Yanzhi Wang is an assistant professor in the Department of Electrical and Computer Engineering with an affiliation at the Khoury College of Computer Sciences.

His research focuses on real-time and energy-efficient deep learning and artificial intelligence systems. He explores algorithms and implementations in mobile and embedded systems, field-programmable gate arrays, circuit tapeouts, graphics processing units, emerging devices, and autonomous aerial vehicles.

Wang has achieved and maintained the highest model compression rates on representative deep neural networks (DNNs). He was the first to achieve real-time execution of representative large-scale DNNs on an off-the-shelf mobile device and still has the highest performance and energy efficiency in DNN implementations across multiple platforms. Wang has also achieved the highest energy efficiency of all hardware devices with his work on adiabatic quantum-flux-parametron superconducting-based DNN inference acceleration.

He has earned numerous best paper awards and nominations from the Institute of Electrical and Electronics Engineers (IEEE) and authored a featured article for the Communications of Association for Computing Machinery. Wang’s accolades include a U.S. Army Research Office Young Investigator Award, an IEEE Technical Committee on Secure and Dependable Measurement Early Career Award, and the Martin W. Essigmann Outstanding Teaching Award. His group has received the Acorn Award, Google Research Award, MathWorks Faculty Award, and many others.

Wang earned his doctoral degree in computer engineering from the University of Southern California. He won the Ming Hsieh Scholar Award and a Bachelor of Science in electrical engineering from Tsinghua University, with distinctions from the university and the city of Beijing.