Author

G. Amati

h-index 20 View on Semantic Scholar

We have 2 of 400 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Learning-to-Optimize as the Missing Architectural Layer of AI-Native Networks

This paper argues that the Learning-to-Optimize (L2O) represents the missing architectural layer between optimisation and AI-native intelligence, and establishes L2O as an architectural abstraction applicable across heterogeneous communication and computing systems.

G. Amati, Federica Mangiatordi, P. Salvo et al. · 0 citations

Conference Open access Jul 2026

AI-Driven Multi-Hop Relay Selection for Smart Urban NR-V2X Networks via Learning-to-Optimize Graph Neural Networks

A Learning-to-Optimise (L2O) framework based on Graph Neural Networks (GNNs) for real-time NR-V2X relay selection that achieves connectivity comparable to that of the MILP oracle while reducing execution time by orders of magnitude.

G. Amati, Federica Mangiatordi, Simone Angelini et al. · International Conference on... · 1 citation