Bio
Yu Zeng is a Research Scientist at NVIDIA. Her research advances scalable artificial intelligence through two primary directions: generative AI and label-efficient learning for computer vision. She develops generative models for visual synthesis using multimodal and hierarchical inputs while ensuring their trustworthiness and real-world applicability. Her most recent research focuses on advancing embodied AI using deep generative models. Through her experience spanning academia and industry, she conducts research that combines fundamental innovation with real-world deployment. Before joining NVIDIA, she obtained her PhD from Johns Hopkins University. Before that, she worked as a researcher at Tencent. She also worked with the research teams at Adobe during PhD and Master’s studies.