Jaehyun Kang

Research Engineer @ RLWRLD

profile.jpg

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! :sparkles: Check out our paper and project website.
Jul 02, 2024 One paper accepted to ECCV 2024.

Publications

(* indicates equal contributions)

  1. UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations thumbnail
    UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
    CoRL 2025
  2. VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement thumbnail
    VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement
    ECCV 2024
  3. Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learning thumbnail
    Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learning
    Jinwoo Kim* , Janghyuk Choi* , Jaehyun Kang , Changyeon Lee , Ho-Jin Choi , Seon Joo Kim
    CVPR Workshop 2024