Mara Graziani

My work is at the intersection of technology and applications, with the focus on leveraging AI to enhance our understanding of complex problems. My research is centered around the safety and alignment of foundation models in vision and language, the use of interpretable deep learning to facilitate knowledge discovery, and estimating uncertainty in model predictions on structured data.

My background is in Information Technology Engineering. I hold advanced degrees from both the University of Geneva, where I earned my Ph.D. in Computer Science, and the University of Cambridge, where I completed an M.Phil. program in Machine Learning, Speech, and Language. My doctoral thesis received the best thesis award from the IEEE Technical Committee on Computational Life Sciences in 2021, and I received an award from the Cambridge Engineering Department to support my M.Phil in 2016. As part of my doctoral studies, I spent time as a visiting student at the Harvard Medical School in Boston, where I studied the interaction between physicians and deep learning systems.

Invited Talks >>

• Tübingen AI Explainability, Tübingen, Germany, 2023 → "Concept discovery with Singular Value Decomposition";
• Royal Society of Medicine, London, UK, 2023 → “The human-AI horizon in microscopy imaging“;
• Banff International Research Station, Banff, Canada, 2022 → “DL Interpretability for the discovery of biomedical patterns” ;
• Argonne National Laboratory, Chicago, USA, 2018 → “Regression Concept Vectors for Bidirectional Explanations in AI”

Selected Press >>

• Le Temps 2022, Forum des 100 → Innovateurs, Mara Graziani: Chercheuse spécialiste en intelligence artificielle
• Le Temps 2022, Tête Chercheuse → Mara Graziani: «Je peux avoir une idée le matin et la tester tout de suite, le jour même»