| Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models G Ortiz-Jimenez*, A Favero*, P Frossard Advances in Neural Information Processing Systems 36, 66727-66754, 2024 | 118 | 2024 |
| Multi-Modal Hallucination Control by Visual Information Grounding A Favero, L Zancato, M Trager, S Choudhary, P Perera, A Achille, ... IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14303 …, 2024 | 61 | 2024 |
| A phase transition in diffusion models reveals the hierarchical nature of data A Sclocchi, A Favero, M Wyart Proceedings of the National Academy of Sciences 122 (1), e2408799121, 2025 | 34* | 2025 |
| How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model F Cagnetta, L Petrini, UM Tomasini, A Favero, M Wyart Physical Review X 14 (3), 031001, 2024 | 30 | 2024 |
| What Can Be Learnt With Wide Convolutional Neural Networks? F Cagnetta*, A Favero*, M Wyart International Conference on Machine Learning, PMLR 202, 3347-3379, 2023 | 25 | 2023 |
| Locality defeats the curse of dimensionality in convolutional teacher-student scenarios A Favero*, F Cagnetta*, M Wyart Advances in Neural Information Processing Systems 34, 9456-9467, 2021 | 23 | 2021 |
| Relative stability toward diffeomorphisms indicates performance in deep nets L Petrini, A Favero, M Geiger, M Wyart Advances in Neural Information Processing Systems 34, 8727-8739, 2021 | 16 | 2021 |
| Lines: Post-training layer scaling prevents forgetting and enhances model merging K Wang, N Dimitriadis, A Favero, G Ortiz-Jimenez, F Fleuret, P Frossard International Conference on Learning Representations (ICLR), 2025 | 4 | 2025 |
| Probing the Latent Hierarchical Structure of Data via Diffusion Models A Sclocchi*, A Favero*, NI Levi*, M Wyart International Conference on Learning Representations (ICLR), 2025 | 4 | 2025 |
| How compositional generalization and creativity improve as diffusion models are trained A Favero, A Sclocchi, F Cagnetta, P Frossard, M Wyart arXiv preprint arXiv:2502.12089, 2025 | | 2025 |
| Computational complexity of deep learning: fundamental limitations and empirical phenomena B Barak, A Carrell, A Favero, W Li, L Stephan, A Zlokapa Journal of Statistical Mechanics: Theory and Experiment 2024 (10), 104008, 2024 | | 2024 |
| What can be learnt with wide convolutional neural networks?* F Cagnetta, A Favero, M Wyart Journal of Statistical Mechanics: Theory and Experiment 2024 (10), 104020, 2024 | | 2024 |
| Unraveling the Latent Hierarchical Structure of Language and Images via Diffusion Models A Sclocchi, NI Levi, A Favero, M Wyart NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning, 2024 | | 2024 |
| Task Addition and Weight Disentanglement in Closed-Vocabulary Models A Hazimeh*, A Favero*, P Frossard ICML 2024 Workshop on Efficient Systems for Foundation Models II, 2024 | | 2024 |
| Statistical Mechanics of Infinitely-Wide Convolutional Networks A Favero, F Cagnetta, M Wyart Bulletin of the American Physical Society, 2023 | | 2023 |
| Diffeomorphisms invariance is a proxy of performance in deep neural networks L Petrini, A Favero, M Geiger, M Wyart Bulletin of the American Physical Society, 2023 | | 2023 |
| Locality defeats the curse of dimensionality in convolutional teacher-student scenarios* A Favero, F Cagnetta, M Wyart Journal of Statistical Mechanics: Theory and Experiment 2022 (11), 114012, 2022 | | 2022 |
| Relative stability toward diffeomorphisms indicates performance in deep nets* L Petrini, A Favero, M Geiger, M Wyart Journal of Statistical Mechanics: Theory and Experiment 2022 (11), 114013, 2022 | | 2022 |
| Spectral analysis of infinitely wide convolutional neural networks A Favero Politecnico di Torino, 2020 | | 2020 |
Matthieu WyartProfessor of Physics, Johns HopkinsBestätigte E-Mail-Adresse bei epfl.ch
