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. |
||