Mingrui Li
Papers
1
Total Citations
2
H-Index
1
About
Mingrui Li is an emerging researcher at the intersection of artificial intelligence, computer vision, and smart manufacturing systems. His work focuses on advancing cognitive manufacturing through cutting-edge vision-language model architectures, with a particular emphasis on scene graph generation (SGG) — a challenging task that enables machines and robots to semantically understand complex environments by identifying objects and their spatial and relational context. His 2024 paper, "ManufVisSGG," represents a notable contribution to this domain, addressing critical limitations in existing detection and panoptic segmentation approaches by applying vision-language models to industrial manufacturing scenarios. This work reflects a broader ambition to bridge the gap between general-purpose AI perception and the specialized, high-stakes demands of real-world manufacturing systems. While still in the early stages of building a citation record, with his foundational paper already accumulating recognition within the community, Li's research positions him at the forefront of cognitive robotics and intelligent automation. His scholarship is particularly relevant for researchers and students exploring human-robot collaboration, industrial AI, and the application of multimodal deep learning in engineering contexts.
Research Focus
Key Achievements
Top Papers
- 1