Home  | Research | Groups | Stefan Bauer

Research Group Stefan Bauer


Link to website at TUM PI Matchmaking

Stefan Bauer

Prof. Dr.

Principal Investigator

Stefan Bauer

is an Associate Professor of Algorithmic Machine Learning & Explainable AI at TU Munich and senior PI at Helmholtz AI.

His team develops approaches that enable models to refine their internal hypotheses, adapt their computation to the task at hand, and work with discrete, structured representations. These capabilities strengthen a model’s ability to form abstractions, perform adaptive inference, and carry out multi-step decision making. The goal is to advance AI systems that can address increasingly complex reasoning tasks with greater flexibility and precision, and in doing so, help uncover the underlying principles of intelligence.

Team members @MCML

PostDocs

Link to website

Andrea Dittadi

Dr.

PhD Students

Link to website

Emmanouil Angelis

Link to website

Tobias Höppe

Vincent Pauline

Vincent Pauline

Recent News @MCML

Link to MCML at ICML 2025

11.07.2025

MCML at ICML 2025

25 Accepted Papers (20 Main, and 5 Workshops)

Link to MCML at CVPR 2025

09.06.2025

MCML at CVPR 2025

35 Accepted Papers (29 Main, and 6 Workshops)

Link to MCML Researchers in Highly-Ranked Journals

02.01.2025

MCML Researchers in Highly-Ranked Journals

155 Papers in 2025 Highlight Scientific Impact

Link to MCML at NeurIPS 2024

06.12.2024

MCML at NeurIPS 2024

31 Accepted Papers (23 Main, and 8 Workshops)

Publications @MCML

2025


[8]
V. PaulineT. Höppe • K. Neklyudov • A. Tong • S. BauerA. Dittadi
Foundations of Diffusion Models in General State Spaces: A Self-Contained Introduction.
Preprint (Dec. 2025). arXiv

[7] A* Conference
A. Uselis • A. Dittadi • S. J. Oh
Does Data Scaling Lead to Visual Compositional Generalization?
ICML 2025 - 42nd International Conference on Machine Learning. Vancouver, Canada, Jul 13-19, 2025. URL GitHub

[6]
L. Waldmann • A. Shah • Y. Wang • N. LehmannA. J. StewartZ. XiongX. ZhuS. Bauer • J. Chuang
Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation.
EARTHVISION @CVPR 2025 - Workshop EarthVision: Large Scale Computer Vision for Remote Sensing Imagery at IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville, TN, USA, Jun 11-15, 2025. DOI

[5] Top Journal
A. Tejada-Lapuerta • P. Bertin • S. Bauer • H. Aliee • Y. Bengio • F. J. Theis
Causal machine learning for single-cell genomics.
Nature Genetics. Mar. 2025. DOI

[4]
P. Bertin • J. D. Viviano • A. Tejada-Lapuerta • W. Wang • S. BauerF. J. Theis • Y. Bengio
A scalable gene network model of regulatory dynamics in single cells.
Preprint (Mar. 2025). arXiv

[3] Top Journal
T. Willem • V. A. Shitov • M. D. Luecken • N. KilbertusS. Bauer • M. Piraud • A. Buyx • F. J. Theis
Biases in machine-learning models of human single-cell data.
Nature Cell Biology. Feb. 2025. DOI

2024


[2]
B. M. G. Nielsen • L. Gresele • A. Dittadi
Challenges in Explaining Representational Similarity through Identifiability.
UniReps @NeurIPS 2024 - 2nd Workshop on Unifying Representations in Neural Models at the 37th Conference on Neural Information Processing Systems. Vancouver, Canada, Dec 10-15, 2024. URL

[1] Top Journal
S. FeuerriegelD. FrauenV. MelnychukJ. SchweisthalK. Heß • A. Curth • S. BauerN. Kilbertus • I. S. Kohane • M. van der Schaar
Causal machine learning for predicting treatment outcomes.
Nature Medicine 30. Apr. 2024. DOI