Hierarchical nucleation in deep neural networks D Doimo, A Glielmo, A Ansuini, A Laio Advances in Neural Information Processing Systems 33, 7526-7536, 2020 | 43* | 2020 |
The geometry of hidden representations of large transformer models L Valeriani*, D Doimo*, F Cuturello, A Laio, A Ansuini, A Cazzaniga Advances in Neural Information Processing Systems 36, 2023 | 22 | 2023 |
The Generalized Ratios Intrinsic Dimension Estimator F Denti, D Doimo, A Laio, A Mira Scientific Reports 12 (1), 20005, 2022 | 20* | 2022 |
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 | 19 | 2022 |
Redundant representations help generalization in wide neural networks D Doimo, A Glielmo, S Goldt, A Laio Advances in Neural Information Processing Systems 35, 2022 | 8* | 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, 2024 | 2 | 2024 |
Optimal transfer protocol by incremental layer defrosting F Gerace, D Doimo, SS Mannelli, L Saglietti, A Laio arXiv preprint arXiv:2303.01429, 2023 | 1 | 2023 |
Emergence of a High-Dimensional Abstraction Phase in Language Transformers E Cheng, D Doimo, C Kervadec, I Macocco, J Yu, A Laio, M Baroni arXiv preprint arXiv:2405.15471, 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 |
How to choose the right transfer learning protocol? A qual-itative analysis in a controlled set-up F Gerace, D Doimo, SS Mannelli, L Saglietti, A Laio | | |