Score: 0

A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents

Published: October 21, 2025 | arXiv ID: 2510.18608v1

By: Luigi Quarantiello , Elia Piccoli , Jack Bell and more

Potential Business Impact:

AI learns new things without forgetting old ones.

Business Areas:
Artificial Intelligence Artificial Intelligence, Data and Analytics, Science and Engineering, Software

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.

Country of Origin
🇮🇹 Italy

Page Count
2 pages

Category
Computer Science:
Robotics