collaborators

7 papers

cs.LG2026

SEAL: Searching Expandable Architectures for Incremental Learning

Matteo Gambella, Manuel Roveri

Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge: balancing plasticity (learning new t…

cs.LG2026

HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search

Matteo Gambella, Fabrizio Pittorino, Manuel Roveri

Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transit…

cs.LG2026

Architecture-Aware Minimization (AM): How to Find Flat Minima in Neural Architecture Search

Matteo Gambella, Fabrizio Pittorino, Manuel Roveri

Neural Architecture Search (NAS) has become an essential tool for designing effective and efficient neural networks. In this paper, we investigate the geometric properties of neura…

cs.LG2026

SQUAD: Scalable Quorum Adaptive Decisions via ensemble of early exit neural networks

Matteo Gambella, Fabrizio Pittorino, Giuliano Casale +1

Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. However, standard approac…

cs.LG2025

NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networks

Matteo Gambella, Jary Pomponi, Simone Scardapane +1

Early Exit Neural Networks (EENNs) endow astandard Deep Neural Network (DNN) with Early Exit Classifiers (EECs), to provide predictions at intermediate points of the processing whe…

cs.CL2025

DYNAMAX: Dynamic computing for Transformers and Mamba based architectures

Miguel Nogales, Matteo Gambella, Manuel Roveri

Early exits (EEs) offer a promising approach to reducing computational costs and latency by dynamically terminating inference once a satisfactory prediction confidence on a data sa…