Abstract
In this talk, we will explore the cutting-edge field of generative AI, with a focus on its applications in vision and language models. Generative AI involves creating intelligent systems that can generate new and diverse data or content, such as images, videos, music, and text. We will start by discussing the history of generative AI and how recent breakthroughs in deep learning and neural networks have revolutionized the field. We well then delve into generative AI for dealing with multiple data modalities. More particularly, we well talk about recent advances in vision and language, and we well cover two of our recent works on image captioning and text-to-image synthesis, which are recently published at NeurIPS 2022 and AAAI 2023.