Fall 2026 GRASP on Robotics: Georgia Gkioxari, California Institute of Technology, “Towards Self-Improving Machine Perception”
September 18 at 10:30 AM - 11:45 AM
Organizer
grasplab@seas.upenn.edu
View Website
Venue
This will be an in-person event ONLY in Wu and Chen Auditorium.
ABSTRACT
Self-Improving machine perception explores how we can build visual systems that do not just perceive the world, but continually improve at doing so. In this talk, I will argue that the next leap in AI will come not only from larger models, but from closed-loop learning systems that generate, critique, and re-curate their own training data. I will present recent work on 3D perception, semantic grounding, and spatial reasoning, and discuss how self-improving learning can enable more capable world models, more reliable perception, and AI systems that learn in domains where labeled data is scarce.
Speaker
Georgia Gkioxari
California Institute of Technology
Georgia is an assistant professor at the Computing + Mathematical Sciences at Caltech. She obtained her PhD in Electrical Engineering and Computer Science from UC Berkeley, where she was advised by Jitendra Malik. Prior to Berkeley, she earned her diploma from the National Technical University of Athens in Greece. After earning her PhD, she was a research scientist at Meta’s FAIR team. In 2025, she was named a Packard Fellow. In 2021, she received the PAMI Young Researcher Award, which recognizes a young researcher for their distinguished research contribution to computer vision. She is the recipient of the PAMI Mark Everingham Award for the open-source software suite Detectron (2021), the Google Faculty Award (2024) and the Okawa Research Award (2024). In 2017, Georgia and her co-authors received the Marr Prize for “Mask R-CNN” published and presented at ICCV. She was named one of 30 influential women advancing AI in 2019 by ReWork and was nominated for the Women in AI Awards in 2020 by VentureBeat.