# NVIDIA GR00T 2 predicts video and robot actions

> NVIDIA reports manipulation tests and plans December code.

By BIGCHANGE.AI Editorial

Published: 2026-11-10T02:05:37.994Z
Updated: 2026-11-10T02:05:37.994Z
Canonical: https://bigchange.ai/blog/nvidia-gr00t-2-robot-world-action-model

![A robotic gripper positions filter paper over a laboratory funnel.](https://bigchange.ai/api/media/file/groot2-concept.png)
AI-generated illustration for BIG CHANGE

NVIDIA [introduced GR00T 2](https://blogs.nvidia.com/blog/robotics-simulation-advancements-corl/) on November 9. The model predicts future video and robot actions together, executing action chunks in a repeated control loop.

## The big change

- **The change:** Prediction informs motion.
- **Why it matters:** Human demonstrations can provide examples without repeating every task on a target robot.
- **What to watch:** Physical success requires testing with real equipment and surroundings.

## Learning from demonstrations

Robot manipulation involves choosing a movement and coping with how objects respond. NVIDIA’s earlier [DreamZero paper](https://arxiv.org/html/2602.15922v1) studied joint video and action prediction and transfer from humans or other robots. In that earlier study, adding human video raised average progress on unseen tasks from 38.3% to 54.3%; the researchers describe it as an early signal, with moderate success rates. A demonstration can help describe a skill without providing a trajectory for the target robot’s own joints. Different hands and surroundings can still make execution difficult: a plausible predicted scene does not prove that a real grasp will succeed.

## What the test found

The [project page](https://research.nvidia.com/labs/gear/gr00t-2/) reports 40% average zero-shot success across 50 tasks seen in human or other-robot data but absent from the target two-handed robot’s task data. Five demonstrations per task, each set under three minutes, raised the reported average to 95% after a 30-minute LoRA fine-tune per task on one RTX 5090. Without those demonstrations, 40 of the 50 tasks succeeded at least once.

The company-reported physical-robot test is not independent validation or evidence of routine commercial deployment.

## What developers can use

NVIDIA plans code for December; current GR00T 2 weight availability is not established on the project page. The existing [Isaac GR00T repository](https://github.com/NVIDIA/Isaac-GR00T) provides code and weights for the earlier N1.7 model. That is a separate release.

## Sources

- [GR00T 2: Scaling Robot Foundation Models for Generalization, Dexterity, and Adaptation](https://research.nvidia.com/labs/gear/gr00t-2/) — NVIDIA describes its model, tests and planned code release.
- [World Action Models are Zero-shot Policies](https://arxiv.org/html/2602.15922v1) — Earlier research describes joint video and action prediction.
- [NVIDIA Isaac GR00T repository](https://github.com/NVIDIA/Isaac-GR00T) — Repository documents the earlier N1.7 release.