Papers
1
Total Citations
2
H-Index
1
About
Zhi Xue is a rising researcher at the forefront of robotic manipulation and language-guided AI, with a focus on bridging natural language instructions and physical action. Their most notable contribution is the development of DISCO (Diffusion Policies with Constrained Inpainting), a pioneering framework that leverages diffusion models to enable robots to follow open-vocabulary language commands in everyday environments. This work addresses a critical challenge in robotics: generalizing beyond fixed, pre-trained instructions to handle the unpredictable variety of human language. By combining diffusion policies with constrained inpainting, Xue’s approach allows for more flexible and robust manipulation, even in cluttered or novel settings. Though early in their career—with their flagship paper already garnering 2 citations shortly after its 2025 release—Xue’s research signals a significant step toward more adaptive and user-friendly robotic systems. Their work is particularly relevant for students and researchers interested in the intersection of generative AI, embodied intelligence, and human-robot interaction.
Research Focus
Key Achievements
Top Papers
- 1