Event Date
Robust Knowledge Integration for Interactive AI Systems
Zhe Zhao
Assistant Professor, Department of Computer Science, UC Davis
Abstract
While AI continues to reshape our world, current models often lack the personalization, interactivity, and specialization needed to truly serve users. This talk explores our research on robust knowledge integration for interactive AI systems, focusing on key advancements in knowledge integration, robust machine learning, and interactive platforms. To demonstrate these concepts in action, I will discuss three recent works: finding the optimal model for specific tasks using ModelLens, advancements in personalized generation, and analyzing user addiction to short-form videos.
Bio
Zhe Zhao is an Assistant Professor in the Department of Computer Science at the University of California, Davis. His research focuses on the efficiency and robustness of machine learning models, with a particular interest in deep learning applications for recommendation systems, natural language understanding, and computer vision. Prior to joining UC Davis, he was a Research Scientist at Google DeepMind (formerly Google Brain), where he worked on multi-task deep learning. He earned his Ph.D. in Computer Science from the University of Michigan and holds B.S. and M.S. degrees in Computer Science from Peking University.