Zizhang Li
Papers
2
Total Citations
53
H-Index
2
About
Zizhang Li is a robotics researcher whose work sits at the intersection of computer vision, natural language processing, and robotic manipulation. His primary research areas include language-conditioned robotic grasping, vision-language-action joint modeling, and self-assessable policy learning for safe robot execution. Li’s most impactful contribution is his pioneering work on target-oriented grasping in cluttered environments, where he proposed a unified framework that jointly models vision, language, and action—moving beyond the traditional two-stage approach of separate visual grounding and grasp generation. This work, published in 2023, has already accumulated 50 citations, signaling its rapid influence in the field. In parallel, Li has advanced the concept of self-assessment in robotics, developing failure-aware policy learning methods that enable robots to evaluate the feasibility of their own actions before execution, a critical step toward safe and reliable real-world deployment. His research is particularly notable for addressing the gap between perception and action in human-robot interaction, making robots more responsive to natural language commands. As an emerging researcher, Li’s work is shaping the future of intelligent, language-guided robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Failure-aware Policy Learning for Self-assessable Robotics Tasks3 citations · 2023