Florian P.
Mahner

I am a PhD Candidate in Machine Learning at the Max Planck Research Group Vision and Computational Cognition supervised by Martin Hebart and at TU Berlin supervised by Klaus-Robert Müller. During my PhD I was also supervised by Umut Güçlü.

My work primarily focuses on representation learning in humans and machines. I combine computational modeling and machine learning with insights from cognitive science to understand the similarities and differences between human and artificial systems. I mostly work on vision, but also use insights from language and other domains.

I am particularly interested in interpretable alignment of representations. For this, I use insights from cognitive science to learn something about machine learning models, and machine learning to improve our understanding of the brain. If you are interested in collaborating, feel free to reach out.

From Oct 2026Postdoctoral Researcher, Machine Learning Machine Learning Group, TU Berlin
2022–2026PhD Machine Learning Vision and Computational Cognition Group, MPI CBS & TU Berlin
2018–2021MSc Artificial Intelligence Radboud University
2013–2017BSc Cognitive Science Osnabrück University
Characterizing universal object representations across vision models
Florian P. Mahner*, Johannes Roth*, Ka Chun Lam, Michael F. Bonner, Francisco Pereira, Martin N. Hebart
Preprint at arXiv 2026 Paper Web
Similarity-based representation factorization for revealing interpretable dimensions in representational data
Florian P. Mahner*, Ka Chun Lam*, Francisco Pereira, Martin N. Hebart
Preprint at arXiv 2026 Paper Web
Dimensions underlying the representational alignment of deep neural networks with humans
Florian P. Mahner*, Lukas Muttenthaler*, Umut Güçlü, Martin N. Hebart
Nature Machine Intelligence 2025 Paper Web