DART: Distillation-Aware Reparameterization for Training-Free LoRA Reuse in Few-Step Video Diffusion Models
DART is proposed, a training-free reparameterization method that transports source LoRAs into aligned coordinates through a low-rank distillation bridge and complements response calibration, with adapter-level benefits encompassing both functional preservation and reduced negative transfer.
Shi-Hong Li, Jun-Tao Xu, Cao Jin et al.
· 1 citation