Vision-Language-Action Models for Self-working Humanoid Robots

Recent advances in foundation models are extending AI beyond perception and language understanding toward embodied systems that can perceive, reason, and act in the physical world. This transition is accelerating the development of vision-language-action (VLA) models and robot foundation models that aim to provide robots with more general, adaptive, and deployable intelligence.
This talk presents recent progress toward self-working humanoid robots, covering key ideas in embodied AI such as multimodal understanding, long-horizon planning, action generation, and real-world deployment. It also introduces recent research from Seoul National University BI Lab and AI Institute on human-robot interaction, personalization, continual adaptation, and language-conditioned robot learning, together with the Habilis framework developed at Tommoro Robotics for deployable humanoid intelligence.
Finally, the talk discusses a future architecture for self-working humanoids that integrates perception, memory, reasoning, planning, and action into a unified learning system. The central theme is that while large language models enabled machines to communicate, vision-language-action models will enable machines to work autonomously in the real world.

Byoung-Tak Zhang's biography
Present:         
Professor of Computer Science, Seoul National University,
Director of the Humanoid AI Robot Center (HARC),
Chairman of the K-Humanoid Alliance (Korean Government)
2019-2025:     
Founding Director of SNU AI Institute (AIIS)
2007-2008:     
Visiting Professor, Samsung Advanced Institute of Technology
2003-2004:     
Visiting Professor, MIT CS&AI Lab (CSAIL)
1992-1995:     
Research Associate, German National Research Center for Computer Science (GMD)
1988-1992:     
PhD in Computer Science, University of Bonn
1982-1988:     
BS and MS in Computer Science, Seoul National University