Clean implementation of generative models, designed for robot learning

Unfied World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

A generative and self-guided robotic agent that endlessly propose and master new skills.

A generative world for general-purpose robotics & embodied AI learning.