I am a Staff Engineer in the Robotics AI Group, Robotics eXperience Office at Samsung Electronics, where I designed and trained an in-house Vision-Language-Action (VLA) model for Samsung's humanoid robots. Currently, I am advancing it with memory architectures and in-context learning. More broadly, my research interests lie in robot learning, including VLAs, WAMs, reinforcement learning, and agentic decision-making of embodied agents powered by frontier foundation models.
Previously, I worked as an AI Robotics Researcher at Sequor Robotics, Inc. I obtained my Ph.D. degree in Electrical and Computer Engineering from Seoul National University (SNU) in 2024, advised by Songhwai Oh at Robot Learning Laboratory. I got my bachelor's degree in Electrical and Computer Engineering with highest honors from SNU as well in 2017.
Representative papers are highlighted.
Please check my Google Scholar profile for a full paper list.
Shallow-π: Knowledge Distillation for Flow-based VLAs Boseong Jeon, Yunho Choi, and Taehan Kim IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026.   (Best Paper Award Finalist) project page
/
arXiv
/
code
/
video
KG-Nav: Bridging the Gap between Visual Servoing and Image-Goal Navigation via Keypoint Graph-Based Reinforcement Learning Yunho Choi, Jaeseok Heo, Nuri Kim,
and Songhwai Oh. Preprint, 2023.  
preprint
/
Ph.D. dissertation