Niklas Bühler

I'm a PhD candidate at the Chair for Artificial Intelligence in Medicine (TUM), focused on representation learning in the medical domain. My early research explored large-scale self-supervised pre-training for X-rays. Currently, I'm developing models that encode a patient's complete health profile to enable multi-disease risk prediction and biomarker discovery.

Interests: 

• Representation learning
• Tabular / multimodal foundation models
• Disease risk prediction
• Self-supervised learning for medical imaging

Education:

• M. Sc. Informatics, 2025 Technical University of Munich
• B. Sc. Informatics, 2021 Karlsruhe Institute of Technology