{"ID":2861650,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.02296","arxiv_id":"2510.02296","title":"Continual Personalization for Diffusion Models","abstract":"Updating diffusion models in an incremental setting would be practical in real-world applications yet computationally challenging. We present a novel learning strategy of Concept Neuron Selection (CNS), a simple yet effective approach to perform personalization in a continual learning scheme. CNS uniquely identifies neurons in diffusion models that are closely related to the target concepts. In order to mitigate catastrophic forgetting problems while preserving zero-shot text-to-image generation ability, CNS finetunes concept neurons in an incremental manner and jointly preserves knowledge learned of previous concepts. Evaluation of real-world datasets demonstrates that CNS achieves state-of-the-art performance with minimal parameter adjustments, outperforming previous methods in both single and multi-concept personalization works. CNS also achieves fusion-free operation, reducing memory storage and processing time for continual personalization.","short_abstract":"Updating diffusion models in an incremental setting would be practical in real-world applications yet computationally challenging. We present a novel learning strategy of Concept Neuron Selection (CNS), a simple yet effective approach to perform personalization in a continual learning scheme. CNS uniquely identifies ne...","url_abs":"https://arxiv.org/abs/2510.02296","url_pdf":"https://arxiv.org/pdf/2510.02296v1","authors":"[\"Yu-Chien Liao\",\"Jr-Jen Chen\",\"Chi-Pin Huang\",\"Ci-Siang Lin\",\"Meng-Lin Wu\",\"Yu-Chiang Frank Wang\"]","published":"2025-10-02T17:58:56Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}