cs.CV, cs.LG

Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning

arXiv:2603.00191v2 Announce Type: replace-cross
Abstract: Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuni…