Nvidia's model GR00T 2 watches humans on video, then imagines itself as the robot
Live
- Newsrooms
- 2
- Last 3 hours
- 0 reports
- Momentum
- Quiet
Reports per hour, last 24 hours
1Nvidia'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
In The Decoder’s words.2
The story so far
2 newsrooms- Reports
- 2
- Newsrooms and sources
- 2
- Last 3 hours
- 0
First with it: The Next Web, 1 day before anyone else.
Reported by 2 newsrooms.
The numbers behind it
How it spread, where it’s heading and where the coverage is from
Reports a day, last 7 days
| Day | Stories |
|---|---|
| Thu | 0 |
| Fri | 0 |
| Sat | 0 |
| Sun | 0 |
| Mon | 0 |
| Tue | 1 |
| Today | 1 |
Every report, in order
2 reports from 2 newsrooms, first to latest. Each links to the original.



