Summary
Yizhe Zhu is a Member of Technical Staff in Seattle with a PhD in Computer Science and a decade of research-to-production experience specializing in multimodal and generative models for AIGC, particularly text-guided image and video generation and editing. He has shipped consumer-facing GenAI features at ByteDance and now builds state-of-the-art image and video generation tools at Moonvalley, bridging top-tier research (CVPR/ICCV/ICLR/NeurIPS) with product-grade engineering. His work spans disentangled representation learning, self-supervised methods, and multimodal alignment, and he has a track record of launching large-scale effects like AI portrait and AI Everywhere. Beyond publications, Yizhe combines deep theoretical insight with hands-on model deployment and personalization, making him adept at turning novel generative techniques into usable features.
10 years of coding experience
6 years of employment as a software developer
University of Missouri
Bachelor’s Degree Telecommunications Engineering, Bachelor’s Degree Telecommunications Engineering at Shanghai University
Doctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at Rutgers University
English, Chinese