A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Quarantiello, Luigi, Piccoli, Elia, Bell, Jack, Li, Malio, Carfì, Giacomo, Coleman, Eric Nuertey, Gramaglia, Gerlando, Li, Lanpei, Madeddu, Mauro, Testa, Irene, Lomonaco, Vincenzo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915567589392384
author Quarantiello, Luigi
Piccoli, Elia
Bell, Jack
Li, Malio
Carfì, Giacomo
Coleman, Eric Nuertey
Gramaglia, Gerlando
Li, Lanpei
Madeddu, Mauro
Testa, Irene
Lomonaco, Vincenzo
author_facet Quarantiello, Luigi
Piccoli, Elia
Bell, Jack
Li, Malio
Carfì, Giacomo
Coleman, Eric Nuertey
Gramaglia, Gerlando
Li, Lanpei
Madeddu, Mauro
Testa, Irene
Lomonaco, Vincenzo
contents The birth of Foundation Models brought unprecedented results in a wide range of tasks, from language to vision, to robotic control. These models are able to process huge quantities of data, and can extract and develop rich representations, which can be employed across different domains and modalities. However, they still have issues in adapting to dynamic, real-world scenarios without retraining the entire model from scratch. In this work, we propose the application of Continual Learning and Compositionality principles to foster the development of more flexible, efficient and smart AI solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18608
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents
Quarantiello, Luigi
Piccoli, Elia
Bell, Jack
Li, Malio
Carfì, Giacomo
Coleman, Eric Nuertey
Gramaglia, Gerlando
Li, Lanpei
Madeddu, Mauro
Testa, Irene
Lomonaco, Vincenzo
Robotics
Machine Learning
The birth of Foundation Models brought unprecedented results in a wide range of tasks, from language to vision, to robotic control. These models are able to process huge quantities of data, and can extract and develop rich representations, which can be employed across different domains and modalities. However, they still have issues in adapting to dynamic, real-world scenarios without retraining the entire model from scratch. In this work, we propose the application of Continual Learning and Compositionality principles to foster the development of more flexible, efficient and smart AI solutions.
title A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents
topic Robotics
Machine Learning
url https://arxiv.org/abs/2510.18608