Yu-Chun Ding
Papers
1
Total Citations
1
H-Index
1
About
Yu-Chun Ding is a leading researcher in energy-efficient deep learning accelerators, with a primary focus on hardware-software co-design for real-time computer vision. His most-cited work, "A 16nm 5.7TOPS CNN Processor Supporting Bi-Directional FPN for Small-Object Detection on High-Resolution Videos," introduces a groundbreaking processor architecture that integrates a bidirectional feature pyramid network (FPN) directly onto silicon. This innovation tackles the critical challenge of detecting small objects—such as distant pedestrians or obstacles—in high-resolution video streams, a task vital for autonomous driving, UAV navigation, and augmented reality. By achieving 5.7 trillion operations per second (TOPS) on a 16nm process, Ding’s design demonstrates how hardware can be tailored to enhance both speed and accuracy for safety-critical applications. The work has garnered 1 citation to date, reflecting its emerging influence in the chip design and computer vision communities. Ding’s contributions bridge the gap between algorithmic complexity and practical deployment, offering a scalable path for integrating advanced neural networks into power-constrained edge devices. His research continues to push the boundaries of real-time intelligent systems, making him a key figure in the evolution of efficient, high-performance AI hardware.
Research Focus
Key Achievements
Top Papers
- 1