让大模型像积木一样组合，实现机器人智能的持续进化
A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents
- 用持续学习与组合范式构建可动态扩展的智能体
- 无需从头训练即可适应新任务，提升部署效率
- 适合研发可长期进化的机器人系统开发者
基础模型的出现带来了语言、视觉到机器人控制等多任务的突破性进展。这些模型能处理海量数据并提取跨领域、跨模态的丰富表征。然而，在无需重新训练整个模型的前提下，它们仍难以适应动态真实场景。本文提出将持续学习与组合性原则应用于基础模型，以推动更灵活、高效且智能的AI解决方案发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。