[go: up one dir, main page]

Follow
Alberto Cazzaniga
Alberto Cazzaniga
Researcher, AREA Science Park
Verified email at areasciencepark.it - Homepage
Title
Cited by
Cited by
Year
The geometry of hidden representations of large transformer models
L Valeriani, D Doimo, F Cuturello, A Laio, A Ansuini, A Cazzaniga
Advances in Neural Information Processing Systems 37, 2024
912024
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals
F Ortu, Z Jin, D Doimo, M Sachan, A Cazzaniga, B Schölkopf
Proceedings of the 62nd Annual Meeting of the Association for Computational …, 2024
412024
Framed sheaves on projective space and Quot schemes
A Cazzaniga, AT Ricolfi
Mathematische Zeitschrift 300 (1), 745-760, 2022
252022
Higher rank motivic Donaldson–Thomas invariants of via wall-crossing, and asymptotics
A Cazzaniga, D Ralaivaosaona, AT Ricolfi
Mathematical Proceedings of the Cambridge Philosophical Society, 1-26, 2023
212023
Enhancing predictions of protein stability changes induced by single mutations using MSA-based language models
F Cuturello, M Celoria, A Ansuini, A Cazzaniga
Bioinformatics 40 (7), btae447, 2024
142024
Motivic Donaldson–Thomas invariants of some quantized threefolds
A Cazzaniga, A Morrison, B Pym, B Szendrői
Journal of Noncommutative Geometry 11 (3), 1115-1139, 2017
142017
The representation landscape of few-shot learning and fine-tuning in large language models
D Doimo, A Serra, A Ansuini, A Cazzaniga
Advances in Neural Information Processing Systems 38, 2025
132025
Emergent representations in networks trained with the Forward-Forward algorithm
N Tosato, L Basile, E Ballarin, G De Alteriis, A Cazzaniga, A Ansuini
TMLR, 2025
132025
The geometry of tokens in internal representations of large language models
K Viswanathan, Y Gardinazzi, G Panerai, A Cazzaniga, M Biagetti
arXiv preprint arXiv:2501.10573, 2025
112025
Framed motivic Donaldson–Thomas invariants of small crepant resolutions
A Cazzaniga, AT Ricolfi
Mathematische Nachrichten 295 (6), 1096-1112, 2022
112022
On some computations of refined Donaldson-Thomas invariants
A Cazzaniga
University of Oxford, 2015
92015
Towards the FAIRification of scanning tunneling microscopy images
T Rodani, E Osmenaj, A Cazzaniga, M Panighel, A Cristina, S Cozzini
Data Intelligence 5 (1), 27-42, 2023
72023
The geometry of hidden representations of protein language models
L Valeriani, F Cuturello, A Ansuini, A Cazzaniga
NeurIPS Workshop MLSB, 2022
62022
Adversarial Attacks on Protein Language Models
G Carbone, F Cuturello, L Bortolussi, A Cazzaniga
NeurIPS Workshop MLSB, 2022
52022
When seeing overrides knowing: Disentangling knowledge conflicts in vision-language models
F Ortu, Z Jin, D Doimo, A Cazzaniga
arXiv preprint arXiv:2507.13868, 2025
42025
Persistent topological features in large language models
Y Gardinazzi, K Viswanathan, G Panerai, A Ansuini, A Cazzaniga, ...
ICML 2025, 2025
42025
What is the probability that a random symmetric tensor is close to rank-one?
A Cazzaniga, A Lerario, A Rosana
SIAM Journal on Applied Algebra and Geometry 8 (2), 227-258, 2024
42024
Protein family annotation for the Unified Human Gastrointestinal Proteome by DPCfam clustering
F Barone, ET Russo, EN Villegas Garcia, M Punta, S Cozzini, A Ansuini, ...
Scientific Data 11 (1), 568, 2024
42024
Deep artificial neural network for prediction of atrial fibrillation through the analysis of 12-leads standard ECG
A Scagnetto, G Barbati, I Gandin, C Cappelletto, G Baj, A Cazzaniga, ...
arXiv preprint arXiv:2202.05676, 2022
42022
An Unsupervised Machine Learning Method Stratifies Chronic Lymphocytic Leukemia Patients in Novel Categories with Different Risk of Early Treatment
F Cuturello, F Pozzo, EN Villegas Garcia, FM Rossi, M Degan, P Nanni, ...
Blood, The Journal of the American Society of Hematology 140 (Supplement 1 …, 2022
32022
The system can't perform the operation now. Try again later.
Articles 1–20