Kaiming Wang
Papers
1
Total Citations
15
H-Index
1
About
Kaiming Wang is a rising researcher at the forefront of multimodal perception and 3D visual quality assessment. His work centers on the intersection of large language models (LLMs), graph learning, and point cloud processing, with a particular focus on ensuring the reliability of 3D data in high-stakes applications like autonomous driving, robotics, and virtual reality. Wang’s most notable contribution, "LLM-Guided Cross-Modal Point Cloud Quality Assessment: A Graph Learning Approach" (2024), pioneers a novel framework that leverages LLMs to guide graph-based models in evaluating the perceptual quality of point clouds. This work, already garnering 15 citations in its first year, addresses a critical gap in 3D vision by enabling more accurate and context-aware quality metrics—essential for safe autonomous systems and immersive VR experiences. By fusing semantic understanding from LLMs with structural reasoning from graph neural networks, Wang’s approach sets a new standard for cross-modal quality assessment. His research promises to shape the future of robust 3D perception, making him a key figure to watch in the evolving landscape of multimodal AI and computer vision.
Research Focus
Key Achievements
Top Papers
- 1