David Drexlin is a doctoral researcher in machine learning with a focus on generative models for biomedical imaging. He completed his M.Sc. in Computer Science at the Technical University of Berlin, where his thesis studied metadata-guided diffusion models for mitigating batch effects in histopathology.

His current interests include multimodal learning, diffusion-based generative modeling, representation learning, digital pathology, and learning shared representations across imaging and molecular data.

Selected publications

• Drexlin, D.J., Dippel, J., Hense, J. et al. Metadata-Guided Generative Diffusion Model Framework (MeDi) for Bias Mitigation in Histopathology [arXiv, 2025]