Selective LoRA for Visual Tokens and Attention Heads

arXiv:2512.19219v2 Announce Type: replace-cross Abstract: Low-rank adaptation (LoRA) is widely used for parameter-efficient fine-tuning, but its standard all-token, all-head design ignores the heterogeneous structure of vision language model (VLM) inputs. We introduce \emph{Image-LoRA}, a...