# Nvidia's 2-billion-parameter GR00T 2 learns chemistry-lab tasks from a handful of demonstrations and will ship open weights

Jim Fan, Nvidia's director of robotics, says a lab demo that ends with the robot cleaning up was run autonomously, uncut and at real speed on onboard compute. Weights are due in December.

- Published: 2026-11-12T06:18:53.763Z
- Canonical: https://polylog.news/ai/2026-11-12/nvidia-s-2-billion-parameter-gr00t-2-learns-chemistry-lab-ta
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [NVIDIA GEAR whitepaper](https://research.nvidia.com/labs/gear/gr00t-2/assets/gr00t2_whitepaper.pdf), [Humanoids Daily](https://www.humanoidsdaily.com/news/nvidia-gr00t-2-world-action-model-corl-2026)

Nvidia presented GR00T 2 at the Conference on Robot Learning (CoRL) in Austin on November 9. Jim Fan, Nvidia's director of robotics, described it as a 2-billion-parameter model, Humanoids Daily reported. The video that circulated most widel…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-12/nvidia-s-2-billion-parameter-gr00t-2-learns-chemistry-lab-ta (subscription information: https://polylog.news/pricing).