What happened
NVIDIA introduced GR00T 2 at CoRL in Austin, describing it as a world action model that predicts future video and robot actions together. The report details three paths for transferring demonstrations across humans, handheld devices, and robots, and cites success rates of 65% on Dexter and 60% on YAM for specific tasks. NVIDIA says 100,000 hours of human data are already open, with additional model, data, simulation, and collection resources to follow.
Why it matters
The report connects GR00T 2’s cross-embodiment transfer results with its training data and supporting tools, showing how NVIDIA frames the release as a broader robotics development system.