2 papers
cs.RO2026
DexForge: High-Fidelity Physics-Informed Dexterous Retargeting
Meizhong Wang, Kun Cao, Ruiqi Ni +2
Human demonstrations offer rich examples of precise dexterous manipulation and a promising source of robot training data. However, high-fidelity reproduction of demonstrated motion…
cs.RO2026
ContactGaussian-WM: Learning Physics-Grounded World Model from Videos
Meizhong Wang, Wanxin Jin, Kun Cao +2
Developing world models that understand complex physical interactions is essential for advancing robotic planning and simulation.However, existing methods often struggle to accurat…