Diego Doimo

According to our database, Diego Doimo authored at least 14 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models.

Francesco Ortu, Zhijing Jin, Diego Doimo, Alberto Cazzaniga

CoRR, July, 2025

Emergence of a High-Dimensional Abstraction Phase in Language Transformers.

Emily Cheng, Diego Doimo, Corentin Kervadec, Iuri Macocco, Lei Yu, Alessandro Laio, Marco Baroni

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

How to choose the right transfer learning protocol? A qualitative analysis in a controlled set-up.

Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio

Trans. Mach. Learn. Res., 2024

The Narrow Gate: Localized Image-Text Communication in Vision-Language Models.

Alessandro Serra, Francesco Ortu, Emanuele Panizon, Lucrezia Valeriani, Lorenzo Basile, Alessio Ansuini, Diego Doimo, Alberto Cazzaniga

CoRR, 2024

Understanding Variational Autoencoders with Intrinsic Dimension and Information Imbalance.

Charles Camboulin, Diego Doimo, Aldo Glielmo

CoRR, 2024

Emergence of a High-Dimensional Abstraction Phase in Language Transformers.

Emily Cheng, Diego Doimo, Corentin Kervadec, Iuri Macocco, Jade Yu, Alessandro Laio, Marco Baroni

CoRR, 2024

The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models.

Diego Doimo, Alessandro Serra, Alessio Ansuini, Alberto Cazzaniga

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals.

Francesco Ortu, Zhijing Jin, Diego Doimo, Mrinmaya Sachan, Alberto Cazzaniga, Bernhard Schölkopf

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023

Optimal transfer protocol by incremental layer defrosting.

Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio

CoRR, 2023

The geometry of hidden representations of large transformer models.

Lucrezia Valeriani, Diego Doimo, Francesca Cuturello, Alessandro Laio, Alessio Ansuini, Alberto Cazzaniga

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

DADApy: Distance-based analysis of data-manifolds in Python.

Aldo Glielmo, Iuri Macocco, Diego Doimo, Matteo Carli, Claudio Zeni, Romina Wild, Maria d'Errico, Alex Rodriguez, Alessandro Laio

Patterns, 2022

Redundant representations help generalization in wide neural networks.

Diego Doimo, Aldo Glielmo, Sebastian Goldt, Alessandro Laio

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Representation mitosis in wide neural networks.

Diego Doimo, Aldo Glielmo, Sebastian Goldt, Alessandro Laio

CoRR, 2021

2020

Hierarchical nucleation in deep neural networks.

Diego Doimo, Aldo Glielmo, Alessio Ansuini, Alessandro Laio

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020