Kyungyoon Kim

M.S. Student, Graduate School of AI, Korea University · Decision Making Lab (DM-Lab)

prof_pic.jpg

I am an M.S. student at the Graduate School of Artificial Intelligence, Korea University, where I am a member of the Decision Making Lab (DM-Lab) advised by Prof. Byung-Jun Lee.

My research centers on reinforcement learning and generative models. I am especially interested in the intersection of the two—leveraging generative models to advance reinforcement learning. I am also drawn to robotics as a setting where these methods come together.

Before joining Korea University, I completed the Naver BoostCamp AI Tech program (Computer Vision track) and earned a B.B.A. from Kyung Hee University. Feel free to reach out via email.

News

Jul 2026 Ongoing joint research with Microsoft Research Asia on VLA + teleoperation. 🤖
May 2026 Our paper “Score-Based One-step MeanFlow Policy Optimization” is now available on arXiv. 🎉
Feb 2026 Our paper “Direct Soft-Policy Sampling via Langevin Dynamics” is available on arXiv. 🎉
Sep 2025 Started my M.S. in Artificial Intelligence at Korea University, joining the Decision Making Lab (DM-Lab). 🎓
Feb 2025 Completed the Naver BoostCamp AI Tech program (Computer Vision track). See the projects page. 🚀

Publications

  1. arXiv
    Score-Based One-step MeanFlow Policy Optimization
    Kyungyoon Kim, Donghyeon Ki, Hee-Jun Ahn, and Byung-Jun Lee
    arXiv preprint arXiv:2605.23365, 2026
  2. arXiv
    Direct Soft-Policy Sampling via Langevin Dynamics
    Donghyeon Ki, Hee-Jun Ahn, Kyungyoon Kim, and Byung-Jun Lee
    arXiv preprint arXiv:2602.07873, 2026