kveton and others. <br>
His work has been presented at leading international AI conferences, including AISTATS, NeurIPS, ICLR, and AAAI, where he has also contributed as a reviewer. He received the Best Reviewer Award at AISTATS 2025, Best Student Paper Award at OPODIS 2023, and Best Paper Awards at multiple Korean AI conferences, including KSC '23, JKAIA '21, and CKAIA '22 and '24. Junghyun earned his MSc from the same school and his BSc in Mathematical Sciences and Computer Science (double major, cum laude), also from KAIST.