Preprint
Aug 2026
When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy
Experiments on vision and language tasks across multiple privacy budgets show that DP-Merging consistently improves private merged-model performance while preserving the privacy guarantees of the underlying DP fine-tuning procedures.
Jin Liu, Jun-Kang Liu, Ning Xi et al.
· 0 citations