Compositionality is one of the fundamental abilities of the human reasoning process, that allows to decompose a complex problem into simpler elements. Such property is crucial also for neural networks, especially when aiming for a more efficient and sustainable AI framework. We propose a compositional approach by ensembling zero-shot a set of expert models, assessing our methodology using a challenging benchmark, designed to test compositionality capabilities. We show that our Expert Composition method is able to achieve a much higher accuracy than baseline algorithms while requiring less computational resources, hence being more efficient.
@article{arxiv.2506.15566,
title = {Task-Agnostic Experts Composition for Continual Learning},
author = {Luigi Quarantiello and Andrea Cossu and Vincenzo Lomonaco},
journal= {arXiv preprint arXiv:2506.15566},
year = {2025}
}