Jaehyun Kang

Graduate Student | Yonsei University | Computer Science

jaehyun_43.jpg

I am a final-semester M.S. student in Computer Science at Yonsei University, advised by Prof. Seon Joo Kim in the Computational Intelligence & Photography Lab (CIPLAB). I received my B.S. in Computer Science from Yonsei University as well.

My research focuses on Robot Learning and Video Understanding, actively collaborating with Prof. Youngwoon Lee. Recently, I’m interested in developing robotics foundation models for generalist agents. This includes leveraging VLAs and large-scale video datasets, including egocentric videos – to learn and utilize the priors of the world. My long-term ambition is to build embodied agents capable of adapting to novel scenes and tasks, ultimately contributing to a society where humans and robots coexist.

News

May 13, 2025 UniSkill is out! :sparkles: Check out our paper and project website.
Jul 02, 2024 One paper accepted to ECCV 2024.
May 03, 2024 One paper accepted to CVPR Workshop on “Causal and Object-Centric Representations for Robotics” 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
    Preprint
  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