# NVIDIA unveils GR00T 2, a model that predicts robot video and actions together

> NVIDIA says GR00T 2 predicts future video and robot actions together, reaching 40% zero-shot success on 50 unseen tasks and 95% after fine-tuning on five demonstrations per task.

- Status: reported (One outlet, not independently verified yet.)
- Topic: Models
- Published: 2026-11-10T01:32:23+00:00
- Updated: 2026-11-10T02:10:46.912756+00:00
- Web page: https://ai-news.ikangai.com/story/nvidia-unveils-gr00t-2-a-model-that-predicts-robot-video-and-actions-together/
- Seen in: Turing Post
- Change: capability (New capability)
- Applies to: GR00T 2

## What changed

NVIDIA introduced GR00T 2, a robot model that predicts future video and robot actions together, with code planned for release in December.

NVIDIA introduced GR00T 2 on Monday. The robot model predicts future video and robot actions together. On 50 tasks that the target robot had not previously been shown, NVIDIA reports 40% average zero-shot success, meaning the robot attempted the tasks without any demonstrations for them. That figure rises to 95% after fine-tuning on five demonstrations per task.

The zero-shot number deserves a close read, because it measures performance before the model sees any examples of a new task. According to NVIDIA's figures, success was 71% with a single demonstration per task. The gains come in steps: about 40% with none, 71% with one, and 95% with five. NVIDIA describes the mechanism as the model predicting the next video frames and the robot's next actions together.

Code is planned for December, so outside researchers cannot yet run the model on their own hardware.

## Why it matters

Robotics teams can see a path to deploying new robot tasks from a handful of demonstrations, though the code is not yet released.

## What you can do

Add GR00T 2 to your evaluation list and plan testing once NVIDIA releases the code, which is planned for December.

---

AI wrote this summary from the sources listed, and nobody reviewed it individually before publication. Check the original source before you rely on it.

Cite as: IKANGAI AI News, "NVIDIA unveils GR00T 2, a model that predicts robot video and actions together", 2026-11-10, https://ai-news.ikangai.com/story/nvidia-unveils-gr00t-2-a-model-that-predicts-robot-video-and-actions-together/
