publications
Check Google Scholar for the most updated list. * denotes co-first authorship.
2024
- CVPRMulti-modal hallucination control by visual information groundingProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
- arXivA phase transition in diffusion models reveals the hierarchical nature of dataarXiv preprint, 2024
2023
- arXivHow deep neural networks learn compositional data: The Random Hierarchy ModelarXiv preprint, 2023
- NeurIPSTask arithmetic in the tangent space: Improved editing of pre-trained modelsAdvances in Neural Information Processing Systems, 2023Oral Presentation
- ICMLWhat can be learnt with wide convolutional neural networks?ICML, Proceedings of Machine Learning Research, 2023
2021
- NeurIPSLocality defeats the curse of dimensionality in convolutional teacher-student scenariosAdvances in Neural Information Processing Systems, 2021Journal of Statistical Mechanics, Theory and Experiment, 2022
- NeurIPSRelative stability toward diffeomorphisms indicates performance in deep netsAdvances in Neural Information Processing Systems, 2021Journal of Statistical Mechanics, Theory and Experiment, 2022
2020
- ThesisSpectral analysis of infinitely wide convolutional neural networksMaster’s Thesis, Sorbonne Université and Politecnico di Torino, 2020