| 2025 | ICLR | How to Probe: Simple Yet Effective Techniques for Improving Post-hoc Explanations. | Siddhartha Gairola, Moritz Bhle, Francesco Locatello, Bernt Schiele |
| 2024 | ECCV | Good Teachers Explain: Explanation-Enhanced Knowledge Distillation. | Amin Parchami-Araghi, Moritz Bhle, Sukrut Rao, Bernt Schiele |
| 2024 | ECCV | Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. | Sukrut Rao, Sweta Mahajan, Moritz Bhle, Bernt Schiele |
| 2023 | ICCV | Studying How to Efficiently and Effectively Guide Models with Explanations. | Sukrut Rao, Moritz Bhle, Amin Parchami-Araghi, Bernt Schiele |
| 2023 | ICLR | Temperature Schedules for self-supervised contrastive methods on long-tail data. | Anna Kukleva, Moritz Bhle, Bernt Schiele, Hilde Kuehne, Christian Rupprecht |
| 2022 | CVPR | B-cos Networks: Alignment is All We Need for Interpretability. | Moritz Bhle, Mario Fritz, Bernt Schiele |
| 2022 | CVPR | Towards Better Understanding Attribution Methods. | Sukrut Rao, Moritz Bhle, Bernt Schiele |
| 2021 | CVPR | Convolutional Dynamic Alignment Networks for Interpretable Classifications. | Moritz Bhle, Mario Fritz, Bernt Schiele |