Kaiyuan Guo

Papers

Total Citations

1,276

H-Index

About

Kaiyuan Guo is a leading researcher at the intersection of deep learning and reconfigurable computing, with a primary focus on accelerating convolutional neural networks (CNNs) and real-time robotic perception on FPGA platforms. His seminal work, "Going Deeper with Embedded FPGA Platform for Convolutional Neural Network" (2016), has garnered over 1,260 citations, establishing a foundational framework for deploying computationally intensive CNNs on resource-constrained embedded systems. This contribution directly addressed the critical challenge of balancing model depth with hardware efficiency, enabling practical AI applications in edge devices. Guo also advanced autonomous navigation through his work on an FPGA-based real-time simultaneous localization and mapping (SLAM) system (2015), demonstrating how reconfigurable logic can overcome power and payload limitations in mobile robotics. His research has been instrumental in bridging the gap between high-performance neural architectures and energy-efficient hardware, making him a key figure in the field of embedded AI. Guo’s achievements continue to inspire students and engineers seeking to optimize deep learning for real-world, low-power environments.