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

Indonesian

Metode yang ada, bagaimanapun, biasanya melatih setiap konsep secara independen atau mengasumsikan bahwa semua konsep tersedia secara bersamaan. Dalam aplikasi praktis, konsep sering datang secara berurutan, mengharuskan model untuk terus belajar konsep baru, objek, atau gaya dari hanya beberapa gambar referensi. Metode yang ada, bagaimanapun, biasanya melatih setiap konsep secara independen atau mengasumsikan bahwa semua konsep tersedia secara bersamaan. Dalam aplikasi praktis, konsep sering datang secara berurutan, mengharuskan model untuk terus mempelajari subjek baru, objek, atau gaya sambil meminimalkan gangguan dengan konsep-konsep yang telah diperoleh sebelumnya. Kami menangani pengaturan konsep yang berterusan ini dengan memperluas adaptasi ruang residual ke adaptasi stochastic proses dari model diffusion pretrained. Pekerjaan kami mencapai kesetiaan konsep tertinggi di antara metode personalisasi berkelanjutan yang bersaing

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