Author name: Shen Lin, Jing Lin, Junhao Dong, Piotr Koniusz, Li Xu

arXiv:2605.14309v2 Announce Type: replace
Abstract: Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semanti…

arXiv:2605.14309v1 Announce Type: cross
Abstract: Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics…