Ongoing Collaborations
We are working in collaboration with multiple labs and professors around the world. Each collaboration pairs our work on vision and interpretability with a partner group's expertise on a shared research problem.
Current research directions
Open Vocabulary Detection
We build detectors that find objects named in free-form text, not a fixed label set. The work studies how well these models generalize to unseen categories and where they fail.
Physics-Based VLMs
We study vision-language models that reason about physical quantities such as motion, scale, and force. The goal is to ground model answers in physical laws and check that they hold.
Collaborating with
We are currently collaborating with the following researcher.
Muhamad Zeshan Alam
CollaboratorMuhamad Zeshan Alam received his Ph.D. degree in Electrical Engineering and Cyber-Systems. He was a Postdoctoral Fellow at the University of Cambridge, U.K., where his research focused on computer vision and machine learning.
He has held academic positions as an Assistant Professor at several universities in Canada, including Brandon University and the University of New Brunswick. He is a Senior Member of the IEEE and a member of Professional Engineers Ontario (PEO).
His research interests include immersive video technologies, computational imaging, computer vision, and machine learning.
Collaborate with us
If your group works on a related problem and wants to collaborate, write to us.
Contact the lab