| Towards neural networks that provably know when they don't know A Meinke, M Hein arXiv preprint arXiv:1909.12180, 2019 | 174 | 2019 |
| Adversarial robustness on in-and out-distribution improves explainability M Augustin, A Meinke, M Hein European Conference on Computer Vision, 228-245, 2020 | 106 | 2020 |
| Certifiably adversarially robust detection of out-of-distribution data J Bitterwolf, A Meinke, M Hein Advances in Neural Information Processing Systems 33, 16085-16095, 2020 | 88 | 2020 |
| Breaking down out-of-distribution detection: Many methods based on ood training data estimate a combination of the same core quantities J Bitterwolf, A Meinke, M Augustin, M Hein International conference on machine learning, 2041-2074, 2022 | 36 | 2022 |
| Provably adversarially robust detection of out-of-distribution data (almost) for free A Meinke, J Bitterwolf, M Hein Advances in Neural Information Processing Systems 35, 30167-30180, 2022 | 32* | 2022 |
| Me, myself, and ai: The situational awareness dataset (sad) for llms R Laine, B Chughtai, J Betley, K Hariharan, J Scheurer, M Balesni, ... arXiv preprint arXiv:2407.04694, 2024 | 19 | 2024 |
| Network inference and maximum entropy estimation on information diagrams EA Martin, J Hlinka, A Meinke, F Děchtěrenko, J Tintěra, I Oliver, ... Scientific reports 7 (1), 7062, 2017 | 16 | 2017 |
| Towards a situational awareness benchmark for llms R Laine, A Meinke, O Evans Socially responsible language modelling research, 2023 | 10 | 2023 |
| Towards evaluations-based safety cases for ai scheming M Balesni, M Hobbhahn, D Lindner, A Meinke, T Korbak, J Clymer, ... arXiv preprint arXiv:2411.03336, 2024 | 6 | 2024 |
| Frontier models are capable of in-context scheming A Meinke, B Schoen, J Scheurer, M Balesni, R Shah, M Hobbhahn arXiv preprint arXiv:2412.04984, 2024 | 5 | 2024 |
| Tell, don't show: Declarative facts influence how LLMs generalize A Meinke, O Evans arXiv preprint arXiv:2312.07779, 2023 | 4 | 2023 |
| Classifiers should do well even on their worst classes J Bitterwolf, A Meinke, V Boreiko, M Hein ICML 2022 Shift Happens Workshop, 2022 | 4 | 2022 |
| Robust out-of-distribution detection in deep classifiers A Meinke Universität Tübingen, 2023 | | 2023 |
| Improving Fairness and Cybersecurity in the Artificial Intelligence Act. G Carovano, A Meinke EWAF, 2023 | | 2023 |
| Applications of the Extremal Functional Bootstrap A Meinke Universidade de São Paulo, 2018 | | 2018 |
Matthias HeinProfessor of Computer Science, University of TübingenE-mailová adresa ověřena na: uni-tuebingen.de