Xunlong Xia
Papers
1
Total Citations
2
H-Index
1
About
Xunlong Xia is a rising researcher at the forefront of embodied intelligence, whose work bridges perception, language, and action in 3D environments. His primary research focuses on grounding 3D object affordance—the task of precisely locating where and how objects can be manipulated by intelligent agents like robots. In his highly cited 2025 work, Xia introduced a novel framework that integrates language instructions, visual observations, and physical interactions to teach machines not just to see objects, but to understand their functional possibilities. This contribution is pivotal for enabling robots to follow human commands and grasp objects correctly in complex, real-world spaces. Though early in his career, his paper has already garnered 2 citations, signaling growing interest in his approach to linking high-level language with low-level robotic control. Xia’s work stands out for its practical focus on closing the gap between human instruction and machine execution, making him a promising voice in the fields of embodied AI, 3D scene understanding, and human-robot interaction. His research is essential reading for anyone interested in how robots can learn to interact with the world as humans do.
Research Focus
Key Achievements
Top Papers
- 1