| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, JB Alayrac, J Yu, R Soricut, J Schalkwyk, ... arXiv preprint arXiv:2312.11805, 2023 | 2217 | 2023 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ... arXiv preprint arXiv:2403.05530, 2024 | 703 | 2024 |
| Towards understanding knowledge distillation M Phuong, C Lampert International conference on machine learning, 5142-5151, 2019 | 336 | 2019 |
| Distillation-based training for multi-exit architectures M Phuong, CH Lampert Proceedings of the IEEE/CVF international conference on computer vision …, 2019 | 210 | 2019 |
| Model evaluation for extreme risks T Shevlane, S Farquhar, B Garfinkel, M Phuong, J Whittlestone, J Leung, ... arXiv preprint arXiv:2305.15324, 2023 | 134 | 2023 |
| Formal algorithms for transformers M Phuong, M Hutter arXiv preprint arXiv:2207.09238, 2022 | 100 | 2022 |
| Goal misgeneralization: Why correct specifications aren't enough for correct goals R Shah, V Varma, R Kumar, M Phuong, V Krakovna, J Uesato, Z Kenton arXiv preprint arXiv:2210.01790, 2022 | 57 | 2022 |
| The inductive bias of ReLU networks on orthogonally separable data P Bui Thi Mai, C Lampert 9th International Conference on Learning Representations, 2021 | 44 | 2021 |
| Functional vs. parametric equivalence of ReLU networks P Bui Thi Mai, C Lampert 8th International Conference on Learning Representations, 2020 | 40 | 2020 |
| Evaluating frontier models for dangerous capabilities M Phuong, M Aitchison, E Catt, S Cogan, A Kaskasoli, V Krakovna, ... arXiv preprint arXiv:2403.13793, 2024 | 38 | 2024 |
| The mutual autoencoder: Controlling information in latent code representations M Phuong, M Welling, N Kushman, R Tomioka, S Nowozin | 25 | 2018 |
| Model evaluation for extreme risks (arXiv: 2305.15324). arXiv T Shevlane, S Farquhar, B Garfinkel, M Phuong, J Whittlestone, J Leung, ... | 10 | 2023 |
| The mutual autoencoder: Controlling information in latent code representations, 2018 M Phuong, M Welling, N Kushman, R Tomioka, S Nowozin URL https://openreview. net/forum, 0 | 8 | |
| Against the flow of time with multi-output models J Jakubík, P Bui Thi Mai, M Chvosteková, A Krakovská Measurement Science Review 23 (4), 2023 | | 2023 |
| Underspecification in deep learning P Bui Thi Mai | | 2021 |
