Alvaro Arroyo

15 papers A* 2Misc 2Journal 11
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Survey on Over-smoothing and Over-squashing: Unified Propagation Perspectives on Graph Neural Networks and Transformers.
Trans. Mach. Learn. Res.
Alvaro Arroyo, Federico Barbero, Hugh Blayney, Michael M. Bronstein, Xiaowen Dong, Pietro Lio, Razvan Pascanu, Pierre Vandergheynst
2025 J jnl
Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin.
CoRR
Enrique Queipo-de-Llano, Alvaro Arroyo, Federico Barbero, Xiaowen Dong, Michael M. Bronstein, Yann LeCun, Ravid Shwartz-Ziv
2025 J jnl
On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning.
CoRR
Alvaro Arroyo, Alessio Gravina, Benjamin Gutteridge, Federico Barbero, Claudio Gallicchio, Xiaowen Dong, Michael M. Bronstein, Pierre Vandergheynst
2025 J jnl
Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks.
CoRR
Ali Hariri, Alvaro Arroyo, Alessio Gravina, Moshe Eliasof, Carola-Bibiane Schönlieb, Davide Bacciu, Kamyar Azizzadenesheli, Xiaowen Dong, Pierre Vandergheynst
2025 J jnl
Why do LLMs attend to the first token?
CoRR
Federico Barbero, Alvaro Arroyo, Xiangming Gu, Christos Perivolaropoulos, Michael M. Bronstein, Petar Velickovic, Razvan Pascanu
2025 J jnl
gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity.
CoRR
Hugh Blayney, Alvaro Arroyo, Xiaowen Dong, Michael M. Bronstein
2024 J jnl
Rough Transformers for Continuous and Efficient Time-Series Modelling.
CoRR
Fernando Moreno-Pino, Alvaro Arroyo, Harrison Waldon, Xiaowen Dong, Álvaro Cartea
2024 J jnl
Rough Transformers: Lightweight Continuous-Time Sequence Modelling with Path Signatures.
CoRR
Fernando Moreno-Pino, Alvaro Arroyo, Harrison Waldon, Xiaowen Dong, Álvaro Cartea
2024 A* conf
Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching.
NeurIPS
Fernando Moreno-Pino, Alvaro Arroyo, Harrison Waldon, Xiaowen Dong, Álvaro Cartea
2023 J jnl
Gromov-Hausdorff Distances for Comparing Product Manifolds of Model Spaces.
CoRR
Haitz Sáez de Ocáriz Borde, Alvaro Arroyo, Ismael Morales, Ingmar Posner, Xiaowen Dong
2023 A* conf
Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization.
NeurIPS
Haitz Sáez de Ocáriz Borde, Alvaro Arroyo, Ismael Morales, Ingmar Posner, Xiaowen Dong
2023 J jnl
Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization.
CoRR
Haitz Sáez de Ocáriz Borde, Alvaro Arroyo, Ismael Morales, Ingmar Posner, Xiaowen Dong
2023 J jnl
Projections of Model Spaces for Latent Graph Inference.
CoRR
Haitz Sáez de Ocáriz Borde, Alvaro Arroyo, Ingmar Posner
2022 Misc conf
Dynamic Portfolio Cuts: A Spectral Approach to Graph-Theoretic Diversification.
ICASSP
Alvaro Arroyo, Bruno Scalzo, Ljubisa Stankovic, Danilo P. Mandic
2021 Misc conf
Nonstationary Portfolios: Diversification in the Spectral Domain.
ICASSP
Bruno Scalzo, Alvaro Arroyo, Ljubisa Stankovic, Danilo P. Mandic