The Division of Games is delighted to announce Dr. Tomer Weiss as an upcoming speaker for the 2024-2025 Utah Games Speaker Series.  This speaker is hosted by Dr. Fernando Rodriguez, Assistant Professor, Lecturer in the Division of Games.

When & Where: Wednesday, February 12 2025, from 3:00pm to 4:00pm. Room 270 of Building 72.

Talk Title: Learning to Simulate Virtual AI Agents at Scale  

Talk Abstract: Virtual worlds are prevalent in applications ranging from entertainment, healthcare, retail, to workforce training. With the demand for virtual content growing exponentially, the market for such content is valued at over $200 Billion, which is accelerating the need for advanced computational solutions. In this talk, I will focus on a key challenge in virtual content creation: simulating virtual autonomous agents. I begin by overviewing this problem domain, and proposing a fast, parallel algorithm for simulating thousands of agents at interactive rates through GPU programming, achieving a level of performance previously unattainable. 

Next, I’ll present our recent results in Deep Reinforcement Learning for multi-agent navigation, which enable refined, reward-based strategies to control movement. We demonstrate how these techniques can simulate realistic AI crowds, with broad applications in visualization, pedestrian dynamics, and robotics. Lastly, I conclude my talk by discussing our lab’s work-at-large and the wide range of research opportunities in this emerging area.

Speaker Bio: Tomer Weiss joined the New Jersey Institute of Technology as an assistant professor in 2020. Before that, he was a research scientist with Wayfair, Boston. In 2018, he defended his PhD advised by Prof. Terzopoulos at the University of California, Los Angeles. He received the Best Paper Award from the ACM SIGGRAPH conference on Motion in Games, for his work on virtual crowd simulation. He was also a finalist in both ACM SIGGRAPH Thesis Fast Forward, and the ACM SIGGRAPH Asia Doctoral Symposium in 2018. He received his MS in computer science from UCLA in 2016, and his BSc degree in computer science from Tel Aviv University in 2013. His research interests include multi-agent dynamics, scene understanding, and interactive visual computing.