1.9k citations · 12.8k across the 146 of their papers we have counts for
147 papers
Learning infinite context windows in recurrent architectures via spatial neural computing
Aleix Salvador-Pomarol, Arthur N. Montanari, Earl K. Miller +2
Recurrent neural networks (RNNs) offer linear-time scaling with sequence length while requiring only constant memory, yet they struggle to capture long-range dependencies due to va…
Disorder-promoted stability
Arthur N. Montanari, Pietro Zanin, Adilson E. Motter
Previous studies of network dynamics have suggested that heterogeneity among nodes inhibits stability, at odds with the ubiquity of inherently heterogeneous natural and engineered…
Generalized Master Stability of Heterogeneous Delay-Coupled Networks
Ana Elisa D. Barioni, Arthur N. Montanari, Adilson E. Motter
Time delays are ubiquitous in physical and biological networked systems, playing a fundamental role in the emergence and stability of collective behavior. Yet, existing theoretical…
Rethinking the green power grid for stability, not just for climate
Yiming Wang, Arthur N. Montanari, Adilson E. Motter
The 2025 Iberian blackout has renewed concerns about the resilience of power grids with high shares of renewable generation. This commentary argues that renewable generation can no…
Irregular Metamaterial Networks
Thomas P. Wytock, Chiara Daraio, Heinrich M. Jaeger +4
Metamaterials can achieve exceptional functionality through careful engineering of their mesoscale structure. Although appropriately introduced irregularities can be advantageous,…
Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization
Arthur N. Montanari, Francesco Bullo, Dmitry Krotov +1
Recent advances at the intersection of control theory, neuroscience, and machine learning have revealed novel mechanisms by which dynamical systems perform computation. These advan…