| Efficient Transformers: A Survey D Tay, Yi and Dehghani, Mostafa and Bahri, Dara and Metzler ACM Computing Surveys, 2022 55 (0360-0300), 2022 | 1248* | 2022 |
| Long range arena: A benchmark for efficient transformers Y Tay, M Dehghani, S Abnar, Y Shen, D Bahri, P Pham, J Rao, L Yang, ... arXiv preprint arXiv:2011.04006, 2020 | 602 | 2020 |
| Berkeley advanced reconstruction toolbox M Uecker, F Ong, JI Tamir, D Bahri, P Virtue, JY Cheng, T Zhang, M Lustig Proc. Intl. Soc. Mag. Reson. Med 23 (2486), 9, 2015 | 442 | 2015 |
| Synthesizer: Rethinking self-attention for transformer models Y Tay, D Bahri, D Metzler, DC Juan, Z Zhao, C Zheng International conference on machine learning, 10183-10192, 2021 | 355 | 2021 |
| Sparse sinkhorn attention Y Tay, D Bahri, L Yang, D Metzler, DC Juan International Conference on Machine Learning, 9438-9447, 2020 | 317 | 2020 |
| Ul2: Unifying language learning paradigms Y Tay, M Dehghani, VQ Tran, X Garcia, J Wei, X Wang, HW Chung, ... arXiv preprint arXiv:2205.05131, 2022 | 239 | 2022 |
| Transformer memory as a differentiable search index Y Tay, V Tran, M Dehghani, J Ni, D Bahri, H Mehta, Z Qin, K Hui, Z Zhao, ... Advances in Neural Information Processing Systems 35, 21831-21843, 2022 | 203 | 2022 |
| Ext5: Towards extreme multi-task scaling for transfer learning V Aribandi, Y Tay, T Schuster, J Rao, HS Zheng, SV Mehta, H Zhuang, ... arXiv preprint arXiv:2111.10952, 2021 | 195 | 2021 |
| Scarf: Self-supervised contrastive learning using random feature corruption D Bahri, H Jiang, Y Tay, D Metzler arXiv preprint arXiv:2106.15147, 2021 | 150 | 2021 |
| Rethinking search: making domain experts out of dilettantes D Metzler, Y Tay, D Bahri, M Najork Acm sigir forum 55 (1), 1-27, 2021 | 135 | 2021 |
| Confident adaptive language modeling T Schuster, A Fisch, J Gupta, M Dehghani, D Bahri, V Tran, Y Tay, ... Advances in Neural Information Processing Systems 35, 17456-17472, 2022 | 134 | 2022 |
| Unifying language learning paradigms Y Tay, M Dehghani, VQ Tran, X Garcia, D Bahri, T Schuster, HS Zheng, ... arXiv preprint arXiv:2205.05131 10, 2022 | 130 | 2022 |
| Charformer: Fast character transformers via gradient-based subword tokenization Y Tay, VQ Tran, S Ruder, J Gupta, HW Chung, D Bahri, Z Qin, ... arXiv preprint arXiv:2106.12672, 2021 | 130 | 2021 |
| Deep k-nn for noisy labels D Bahri, H Jiang, M Gupta International Conference on Machine Learning, 540-550, 2020 | 85 | 2020 |
| Sharpness-aware minimization improves language model generalization D Bahri, H Mobahi, Y Tay arXiv preprint arXiv:2110.08529, 2021 | 83 | 2021 |
| Are pre-trained convolutions better than pre-trained transformers? Y Tay, M Dehghani, J Gupta, D Bahri, V Aribandi, Z Qin, D Metzler arXiv preprint arXiv:2105.03322, 2021 | 83 | 2021 |
| StructFormer: Joint unsupervised induction of dependency and constituency structure from masked language modeling Y Shen, Y Tay, C Zheng, D Bahri, D Metzler, A Courville arXiv preprint arXiv:2012.00857, 2020 | 42 | 2020 |
| Hypergrid transformers: Towards a single model for multiple tasks Y Tay, Z Zhao, D Bahri, D Metzler, DC Juan International conference on learning representations, 2020 | 41 | 2020 |
| Omninet: Omnidirectional representations from transformers Y Tay, M Dehghani, V Aribandi, J Gupta, PM Pham, Z Qin, D Bahri, ... International Conference on Machine Learning, 10193-10202, 2021 | 34 | 2021 |
| Diminishing returns shape constraints for interpretability and regularization M Gupta, D Bahri, A Cotter, K Canini Advances in neural information processing systems 31, 2018 | 29 | 2018 |
