A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents
Luigi Quarantiello, Elia Piccoli, Bell, Jack, Malio Li, Giacomo Carfì, Coleman, Eric Nuertey, Gerlando Gramaglia, Lanpei Li, Mauro Madeddu, Irene Testa, Vincenzo Lomonaco · arXiv (Cornell University) · 2025
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.