NVIDIA Cosmos 3 is an open Mixture-of-Transformers world model family unifying physical reasoning, world generation, and action generation.

A Blog post by NVIDIA on Hugging Face

Physical AI systems must understand the real world before they can act within it. Robots, autonomous vehicles, and smart spaces need to understand what’s happening in their world…

The new, open NVIDIA world foundation model brings vision reasoning, multimodal generation and action prediction together to help robots, autonomous vehicles and vision AI agents…

The chip giants aims to become a platform for physical AI.

Nvidia's Cosmos 3 world model generates 30-second predictive videos to help robots navigate real-world environments, building on adoption by Figure AI and Uber.

Nvidia used GTC Taipei to launch a series of models for robots, autonomous vehicles, and video systems. The centerpieces are the new world model Cosmos 3, a significantly…

NVIDIA Cosmos 3 is an open Mixture-of-Transformers world model family unifying physical reasoning, world generation, and action generation.

Nvidia stellt Cosmos 3 als Weltmodell vor. Sie werden oft als „wichtiger Schritt“ zur Superintelligenz bezeichnet. Was ist ein Weltmodell?