Generative Foundation Models for Robotics:
From Language and Vision to Embodied Action

The convergence of generative foundation models with robotics represents a paradigm shift toward truly intelligent, adaptable robotic systems. This special event explores how large-scale generative models—including language models, visual language models, diffusion models, flow matching, variational autoencoders, and normalizing flows—are revolutionizing robotics by bridging the gap between high-level semantic understanding and low-level motor control, enabling robots to understand natural language instructions, perceive complex visual scenes, and execute sophisticated robotic tasks in complex environments.