| Language models as knowledge bases? F Petroni, T Rocktäschel, P Lewis, A Bakhtin, Y Wu, AH Miller, S Riedel arXiv preprint arXiv:1909.01066, 2019 | 2844 | 2019 |
| Human-level play in the game of Diplomacy by combining language models with strategic reasoning Meta Fundamental AI Research Diplomacy Team (FAIR)†, A Bakhtin, ... Science 378 (6624), 1067-1074, 2022 | 225 | 2022 |
| Combining deep reinforcement learning and search for imperfect-information games N Brown, A Bakhtin, A Lerer, Q Gong Advances in Neural Information Processing Systems 33, 17057-17069, 2020 | 161 | 2020 |
| Real or fake? learning to discriminate machine from human generated text A Bakhtin, S Gross, M Ott, Y Deng, MA Ranzato, A Szlam arXiv preprint arXiv:1906.03351, 2019 | 160 | 2019 |
| Residual energy-based models for text generation Y Deng, A Bakhtin, M Ott, A Szlam, MA Ranzato arXiv preprint arXiv:2004.11714, 2020 | 149 | 2020 |
| Towards Measuring the Representation of Subjective Global Opinions in Language Models E Durmus, K Nyugen, TI Liao, N Schiefer, A Askell, A Bakhtin, C Chen, ... arXiv preprint arXiv:2306.16388, 2023 | 139 | 2023 |
| Phyre: A new benchmark for physical reasoning A Bakhtin, L van der Maaten, J Johnson, L Gustafson, R Girshick Advances in Neural Information Processing Systems 32, 2019 | 136 | 2019 |
| Streaming small-footprint keyword spotting using sequence-to-sequence models Y He, R Prabhavalkar, K Rao, W Li, A Bakhtin, I McGraw 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2017 | 103 | 2017 |
| On the efficient representation and execution of deep acoustic models R Alvarez, R Prabhavalkar, A Bakhtin arXiv preprint arXiv:1607.04683, 2016 | 67 | 2016 |
| Modeling strong and human-like gameplay with KL-regularized search AP Jacob, DJ Wu, G Farina, A Lerer, H Hu, A Bakhtin, J Andreas, N Brown International Conference on Machine Learning, 9695-9728, 2022 | 59 | 2022 |
| Human-level performance in no-press diplomacy via equilibrium search J Gray, A Lerer, A Bakhtin, N Brown arXiv preprint arXiv:2010.02923, 2020 | 54 | 2020 |
| No-press diplomacy from scratch A Bakhtin, D Wu, A Lerer, N Brown Advances in Neural Information Processing Systems 34, 18063-18074, 2021 | 45 | 2021 |
| Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning A Bakhtin, DJ Wu, A Lerer, J Gray, AP Jacob, G Farina, AH Miller, ... arXiv preprint arXiv:2210.05492, 2022 | 43 | 2022 |
| Residual energy-based models for text A Bakhtin, Y Deng, S Gross, M Ott, MA Ranzato, A Szlam Journal of Machine Learning Research 22 (40), 1-41, 2021 | 42 | 2021 |
| Key phrase spotting W Li, RP Prabhavalkar, KK Rao, Y He, IC McGraw, A Bakhtin US Patent 11,295,739, 2022 | 15 | 2022 |
| Lightweight adaptive mixture of neural and n-gram language models A Bakhtin, A Szlam, MA Ranzato, E Grave arXiv preprint arXiv:1804.07705, 2018 | 15 | 2018 |
| Ogre: An object-based generalization for reasoning environment KR Allen, A Bakhtin, K Smith, JB Tenenbaum, L van der Maaten NeurIPS Workshop on Object Representations for Learning and Reasoning, 2020 | 10 | 2020 |
| Energy-based models for text A Bakhtin, Y Deng, S Gross, M Ott, M Ranzato, A Szlam arXiv preprint arXiv:2004.10188, 2020 | 10 | 2020 |
| Dictionary Augmented Sequence-to-Sequence Neural Network for Grapheme to Phoneme Prediction. A Bruguier, A Bakhtin, D Sharma INTERSPEECH, 3733-3737, 2018 | 9 | 2018 |
| Physical Reasoning Using Dynamics-Aware Models E Ahmed, A Bakhtin, L van der Maaten, R Girdhar arXiv preprint arXiv:2102.10336, 2021 | 6 | 2021 |
Marc'Aurelio RanzatoGoogle DeepMindVerified email at google.com
