Taylor Symposium on Applied AI
Please join us for the inaugural Taylor Symposium on Applied AI on May 15th, which focuses on emerging trends in artificial intelligence.
The event showcases the various applied AI research and initiatives underway within the Faculty of Engineering, with a special keynote lecture by Michael Rabbat, former McGill professor in Electrical and Computer Engineering, and Co‑Founder and Vice President of World Models at AMI. Please register below.
The symposium is organized by the Faculty of Engineering and made possible through the generous support of Scott Taylor.
Event info and schedule:
Date: May 15, 2026
Location: McGill Faculty Club (3450 Rue McTavish)
- 8:00 Am | Registration / Breakfast
- 8:30 AM | Welcome / Introduction
- 8:45 - 10:00 AM | Lightning talks: Profs. James Clark, Brett Meyer, Lili Wei, and Michael Coates
- 10:00 - 11:00 AM | Keynote presentation: Towards AI that learns and acts with World Models by Michael Rabbat, Co-founder and VP World Models at AMI
- 11:00 - 11:15 AM | Coffee break
- 11:15 AM - 12:00 PM | Lightning talks: Profs. Tim Xie, and Jiangbo Yu
- 12:00 - 1:00 PM | Lunch
- 1:00 - 2:15 PM | Lightning talks: Profs. Fiona Zhao, Audrey Sedal, Guillaume Durandau, and Jozsef Kovecses
- 2:15 - 3:00 PM | Panel discussion
- 3:00 - 3:15 PM | Coffee break
- 3:15 - 4:30 PM | Lightning talks: Profs. Roussos Dimitrakopoulos, Mustafa Kumral, Samuel Huberman, Natalie Reznikov, and Codruta Ignea
- 4:30 PM | Closing remarks
- 4:45 PM | Cocktail reception
Keynote presentation: Towards AI that learns and acts with World Models
Keynote speaker: Michael Rabbat
In this talk, Michael Rabbat explores the next frontier in AI - World Models. He discusses how recent work on V‑JEPA 2 moves AI beyond simple word prediction toward systems that learn through observation of the physical world. By learning directly from video without the need for human‑labeled data, this self‑supervised approach offers a more efficient path toward machines that can model the underlying dynamics of their environment. He will outline how this direction enables the development of the next generation of intelligent agents—systems that do not merely communicate, but can truly understand, plan, and act in the physical world.
Bio:
Michael Rabbat is Co-founder and VP World Models at Advanced Machine Intelligence (AMI Labs), where he is building a new breed of AI systems focused on understanding and reasoning about the world. He is also an Associate Industry Member at Mila.
Previously, Michael was a Research Director at Meta, where he was a founding member of FAIR Montréal, contributing to the company's fundamental AI research efforts. Prior to that, he spent over a decade as a professor at McGill University in Electrical and Computer Engineering. He earned his PhD from the University of Wisconsin, Madison.
Throughout his career he has worked on a variety of topics across signal processing, learning, and optimization, including distributed optimization and federated learning. His current research is focused on learning world models and using them for planning and control.
