Seminar by Professor Ser Nam Lim (University of Central Florida) at 10am on June 11 (Tuesday)

Title: What can Generative do for You?

Time: June  11 (Tuesday), 11:00am-12:00pm

Venue: ABN Seminar Room 1-1 (ABN-01a-CF2)

Abstract: In this talk, I will dive into the work that my group and collaborators have been working on in the field of generative AI. I will first cover how generative AI is even transforming the tasks that "traditional" deep discriminative models excel at, including object recognition and detection. I will then cover topics ranging from view synthesis to ARVR applications that my group is working on, and the "positive" aspects of generative AI in bringing ground breaking possibilities to transform many of these tasks. I will then switch gear to discuss the other side of generative AI in terms of its safety and vulnerability. Finally, I will sum up by discussing how we can utilize the insights from a work on neuro symbolic spatio-termporal scene graphs to build a generative aware information system as ongoing and future work.

Bio: Sernam is currently an Associate Professor in the Computer Science Department at the University of Central Florida. Sernam’s background is in Computer Vision and the field of AI. He pursued and earned a PhD at the University of Maryland, College Park, in 2005. Sernam spent a decade at GE Research working on different areas of Computer Vision including video recognition, 3D reconstruction, representation, and visual matching. At GE Research, Sernam started as a Research Scientist, then took a role as the Computer Vision Lab Manager, and finished his career there as a Senior Principal and Director. During his tenure at GE, he was also the PI of IARPA CORE3D and a prolific contributor of many other government research grants including DARPA, NIJ, ONR, etc. From 2018-2023, Sernam managed multiple AI teams at Meta (formerly Facebook) that conduct research in Computer Vision, NLP and other areas of AI with a focus on applying and scaling to huge amounts of data on the Meta platform. Sernam’s work has accomplished impactful production outcomes in ensuring safety in the Aviation and Power industry as well as detecting misinformation and other integrity issues on the Meta platform. Most recently, Sernam lead projects focused on AI for user to content recommendations, as well as search engines that include the intersection of Large Language Models (LLM) and Computer Vision. Sernam has published over 100 peer-refereed papers, with more than half in top AI venues.