2 papers
cs.LG2026
Stable-Plastic Subspace Construction for Differentially Private Continual LoRA
Jin Liu, Ning Xi, Yinbin Miao +3
Continual learning (CL) adapts pretrained models to a sequence of tasks while retaining knowledge acquired from earlier tasks. When task data are sensitive, differential privacy (D…
cs.LG2026
When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy
Jin Liu, Junkang Liu, Ning Xi +4
Model merging promises to construct a single multi-task model from independently fine-tuned task models without accessing the original task data. This makes it attractive when task…