publications

* denotes co-first authorship. Check also my Google Scholar profile.

2025

  1. memoir.png
    MEMOIR: Lifelong model editing with minimal overwrite and informed retention for LLMs
    Ke Wang, Yiming Qin, Nikolaos Dimitriadis, Alessandro Favero, and 1 more author
    arXiv preprint, 2025
  2. memorization.png
    Bigger isn’t always memorizing: Early stopping overparameterized diffusion models
    Alessandro Favero*, Antonio Sclocchi*, and Matthieu Wyart
    arXiv preprint, 2025
  3. scaling.png
    Scaling laws and representation learning in simple hierarchical languages: Transformers vs. convolutional architectures
    Francesco Cagnetta, Alessandro Favero, Antonio Sclocchi, and Matthieu Wyart
    arXiv preprint, 2025
  4. compositional_diffusion.png
    How compositional generalization and creativity improve as diffusion models are trained
    Alessandro Favero*, Antonio Sclocchi*, Francesco Cagnetta, Pascal Frossard, and 1 more author
    International Conference on Machine Learning (ICML), PMLR, 2025
  5. susceptibility.png
    Probing the latent hierarchical structure of data via diffusion models
    Antonio Sclocchi*Alessandro Favero*, Noam Levi*, and Matthieu Wyart
    International Conference on Learning Representations (ICLR), 2025
  6. lines.png
    LiNeS: Post-training layer scaling prevents forgetting and enhances model merging
    Ke Wang, Nikolaos Dimitriadis, Alessandro Favero, Guillermo Ortiz-Jimenez, and 2 more authors
    International Conference on Learning Representations (ICLR), 2025
  7. phase.png
    A phase transition in diffusion models reveals the hierarchical nature of data
    Antonio Sclocchi, Alessandro Favero, and Matthieu Wyart
    Proceedings of the National Academy of Sciences (PNAS), 2025

2024

  1. multimodal.png
    Multi-modal hallucination control by visual information grounding
    Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary, and 4 more authors
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
  2. disentanglement_2.png
    Task addition and weight disentanglement in closed-vocabulary models
    Adam Hazimeh*Alessandro Favero*, and Pascal Frossard
    ICML 2024 Efficient Systems for Foundation Models Workshop, 2024
  3. rhm.png
    How deep neural networks learn compositional data: The Random Hierarchy Model
    Francesco Cagnetta, Leonardo Petrini, Umberto Tomasini, Alessandro Favero, and 1 more author
    Physical Review X, 2024
  4. computational_2.png
    Computational complexity of deep learning: fundamental limitations and empirical phenomena
    Boaz Barak, Annabelle Carrell, Alessandro Favero, Weiyu Li, and 2 more authors
    Journal of Statistical Mechanics: Theory and Experiment (JSTAT), 2024

2023

  1. task_arithmetic_2.png
    Task arithmetic in the tangent space: Improved editing of pre-trained models
    Guillermo Ortiz-Jimenez*Alessandro Favero*, and Pascal Frossard
    Advances in Neural Information Processing Systems (NeurIPS), Oral presentation (top 0.54%) , 2023
  2. deepcnn.png
    What can be learnt with wide convolutional neural networks?
    Francesco Cagnetta*Alessandro Favero*, and Matthieu Wyart
    International Conference on Machine Learning (ICML), PMLR, 2023

2021

  1. learning_curves_local.png
    Locality defeats the curse of dimensionality in convolutional teacher-student scenarios
    Alessandro Favero*, Francesco Cagnetta*, and Matthieu Wyart
    Advances in Neural Information Processing Systems (NeurIPS), 2021
  2. diffeo.png
    Relative stability toward diffeomorphisms indicates performance in deep nets
    Leonardo Petrini, Alessandro Favero, Mario Geiger, and Matthieu Wyart
    Advances in Neural Information Processing Systems (NeurIPS), 2021

2020

  1. Spectral analysis of infinitely wide convolutional neural networks
    Alessandro Favero
    Master’s Thesis, Sorbonne Université and Politecnico di Torino, 2020