MoRe: Modular Representations for Principled Continual Representation Learning on Squantial Data

ArXi:2605.14364v1 Announce Type: new Continual learning requires models to adapt to new data while preserving previously acquired knowledge. At its core, this challenge can be viewed as principled one-step adaptation: incorporating new information with minimal interference to existing representations. Most existing approaches address this challenge by modifying model parameters or architectures in a supervised, task-specific manner.