Skip to content

Nvidia releases GR00T 2 robot foundation model

What happened

AI digest

On 11 November 2026, The Decoder reported that Nvidia has released GR00T 2, a world-action model (WAM). According to the report, Nvidia says in its GR00T 2 research report that the model predicts both the next action and short future video frames at once, transferring human actions from video to robot arms and reducing teleoperation training. The report does not mention when the earlier GR00T version was released, its technical details or how it differs from GR00T 2, and gives no model parameters, test data or commercialisation plans. Public information so far comes only from this one report, and the story remains at the stage of a research model release, with no disclosure yet on whether it will be opened up or how it will be deployed.

Written by AI from the reports · updated 5 d ago

Timeline

Follow the reports to see the event from each side.

Nov 11
  1. The Decoder
    Nvidia's model GR00T 2 watches humans on video, then imagines itself as the robot

    Nvidia's new AI model GR00T 2 is designed to teach robots new tasks without laborious teleoperation. Instead, the system transfers human hand movements from videos to robotic arms, trained on about 400,000 hours of video footage. Success rates still vary widely, though, ranging from 10 to 80 percent depending on the task.

Heat of this event

Current heat 3·Peak in the comparable range 9(Nov 11 05:00)·Change over 24 hours in the comparable range -49%

02.557.510Nov 1105:00Nov 1120:00Nov 1211:00Nov 1302:00

The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.