Towards Explainable, Unbiased, and Personalized Generative AI: Take Vision & Language Models as Examples

Abstract

The convergence of language, vision, and generative models is a captivating and rapidly advancing research domain. In this talk, I will first delve into the intricate interplay between these disciplines, showcasing how generative models have sparked a revolution in creative and analytical applications. I will briefly go through the mechanisms behind models' ability to decode images into text and vice versa, shedding light on their potential to reshape human-machine interaction. Recent research trends and challenges on vision and language based generative AI, including model interpretability, bias, safety, and personalization will be covered in this talk.

Biography

Yu-Chiang Frank Wang received his B.S. degree in Electrical Engineering from National Taiwan University in 2001. He earned his M.S. and Ph.D. degrees in Electrical and Computer Engineering from Carnegie Mellon University in 2004 and 2009, respectively. In 2009, Dr. Wang joined the Research Center for Information Technology Innovation (CITI) at Academia Sinica, where he also served as the Deputy Director from 2015 to 2017. In 2017, Dr. Wang joined the Department of Electrical Engineering at National Taiwan University as an Associate Professor and was promoted to Professor in 2019. Starting in August 2022, Dr. Wang joined NVIDIA as the Research Director for Deep Learning and Computer Vision, leading NVIDIA Research Taiwan.

With a continuing research focus on computer vision and deep learning, Dr. Wang's recent research topics include vision and language, 3D vision, and explainable AI. Dr. Wang has served as an organizing committee member and area chair for multiple international conferences, including CVPR, ICCV, ECCV, and ACCV. Several of his papers have been nominated for best paper awards, including at IEEE ICIP, ICME, AVSS, and MVA. Dr. Wang was twice selected as an Outstanding Young Researcher by the Ministry of Science and Technology of Taiwan (2013–2015 and 2017–2019). He received the Y. Z. Hsu Scientific Paper Award in the category of Artificial Intelligence in 2022. In 2023, he was honored with the Outstanding Young Scholar Award from the Foundation for the Advancement of Outstanding Scholarship. In addition to his research achievements, Dr. Wang received the Excellence in Teaching Award at NTU for four consecutive years, from 2019 to 2024.