VLA Models
Vision-Language-Action agents that combine perception, language understanding, and motor control for embodied AI.
Physical AI
Physical AI
Physical AI systems that combine perception, language, and action for embodied intelligence.
Physical AI represents the convergence of the AI and robotics tracks — systems that perceive the world, reason about it using language and vision, and act in physical environments.
This section covers Vision-Language-Action (VLA) models and the broader Physical AI landscape where foundation models meet embodied systems.