Zejun Yang
Papers
1
Total Citations
13
H-Index
1
About
Zejun Yang is at the forefront of integrating large language models with robotic task planning, a field where his work is redefining how autonomous systems adapt to dynamic environments. His key research areas span reactive task planning, human-robot interaction, and the application of foundation models in robotics. Yang’s major contribution lies in bridging the gap between rigid, rule-based planners and the flexibility required for real-world deployment. His highly cited 2024 paper, “Text2Reaction: Enabling Reactive Task Planning Using Large Language Models,” introduces a novel framework that leverages LLMs to generate and revise plans on the fly, eliminating the need for meticulously predefined rules or extensive labeled datasets. This work has already garnered 13 citations, signaling its immediate impact on the robotics community. By enabling robots to interpret environmental changes through natural language, Yang’s research paves the way for more intuitive and resilient autonomous systems. His achievements highlight a promising trajectory in making robots truly adaptive partners in complex, unstructured settings—a critical step toward practical deployment in homes, factories, and beyond.
Research Focus
Key Achievements
Top Papers
- 1Text2Reaction : Enabling Reactive Task Planning Using Large Language Models13 citations · 2024