研究人员开发了一个名为ReCARE的新框架，以改进从扩散模型中遗忘有害概念的过程。现有方法可能会无意中移除相关的良性概念，例如在遗忘“裸露”概念时抑制“人”的观念。ReCARE通过在遗忘过程中识别并保留这些“共现相关保留概念”（CARE）来解决这个问题。实验表明，ReCARE能有效平衡移除不需要的概念与保留基本概念，其性能优于以往的方法。 AI
影响 增强了对扩散模型的控制，能够更精确地移除有害内容，同时不牺牲通用的图像生成能力。
排序理由 该集群包含一篇详细介绍扩散模型遗忘新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.24192v1 Announce Type: cross Abstract: Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not only the target concept, but also benign co-occurring concepts. As illustrated in Fig…
Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not only the target concept, but also benign co-occurring concepts. As illustrated in Fig.1, unlearning nudity can unintentionally suppress…