Xiaowen Qiu

Papers

Total Citations

H-Index

About

Xiaowen Qiu is a rising star in artificial intelligence, whose work sits at the critical intersection of 3D computer vision, natural language processing, and robotic action. His primary research focus is on developing generative world models that enable AI systems to not only perceive but also understand and interact with the three-dimensional physical environment. Qiu’s most notable contribution is the introduction of **3D-VLA (3D Vision-Language-Action)**, a pioneering generative world model that moves beyond traditional 2D-based vision-language-action systems. By integrating 3D spatial reasoning with language understanding and action prediction, his model allows AI to grasp the physical dynamics and object relations that govern the real world, rather than simply mapping perception to action. This breakthrough, published in 2024, has already garnered significant early attention with 14 citations, signaling its profound potential to reshape embodied AI and robotics. Through his innovative approach, Qiu is laying the groundwork for more intelligent, context-aware agents that can navigate and manipulate complex 3D environments, marking him as a key figure to watch in the next wave of AI research.