| On over-squashing in message passing neural networks: The impact of width, depth, and topology F Di Giovanni, L Giusti, F Barbero, G Luise, P Lio, M Bronstein International Conference on Machine Learning (ICML 2023), 2023 | 251 | 2023 |
| Scalable emulation of protein equilibrium ensembles with generative deep learning S Lewis, T Hempel, J Jiménez Luna, M Gastegger, Y Xie, AYK Foong, ... Cover of Science, 2024.12. 05.626885, 2024 | 180* | 2024 |
| Transcending transcend: Revisiting malware classification with conformal evaluation F Barbero, F Pendlebury, F Pierazzi, L Cavallaro 2022 IEEE Symposium on Security and Privacy, 1332-1349, 2022 | 170* | 2022 |
| Round and Round We Go! What makes Rotary Positional Encodings useful? F Barbero, A Vitvitskyi, C Perivolaropoulos, R Pascanu, P Veličković International Conference on Learning Representations (ICLR 2025), 2025 | 64 | 2025 |
| Sheaf neural networks with connection laplacians F Barbero, C Bodnar, HS de Ocáriz Borde, M Bronstein, P Veličković, ... Topological, Algebraic and Geometric Learning Workshops 2022, 28-36, 2022 | 61 | 2022 |
| Locality-aware graph-rewiring in gnns F Barbero, A Velingker, A Saberi, M Bronstein, F Di Giovanni International Conference on Learning Representations (ICLR 2024), 2024 | 60 | 2024 |
| Transformers need glasses! Information over-squashing in language tasks F Barbero, A Banino, S Kapturowski, D Kumaran, JGM Araújo, A Vitvitskyi, ... Advances in Neural Information Processing Systems (NeurIPS 2024), 2024 | 57* | 2024 |
| Why do LLMs attend to the first token? F Barbero, Á Arroyo, X Gu, C Perivolaropoulos, M Bronstein, P Veličković, ... arXiv preprint arXiv:2504.02732, 2025 | 37* | 2025 |
| Sheaf attention networks F Barbero, C Bodnar, HS de Ocáriz Borde, P Lio NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations, 2022 | 34 | 2022 |
| Latent Graph Inference using Product Manifolds HS de Ocáriz Borde, A Kazi, F Barbero, P Lio International Conference on Learning Representations (ICLR 2023), 2023 | 31 | 2023 |
| On vanishing gradients, over-smoothing, and over-squashing in gnns: Bridging recurrent and graph learning Á Arroyo, A Gravina, B Gutteridge, F Barbero, C Gallicchio, X Dong, ... arXiv preprint arXiv:2502.10818, 2025 | 24 | 2025 |
| Bundle Neural Networks for message diffusion on graphs J Bamberger, F Barbero, X Dong, M Bronstein International Conference on Learning Representations (ICLR 2025) Spotlight, 2025 | 15 | 2025 |
| Softmax is not Enough (for Sharp Size Generalisation) P Veličković, C Perivolaropoulos, F Barbero, R Pascanu arXiv preprint arXiv:2410.01104, 2024 | 14* | 2024 |
| Enhancing the Expressivity of Temporal Graph Networks through Source-Target Identification BA Tjandra, F Barbero, M Bronstein NeurIPS 2024 Workshop on Symmetry and Geometry in Neural Representations, 2024 | 5* | 2024 |
| Graph Neural Network Expressivity and Meta-Learning for Molecular Property Regression HS de Ocáriz Borde, F Barbero The First Learning on Graphs Conference, 2022 | 4* | 2022 |
| Interpreting the Repeated Token Phenomenon in Large Language Models I Yona, I Shumailov, J Hayes, F Barbero, Y Gandelsman arXiv preprint arXiv:2503.08908, 2025 | 3 | 2025 |
| Attention sinks and compression valleys in llms are two sides of the same coin E Queipo-de-Llano, Á Arroyo, F Barbero, X Dong, M Bronstein, Y LeCun, ... arXiv preprint arXiv:2510.06477, 2025 | 1 | 2025 |
| Attention-based Sheaf Neural Networks F Barbero MPhil thesis. University of Cambridge, 2022 | 1 | 2022 |
| Bridging Graph Neural Networks and Large Language Models: A Survey and Unified Perspective Á Arroyo, F Barbero, H Blayney, M Bronstein, X Dong, P Liò, R Pascanu, ... OpenReview, 2025 | | 2025 |
| Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions V Veeriah, F Barbero, M Chiam, X Feng, M Dennis, R Pachauri, T Tumiel, ... arXiv preprint arXiv:2510.23772, 2025 | | 2025 |
Petar VeličkovićSenior Staff Research Scientist, Google DeepMind | Affiliated Lecturer, University of CambridgeVerified email at google.com
