Saliency-Aware Model Merging 事件

Saliency-Aware Model Merging arXiv:2606.00511v1 Announce Type: cross Abstract: Model merging aims to consolidate multiple task-specific models fine-tuned on different datasets into a unified architecture that performs cross-domain proficiency. Current data-free model merging methods often struggle to scale as they rely on simple parameter-level heuristics that ignore inter-layer dependencies and non-uniform distribution of expertise. This work proposes SA-Merging, which is built upon connectivi