A Model Merging Approach for Continual MLLM Unlearning
Quick summary
arXiv:2608.04548v1 Announce Type: cross Abstract: Multimodal large language model (MLLM) unlearning methods have been proposed to remove private, sensitive, or proprietary information from well-trained models. However, most existing MLLM unlearning methods are designed for one-shot requests and fail to adequately address continual scenarios, as repeatedly applying one-shot operations leads to cumulative utility degradation, unlearning rebound, and retention drift. We introduce Merging for Continual Unlearning (MCU), an approach that dynamically merges multiple one-shot unlearning adapters into
Key takeaways
- arXiv:2608.04548v1 Announce Type: cross Abstract: Multimodal large language model (MLLM) unlearning methods have been proposed to remove private, sensitive, or proprietary information from well-trained models.
- However, most existing MLLM unlearning methods are designed for one-shot requests and fail to adequately address continual scenarios, as repeatedly applying one-shot operations leads to cumulative utility degradation, unlearning rebound, and retention drift.
- We introduce Merging for Continual Unlearning (MCU), an approach that dynamically merges multiple one-shot unlearning adapters into
Why it matters
“A Model Merging Approach for Continual MLLM Unlearning” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments