arXiv cs.CV
· Papers
CT-Merging: Consensus Directions and Task-Level Scaling for LoRA Adapter Merging
arXiv:2607.20561v1 Announce Type: cross Abstract: LoRA adapters provide an efficient way to specialize a pretrained model for many downstream tasks, but deploying one adapter per task requires adapter storage and task selection at inference time. Model merging addresses this issue by combining independently trained ada