Jaehyun Kang
Research Engineer @ RLWRLD
I am a research engineer at RLWRLD. I received my M.S. and B.S. in Computer Science from Yonsei University, where I was advised by Prof. Seon Joo Kim in CIPLAB. I also had the fortunate opportunity to collaborate with Prof. Youngwoon Lee.
My research focuses on Dexterous VLA — building vision-language-action models that enable robotic hands to perform complex manipulation tasks. I’m particularly interested in bridging human video understanding and robot action, leveraging large-scale human demonstrations to ground dexterous manipulation skills. Previously, my work explored video understanding and robot learning, which continues to shape my current focus on transferring knowledge from human demonstrations to robot policies at scale.
News
| Aug 01, 2025 | UniSkill is accepted to CoRL 2025 ! |
|---|---|
| Jun 16, 2025 | Joined RLWRLD as a Research Engineer! |
| May 13, 2025 | UniSkill is out! |
| Jul 02, 2024 | One paper accepted to ECCV 2024. |
Publications
(* indicates equal contributions)
-
UniSkill: Imitating Human Videos via Cross-Embodiment Skill RepresentationsCoRL 2025 -
VISAGE: Video Instance Segmentation with Appearance-Guided EnhancementECCV 2024 -
Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric LearningCVPR Workshop 2024[Paper]