Research Group Carsten Marr
Carsten Marr
Prof. Dr.
Core PI
Carsten Marr
is Professor of Artificial Intelligence in Cell Therapy and Hematology at LMU Munich and Director of the Institute of AI for Health at Helmholtz Munich.
His lab focuses on improving the diagnosis, treatment, and understanding of severe blood disorders. The team develops machine learning algorithms to classify individual cells and patients and uses single-cell data to identify potential drug targets. Combining AI with mechanistic models of haematopoiesis – the production of blood cells – is a key focus of their research.
Team members @MCML
PostDocs
Amirhossein Kardoost
Dr.
→ Group Carsten Marr
Artificial Intelligence in Cell Therapy and Hematology
Ario Sadafi
→ Group Carsten Marr
Artificial Intelligence in Cell Therapy and Hematology
→ Co-Group Nassir Navab
PhD Students
Christian Brechenmacher
→ Group Carsten Marr
Artificial Intelligence in Cell Therapy and Hematology
Recent News @MCML
Publications @MCML
2026
Re-mixing Embeddings for Patient Augmentation in Data Scarce Multiple Instance Learning.
MICCAI 2026 - 29th International Conference on Medical Image Computing and Computer Assisted Intervention. Strasbourg, France, Sep 27-Oct 01, 2026. To be published. Preprint available. arXiv GitHub
Genetically Aligned Patient Representations Improve Hematological Diagnosis.
MICCAI 2026 - 29th International Conference on Medical Image Computing and Computer Assisted Intervention. Strasbourg, France, Sep 27-Oct 01, 2026. To be published. Preprint available. arXiv GitHub
3D Masked Autoencoders are Robust Learners of Volumetric and Multimodal Cellular Representations for Microscopy.
MICCAI 2026 - 29th International Conference on Medical Image Computing and Computer Assisted Intervention. Strasbourg, France, Sep 27-Oct 01, 2026. To be published. Preprint available. arXiv URL
Measuring Prediction Uncertainty in Neural Cellular Automata.
MICCAI 2026 - 29th International Conference on Medical Image Computing and Computer Assisted Intervention. Strasbourg, France, Sep 27-Oct 01, 2026. To be published. Preprint available. arXiv GitHub
Are Object-Centric Representations Better at Compositional Generalization?
ICML 2026 - 43rd International Conference on Machine Learning. Seoul, South Korea, Jul 06-11, 2026. To be published. Preprint available. URL
A Multicenter Benchmark of Multiple Instance Learning Models for Lymphoma Subtyping from HE-stained Whole Slide Images.
Workshop @CVPR 2026 - Workshop at the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Denver, CO, USA, Jun 03-07, 2026. To be published. Preprint available. URL GitHub
AI-based hematological malignancy prediction from peripheral blood smears in a large diagnostic laboratory cohort.
Leukemia 40.6. Jun. 2026. DOI
EchoVisuALL: From Echocardiography to Gene Discovery.
Preprint (Feb. 2026). DOI
2025
A large expert-annotated single-cell peripheral blood dataset for hematological disease diagnostics.
Scientific Data 12.1773. Nov. 2025. DOI
Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings.
Preprint (Nov. 2025). arXiv
Attention Pooling Enhances NCA-based Classification of Microscopy Images.
MLMI @MICCAI 2025 - 16th International Workshop on Machine Learning in Medical Imaging at the 28th International Conference on Medical Image Computing and Computer Assisted Intervention. Daejeon, Republic of Korea, Sep 23-27, 2025. DOI
Topological Inductive Bias fosters Multiple Instance Learning in Data-Scarce Scenarios.
Transactions on Machine Learning Research Vol. 2025. Feb. 2025. URL GitHub
©all images: LMU | TUM
2025-10-20 - Last modified: 2026-07-03