Machine Learning & Intelligent Control Lab.
Principal Investigator
Seungyul Han
Associate Professor
AI Graduate School (AIGS) & Department of Electrical Engineering (EE)
Ulsan National Institute of Science and Technology (UNIST)
50 Unist-gil, Ulsan, 44919, South Korea
Biography
Seungyul Han is an Associate Professor in the Artificial Intelligence Graduate School (AIGS) and the Department of Electrical Engineering (EE) at the Ulsan National Institute of Science and Technology (UNIST). He received his B.S. degree (double major in Mathematical Sciences) and M.S. degree in Electrical Engineering from the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea, in 2013 and 2016, respectively, and his Ph.D. degree in Electrical Engineering from KAIST. Prior to joining UNIST, he was a postdoctoral researcher at the Institute of Information Electronics at KAIST. He served as an assistant professor at UNIST until 2026 and is currently an associate professor at UNIST. His research focuses on reinforcement learning (RL) and LLM-based agentic AI, with an emphasis on learning, reasoning, and decision making for autonomous agents.
Recruitment
We are looking for motivated M.S. and Ph.D. students interested in Agentic AI (LLM/RL), and Physical AI. Interested applicants are encouraged to contact us (syhan@unist.ac.kr) with their CV, academic transcript, and a brief description of their research interests.
We are also recruiting postdoctoral researchers through the National Defense InnoCORE program (Annual Salary: KRW 90 million). We seek researchers interested in advancing research in these areas, with preference given to candidates who have published at top-tier AI/ML conferences. Interested applicants should contact us (syhan@unist.ac.kr) with their CV and representative publications.
Research Areas
Our laboratory conducts fundamental research in machine learning (ML) and reinforcement learning (RL), with a focus on building intelligent agents that can reason, learn, and make decisions through interaction. We study the integration of large language models (LLMs) and RL for agentic AI, develop RL methods for physical AI and embodied agents, and advance learning-based control and sequential decision making. We also explore real-world domains where these advances can enable intelligent and autonomous systems. Our research is organized into four main directions, as summarized in the figure below:
News
[2026/09] Four papers from our lab have been accepted to NeurIPS 2026, with one selected as a Spotlight paper. Congratulations!
[2026/09] Jeongha Park and Myoungseok Han joined our lab. Welcome!
[2026/08] Our paper, “MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games,” has been accepted to EMNLP 2026. Congratulations!
[2026/05] Two papers from our lab have been accepted to ICML 2026. Congratulations!
[2026/03] Prof. Han (PI) has been promoted to Associate Professor. Congratulations!
[2026/01] Four papers from our lab have been accepted to ICLR 2026. Congratulations!
[2025/12] Our paper, “Generalized Per-Agent Advantage Estimation for Multi-Agent Policy Optimization,” has been accepted to AAMAS 2026 and nominated for the Best Paper Award. Congratulations!
[2025/09] Gwanwoo Choi, Mingu Kang, and Sangwoo Bang joined our lab. Welcome!
[2025/08] New Project (PI): “End-to-End 대규모 자율군집 제어를 위한 LLM 기반 다중 에이전트 강화학습 기술 개발” (NRF 국가아젠다 기초연구, 2025.09–2028.08, 총 연구비 4.8억 원)
[2025/05] Two papers from our lab have been accepted to ICML 2025. Congratulations!
[2025/03] Junhyun Bae and Yechan Whang joined our lab. Welcome!
[2024/09] Our paper, “Exclusively Penalized Q-learning for Offline Reinforcement Learning,” has been accepted to NeurIPS 2024 as a Spotlight paper. Congratulations!
[2022/04] New Project (PI): “자율 드론 실용화를 위한 목적지향 강화학습 핵심기술 개발” (IITP 사람중심인공지능 핵심원천기술개발, 2022.04–2026.12, 총 연구비 47.5억 원)