Boxun Li

About

Boxun Li is a leading researcher at the intersection of hardware acceleration and deep learning, with a primary focus on designing efficient FPGA-based platforms for convolutional neural networks (CNNs). His seminal 2016 paper, "Going Deeper with Embedded FPGA Platform for Convolutional Neural Network," has garnered over 1,260 citations, establishing him as a pioneer in enabling real-time, energy-efficient CNN inference on embedded devices. Li’s major contribution lies in bridging the gap between complex deep learning models and resource-constrained hardware, demonstrating that FPGAs can effectively accelerate state-of-the-art networks without sacrificing accuracy. His work has profoundly influenced the fields of edge computing, autonomous systems, and low-power AI, providing a practical pathway for deploying CNNs in real-world applications where traditional GPUs are impractical. Beyond this landmark study, Li continues to advance reconfigurable computing architectures, earning recognition for his innovative approaches to hardware-software co-design. His research remains essential reading for students and engineers seeking to understand how custom hardware can unlock the full potential of deep learning in embedded environments.

Research Focus

Key Achievements

Top Papers

1. 1
   Going Deeper with Embedded FPGA Platform for Convolutional Neural Network

   1,260 citations · 2016

Key Collaborators

Contact & Links