Yujin Sung

Hi!😀 I’m a M.S. Student at Korea University, Vision & AI lab (Advisor: Prof. Jungbeom Lee & Jinkyu Kim). I earned a Bachelor’s degree in Computer Science from Korea University.

My research focuses on developing generalist robot policies that enable robots to perform diverse tasks in complex, unstructured environments. I am particularly interested in enabling robots to continually learn from real-world interaction and efficiently acquire skills from human demonstrations. Ultimately, I aim to build safe and robust robotic systems that can operate reliably in everyday environments.

Currently, I am researching about fully autonomous robot learning framework that can learn from real-world interaction without human intervention.

Email  /  CV  /  Github

profile photo

Research

AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation Jiyun Jang, Yujin Sung, Woosung Joung, Daewon Chae, Sangwon Lee, Sohwi Kim, Jinkyu Kim, Jungbeom Lee
Under Review
project / paper / code

A framework that injects action coordinate cues into RGB observations to explicitly ground the robot’s action space, improving zero-shot execution and robustness in visuomotor manipulation across diverse environments.

uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data Dahyun Chung*, Donghyun Shin*, Yujin Sung*, Seunggi Moon*, Jinwoo Jeon, Byung-Jun Lee
AAAI, 2026
project / paper / code

Lightweight framework that enables multilingual vision–language alignment for underrepresented languages by using English as a semantic pivot and requiring no paired supervision.

Website template from Jon Barron.