Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins

ArXi:2512.03537v3 Announce Type: replace Continual learning requires models to learn continuously while preserving prior knowledge under evolving data streams. Distillation-based methods are appealing for retaining past knowledge in a shared single-model framework with low storage overhead. However, they remain constrained by the stability-plasticity dilemma: knowledge acquisition and preservation are still optimized through coupled objectives, and existing enhancement methods do not alter this underlying bottleneck.