Runtong ZHANG

Null-Space Filtering for Data-free Continual Model Merging: Preserving Transparency, Promoting Fidelity

Data-free continual model merging (DFCMM) aims to fuse independently fine-tuned models into a single backbone that evolves with incoming tasks without accessing task data. This paper formulate two fundamental desiderata for DFCMM: transparency, avoiding interference with earlier tasks, and fidelity,…