Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models

Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models explores A framework for large vision-language models to selectively forget specific concepts while preserving general utility, enabling precise refusal of unwanted image-instruction pairs.. Commercial viability score: 7/10 in Continual Learning.