TECHNOLOGYAXIOS
Nvidia's new world model helps robots navigate the world
Nvidia unveiled Cosmos 3, an open AI world model designed to help robots and autonomous vehicles understand and predict real-world environments by simulating physical actions. The model is trained on 20 trillion tokens of multimodal data, including action data from humans and robots, and aims to enable machines to navigate and manipulate the physical world more effectively.
Mentioned
Related Signal
Adjacent reporting
- ‘World models’ are AI’s latest sensation: what are they and what can they do?
- Google’s Genie world model can now simulate real streets with Street View
- Google's Latest AI Update Makes Industrial Robots Way Smarter—Here's How
- New AI brain lets robots move like humans
- I Gave My OpenClaw Agent a Physical Body
- DeepSeek promises its new AI model has 'world-class' reasoning