activity
20242026
collaborators

5 papers

cs.LG2026

Variational meta-learning inference for low dimensional neural system identification

Matteo Rufolo, Dario Piga, Marco Forgione

Deep learning has proven highly effective for nonlinear system identification, but heavily parameterized neural networks are prone to overfitting in low-data regimes and lack relia…

cs.LG2026

Diffusion Sequence Models for Generative In-Context Meta-Learning of Robot Dynamics

Angelo Moroncelli, Matteo Rufolo, Gunes Cagin Aydin +2

Accurate modeling of robot dynamics is essential for model-based control, yet remains challenging under distributional shifts and real-time constraints. In this work, we formulate…

cs.LG2025

Distributionally robust minimization in meta-learning for system identification

Matteo Rufolo, Dario Piga, Marco Forgione

Meta learning aims at learning how to solve tasks, and thus it allows to estimate models that can be quickly adapted to new scenarios. This work explores distributionally robust mi…

cs.LG2025

Manifold meta-learning for reduced-complexity neural system identification

Marco Forgione, Ankush Chakrabarty, Dario Piga +2

System identification has greatly benefited from deep learning techniques, particularly for modeling complex, nonlinear dynamical systems with partially unknown physics where tradi…

cs.LG2024

Enhanced Transformer architecture for in-context learning of dynamical systems

Matteo Rufolo, Dario Piga, Gabriele Maroni +1

Recently introduced by some of the authors, the in-context identification paradigm aims at estimating, offline and based on synthetic data, a meta-model that describes the behavior…