发表机构
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MePo++是统一表示精炼与协调的后训练框架，通过MetaPrep和StreamAlign组件提升预训练模型在通用持续学习中的可塑性与稳定性，经多组实验验证其有效性与通用性。
AI 中文摘要
通用持续学习（General Continual Learning, GCL）旨在从不断演化的数据流中学习，无需任务标识、明确的边界或对先前数据的重复访问，是持续智能领域中现实却极具挑战性的场景。尽管预训练模型（Pretrained Models, PTMs）为解决GCL中监督有限与非平稳性问题提供了丰富的先验知识，但现有基于PTM的方法往往直接适配预训练表示，忽视了两个关键差距：上游预训练与下游持续适应之间的错位，以及模糊数据流下传统输出对齐的不可靠性。本文提出MePo++，一个通过表示精炼与协调来衔接预训练知识与下游GCL的统一后训练框架。MePo++包含两个互补组件：MetaPrep，通过对伪持续序列进行无监督元精炼，提升持续适应的表示可塑性；StreamAlign，通过协调演化的在线特征与稳定的预训练几何结构，增强表示稳定性。MePo++通过在适应前提升表示可学习性，并在持续学习过程中保持对齐，使PTM既能对新概念保持可塑性，又能在演化的数据流中保持稳定性。在不同PTM、数据集及持续学习基准上的实验，验证了MePo++在基于PTM的GCL任务中的一致有效性与通用性。代码可在指定URL获取。
英文摘要
General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated access to previous data, making it a realistic yet challenging setting for continual intelligence. Although pretrained models (PTMs) provide rich prior knowledge for addressing the limited supervision and non-stationary nature of GCL, existing PTM-based methods often directly adapt pretrained representations and overlook two critical gaps: the misalignment between upstream pretraining and downstream continual adaptation, and the unreliability of conventional output alignment under blurry streams. Here we propose MePo++, a unified post-training framework that bridges pretrained knowledge and downstream GCL through representation refinement and reconciliation. MePo++ introduces two complementary components: MetaPrep, which improves representation plasticity for continual adaptation through unsupervised meta-refinement over pseudo continual sequences; and StreamAlign, which reinforces representation stability by reconciling evolving online features with a stable pretrained geometry. By improving representation learnability before adaptation and preserving alignment during continual learning, MePo++ enables PTMs to remain both plastic for new concepts and stable over evolving streams. Experiments across diverse PTMs, datasets, and continual learning baselines demonstrate the consistent effectiveness and generality of MePo++ for PTM-based GCL. Our code is available at https://github.com/SunGL001/MePo_Plus.
