Research

Three core pillars, with applications in healthcare, the industrial internet of things, life sciences and optics.

Foundational AI

We advance deep learning and its subfields, including graph-based and generative models, with a focus on improving model efficiency, generalization, and handling multimodal data.

Responsible AI

We develop privacy-preserving and trustworthy AI systems using federated learning, ensuring data confidentiality while addressing challenges such as heterogeneity, communication efficiency, personalization, privacy and security. We also develop machine unlearning methods that help AI comply with the GDPR and the EU AI Act, and we study the faithfulness of AI explanations, promoting fairness, transparency and unbiased decision-making.

Quantum AI

We co-design AI architectures to align with quantum requirements, enabling efficient implementation of classical AI models in the quantum domain.

Applied AI

Our applied research has led to a personalized cervical cancer screening recommender system that mitigates under- and over-treatment, and continues with AI-based early detection systems for colorectal cancer, coronary artery calcification and dementia.