- Who
- NVIDIA
- What
- introduced GR00T 2, an open robotics model
- Quote
Introducing GR00T 2: our most advanced, open System One model for robotics.
What happened
Jim Fan introduces GR00T 2 as an open System One model for robotics that runs on a robot’s onboard compute. He describes tasks spanning 20+ steps and 5+ minutes, X-Adapt for adapting from human wearables and simulation before zero-shot deployment to diverse real robots, and integrations with frontier agents. The post says the model weights, agentic framework, simulation engine, annotation engine, hardware design, and 100K hours of training data are available today; X-Adapt recipes are coming in December.
Why it matters
The post outlines GR00T 2's long-horizon tasks, adaptation approach, and bundled open resources, giving readers a concrete view of the release's scope.
Read next
See the full storyNVIDIA Introduces GR00T 2 and Shares Real-Time Robot DemonstrationIntroducing GR00T 2: our most advanced, open System One model for robotics. It runs entirely on your robot’s onboard compute, fully untethered, and you own every weight of it. GR00T 2 features:
- Long-horizon tasks: dexterous manipulation and whole-body control chained over 20+ steps and 5+ minutes, such as performing chemistry lab experiments or assembling model airplanes end to end.
- X-Adapt: adapting from easy data sources (human wearables and simulation) and deploying zero-shot to diverse real robots.
- Unified Cognition: native integrations with frontier agents for advanced physical reasoning, robust error recovery, and safety monitoring.
It's an open-source buffet! We are releasing not only the model weights and X-Adapt recipes (coming December), but also our agentic framework, simulation engine, annotation engine, hardware design, and even training data (100K hours, that's ~11 yrs of experience), all available today!
Everything that moves will be autonomous. Anyone can become a roboticist.
Lock in, build with us!
Deep dive in thread:
The story so far
NVIDIA introduced GR00T 2 as an open robotics model designed to run on a robot’s onboard compute, and Jim Fan later shared a video of it controlling dexterous hands through a chemistry experiment and cleanup. Fan described the footage as autonomous, uncut, and shown at real-time speed. Fan said GR00T 2 handles tasks spanning more than 20 steps and five minutes, and that X-Adapt can use human-wearable and simulation data to adapt it for zero-shot deployment on different real robots. NVIDIA says the model weights, agentic framework, simulation and annotation engines, hardware design, and 100,000 hours of training data are available now; X-Adapt recipes are expected in December.
How the story developed · 2
View full event- 11/12 00:02 (UTC+8)Jim Fan Shares Real-Time Footage of GR00T 2 Running a Chemistry Lab ExperimentJim Fan · X
- 11/11 00:51 (UTC+8)
Jim Fan Introduces GR00T 2, an Open Robotics Model for Onboard Compute This report