Compositional, Efficient, and Robust Visual Concept Learning in the #GenAI Era

The goal of Computer Vision, as initially defined by David Marr, is to develop algorithms that can answer “What is Where at When” from visual appearance. Expanding on this notion, Professor Yang advocates for the importance of understanding underlying entities and their relationships beyond mere visual appearance, following an Active Perception paradigm. In this talk, he will discuss his decade-long research efforts, including:

Bio
https://search.asu.edu/profile/3020558

Yezhou (YZ) Yang is an Associate Professor and a Fulton Entrepreneurial Professor at the School of Computing and Augmented Intelligence (SCAI), Arizona State University. He founded and directs the ASU Active Perception Group and serves as the topic lead (situation awareness) at the Institute of Automated Mobility, Arizona Commerce Authority. Additionally, he is a thrust lead (AVAI) at Advanced Communications Technologies (ACT), a Science and Technology Center under Arizona’s New Economy Initiative. Professor Yang’s work focuses on visual primitives, representation learning in visual and language understanding, grounding through natural language, and high-level reasoning for intelligent systems, robust AI, and V&L model evaluation alignment. He has received numerous awards, including the NSF CAREER Award 2018 and the Amazon AWS Machine Learning Research Award 2019. Professor Yang completed his Ph.D. at the University of Maryland at College Park and his B.E. from Zhejiang University, China.