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.

翻译：基础模型的诞生在从语言、视觉到机器人控制等广泛任务中带来了前所未有的成果。这些模型能够处理海量数据，并能提取和构建丰富的表征，这些表征可跨不同领域与模态进行应用。然而，在适应动态的真实世界场景时，它们仍存在无需从头重新训练整个模型的问题。在本研究中，我们提出应用持续学习与组合性原理，以促进开发更灵活、高效和智能的人工智能解决方案。