Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models

ArXi:2605.07512v1 Announce Type: new Class-incremental learning aims to continuously acquire new knowledge while preserving previously learned information, thereby mitigating catastrophic forgetting. Existing methods primarily restrict parameter updates but often overlook their structural properties in high-dimensional spaces. From a subspace perspective, updates induced by different tasks tend to lie in multiple overlapping low-rank subspaces, leading to cross-task subspace interference and severe forgetting.