UnHype: 基于CLIP的超网络用于动态LoRA反学习
UnHype: CLIP-Guided Hypernetworks for Dynamic LoRA Unlearning
AI总结：
本文提出UnHype框架，通过将超网络引入单概念和多概念LoRA训练，解决传统LoRA方法在概念语义适应性差、难以平衡删除相关概念与保持泛化能力以及多概念同时删除时的可扩展性问题，展示了在物体擦除、名人擦除和色情内容删除等任务中的有效性。
摘要：
近期大规模扩散模型的进步加剧了对其潜在滥用的担忧，特别是生成逼真但有害或社会 disruptive 的内容。这一挑战推动了有效机器反学习的研究，即在不损害模型整体生成能力的情况下，选择性地移除特定知识或概念。在各种方法中，低秩适应（LoRA）已成为一种有效的、高效的微调方法，用于针对反学习的定向调整。然而，基于LoRA的方法在概念语义适应性方面有限，并且在删除密切相关概念与保持更广泛意义的泛化能力之间难以平衡。此外，当必须同时删除多个概念时，这些方法面临可扩展性挑战。为了解决这些限制，我们引入了UnHype框架，该框架将超网络引入单概念和多概念LoRA训练中。所提出的架构可以直接插入到Stable Diffusion以及现代流基文本到图像模型中，其中展示了稳定的训练行为和有效的概念控制。在推理过程中，超网络根据CLIP嵌入动态生成适应性的LoRA权重，使反学习更加上下文感知和可扩展。我们评估了UnHype在多个具有挑战性的任务中的表现，包括物体擦除、名人擦除和色情内容删除，展示了其有效性和通用性。见GitHub上的代码：https://github.com/gmum/UnHype。
英文摘要：
Recent advances in large-scale diffusion models have intensified concerns about their potential misuse, particularly in generating realistic yet harmful or socially disruptive content. This challenge has spurred growing interest in effective machine unlearning, the process of selectively removing specific knowledge or concepts from a model without compromising its overall generative capabilities. Among various approaches, Low-Rank Adaptation (LoRA) has emerged as an effective and efficient method for fine-tuning models toward targeted unlearning. However, LoRA-based methods often exhibit limited adaptability to concept semantics and struggle to balance removing closely related concepts with maintaining generalization across broader meanings. Moreover, these methods face scalability challenges when multiple concepts must be erased simultaneously. To address these limitations, we introduce UnHype, a framework that incorporates hypernetworks into single- and multi-concept LoRA training. The proposed architecture can be directly plugged into Stable Diffusion as well as modern flow-based text-to-image models, where it demonstrates stable training behavior and effective concept control. During inference, the hypernetwork dynamically generates adaptive LoRA weights based on the CLIP embedding, enabling more context-aware, scalable unlearning. We evaluate UnHype across several challenging tasks, including object erasure, celebrity erasure, and explicit content removal, demonstrating its effectiveness and versatility. See the code on GitHub: https://github.com/gmum/UnHype.
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。
