Active Generative Agents Lab
Intelligent biological agents generate actions to explore the world actively. Artificially intelligent agents today attempt to mimic them, but they fall significantly behind in terms of efficiency, effectiveness, and reliability. The Active Generative Agents (AGA) Lab at the UNIST Graduate School of AI aims to investigate the principles underlying intelligence and apply them to build intelligent systems that can interact with the world actively, efficiently, and safely.
AGA Lab is primarily interested in developing principled methods at the intersection of generative modeling and reinforcement learning. We apply our algorithms to various high-impact real-world applications, including, but not limited to, robotics foundation models, biochemistry, particle physics, chemical engineering, and adtech.
UNIST AGA Lab is supported by the UNIST AI Graduate School (IITP), AI Star Fellowship (IITP), NIPA, Basic Research Laboratory (NRF), and AB180.
Principal Investigator
Sangwoong Yoon윤상웅
Assistant Professor, Graduate School of AI, UNIST
Affiliated Professor, Department of Electrical Engineering, UNIST
Sangwoong is an Assistant Professor at UNIST Graduate School of AI, jointly affiliated with the Department of Electrical Engineering. He was previously a Research Fellow at University College London (UCL) and Korea Institute for Advanced Study (KIAS). He also worked as an applied scientist intern at Amazon (Seattle, US) and as a research scientist intern at Kakao Brain.
He has received the Outstanding Doctoral Dissertation Award from Seoul National University, the Qualcomm Innovation Fellowship Korea, the Youlchon AI Stars Scholarship from the SNU AI Institute, and the Best Poster Award at MLSS 2021 Taipei.
He currently serves as an Area Chair for NeurIPS and ICLR, and has served as a reviewer for NeurIPS, ICLR, ICML, CVPR, AISTATS, and AAAI.
- Ph.D. in Mechanical Engineering, Seoul National University
(Advisor: Frank Chongwoo Park) - M.S. in Neuroscience, Seoul National University
(Advisor: Byoung-Tak Zhang) - B.S. in Chemical and Biological Engineering, Seoul National University
News
Open position: We are hiring an InnoCORE postdoctoral researcher for 2027! Details →
- AGA Lab participates in KIAS Center for AI and Natural Sciences Workshop. Sangwoong gives an invited talk.
- Sangwoong gives a seminar at the Department of Electrical Engineering and Computer Science, DGIST, hosted by Professor Chang-Eop Kim.
- GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models is accepted at NeurIPS 2026
- Rethinking Knowledge Distillation for Diffusion Language Models is accepted at NeurIPS 2026
- Sangwoong attends ICML 2026 in Seoul, Republic of Korea
- Sangwoong co-hosts Post-ICML@UNIST workshop.
- Sangwoong gives a talk at 2026 KSIAM Spring Conference at UNIST
- Multi-Task GRPO: Reliable LLM Reasoning Across Tasks is accepted at ICML 2026
- RSPO: Regularized Self-Play Alignment of Large Language Models is accepted at ICML 2026
- Awarded funding for supporting post-doctoral researchers. AGA Lab participates in the InnoCORE program as a member of the BIO-MAX research group