AIM: Anchor Identity Features, Then Match for Multimodal Large Language Model Unlearning

Paper recorded by Signals 4 on 2026-08-28 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-28 on arXiv · recorded by Signals 4 on 2026-08-31

Category: cs.CV · 计算机视觉 · first seen 2026-08-31

Abstract

Multimodal large language models (MLLMs) can memorize identity-specific facts about people in their fine-tuning data, creating privacy risks when a person requests deletion. Existing MLLM unlearning methods often assume access to retain images or ground-truth answers during deletion, which is unrealistic in many practical scenarios. We study identity unlearning when retain images are unavailable a

Read on arXiv →