| 2025 | CVPR | Joint Out-of-Distribution Filtering and Data Discovery Active Learning. | Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Gnnemann |
| 2025 | ICLR | Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecasting. | Marcel Kollovieh, Marten Lienen, David Ldke, Leo Schwinn, Stephan Gnnemann |
| 2025 | ICLR | A Probabilistic Perspective on Unlearning and Alignment for Large Language Models. | Yan Scholten, Stephan Gnnemann, Leo Schwinn |
| 2025 | ICML | Efficient Time Series Processing for Transformers and State-Space Models through Token Merging. | Leon Gtz, Marcel Kollovieh, Stephan Gnnemann, Leo Schwinn |
| 2025 | ICML | When to retrain a machine learning model. | Florence Regol, Leo Schwinn, Kyle Sprague, Mark Coates, Thomas Markovich |
| 2023 | AAAI | FastAMI - a Monte Carlo Approach to the Adjustment for Chance in Clustering Comparison Metrics. | Kai Klede, Leo Schwinn, Dario Zanca, Bjrn M. Eskofier |
| 2023 | IJCNN | Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networks. | Thomas Altstidl, An Nguyen, Leo Schwinn, Franz Kferl, Christopher Mutschler, Bjrn M. Eskofier, Dario Zanca |
| 2022 | ICML | Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification. | Leo Schwinn, Leon Bungert, An Nguyen, Ren Raab, Falk Pulsmeyer, Doina Precup, Bjoern M. Eskofier, Dario Zanca |
| 2021 | IJCNN | Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks. | Leo Schwinn, An Nguyen, Ren Raab, Dario Zanca, Bjoern M. Eskofier, Daniel Tenbrinck, Martin Burger |
| 2021 | UAI | Identifying untrustworthy predictions in neural networks by geometric gradient analysis. | Leo Schwinn, An Nguyen, Ren Raab, Leon Bungert, Daniel Tenbrinck, Dario Zanca, Martin Burger, Bjrn M. Eskofier |
| 2020 | ICPM | Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring. | An Nguyen, Srijeet Chatterjee, Sven Weinzierl, Leo Schwinn, Martin Matzner, Bjoern M. Eskofier |