| Transformers learn in-context by gradient descent J von Oswald, E Niklasson, E Randazzo, J Sacramento, A Mordvintsev, ... ICML 2023 (Oral), 2023 | 779 | 2023 |
| Continual learning with hypernetworks J von Oswald, C Henning, BF Grewe, J Sacramento ICLR 2020 (Spotlight), 2019 | 554 | 2019 |
| Uncovering mesa-optimization algorithms in transformers J von Oswald, M Schlegel, A Meulemans, S Kobayashi, E Niklasson, ... arXiv preprint arXiv:2309.05858, 2023 | 113* | 2023 |
| Posterior meta-replay for continual learning C Henning, M Cervera, F D'Angelo, J von Oswald, R Traber, B Ehret, ... NeurIPS 2021, 2021 | 94 | 2021 |
| Meta-Learning via Hypernetworks D Zhao, S Kobayashi, J Sacramento, J von Oswald 4th Workshop on Meta-Learning at NeurIPS 2020, Vancouver, Canada, 2020 | 87 | 2020 |
| Learning where to learn: Gradient sparsity in meta and continual learning J von Oswald, D Zhao, S Kobayashi, S Schug, M Caccia, N Zucchet, ... NeurIPS 2021, 2021 | 80 | 2021 |
| Continual learning in recurrent neural networks B Ehret, C Henning, MR Cervera, A Meulemans, J von Oswald, BF Grewe ICLR 2021, 2020 | 78* | 2020 |
| Neural networks with late-phase weights J von Oswald, S Kobayashi, A Meulemans, C Henning, BF Grewe, ... ICLR 2021, 2020 | 48 | 2020 |
| The least-control principle for local learning at equilibrium A Meulemans, N Zucchet, S Kobayashi, J von Oswald, J Sacramento NeurIPS 2022 (Oral), 2022 | 36 | 2022 |
| Weight decay induces low-rank attention layers S Kobayashi, Y Akram, J von Oswald NeurIPS 2024, 2024 | 30 | 2024 |
| Random initialisations performing above chance and how to find them F Benzing, S Schug, R Meier, J von Oswald, Y Akram, N Zucchet, ... OPT2022: 14th Annual Workshop on Optimization for Machine Learning, 2022 | 30 | 2022 |
| Linear Transformers are Versatile In-Context Learners M Vladymyrov, J von Oswald, M Sandler, R Ge NeurIPS 2024, 2024 | 27 | 2024 |
| Approximating the predictive distribution via adversarially-trained hypernetworks C Henning, J von Oswald, J Sacramento, SC Surace, JP Pfister, ... Bayesian Deep Learning Workshop, NeurIPS 2018 (Spotlight), 2018 | 27 | 2018 |
| A contrastive rule for meta-learning N Zucchet, S Schug, J von Oswald, D Zhao, J Sacramento NeurIPS 2022, 2022 | 26 | 2022 |
| Discovering modular solutions that generalize compositionally S Schug, S Kobayashi, Y Akram, M Wołczyk, A Proca, J von Oswald, ... ICLR 2024, 2023 | 25 | 2023 |
| MesaNet: Sequence Modeling by Locally Optimal Test-Time Training J von Oswald, N Scherrer, S Kobayashi, L Versari, S Yang, M Schlegel, ... arXiv preprint arXiv:2506.05233, 2025 | 21 | 2025 |
| Gated recurrent neural networks discover attention N Zucchet, S Kobayashi, Y Akram, J von Oswald, M Larcher, A Steger, ... arXiv preprint arXiv:2309.01775, 2023 | 16 | 2023 |
| Adversarial robustness of in-context learning in transformers for linear regression U Anwar, J von Oswald, L Kirsch, D Krueger, S Frei arXiv preprint arXiv:2411.05189, 2024 | 13 | 2024 |
| On the reversed bias-variance tradeoff in deep ensembles S Kobayashi, J von Oswald, BF Grewe ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning, 2021 | 11 | 2021 |
| When can transformers compositionally generalize in-context? S Kobayashi, S Schug, Y Akram, F Redhardt, J von Oswald, R Pascanu, ... ICML 2024 Next Generation of Sequence Modeling Architectures Workshop, 2024 | 5 | 2024 |
João SacramentoGoogleVerified email at joaosacramento.com
