| Scaling vision transformers to 22 billion parameters M Dehghani, J Djolonga, B Mustafa, P Padlewski, J Heek, J Gilmer, ... ICML 2023, 2023 | 253 | 2023 |
| VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation M Kumar, M Babaeizadeh, D Erhan, C Finn, S Levine, L Dinh, D Kingma ICLR 2020, 2020 | 233* | 2020 |
| scikit-optimize/scikit-optimize: v0. 5.2 T Head, M Kumar, L Gilles, I Shcherbatyi Zenodo, 2018 | 219* | 2018 |
| Colorization Transformer M Kumar, D Weissenborn, N Kalchbrenner ICLR 2021, 2021 | 165 | 2021 |
| Deep learning for twelve hour precipitation forecasts L Espeholt, S Agrawal, C Sønderby, M Kumar, J Heek, C Bromberg, ... Nature communications 13 (1), 1-10, 2022 | 162* | 2022 |
| Parallel architecture and hyperparameter search via successive halving and classification M Kumar, GE Dahl, V Vasudevan, M Norouzi arXiv preprint arXiv:1805.10255, 2018 | 30 | 2018 |
| Do better ImageNet classifiers assess perceptual similarity better? M Kumar, N Houlsby, N Kalchbrenner, ED Cubuk TMLR 2022, 2022 | 29* | 2022 |
| Image Captioners Are Scalable Vision Learners Too M Tschannen, M Kumar, A Steiner, X Zhai, N Houlsby, L Beyer NeurIPS 2023, 2023 | 24 | 2023 |
| Dual PatchNorm M Kumar, M Dehghani, N Houlsby TMLR 2023, 2023 | 4 | 2023 |
| Frozen Feature Augmentation for Few-Shot Image Classification A Bär, N Houlsby, M Dehghani, M Kumar CVPR 2024, 2024 | | 2024 |
