| 2025 | ICLR | Simple, Good, Fast: Self-Supervised World Models Free of Baggage. | Jan Robine, Marc Hftmann, Stefan Harmeling |
| 2025 | ICLR | The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions. | Stefan Sylvius Wagner, Maike Behrendt, Marc Ziegele, Stefan Harmeling |
| 2024 | ICML | Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations. | Stefan Sylvius Wagner, Stefan Harmeling |
| 2023 | ICLR | Transformer-based World Models Are Happy With 100k Interactions. | Jan Robine, Marc Hftmann, Tobias Uelwer, Stefan Harmeling |
| 2021 | ICANN | Non-iterative Phase Retrieval with Cascaded Neural Networks. | Tobias Uelwer, Tobias Hoffmann, Stefan Harmeling |
| 2021 | ICANN | Learning to Plan via a Multi-step Policy Regression Method. | Stefan Wagner, Michael Janschek, Tobias Uelwer, Stefan Harmeling |
| 2021 | MICCAI | 2D Histology Meets 3D Topology: Cytoarchitectonic Brain Mapping with Graph Neural Networks. | Christian Schiffer, Stefan Harmeling, Katrin Amunts, Timo Dickscheid |
| 2021 | SIGdial | How Will I Argue? A Dataset for Evaluating Recommender Systems for Argumentations. | Markus Brenneis, Maike Behrendt, Stefan Harmeling |
| 2020 | AISTATS | Modular Block-diagonal Curvature Approximations for Feedforward Architectures. | Felix Dangel, Stefan Harmeling, Philipp Hennig |
| 2020 | COMMA | How Much Do I Argue Like You? Towards a Metric on Weighted Argumentation Graphs. | Markus Brenneis, Maike Behrendt, Stefan Harmeling, Martin Mauve |
| 2020 | ICPR | Fast Multi-Level Foreground Estimation. | Thomas Germer, Tobias Uelwer, Stefan Conrad, Stefan Harmeling |
| 2020 | ICPR | Phase Retrieval Using Conditional Generative Adversarial Networks. | Tobias Uelwer, Alexander Oberstra, Stefan Harmeling |
| 2018 | MICCAI | Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks. | Hannah Spitzer, Kai Kiwitz, Katrin Amunts, Stefan Harmeling, Timo Dickscheid |
| 2013 | CVPR | On a Link Between Kernel Mean Maps and Fraunhofer Diffraction, with an Application to Super-Resolution Beyond the Diffraction Limit. | Stefan Harmeling, Michael Hirsch, Bernhard Schlkopf |
| 2013 | CVPR | A Machine Learning Approach for Non-blind Image Deconvolution. | Christian J. Schuler, Harold Christopher Burger, Stefan Harmeling, Bernhard Schlkopf |
| 2013 | ICIP | Improving alpha matting and motion blurred foreground estimation. | Rolf Khler, Michael Hirsch, Bernhard Schlkopf, Stefan Harmeling |
| 2012 | CVPR | Image denoising: Can plain neural networks compete with BM3D? | Harold Christopher Burger, Christian J. Schuler, Stefan Harmeling |
| 2012 | ECCV | Recording and Playback of Camera Shake: Benchmarking Blind Deconvolution with a Real-World Database. | Rolf Khler, Michael Hirsch, Betty J. Mohler, Bernhard Schlkopf, Stefan Harmeling |
| 2012 | ECCV | Blind Correction of Optical Aberrations. | Christian J. Schuler, Michael Hirsch, Stefan Harmeling, Bernhard Schlkopf |
| 2011 | ICCP | Removing noise from astronomical images using a pixel-specific noise model. | Harold Christopher Burger, Bernhard Schlkopf, Stefan Harmeling |
| 2011 | ICCV | Fast removal of non-uniform camera shake. | Michael Hirsch, Christian J. Schuler, Stefan Harmeling, Bernhard Schlkopf |
| 2011 | ICCV | Non-stationary correction of optical aberrations. | Christian J. Schuler, Michael Hirsch, Stefan Harmeling, Bernhard Schlkopf |
| 2011 | ICIP | Automatic foreground-background refocusing. | Alexander Loktyushin, Stefan Harmeling |
| 2010 | CVPR | Efficient filter flow for space-variant multiframe blind deconvolution. | Michael Hirsch, Suvrit Sra, Bernhard Schlkopf, Stefan Harmeling |
| 2010 | ICIP | Multiframe blind deconvolution, super-resolution, and saturation correction via incremental EM. | Stefan Harmeling, Suvrit Sra, Michael Hirsch, Bernhard Schlkopf |
| 2009 | CVPR | Learning to detect unseen object classes by between-class attribute transfer. | Christoph H. Lampert, Hannes Nickisch, Stefan Harmeling |
| 2007 | ACL | An Extensible Probabilistic Transformation-based Approach to the Third Recognizing Textual Entailment Challenge. | Stefan Harmeling |