Physical AI needs to understand the world before it can act in it.

Introducing Cosmos 3, the open world foundation model and the first omni-model for physical AI.

It understands and generates across text, image, video, sound and action – thanks to a new breakthrough… https://t.co/K5RyHTY7gW

— NVIDIA (@nvidia) 4 juin 2026

Physical AI needs to understand the world before it can act in it. Introducing Cosmos 3, the open world foundation model and the first omni-model for physical AI. It understands and generates across text, image, video, sound and action – thanks to a new breakthrough

→ View original post on X — @nvidia