Jaehyun Kang
Graduate Student | Yonsei University | Computer Science

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! ![]() |
---|---|
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)
- UniSkill: Imitating Human Videos via Cross-Embodiment Skill RepresentationsPreprint
- 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]