Research

CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation

Single source1 source14 Oct 2026

arXiv:2610.14763v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can reproduce sensitive, copyrighted, or unsafe information from their training data.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.14763

← Back to all developments · Signals are a development reported by more than one source. See the methodology.