Yu-Xiong Wang

Carnegie Mellon University, University of Illinois Urbana-Champaign

Papers

Total Citations

271

H-Index

About

Yu-Xiong Wang is a leading researcher at the intersection of computer vision, robotics, and embodied AI, with a core focus on enabling machines to perceive, predict, and interact intelligently with dynamic 3D environments. His major contributions span two critical frontiers: human-robot interaction and comprehensive 3D scene understanding. In seminal work on human motion prediction, Wang pioneered few-shot meta-learning approaches that allow robots to anticipate human actions from minimal observations—a foundational capability for safe collaboration, with his 2018 papers each garnering 125 citations. More recently, he has advanced 3D vision-language reasoning, demonstrating that situational awareness is a distinct and critical challenge for household robots, and introduced novel neural radiance field-based methods for synthesizing scene properties beyond standard RGB, enabling richer geometric and semantic understanding. His work on teaching robots to predict human motion directly addresses a crucial first step in human-robot collaboration, while his latest research pushes toward embodied AI that can reason about complex 3D spaces. Wang’s research program is shaping how autonomous systems perceive, anticipate, and act in the human-centered world.