activity
20242026
collaborators

11 papers

cs.LG2026

Learn from your own latents and not from tokens: A sample-complexity theory

Daniel J. Korchinski, Alessandro Favero, Matthieu Wyart

Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude larger than what biological lea…

cs.CL2026

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs

Ke Wang, Yiming Qin, Nikolaos Dimitriadis +2

Language models deployed in real-world systems often require post-hoc updates to incorporate new or corrected knowledge. However, editing such models efficiently and reliably-witho…

cs.LG2025

Task Addition and Weight Disentanglement in Closed-Vocabulary Models

Adam Hazimeh, Alessandro Favero, Pascal Frossard

Task arithmetic has recently emerged as a promising method for editing pre-trained \textit{open-vocabulary} models, offering a cost-effective alternative to standard multi-task fin…

cs.LG2025

Backdoor Unlearning by Linear Task Decomposition

Amel Abdelraheem, Alessandro Favero, Gerome Bovet +1

Foundation models have revolutionized computer vision by enabling broad generalization across diverse tasks. Yet, they remain highly susceptible to adversarial perturbations and ta…

cs.LG2025

The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning

Alessandro Favero

Deep neural networks have achieved remarkable success, yet our understanding of how they learn remains limited. These models can learn high-dimensional tasks, which is generally st…

cs.LG2025

Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models

Alessandro Favero, Antonio Sclocchi, Matthieu Wyart

Diffusion probabilistic models have become a cornerstone of modern generative AI, yet the mechanisms underlying their generalization remain poorly understood. In fact, if these mod…