AI RESEARCH
Fine-Tuning Regimes Define Distinct Continual Learning Problems
arXiv CS.LG
•
ArXi:2604.21927v1 Announce Type: new Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite substantial progress in benchmarking CL methods, comparative evaluations typically keep the fine-tuning regime fixed. In this paper, we argue that the fine-tuning regime, defined by the trainable parameter subspace, is itself a key evaluation variable.