When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry

arXiv:2604.27656v1 Announce Type: cross Abstract: To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stability-plasticity dilemma affects how representations can be reused across tasks: shared structure enables transfer when tasks are similar but may also induce interference when new learning disrupts existing representations. However, it remains unclear when and why struct