学　术

教师发展中心“名师讲堂”活动特别邀请IEEE Fellow、微软AI实验室首席科学家刘自成教授来校作学术交流，具体安排如下，欢迎广大师生参加。

一、主　题：The Evolution of Large Multimodal Models (LMMs)

二、时　间：2023年11月27日（周一）14:00

三、地　点：创新中心A102

四、主讲嘉宾：IEEE Fellow、微软AI实验室首席科学家 刘自成 教授

五、主持人：自动化工程学院 赵洋 助理研究员

六、内容简介：

In this talk, I’ll first give a historical perspective on the progress of large multimodal models followed by an overview on the capabilities of OpenAI’s recently released GPT-4V(ision) model. I’ll then discuss some of our efforts on benchmarking LMMs as well as leveraging GPT-4V for video and GUI navigation applications.

七、嘉宾简介： 

Zicheng Liu, IEEE Fellow, is a partner research manager at Microsoft Azure AI managing the computer vision science group. Current research interests include vision-language learning, 3D human body and hand reconstruction, dynamic convolution, human activity recognition. He has worked on a variety of topics including Steiner trees, average case complexity, linked figure animation, and trimmed NURBS tessellation for large CAD model visualization. He was a member of the Audio and Electroacoustics Committee of IEEE Signal Processing Society. He is the chair of the Multimedia Systems and Applications Technical Committee of IEEE CAS society. He is a steering committee member of IEEE Transactions on Multimedia. He is the Editor-in-Chief of Journal of Visual Communications and Image Representation, and an associate editor of Machine Vision and Applications. He served as a guest editor of IEEE Transactions on Multimedia, and a guest editor of IEEE Multimedia Magazine. He is an affiliate professor in the department of Electrical Engineering, University of Washington.

　　八、主办单位：教师发展中心

　　　　承办单位：自动化工程学院