Alessandro Favero

24 papers A* 8Journal 16

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Backdoor Unlearning by Linear Task Decomposition. CoRR Amel Abdelraheem, Alessandro Favero, Gérôme Bovet, Pascal Frossard
2025	J	`jnl`	Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models. CoRR Alessandro Favero, Antonio Sclocchi, Matthieu Wyart
2025	A*	`conf`	How Compositional Generalization and Creativity Improve as Diffusion Models are Trained. ICML Alessandro Favero, Antonio Sclocchi, Francesco Cagnetta, Pascal Frossard, Matthieu Wyart
2025	J	`jnl`	How compositional generalization and creativity improve as diffusion models are trained. CoRR Alessandro Favero, Antonio Sclocchi, Francesco Cagnetta, Pascal Frossard, Matthieu Wyart
2025	A*	`conf`	LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging. ICLR Ke Wang, Nikolaos Dimitriadis, Alessandro Favero, Guillermo Ortiz-Jiménez, François Fleuret, Pascal Frossard
2025	J	`jnl`	MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs. CoRR Ke Wang, Yiming Qin, Nikolaos Dimitriadis, Alessandro Favero, Pascal Frossard
2025	A*	`conf`	Probing the Latent Hierarchical Structure of Data via Diffusion Models. ICLR Antonio Sclocchi, Alessandro Favero, Noam Itzhak Levi, Matthieu Wyart
2025	J	`jnl`	Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures. CoRR Francesco Cagnetta, Alessandro Favero, Antonio Sclocchi, Matthieu Wyart
2025	J	`jnl`	Task Addition and Weight Disentanglement in Closed-Vocabulary Models. CoRR Adam Hazimeh, Alessandro Favero, Pascal Frossard
2025	J	`jnl`	The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning. CoRR Alessandro Favero
2024	J	`jnl`	A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data. CoRR Antonio Sclocchi, Alessandro Favero, Matthieu Wyart
2024	J	`jnl`	LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging. CoRR Ke Wang, Nikolaos Dimitriadis, Alessandro Favero, Guillermo Ortiz-Jiménez, François Fleuret, Pascal Frossard
2024	A*	`conf`	Multi-Modal Hallucination Control by Visual Information Grounding. CVPR Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary, Pramuditha Perera, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto
2024	J	`jnl`	Multi-Modal Hallucination Control by Visual Information Grounding. CoRR Alessandro Favero, Luca Zancato, Matthew Trager, Siddharth Choudhary, Pramuditha Perera, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto
2024	J	`jnl`	Probing the Latent Hierarchical Structure of Data via Diffusion Models. CoRR Antonio Sclocchi, Alessandro Favero, Noam Itzhak Levi, Matthieu Wyart
2023	J	`jnl`	How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model. CoRR Leonardo Petrini, Francesco Cagnetta, Umberto M. Tomasini, Alessandro Favero, Matthieu Wyart
2023	A*	`conf`	Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models. NeurIPS Guillermo Ortiz-Jiménez, Alessandro Favero, Pascal Frossard
2023	J	`jnl`	Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models. CoRR Guillermo Ortiz-Jiménez, Alessandro Favero, Pascal Frossard
2023	A*	`conf`	What Can Be Learnt With Wide Convolutional Neural Networks? ICML Francesco Cagnetta, Alessandro Favero, Matthieu Wyart
2022	J	`jnl`	How Wide Convolutional Neural Networks Learn Hierarchical Tasks. CoRR Francesco Cagnetta, Alessandro Favero, Matthieu Wyart
2021	A*	`conf`	Locality defeats the curse of dimensionality in convolutional teacher-student scenarios. NeurIPS Alessandro Favero, Francesco Cagnetta, Matthieu Wyart
2021	J	`jnl`	Locality defeats the curse of dimensionality in convolutional teacher-student scenarios. CoRR Alessandro Favero, Francesco Cagnetta, Matthieu Wyart
2021	J	`jnl`	Relative stability toward diffeomorphisms in deep nets indicates performance. CoRR Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart
2021	A*	`conf`	Relative stability toward diffeomorphisms indicates performance in deep nets. NeurIPS Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart