Physical AI Is Coming: When AI Stops Generating Content And Starts Acting On The World

Nvidia introduced new open AI models at CES 2026 that enable robots to perceive, understand, and act in the physical world using vision-language-action (VLA) architecture. These robots can adapt to new objects and tasks with minimal human input, marking a shift from generative AI to physical AI with real-world consequences. This technology is already being deployed in manufacturing settings, allowing virtual training before real-world application.