Xueyan Zou

Papers

Total Citations

H-Index

About

Xueyan Zou is a leading researcher at the intersection of computer vision, robotics, and natural language processing, with a primary focus on developing embodied AI systems that can understand and execute complex human instructions. His most significant contribution is the creation of **NaVILA**, a groundbreaking Vision-Language-Action (VLA) model for legged robot navigation. This work directly tackles the challenge of translating high-level human language commands—such as "proceed to the grass and stop in front of the soccer ball"—into precise, low-level motor actions for robots in unstructured environments. By integrating vision, language, and action, NaVILA enables legged robots to navigate through cluttered, real-world scenes that would be impassable for wheeled platforms, representing a major leap toward practical, general-purpose home assistants. His work on NaVILA has already garnered over 15 citations within its first year, signaling strong interest from the robotics and AI communities. Zou’s research is notable for its direct, real-world applicability, bridging the gap between abstract linguistic concepts and physical robotic control, and positioning him as a key figure in the future of autonomous navigation.