Zhijie Yan
Papers
2
Total Citations
51
H-Index
2
About
Zhijie Yan is a leading researcher at the intersection of computer vision, robotics, and industrial automation, with a primary focus on advancing spatial intelligence through scene graph generation. His most significant contributions lie in developing Vision Language Model (VLM)-based frameworks that bridge the gap between high-level semantic understanding and low-level geometric reasoning for complex manufacturing environments. Yan’s seminal work, "IndVisSGG," introduced a novel approach to industrial scene graph generation, enabling machines to parse and interpret cluttered factory floors with unprecedented accuracy, garnering 35 citations since its 2025 publication. He further extended this paradigm with "VLM-MSGraph," which proposes a multi-hierarchical scene graph architecture specifically tailored for robotic assembly tasks, achieving 16 citations. By integrating VLMs with structured graph representations, Yan has enabled robots to dynamically understand part relationships, tool usage, and assembly sequences—a critical step toward fully autonomous manufacturing. His research not only pushes the boundaries of embodied AI but also provides a scalable foundation for smart factories, demonstrating how language-guided visual reasoning can transform industrial spatial intelligence from a theoretical concept into a practical, deployable technology.
Research Focus
Key Achievements
Top Papers
- 1
- 2