Zizheng Pan

Papers

Total Citations

105

H-Index

About

Zizheng Pan is a researcher at the forefront of embodied AI and vision-and-language navigation (VLN), with a focus on bridging the gap between natural language understanding and autonomous robotic action. His most influential work, the "Object-and-Action Aware Model for Visual Language Navigation" (2020), has garnered 98 citations, establishing him as a key contributor to this rapidly evolving field. Pan's core contribution lies in his innovative approach to parsing the dual nature of natural-language instructions in VLN: extracting both object-level information (what to look for) and action-level cues (how to move). By developing models that simultaneously attend to these two distinct linguistic signals, he has significantly improved the ability of robot agents to interpret complex, human-like commands and navigate unfamiliar environments with greater accuracy. This work addresses a fundamental challenge in embodied AI—turning abstract language into concrete, situated behavior. Pan's research continues to push the boundaries of how machines perceive, reason, and act in the physical world, making him a rising voice in the intersection of computer vision, natural language processing, and robotics.