Xuan Truong Nguyen
Papers
2
Total Citations
6
H-Index
2
About
Xuan Truong Nguyen is a researcher at the forefront of efficient deep learning and autonomous driving perception. His work focuses on optimizing neural networks for real-time deployment, particularly in resource-constrained environments like robotics and autonomous vehicles. Nguyen’s major contribution includes an accurate weight binarization scheme for CNN-based object detectors, such as YOLO, which introduces two scaling factors to significantly reduce model size and computational cost while maintaining detection accuracy—a critical advancement for hardware implementation in drones and self-driving cars. Additionally, he developed the MLS framework, an MAE-aware LiDAR sampling strategy that leverages spatio-temporal information to enhance point cloud processing efficiency in on-road environments, addressing LiDAR’s inherent resolution and resource limitations. Though early in his career, with papers accumulating citations (4 and 2 respectively), Nguyen’s work tackles pressing challenges in edge AI and sensor perception, demonstrating strong potential for impact. His research is particularly notable for bridging the gap between theoretical model compression and practical deployment in autonomous systems, making him a promising voice in the field of efficient computer vision and robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2