Jinxuan Zhu
Papers
1
Total Citations
3
H-Index
1
About
Jinxuan Zhu is a rising researcher in embodied AI and robotic manipulation, with a focus on bridging high-level reasoning and low-level physical skills. Their most cited work, "Manual2Skill," introduces a novel framework that enables robots to interpret human-written assembly manuals using vision-language models and autonomously acquire the dexterous skills needed for furniture assembly. This contribution addresses a critical gap in robotics: the ability to generalize from symbolic instructions to real-world, contact-rich tasks. By leveraging large language models and visual grounding, Zhu’s approach reduces the need for task-specific programming, advancing toward more adaptable and intelligent robotic assistants. Although early in their career, with the 2025 paper already garnering 3 citations, Zhu’s work signals a significant step in integrating natural language understanding with robotic skill acquisition. Their research sits at the intersection of computer vision, natural language processing, and robot learning, promising to make household and industrial automation more accessible. As a young scholar, Zhu is already shaping how future robots will learn from human knowledge—reading manuals, understanding context, and building skills on the fly.
Research Focus
Key Achievements
Top Papers
- 1