NVIDIA's Cosmos 3 teaches physical AI to think before acting
NVIDIA just unveiled Cosmos 3 at GTC Taipei, an open-world foundation model built to give robots and autonomous vehicles physical common sense. Using a mixture-of-transformers setup, it combines visual reasoning with native action prediction, spitting out joint angles and trajectory points directly. It is now open-sourced on Hugging Face to help embodied AI predict before it moves.