Heewoong Choi

I’m a Ph.D. student at Seoul National University, advised by Taesup Moon.

I aim to build adaptive AI agents that reason, plan, and act reliably in the real world. I approach this through reinforcement learning, world models, and self-evolving agents.

My earlier work focused on scalable RL algorithms that improve with more data and generalize over long horizons.

Education

Mar. 2023 - Present	Seoul National University Ph.D. student in Electrical and Computer Engineering M.IN.D Lab (Advisor: Taesup Moon)
Mar. 2017 - Feb. 2023	Seoul National University B.S. in Electrical and Computer Engineering Leave of absence for military service (Mar. 2019 - Feb. 2021)

Publications

(*: equal contribution)

[C4] Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning

Hongjoon Ahn*, Heewoong Choi*, Jisu Han*, Taesup Moon

NeurIPS 2025 (Spotlight)

paper | code | project page

[C3] Genomic Data Classification via Universal Compression

Yasmine Omri, Naomi Sagan, Eugene Min, Heewoong Choi, Taesup Moon, Tsachy Weissman

ISMB/ECCB 2025

[C2] Listwise Reward Estimation for Offline Preference-based Reinforcement Learning

Heewoong Choi, Sangwon Jung, Hongjoon Ahn, Taesup Moon

ICML 2024

paper | code | project page

[C1] NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbations

Sungmin Cha, Naeun Ko, Heewoong Choi, Youngjoon Yoo, Taesup Moon

WACV 2024

Work Experience

Jun. 2022 - Nov. 2022

NAVER CLOVA, AI engineer intern at CLOVA Image-Vision team

Developed a head pose estimation model for real-time applications.

Honors

Mar. 2017 - Feb. 2023

Presidential Science Scholarship

Full enrollment fee from Korea Student Aid Foundation (KOSAF)