Research Group Reinhard Heckel
Reinhard Heckel
Prof. Dr.
Principal Investigator
Reinhard Heckel
is Professor for Machine Learning at TU Munich.
His research is centered on machine learning and information processing. He focuses on developing algorithms and theoretical foundations for deep learning, particularly in medical imaging application, and on establishing mathematical and empirical underpinnings for machine learning. Additionally, he works on DNA data storage and the utilization of DNA as a digital information technology.
Team members @MCML
PhD Students
Florian Fürnrohr
→ Group Reinhard Heckel
Machine Learning and Information Processing
Tobit Klug
→ Group Reinhard Heckel
Machine Learning and Information Processing
Youssef Mansour
→ Group Reinhard Heckel
Machine Learning and Information Processing
Franziska Weindel
→ Group Reinhard Heckel
Machine Learning and Information Processing
Recent News @MCML
Publications @MCML
2025
Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training.
NeurIPS 2025 - 39th Conference on Neural Information Processing Systems. San Diego, CA, USA, Nov 30-Dec 07, 2025. Spotlight Presentation. To be published. Preprint available. URL
Approximating Positive Homogeneous Functions with Scale Invariant Neural Networks.
Journal of Approximation Theory 311.106177. Nov. 2025. DOI
Transformer-Based Decoding in Concatenated Coding Schemes Under Synchronization Errors.
ISIT 2025 - IEEE International Symposium on Information Theory. Ann Arbor, MI, USA, Jul 22-27, 2025. DOI
Trace Reconstruction with Language Models.
Preprint (Jul. 2025). arXiv
OpenThoughts: Data Recipes for Reasoning Models.
Preprint (Jun. 2025). arXiv URL
Reliable Evaluation of MRI Motion Correction: Dataset and Insights.
Preprint (Jun. 2025). arXiv
2024
TTT-MIM: Test-Time Training with Masked Image Modeling for Denoising Distribution Shifts.
ECCV 2024 - 18th European Conference on Computer Vision. Milano, Italy, Sep 29-Oct 04, 2024. DOI GitHub
GAMA-IR: Global Additive Multidimensional Averaging for Fast Image Restoration.
Preprint (Apr. 2024). arXiv
2023
Zero-Shot Noise2Noise: Efficient Image Denoising without any Data.
CVPR 2023 - IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver, Canada, Jun 18-23, 2023. DOI
©all images: LMU | TUM