- This event has passed.
Spring 2026 GRASP on Robotics: Igor Gilitschenski, University of Toronto, “Eyes Do More Than See”
March 27 @ 10:30 am - 11:45 am
This event was in-person ONLY in Wu and Chen Auditorium…
ABSTRACT
Human imagination plays a key role in enabling highly elaborate processes of learning and planning. Large generative models promise to mimic this ability and enabling general purpose robotics. To this day, the diversity and creativity of the generative models are not matched by equally powerful tools for directing their outputs. Model interactions have been largely constrained to text prompts, inspiring a new line of research to overcome this limitation. Focusing on video generation and editing in view synthesis, this talk will discuss some of the underlying technical challenges in achieving greater controllability. Starting with improved textural controls, we will discuss increasingly fine-grained control mechanisms, including spatial and temporal control. Ultimately, the talk will showcase some general model development strategies that allow to broaden their affordances.
Presenter
Igor Gilitschenski - Learn More
Igor Gilitschenski is an Assistant Professor of Computer Science at the University of Toronto, where he leads the Toronto Intelligent Systems Lab. He is also a faculty member at the Vector Institute. Previously, he was a (visiting) Research Scientist at the Toyota Research Institute and a Research Scientist at MIT’s Computer Science and Artificial Intelligence Lab and the Distributed Robotics Lab (DRL). There, he was the technical lead of DRL’s autonomous driving research team. Dr. Gilitschenski joined MIT from the Autonomous Systems Lab of ETH Zurich, where he worked on robotic perception. He obtained his doctorate in Computer Science from the Karlsruhe Institute of Technology and a Diploma in Mathematics from the University of Stuttgart. His current research focuses on understanding perceptual, physical, and behavioral representations for data-driven environment modelling and its applications to Embodied AI. He is the recipient of several best paper awards, including at the American Control Conference, the International Conference of Information Fusion, and the Robotics and Automation Letters.