报告名称：Learning to Generate the Moving World: Video Generative Models and Their Applications
报告时间：8月13日15:00
报告地点：数学馆201
腾讯会议：151-993-578
报告摘要:
Generative AI is rapidly evolving beyond static images and text, entering the dynamic and complex domain of video generation. From producing realistic video content from text prompts to simulating human motion and constructing immersive virtual environments, video generative models are unlocking transformative possibilities across media, entertainment, education, healthcare, and more. In this seminar, we will delve into the foundations and frontiers of video generative models, with a particular focus on their applications in areas such as 3D reconstruction and 3D/4D content generation. We will also explore how these models can be leveraged to build world models for embodied AI, enabling intelligent agents to perceive, predict, and interact with dynamic environments. In addition, we will examine recent advances in efficient generation techniques that significantly accelerate the video synthesis process.
报告人简介:
Jun Zhang received his Ph.D. degree in Electrical and Computer Engineering from the University of Texas at Austin. He is an IEEE Fellow and a Professor in the Department of Electronic and Computer Engineering at the Hong Kong University of Science and Technology. His research interests include integrated communications and AI, generative AI, and edge AI systems. He is a co-recipient of several best paper awards, including the 2021 Best Survey Paper Award of IEEE Communications Society, the 2019 IEEE Communications Society & Information Theory Society Joint Paper Award, and the 2016 Marconi Prize Paper Award in Wireless Communications. He also received the 2016 IEEE ComSoc Asia-Pacific Best Young Researcher Award. He is an Area Editor of IEEE Transactions on Wireless Communications (leading the area of Machine Learning and Artificial Intelligence) and IEEE Transactions on Machine Learning in Communications and Networking (leading the area of Distributed Learning and AI at the Network Edge).
