LR-Merge tunes model combinations without rebuilding every candidate
A new label-free method lets researchers tune model-merge coefficients from unlabeled probes, avoiding repeated construction and evaluation of merged networks. It first measures how one task vector changes another task’s outputs at the receiver model, then builds a simple surrogate that answers new coefficient and task-subset queries in seconds. LR-Merge improved every tested base merger and matched exact teacher matching, whose optimization took roughly three times longer to converge.