Jingyun Xu
Papers
1
Total Citations
3
H-Index
1
About
Jingyun Xu is a rising researcher in embodied AI and robotic manipulation, with a focus on bridging vision, language, and action. Their key research areas include vision-language-action models, object-centric representation learning, and multimodal goal specification for robotics. Xu’s major contribution is the development of CrayonRobo, an object-centric prompt-driven framework that enables robots to interpret task goals across language, images, and videos—addressing the ambiguity of natural language and the overspecification of visual inputs. This work, published in 2025, has already garnered 3 citations, signaling early impact in a rapidly evolving field. Xu’s approach stands out for its practical emphasis on flexible, human-like goal understanding, which is critical for deploying robots in unstructured environments. By integrating object-level reasoning with multimodal prompts, Xu advances the frontier of generalizable robotic manipulation. Their research holds promise for making robots more intuitive to instruct and more adaptive in real-world tasks, positioning Xu as a notable contributor to the next generation of embodied agents.
Research Focus
Key Achievements
Top Papers
- 1