解决多模态模型中敏感信息难删除的问题，实现精准遗忘而不影响整体性能。
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
- 提出跨视觉、语言、音频、视频的统一遗忘框架，按需移除特定知识
- 在多个数据集上验证遗忘效果，保留模型整体性能不受明显影响
- 适合关注模型隐私与合规性的研究者及工业应用开发者
随着视觉-语言模型（VLMs）、扩散模型（DMs）、大语言模型（LLMs）和音频-语言模型（AFMs）的广泛应用，这些多模态基础模型可能无意中编码了来自训练数据的敏感、版权受保护、偏见或不安全的跨模态关联。在删除请求或政策更新后重新训练往往不切实际，且由于知识分布在共享表征中，定向遗忘极为困难。多模态遗忘通过在保持整体效用的前提下，实现跨模态的选择性知识移除，解决了这一挑战。本综述提供了一个系统化的视角，涵盖视觉、语言、音频和视频领域的多模态遗忘方法、数据集与基准测试，基于最新进展、新兴应用与开放问题。我们的分类体系支持跨模型架构与模态的系统比较，阐明了删除强度、保留能力、效率、可逆性与鲁棒性之间的权衡。本文还指出了关键开放问题与实际考量，以推动未来研究与部署。我们发布了精选资源库：https://smsnobin77.github.io/Awesome-Multimodal-Unlearning/
原文摘要 · Abstract (English)
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associations that originate from their training data. Retraining after deletion requests or policy updates is often impractical, and targeted forgetting remains difficult because knowledge is distributed across shared representations. Multimodal unlearning addresses this challenge by enabling selective removal across modalities while retaining overall utility. This survey offers a unified, system-oriented view of multimodal unlearning across vision, language, audio, and video, grounded in recent advances, emerging applications, and open problems. Our taxonomy enables systematic comparison across model architectures and modalities, clarifying trade-offs among deletion strength, retention, efficiency, reversibility, and robustness. This survey highlights open problems and practical considerations to support future research and deployment of multimodal unlearning. We release a curated repository: https://smsnobin77.github.io/Awesome-Multimodal-Unlearning/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。