发表机构
Tsinghua University; IDG/McGovern Institute for Brain Research, Tsinghua University; Tsinghua-Peking Center for Life Sciences（清华大学; 清华大学IDG/麦戈文脑科学研究院; 清华-北大生命科学联合中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
受果蝇大脑启发，提出层次模块化原则，通过专家专业化与集成整合，在预训练模型上轻量适配，显著提升在线不确定数据流下的通用持续学习性能。
AI 中文摘要
持续学习，即从顺序经验中学习同时保留和调整先前知识的能力，是智能系统在变化环境中运行的核心。然而，传统的持续学习通常以离线任务式训练和明确的任务边界进行研究，与在线、不确定和不断发展的数据流下的通用持续学习存在显著差距。在这种模式下，智能系统必须分离冲突经验以减少干扰，同时整合兼容经验以促进泛化。受果蝇学习和记忆系统组织的启发，我们识别出一个层次模块化原则，通过专家专业化和集成整合来协调这两种功能。我们将这一原则实例化为预训练基础模型的轻量级模块化适配，结合脑启发的随机扩展用于专家路由，以及跨空间和时间尺度的多样化模块集成。在视觉识别、视觉-语言理解、自我-他人视频理解和具身视觉-语言-动作学习中，我们的方法在在线和不确定数据流下持续改进学习，在具身操作中相比无回放替代方案取得了超过50个百分点的提升。这些发现支持层次模块化作为从动态经验中学习的生物学基础路径。
英文摘要
Continual learning, the ability to learn from sequential experience while retaining and adapting prior knowledge, is central to intelligent systems operating in changing environments. However, conventional continual learning is typically studied with offline task-wise training and clear task boundaries, leaving a substantial gap from general continual learning under online, uncertain, and evolving data streams. In this regime, intelligent systems must separate conflicting experience to reduce interference while integrating compatible experience to promote generalization. Inspired by the organization of the Drosophila learning and memory system, we identify a hierarchical modular principle that coordinates both functions through expert specialization and ensemble integration. We instantiate this principle as lightweight modular adaptation of pretrained foundation models, combining brain-inspired random expansion for expert routing and diversified modular integration across spatial and temporal scales. Across visual recognition, vision-language understanding, ego-exo video understanding, and embodied vision-language-action learning, our method consistently improves learning under online and uncertain data streams, with gains exceeding 50 percentage points over replay-free alternatives in embodied manipulation. These findings support hierarchical modularity as a biologically grounded path for learning from dynamic experience.
Comments50 pages
