Multimodal large language models (MLLMs) are good at video understanding and code generation, but it remains unclear whether they can recover the physical laws underlying videos, a capability essential for converting videos into executable simulations and for providing structured physical supervision in robotics. Capti...
Souraja Kundu, A. Gupta, Joel Julin et al.· 0 citations
Adapting robotic manipulation to new objects and tasks often requires additional demonstrations or manual engineering. Reusable manipulation skills can reduce this effort, but adapting these skills to new scenes remains challenging. We present ManiSkillFormer, a framework for demonstration-free and compositional manipu...
Pei-Qi Yu, Mosam Dabhi, Shan Li et al.· 1 citation
MAD-HOI is a model performing Masked Autoregression with Diffusion with Diffusion for HOI generation that is capable of motion generation for atomic and composite articulated sequences, conditioned motion completion and infilling, as well as EOM prediction from a single training objective.
Ananya Bal, Kartik Sharma, E. Lai et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.