Mar – Sep 2026
Microsoft Research Asia
Intern · Machine Learning Group
On-site, Beijing. Research collaboration ongoing.
Prior-Guided Diffusion Planning for Offline Reinforcement Learning
Donghyeon Ki, JunHyeok Oh, Seong-Woong Shim, Byung-Jun Lee
Donghyeon Ki
I am a third-semester Ph.D. student in Artificial Intelligence at Korea University, advised by Prof. Byung-Jun Lee in the Decision Making Lab. My research focuses on reinforcement learning, with a recent interest in robotics.
Accepted papers
Adaptive Non-Uniform Timestep Sampling for Accelerating Diffusion Model Training
Myunsoo Kim*, Donghyeon Ki*, Seong-Woong Shim, Byung-Jun Lee
* Equal contribution
Relaxed Stationary Distribution Correction Estimation for Improved Offline Policy Optimization
Woosung Kim, Donghyeon Ki, Byung-Jun Lee
arXiv papers
Score-Based One-step MeanFlow Policy Optimization
Kyungyoon Kim, Donghyeon Ki, Hee-Jun Ahn, Byung-Jun Lee
Direct Soft-Policy Sampling via Langevin Dynamics
Donghyeon Ki, Hee-Jun Ahn, Kyungyoon Kim, Byung-Jun Lee
Actor-Critic without Actor
Donghyeon Ki, Hee-Jun Ahn, Kyungyoon Kim, Byung-Jun Lee
Experience
Education
Sep 2024 – Present
Korea University
Integrated M.S.–Ph.D. in Artificial Intelligence
Entered graduate school in September 2022.
Mar 2018 – Aug 2022
Korea University
B.S. in Biomedical Engineering