I am a Ph.D. student in AI Computing at KAIST, advised by Prof. Sungjin Ahn at MLML. I also received my M.S. from KAIST as a member of MLML, and my B.S. in Computer Science from KAIST.
My research focuses on World Theory Models: AI systems that construct internal theories of how the world works from observations, inspired by how humans make sense of the world through experience. My broader research interests include compositional generalization, world modeling, and reinforcement learning.
News
- Jul 2026Our paper Learning to Theorize the World from Observation received the Best Paper Award at the ICML 2026 Workshop on Compositional Learning (CompLearn).
- May 2026Our paper Learning to Theorize the World from Observation was selected for an ICML 2026 Oral Presentation.
- Mar 2026Our paper Extendable Planning via Multiscale Diffusion was selected for an oral presentation at AAAI 2026.
- Jul 2025Our paper Monte Carlo Tree Diffusion for System 2 Planning was selected as an ICML 2025 Spotlight.
Selected Publications
2026
- ICML
- AAAI
Extendable Planning via Multiscale Diffusion
2025
- ICML
Monte Carlo Tree Diffusion for System 2 Planning
2024
- ICML
Enforcing Constraints in RNA Secondary Structure Predictions: A Post-Processing Framework Based on the Assignment Problem