TILDE：基于倾斜的概念遗忘分布擦除
TILDE: TILt-based Distributional Erasure for Concept Unlearning
AI总结：
文本到图像扩散模型的概念遗忘研究中，提出TILDE方法，将概念遗忘视为分布对齐问题，通过能量倾斜的无锚点目标抑制概念图像，用残差∇-GFlowNet训练实例化，实验显示其在多方面实现强大遗忘效果，提升保留率和分布保真度。
摘要：
文本到图像扩散模型中的概念遗忘对于安全实用的部署至关重要。随着隐私担忧、版权纠纷等问题增加，已部署系统需在训练后抑制不需要的概念。现有方法常能有效去除目标概念，但实际遗忘还需模型在良性生成时保持质量、多样性和语义覆盖。我们提出TILDE，将概念遗忘表述为分布对齐问题，通过基于能量倾斜的无锚点目标抑制表达概念的图像，同时为每个提示保留良性相对质量。我们用残差∇-GFlowNet训练实例化该原则，实验表明TILDE在跨对象、艺术风格和角色等方面实现了强大的遗忘效果，同时提高了保留率和分布保真度。
英文摘要：
Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training. Existing methods often remove the target concept effectively, but practical unlearning also requires an equally fundamental property: the unlearned model should retain quality, diversity, and semantic coverage on benign generation. The gold standard is a retain-only model trained from scratch without the unwanted data. However, common erasure objectives do not specify which post-unlearning distribution should approximate this reference, leaving retention as an implicit consequence of the update rule. We propose TILDE, TILt-based Distributional Erasure, which formulates concept unlearning as a distributional alignment problem: the desired target is the minimum-deviation conditional distribution from the pretrained model under a forgetting constraint. This energy-tilted, anchor-free target suppresses concept-expressing images while preserving benign relative mass for each prompt. We instantiate this principle with residual $\nabla$-GFlowNet training, which learns the score correction induced by the forget energy relative to the pretrained diffusion model. Across objects, artistic styles, and characters, TILDE achieves strong forgetting while improving retention and distributional fidelity over prior baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
