Zixiang Ding
Papers
1
Total Citations
9
H-Index
1
About
Zixiang Ding is a researcher advancing efficient deep learning for resource-constrained environments, with a primary focus on model compression and network pruning. His most notable contribution is the development of ABCP (Automatic Blockwise and Channelwise Network Pruning via Joint Search), a pioneering framework that automates the pruning process by jointly optimizing blockwise and channelwise sparsity. This work, published in 2022 and garnering 9 citations, addresses the critical challenge of deploying deep learning models on devices with limited computational power—such as those used in robotic detection—by eliminating the need for manual, rule-based pruning strategies. Ding’s research bridges the gap between high-performance neural networks and practical, real-world applications, enabling faster and more efficient inference on edge devices. His approach not only reduces model size and computational cost but also maintains accuracy, making it highly relevant for robotics and IoT systems. Through ABCP, Ding has contributed a scalable, automated solution that empowers developers to optimize models without extensive domain expertise, marking a significant step toward democratizing efficient AI deployment.
Research Focus
Key Achievements
Top Papers
- 1