NVIDIA's DreamZero Enables Zero-Shot Robot Control Through World Models

NVIDIA Research unveiled DreamZero, a World Action Model that lets robots perform tasks they've never been trained on by simulating physics internally before acting.

NVIDIA senior research scientist @DrJimFan announced DreamZero, a new World Action Model (WAM) that enables "zero-shot open-world prompting for robots." The system uses an internal world model — essentially a learned physics simulator — to plan actions for tasks the robot has never explicitly trained on. The key insight is cross-embodiment via pixels: rather than training separate models for each robot form factor, DreamZero learns from diverse visual data and generalizes.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief