Papers
1
Total Citations
9
H-Index
1
About
Guohao Li is a leading researcher in 3D deep learning and neural architecture search, with a particular focus on point cloud processing. His work addresses the critical challenge of designing efficient, high-performance architectures for 3D data—a domain essential for autonomous driving, robotics, and augmented reality. In his highly cited paper "LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks" (2022, 9 citations), Li pioneered a novel approach that automatically discovers optimal network structures while respecting real-world latency constraints. This work bridges the gap between theoretical accuracy and practical deployment, enabling point cloud models that are both accurate and computationally efficient. By integrating latency awareness directly into the architecture search process, Li's contributions have advanced the state-of-the-art in automated 3D model design, offering a scalable solution for resource-constrained environments. His research continues to shape how deep learning systems are optimized for real-time 3D perception tasks, making him a key figure in the evolution of efficient neural network design for spatial data.
Research Focus
Key Achievements
Top Papers
- 1