Xiangxiang Chu
Papers
1
Total Citations
4
H-Index
1
About
Xiangxiang Chu is a leading researcher in efficient deep learning, with a primary focus on post-training quantization (PTQ) for 3D perception systems. His most-cited work, "LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection" (2024), addresses a critical bottleneck in autonomous driving and robotics: deploying complex lidar-based 3D detectors on resource-constrained edge devices. By pioneering a PTQ framework tailored for point cloud data, Chu enables significant model compression without retraining, preserving detection accuracy while drastically reducing memory and computational demands. This contribution has already garnered 4 citations in its first year, signaling strong impact in the autonomous systems community. Chu’s research bridges the gap between state-of-the-art 3D perception and practical deployment, making him a key figure in the push toward real-world, low-latency AI for vehicles and robots. His work is essential reading for engineers and researchers tackling the challenges of efficient on-device intelligence.
Research Focus
Key Achievements
Top Papers
- 1