Yu Cheng is a Principal Researcher at Microsoft Research. Before that, he was a Research Staff Member at IBM Research/MIT-IBM Watson AI Lab. He got a Ph.D. degree from Northwestern University in 2015 and a bachelor degree from Tsinghua University in 2010. His research covers deep learning in general, with specific interests in model compression/efficiency, deep generative model, and adversarial robustness. Currently, he focuses on productionizing these techniques to solve challenging industry problems in CV, NLP and Multimodal.