Two Routes to the Middle: Placement Search and Brain Readouts Converge on Where Continual Learners Should Specialize

Excerpt

arXiv:2610.01590v1 Announce Type: new Abstract: Continual learners that keep a task-specific adapter in every block of a pre-trained vision transformer accumulate storage linearly with the number of tasks; keeping task-specific adapters in only a few blocks curbs this growth but raises the question of where to place them. We investigate this question from two perspectives. Algorithmically, training all contiguous four-block placements yields an inverted U: final accuracy peaks at intermediate de