| Adversarial patch TB Brown, D Mané, A Roy, M Abadi, J Gilmer Advances in Neural Information Processing Systems (Workshop Track), 2017 | 1374* | 2017 |
| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ... arXiv preprint arXiv:2312.11805, 2023 | 1126 | 2023 |
| Palm 2 technical report R Anil, AM Dai, O Firat, M Johnson, D Lepikhin, A Passos, S Shakeri, ... arXiv preprint arXiv:2305.10403, 2023 | 1094 | 2023 |
| Technical report on the cleverhans v2.1.0 N Papernot, F Faghri, A Roy, N Carlini, I Goodfellow, R Feinman, ... arXiv preprint arXiv:1610.00768, 2018 | 883* | 2018 |
| Thermometer encoding: One hot way to resist adversarial examples J Buckman, A Roy, C Raffel, I Goodfellow International Conference on Learning Representations (ICLR), 2018 | 750 | 2018 |
| Efficient content-based sparse attention with routing transformers A Roy, M Saffar, A Vaswani, D Grangier Transactions of the Association for Computational Linguistics (TACL) 9, 53-68, 2021 | 540 | 2021 |
| Learning to Remember Rare Events L Kaiser, O Nachum, A Roy, S Bengio International Conference on Learning Representations (ICLR), 2017 | 477* | 2017 |
| Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer D Berthelot, C Raffel, A Roy, I Goodfellow International Conference on Learning Representations (ICLR), 2019 | 311 | 2019 |
| Fast Decoding in Sequence Models Using Discrete Latent Variables Ł Kaiser, A Roy, A Vaswani, N Pamar, S Bengio, J Uszkoreit, N Shazeer International Conference on Machine Learning (ICML), 2390-2399, 2018 | 259* | 2018 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context M Reid, N Savinov, D Teplyashin, D Lepikhin, T Lillicrap, J Alayrac, ... arXiv preprint arXiv:2403.05530, 2024 | 216 | 2024 |
| Hurdles to Progress in Long-form Question Answering K Krishna, A Roy, M Iyyer North American Chapter of the Association for Computational Linguistics (NAACL), 2021 | 153 | 2021 |
| Hierarchical clustering via spreading metrics A Roy, S Pokutta Advances in Neural Information Processing Systems (NIPS), 2316-2324, 2016 | 97 | 2016 |
| Theory and experiments on vector quantized autoencoders A Roy, A Vaswani, A Neelakantan, N Parmar arXiv preprint arXiv:1805.11063, 2018 | 91 | 2018 |
| Reinforcement learning under model mismatch A Roy, H Xu, S Pokutta Advances in Neural Information Processing Systems (NIPS), 3043-3052, 2017 | 87 | 2017 |
| Unsupervised Paraphrasing without Translation A Roy, D Grangier Association for Computational Linguistics (ACL) 57, 6033–6039, 2019 | 63 | 2019 |
| Strong reductions for extended formulations G Braun, S Pokutta, A Roy Mathematical Programming 172 (1-2), 591-620, 2018 | 17 | 2018 |
| The matching problem has no small symmetric SDP G Braun, J Brown-Cohen, A Huq, S Pokutta, P Raghavendra, A Roy, ... ACM-SIAM Symposium on Discrete Algorithms (SODA) 16, 1067-1078, 2017 | 12* | 2017 |
| N-grammer: Augmenting transformers with latent n-grams A Roy, R Anil, G Lai, B Lee, J Zhao, S Zhang, S Wang, Y Zhang, S Wu, ... arXiv preprint arXiv:2207.06366, 2022 | 7* | 2022 |
| Progress and Challenges in Long-Form Open-Domain Question Answering A Roy | 3 | 2022 |
| LP and SDP extended formulations: lower bounds and approximation algorithms A Roy Georgia Institute of Technology, 2017 | | 2017 |
