Newest papers

Continual Concept Personalization in Diffusion Models via Residual-Space Adaptation

Yuzhi Liu, Enis Simsar, Giulia Lanzillotta, Thomas Frank Hofmann · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28567 · cited by 0 works (OpenAlex) · open-access PDF

Chinese

文本到图像个性化旨在为预先训练的扩散模型提供能够从仅几张参考图像中学习用户特定的概念的能力。现有方法通常会独立训练每个概念,或者假设所有概念都可同时使用。在实际应用中,概念往往会连续出现,要求模型不断学习新主题,对象或风格,同时最大限度地减少与先前获得的概念的干扰。我们通过扩展残余空间适应过程中预先训练的扩散模型的斯托哈斯特式适应来解决这个连续概念个性化设置。我们的工作实现了竞争不断的个性化方法中最高的概念忠诚度,同时保持接近零的忘记。 除了这些经验上的收益之外,学习的残余空间动态学揭示了在扩散模型内集中适应能力。 限制适应被识别

Machine translation (Meta M2M100); the English original follows.

Abstract

Text-to-image personalization aims to equip pretrained diffusion models with the ability to learn user-specific concepts from only a few reference images. Existing methods, however, typically train each concept independently or assume that all concepts are available simultaneously. In practical applications, concepts often arrive sequentially, requiring models to continually learn new subjects, objects, or styles while minimizing interference with previously acquired concepts. We address this continual concept personalization setting by extending residual-space adaptation to the stochastic adaptation process of pretrained diffusion models. Our work achieves the highest concept fidelity among competing continual personalization methods while maintaining near-zero forgetting. Beyond these empirical gains, the learned residual-space dynamics reveal where adaptation capacity is concentrated within the diffusion model. Restricting adaptation to the identified layers by our method preserves nearly the same performance while reducing the number of trainable parameters by up to 72\%, demonstrating that residual-space dynamics can identify the layers that contribute most to continual concept personalization and directly guide more parameter-efficient adaptation.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Personalization, Adaptation (eye), Computer science, Process (computing), Fidelity, Artificial intelligence

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange