| The geometry of hidden representations of large transformer models L Valeriani*, D Doimo*, F Cuturello, A Laio, A Ansuini, A Cazzaniga NeurIPS 2023 - Advances in Neural Information Processing Systems 36, 2023 | 42 | 2023 |
| DADApy: Distance-based analysis of data-manifolds in Python A Glielmo, I Macocco, D Doimo, M Carli, C Zeni, R Wild, M d’Errico, ... Patterns 3 (10), 2022 | 41* | 2022 |
| Hierarchical nucleation in deep neural networks D Doimo, A Glielmo, A Ansuini, A Laio NeurIPS 2020 - Advances in Neural Information Processing Systems 33, 7526-7536, 2020 | 35 | 2020 |
| The Generalized Ratios Intrinsic Dimension Estimator F Denti, D Doimo, A Laio, A Mira Scientific Reports 12 (1), 20005, 2022 | 24* | 2022 |
| Redundant representations help generalization in wide neural networks D Doimo, A Glielmo, S Goldt, A Laio NeurIPS 2022 - Advances in Neural Information Processing Systems 35, 2022 | 10 | 2022 |
| Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals F Ortu, Z Jin, D Doimo, M Sachan, A Cazzaniga, B Schölkopf ACL 2024 - Proceedings of the 62nd Annual Meeting of the Association for …, 2024 | 8 | 2024 |
| Emergence of a High-Dimensional Abstraction Phase in Language Transformers E Cheng, D Doimo, C Kervadec, I Macocco, J Yu, A Laio, M Baroni ICLR 2025 - The 13th International Conference on Learning Representations, 2024 | 6 | 2024 |
| How to choose the right transfer learning protocol? A qualitative analysis in a controlled set-up F Gerace, D Doimo, S Sarao Mannelli, L Saglietti, A Laio TMLR - Transactions on Machine Learning Research, 2024 | 1* | 2024 |
| The Narrow Gate: Localized Image-Text Communication in Vision-Language Models A Serra, F Ortu, E Panizon, L Valeriani, L Basile, A Ansuini, D Doimo, ... arXiv preprint arXiv:2412.06646, 2024 | | 2024 |
| Understanding Variational Autoencoders with Intrinsic Dimension and Information Imbalance C Camboulin, D Doimo, A Glielmo NeurIPS 2024 - Workshop on Unifying Representations in Neural Models (UniReps), 2024 | | 2024 |
| The representation landscape of few-shot learning and fine-tuning in large language models D Doimo, A Serra, A Ansuini, A Cazzaniga NeurIPS 2024 - Advances in Neural Information Processing Systems 37, 2024 | | 2024 |
| Redundant representations help generalization in wide neural networks D Doimo, A Glielmo, S Goldt, A Laio Journal of Statistical Mechanics: Theory and Experiment 2023 (11), 114011, 2023 | | 2023 |
Alessandro LaioSISSADirección de correo verificada de sissa.it