Seongwon Cho

I'm a first-year M.S. student at at Seoul National University advised by Prof. Jonghyun Choi. My research focuses on vision-language-action (VLA) models for open-vocabulary mobile manipulation, with an emphasis on enabling robots to adapt and operate robustly in dynamic, continuously changing real-world environments.

I received my B.S. in Computer Science from Yonsei University under the supervision of Prof. Jonghyun Choi. My prior research includes continual learning and generative model–based adaptation, which has provided a foundation for my current work on adaptive embodied intelligence and robotics.

Recently, my primary research interest is on self-evolving robot agents—agents that can autonomously improve their perception, reasoning, and action policies through interaction with the environment over long time horizons.

Email  /  Google Scholar  /  Github

profile photo

    Publications
SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models
Hyeonbeom Choi* , Daechul Ahn*, Youhan Lee , Taewook Kang , Seongwon Cho, Jonghyun Choi
arXiv, 2026
[paper (arXiv)] [bibtex] [project]
BINDER: Instantly Adaptive Mobile Manipulation with Open-Vocabulary Commands
Seongwon Cho*, Daechul Ahn*, Donghyun Shin, Hyeonbeom Choi, San Kim, Jonghyun Choi
ICRA 2026 (To appear)
[pdf] [bibtex] [code] [project page]
What Happens When: Learning Temporal Orders of Events in Videos
Daechul Ahn*, Yura Choi*, Hyeonbeom Choi* , Seongwon Cho, San Kim, Jonghyun Choi
WACV 2026 (To appear)
[paper (Coming soon)]
GenOL: Generating Diverse Examples for Name Only Online Learning
Minhyuk Seo, Seongwon Cho, Minjae Lee, Diganta Misra, Hyeonbeom Choi, Seon Joo Kim, Jonghyun Choi,
TMLR 2025
[paper]

    Awards


This template is from Jon Barron.