Giulia Lanzillotta

According to our database, Giulia Lanzillotta authored at least 8 papers between 2023 and 2025.

Collaborative distances:

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

2025

Asymptotic analysis of shallow and deep forgetting in replay with Neural Collapse.

Giulia Lanzillotta, Damiano Meier, Thomas Hofmann

CoRR, December, 2025

Revisiting Knowledge Distillation: The Hidden Role of Dataset Size.

Giulia Lanzillotta, Felix Sarnthein, Gil Kur, Thomas Hofmann, Bobby He

CoRR, October, 2025

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity.

Amir Joudaki, Giulia Lanzillotta, Mohammad Samragh Razlighi, Iman Mirzadeh, Keivan Alizadeh, Thomas Hofmann, Mehrdad Farajtabar, Fartash Faghri

CoRR, October, 2025

Reactivation: Empirical NTK Dynamics Under Task Shifts.

Yuzhi Liu, Zixuan Chen, Zirui Zhang, Yufei Liu, Giulia Lanzillotta

CoRR, July, 2025

The Importance of Being Lazy: Scaling Limits of Continual Learning.

Jacopo Graldi, Alessandro Breccia, Giulia Lanzillotta, Thomas Hofmann, Lorenzo Noci

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Local vs Global continual learning.

Giulia Lanzillotta, Sidak Pal Singh, Benjamin F. Grewe, Thomas Hofmann

Proceedings of the Conference on Lifelong Learning Agents, 2024

2023

Towards guarantees for parameter isolation in continual learning.

Giulia Lanzillotta, Sidak Pal Singh, Benjamin F. Grewe, Thomas Hofmann

CoRR, 2023

Structure by Architecture: Structured Representations without Regularization.

Felix Leeb, Giulia Lanzillotta, Yashas Annadani, Michel Besserve, Stefan Bauer, Bernhard Schölkopf

Proceedings of the Eleventh International Conference on Learning Representations, 2023