arXiv:2605.15687v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations, while overlooking the generation quality after...
Läs hela artikeln hos källan.
Kommentarer (0)
Inga kommentarer ännu. Bli först med att kommentera!