| Measuring compositional generalization: A comprehensive method on realistic data D Keysers, N Schärli, N Scales, H Buisman, D Furrer, S Kashubin, ... arXiv preprint arXiv:1912.09713, 2019 | 392 | 2019 |
| Continental-scale building detection from high resolution satellite imagery W Sirko, S Kashubin, M Ritter, A Annkah, YSE Bouchareb, Y Dauphin, ... arXiv preprint arXiv:2107.12283, 2021 | 241 | 2021 |
| Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments OT Unke, M Stöhr, S Ganscha, T Unterthiner, H Maennel, S Kashubin, ... Science Advances 10 (14), eadn4397, 2024 | 45 | 2024 |
| Accurate machine learned quantum-mechanical force fields for biomolecular simulations OT Unke, M Stöhr, S Ganscha, T Unterthiner, H Maennel, S Kashubin, ... arXiv preprint arXiv:2205.08306, 2022 | 32 | 2022 |
| Variance reduction in deep learning: More momentum is all you need L Tondji, S Kashubin, M Cisse arXiv preprint arXiv:2111.11828, 2021 | 2 | 2021 |
| The QCML dataset, Quantum chemistry reference data from 33.5 M DFT and 14.7 B semi-empirical calculations S Ganscha, OT Unke, D Ahlin, H Maennel, S Kashubin, KR Müller Scientific Data 12 (1), 406, 2025 | 1 | 2025 |
| Discover: Deep Scalable Variance Reduction LN Tondji, M Cisse, S Kashubin | | 2021 |
