Tal Arbel is a full Professor in the Department of Electrical and Computer Engineering at McGill University and Associate Member of the School of Computer Science. She is the Director of the Probabilistic Vision Group (PVG) and Medical Imaging Lab in the Centre for Intelligent Machines (CIM). She is a Canada CIFAR AI Chair at Mila (Quebec Artificial Intelligence Institute) and an Associate Member of the Goodman Cancer Research Centre. She is a Fellow of the Canadian Academy of Engineering.
Prof. Arbel’s research group pushes the boundaries of probabilistic deep learning and computer vision for medical image analysis. Her team focuses on developing causal-temporal and 3D spatio-temporal generative models, as well as multimodal foundation models (including vision-language MLLMs) and agentic AI frameworks. Purpose-built for real-world challenges, these methodological frameworks are designed to handle complex, longitudinal data. A key focus of the lab is developing these techniques for the large-scale clinical datasets —including a proprietary clinical trial MRI dataset— to model the evolution of neurological diseases (e.g., Multiple Sclerosis) and cancers, and to predict patient-level outcomes and treatment responses. She maintains active collaborations with top academic and industrial partners, including at Stanford, Google Research, and Meta.
She was a recipient of the 2019 McGill Engineering Christophe Pierre Research Award. She regularly serves on the organizing teams of major international conferences (e.g., MICCAI, MIDL, ICCV, CVPR) and is the Executive Editor and co-founder of the online journal: Machine Learning for Biomedical Imaging (MELBA).
