Subhankar Roy is a tenure track researcher (RTT) at the Department of Management, Information and Production Engineering (DIGIP). Previously, he was a Lecturer at the University of Aberdeen and Postdoctoral Researcher at Telecom Paris and University of Trento. He earned his Ph.D. in 2022 with cum laude from the University of Trento, under the supervision of Prof. Elisa Ricci and Prof. Nicu Sebe. His research interest lies at the intersection of machine learning, computer vision and natural language processing. Broadly, his research focuses on enhancing the generalization capabilities of deep learning models under data distribution and semantic shifts, and the data- and compute-efficiency. In particular, he is working on multimodal learning, domain adaptation, continual learning, novel class discovery, and machine unlearning.