Kyowoon Lee

I’m a postdoctoral researcher in SAIL at Korea Advanced Institute of Science and Technology (KAIST). I received my B.S. and Ph.D. degrees from Ulsan National Institute of Science and Technology (UNIST) under the supervision of Prof. Jaesik Choi. I’m interested in developing reliable and data-efficient reinforcement learning (RL) algorithms.

Publications

(*) denotes equal contribution

  • State-Covering Trajectory Stitching for Diffusion Planners
  • Kyowoon Lee, Jaesik Choi
  • Preprint
  • [Paper] [Code]
  • Counterfactual Activation Editing for Post-hoc Prosody and Mispronunciation Correction in TTS Models
  • Kyowoon Lee, Artyom Stitsyuk, Gunu Jho, Inchul Hwang, Jaesik Choi
  • Interspeech 2025
  • [Paper]
  • Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning
  • Kyowoon Lee, Jaesik Choi
  • ICML 2025
  • [Paper] [Code]
  • Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans
  • Kyowoon Lee*, Seongun Kim*, Jaesik Choi
  • NeurIPS 2023
  • [Paper] [Code] [Project]
  • Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills
  • Seongun Kim*, Kyowoon Lee*, Jaesik Choi
  • ICML 2023
  • [Paper] [Code] [Project]
  • Adaptive and Explainable Deployment of Navigation Skills via Hierarchical Deep Reinforcement Learning
  • Kyowoon Lee*, Seongun Kim*, Jaesik Choi
  • ICRA 2023
  • [Paper] [Code] [Project]
  • Confirmatory Bayesian Online Change Point Detection in the Covariance Structure of Gaussian Processes
  • Jiyeon Han*, Kyowoon Lee*, Anh Tong, Jaesik Choi
  • IJCAI 2019
  • [Paper] [Project]
  • Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling
  • Kyowoon Lee*, Sol-A Kim*, Jaesik Choi, Seong-Whan Lee
  • ICML 2018
  • [Paper] [Code] [Project]