Latest
  1. Anthropic publishes guidance on building AI safety evaluations, with figures from its own tests
  2. Pentagon renames its Chief Digital and AI Office the Super Intelligence Office
  3. Donor software firm Mythos sues Anthropic over its Mythos model name
  4. OpenAI launches ChatGPT Wallet so its dots agents can complete purchases
  5. Cohere completes its AISLE acquisition and adds AI code-review company cubic
  6. Firm founded by Alice Huang listed restricted Nvidia servers in Chinese filings, Bloomberg reports
  7. Senate Banking chair asks Jensen Huang and Howard Lutnick to testify on Nvidia
  8. Tasmania’s AI data centres would each run their own community benefit fund

Latest / Frontier models and safety

ResearchFrontierScienceInternationalConfirmed

NVIDIA introduces GR00T 2, a robot model that predicts video and actions

See how this story connects

Source: NVIDIA ResearchAlso reported by GR00T 2 white paper (PDF), The Decoder

NVIDIA Research introduced GR00T 2, a foundation world-action model that predicts future video and robot actions together and runs on parallel grippers, dexterous hands and humanoids. On 50 tasks never seen on the target robot, it succeeds 40% of the time zero-shot, rising to 95% after five demonstrations under 3 minutes of robot data and a 30-minute fine-tune on one RTX 5090. GR00T 2 Turbo runs on the Unitree G1 humanoid, with each prediction taking 124 ms on the robot’s own Jetson Thor.

Why it matters

NVIDIA reports that five demonstrations per task, under 3 minutes of robot data, lifted success on 50 unseen tasks from 40% to 95% after a 30-minute fine-tune on one RTX 5090.

When
10 Nov 2026
ID
WTA-N-2026-0819
Who
NVIDIA

Summary written with AI by wheresthe.ai, from NVIDIA Research and the reporting credited above. Checked against the source on 10 Nov 2026.

Read the original at NVIDIA Research

Source copy: saved on 10 Nov 2026 to check this story and not republished, because the text belongs to its publisher. Also held by the Internet Archive.

Cite this story

WTA-N-2026-0819: “NVIDIA introduces GR00T 2, a robot model that predicts video and actions.” wheresthe.ai, 10 Nov 2026. https://wheresthe.ai/d/intl-nvidia-introduces-gr00t-2-a-robot-model-that-predicts-vid-2026-11/ (source: NVIDIA Research).

Spotted an error? Email [email protected].