Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation
A normalisation-based implicit ensemble that treats each member as a task in a multi-task architecture and modulates the shared backbone through sigmoid-bounded scalers is introduced, which matches or outperforms deep ensembles at a fraction of their parameter cost, scales with ensemble size where partitioning methods collapse, and maintains calibration under distribution shift.