| Underspecification presents challenges for credibility in modern machine learning A D'Amour, K Heller, D Moldovan, B Adlam, B Alipanahi, A Beutel, ... Journal of Machine Learning Research 23 (226), 1-61, 2022 | 1046 | 2022 |
| Transformers learn in-context by gradient descent J Von Oswald, E Niklasson, E Randazzo, J Sacramento, A Mordvintsev, ... International Conference on Machine Learning, 35151-35174, 2023 | 781 | 2023 |
| Hypertransformer: Model generation for supervised and semi-supervised few-shot learning A Zhmoginov, M Sandler, M Vladymyrov International Conference on Machine Learning, 27075-27098, 2022 | 108 | 2022 |
| Gradmax: Growing neural networks using gradient information U Evci, B van Merrienboer, T Unterthiner, M Vladymyrov, F Pedregosa arXiv preprint arXiv:2201.05125, 2022 | 82 | 2022 |
| Uncovering mesa-optimization algorithms in transformers J Von Oswald, M Schlegel, A Meulemans, S Kobayashi, E Niklasson, ... arXiv preprint arXiv:2309.05858, 2023 | 79 | 2023 |
| Fine-tuning image transformers using learnable memory M Sandler, A Zhmoginov, M Vladymyrov, A Jackson Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 69 | 2022 |
| Entropic affinities: Properties and efficient numerical computation M Vladymyrov, M Carreira-Perpinan International conference on machine learning, 477-485, 2013 | 62 | 2013 |
| Locally linear landmarks for large-scale manifold learning M Vladymyrov, MÁ Carreira-Perpinán Joint European Conference on Machine Learning and Knowledge Discovery in …, 2013 | 54 | 2013 |
| Partial-Hessian strategies for fast learning of nonlinear embeddings M Vladymyrov, M Carreira-Perpinan arXiv preprint arXiv:1206.4646, 2012 | 49 | 2012 |
| The variational nystrom method for large-scale spectral problems M Vladymyrov, M Carreira-Perpinan International Conference on Machine Learning, 211-220, 2016 | 35 | 2016 |
| Linear-time training of nonlinear low-dimensional embeddings M Vladymyrov, M Carreira-Perpinan Artificial Intelligence and Statistics, 968-977, 2014 | 30 | 2014 |
| Linear transformers are versatile in-context learners M Vladymyrov, J Von Oswald, M Sandler, R Ge Advances in Neural Information Processing Systems 37, 48784-48809, 2024 | 27 | 2024 |
| Meta-learning bidirectional update rules M Sandler, M Vladymyrov, A Zhmoginov, N Miller, T Madams, A Jackson, ... International Conference on Machine Learning, 9288-9300, 2021 | 19 | 2021 |
| A fast, universal algorithm to learn parametric nonlinear embeddings MA Carreira-Perpinán, M Vladymyrov Advances in Neural Information Processing Systems 28, 2015 | 15 | 2015 |
| Training trajectories, mini-batch losses and the curious role of the learning rate M Sandler, A Zhmoginov, M Vladymyrov, N Miller arXiv preprint arXiv:2301.02312, 2023 | 13 | 2023 |
| How new data permeates LLM knowledge and how to dilute it C Sun, R Aksitov, A Zhmoginov, NA Miller, M Vladymyrov, U Rueckert, ... arXiv preprint arXiv:2504.09522, 2025 | 10 | 2025 |
| Learning and unlearning of fabricated knowledge in language models C Sun, NA Miller, A Zhmoginov, M Vladymyrov, M Sandler arXiv preprint arXiv:2410.21750, 2024 | 7 | 2024 |
| Continual few-shot learning using hypertransformers M Vladymyrov, A Zhmoginov, M Sandler CoRR, 2023 | 7 | 2023 |
| Decentralized learning with multi-headed distillation A Zhmoginov, M Sandler, N Miller, G Kristiansen, M Vladymyrov Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 7 | 2023 |
| No pressure! addressing the problem of local minima in manifold learning algorithms M Vladymyrov Advances in neural information processing systems 32, 2019 | 5 | 2019 |
Andrey ZhmoginovGoogle DeepMindVerified email at google.com
