Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning

ArXi:2605.05909v1 Announce Type: new The core challenge of machine unlearning is to strike a balance between target knowledge removal and non-target knowledge retention. In the context of Multimodal Large Language Models (MLLMs), this challenge becomes even pronounced, as knowledge is further divided into visual and textual modalities that are tightly intertwined. In this paper, we