3 papers
cs.RO2026
CompVLA: A Variable Compliance Vision-Language-Action Model for Contact-rich Manipulation
Jongmin Kim, Junsu Ha, Che-Sang Park +5
Contact-rich manipulation, requiring robots to regulate not only motion but also how they yield to external forces, has emerged as the next frontier for Vision-Language-Action (VLA…
cs.RO2026
Spatial Attention: Adapting Execution Horizons for Diffusion Policies via Observation Sensitivity
Che-Sang Park, Junsu Ha, Jianlong Fu +1
Sampling action chunks via generative models has become a widely adopted methodology for robotic learning from demonstration. However, existing methods often struggle to balance re…
cs.RO2025
ScrewSplat: An End-to-End Method for Articulated Object Recognition
Seungyeon Kim, Junsu Ha, Young Hun Kim +2
Articulated object recognition -- the task of identifying both the geometry and kinematic joints of objects with movable parts -- is essential for enabling robots to interact with…