| Laion-5b: An open large-scale dataset for training next generation image-text models C Schuhmann, R Beaumont, R Vencu, C Gordon, R Wightman, M Cherti, ... Advances in neural information processing systems 35, 25278-25294, 2022 | 3094 | 2022 |
| Large pre-trained language models contain human-like biases of what is right and wrong to do P Schramowski, C Turan, N Andersen, CA Rothkopf, K Kersting Nature Machine Intelligence 4 (3), 258-268, 2022 | 344 | 2022 |
| Making deep neural networks right for the right scientific reasons by interacting with their explanations P Schramowski, W Stammer, S Teso, A Brugger, F Herbert, X Shao, ... Nature Machine Intelligence 2 (8), 476-486, 2020 | 280 | 2020 |
| Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models P Schramowski, M Brack, B Deiseroth, K Kersting Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 251 | 2023 |
| Right for the right concept: Revising neuro-symbolic concepts by interacting with their explanations W Stammer, P Schramowski, K Kersting Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021 | 116 | 2021 |
| Sega: Instructing text-to-image models using semantic guidance M Brack, F Friedrich, D Hintersdorf, L Struppek, P Schramowski, ... Advances in Neural Information Processing Systems 36, 25365-25389, 2023 | 107* | 2023 |
| Auditing and instructing text-to-image generation models on fairness F Friedrich, M Brack, L Struppek, D Hintersdorf, P Schramowski, ... AI and Ethics, 1-21, 2024 | 97* | 2024 |
| Pad\'e activation units: End-to-end learning of flexible activation functions in deep networks A Molina, P Schramowski, K Kersting arXiv preprint arXiv:1907.06732, 2019 | 94 | 2019 |
| Can machines help us answering question 16 in datasheets, and in turn reflecting on inappropriate content? P Schramowski, C Tauchmann, K Kersting Proceedings of the 2022 ACM conference on fairness, accountability, and …, 2022 | 84 | 2022 |
| Semantics derived automatically from language corpora contain human-like moral choices S Jentzsch, P Schramowski, C Rothkopf, K Kersting Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 37-44, 2019 | 84 | 2019 |
| Ledits++: Limitless image editing using text-to-image models M Brack, F Friedrich, K Kornmeier, L Tsaban, P Schramowski, K Kersting, ... Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2024 | 71* | 2024 |
| The moral choice machine P Schramowski, C Turan, S Jentzsch, C Rothkopf, K Kersting Frontiers in artificial intelligence 3, 36, 2020 | 46 | 2020 |
| Extending hyperspectral imaging for plant phenotyping to the UV-range A Brugger, J Behmann, S Paulus, HG Luigs, MT Kuska, P Schramowski, ... Remote Sensing 11 (12), 1401, 2019 | 44 | 2019 |
| Laion-5b: An open large-scale dataset for training next generation image-text models, 2022 C Schuhmann, R Beaumont, R Vencu, C Gordon, R Wightman, M Cherti, ... URL https://arxiv. org/abs/2210.08402, 2022 | 41 | 2022 |
| Right for better reasons: Training differentiable models by constraining their influence functions X Shao, A Skryagin, W Stammer, P Schramowski, K Kersting Proceedings of the AAAI Conference on Artificial Intelligence 35 (11), 9533-9540, 2021 | 37 | 2021 |
| Introducing v0. 5 of the ai safety benchmark from mlcommons B Vidgen, A Agrawal, AM Ahmed, V Akinwande, N Al-Nuaimi, N Alfaraj, ... arXiv preprint arXiv:2404.12241, 2024 | 33 | 2024 |
| Speaking multiple languages affects the moral bias of language models K Hämmerl, B Deiseroth, P Schramowski, J Libovický, CA Rothkopf, ... arXiv preprint arXiv:2211.07733, 2022 | 32 | 2022 |
| BERT has a Moral Compass: Improvements of ethical and moral values of machines P Schramowski, C Turan, S Jentzsch, C Rothkopf, K Kersting arXiv preprint arXiv:1912.05238, 2019 | 31 | 2019 |
| ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming S Tedeschi, F Friedrich, P Schramowski, K Kersting, R Navigli, H Nguyen, ... arXiv preprint arXiv:2404.08676, 2024 | 30 | 2024 |
| Multifusion: Fusing pre-trained models for multi-lingual, multi-modal image generation M Bellagente, M Brack, H Teufel, F Friedrich, B Deiseroth, C Eichenberg, ... Advances in Neural Information Processing Systems 36, 59502-59521, 2023 | 30* | 2023 |
Kristian KerstingProfessor of AI & ML, Technical University of Darmstadt, Co-Director hessian.ai, DFKI, CAIRNE, ELLISبريد إلكتروني تم التحقق منه على cs.tu-darmstadt.de