Ruizhou Ding

Papers

Total Citations

H-Index

About

Ruizhou Ding is a researcher specializing in efficient deep learning, computer vision, and model compression, with a particular focus on making neural networks practical for real-world deployment in resource-constrained environments such as autonomous vehicles and robotics. His work addresses one of the central challenges in modern AI: bridging the gap between the computational demands of state-of-the-art models and the hardware limitations of edge systems. Among his most notable contributions is AdaScale (2019, 39 citations), which challenges the conventional wisdom that detection speed and accuracy are inherently at odds. By leveraging adaptive scaling in video object detection, Ding demonstrated that intelligent input processing can yield real-time performance without sacrificing reliability — a significant advance for autonomous systems. His complementary work on filter pruning, published across two influential papers — LeGR (2019, 22 citations) and "Towards Efficient Model Compression via Learned Global Ranking" (2020, 20 citations) — introduced a global ranking approach that automates the often burdensome process of selecting target model complexity, making neural network compression more accessible and systematic. Together, these contributions reflect Ding's sustained commitment to making deep learning faster, leaner, and deployable in safety-critical applications.