AI RESEARCH
Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning
arXiv CS.LG
•
ArXi:2605.08311v1 Announce Type: new Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement for preserving diverse forms of previous knowledge conflicts with the storage limitations inherent to CL. In this paper, we systematically analyze existing model merging methods under the constraints of CL.