{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:30Z","timestamp":1792786950816,"version":"4.5.0"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62501386"],"award-info":[{"award-number":["62501386"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"CCF-Tencent Rhino-Bird Open Research Fund"},{"name":"CAAI-Tencent Rhino-Bird Open Research Fund"},{"name":"AI Hundred Schools Program and carried out using the Ascend AI technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3700787","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:51:25Z","timestamp":1780948285000},"page":"12211-12228","source":"Crossref","is-referenced-by-count":0,"title":["Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8545-4447","authenticated-orcid":false,"given":"Jiahua","family":"Dong","sequence":"first","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence","place":["Abu Dhabi, UAE"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2261-7744","authenticated-orcid":false,"given":"Wenqi","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Trento","place":["Trento, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2590-9491","authenticated-orcid":false,"given":"Hongliu","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University","place":["Hong Kong, SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5102-0189","authenticated-orcid":false,"given":"Yang","family":"Cong","sequence":"additional","affiliation":[{"name":"South China University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4280-431X","authenticated-orcid":false,"given":"Duzhen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence","place":["Abu Dhabi, UAE"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-4534","authenticated-orcid":false,"given":"Hanbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-6526","authenticated-orcid":false,"given":"Henghui","family":"Ding","sequence":"additional","affiliation":[{"name":"Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2288-5079","authenticated-orcid":false,"given":"Yulun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9502-1749","authenticated-orcid":false,"given":"Salman","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence","place":["Abu Dhabi, UAE"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4263-3143","authenticated-orcid":false,"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence","place":["Abu Dhabi, UAE"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00067"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann. Kulal","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680637"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00630"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32259"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72630-9_25"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3334213"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4132"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00992"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00907"},{"key":"ref13","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Esser","year":"2024"},{"key":"ref14","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gal","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2800768"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0699"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00280"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref20","article-title":"CameraCtrl: Enabling camera control for video diffusion models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00245"},{"key":"ref22","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2021"},{"key":"ref23","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02204"},{"key":"ref25","article-title":"StoryAgent: Customized storytelling video generation via multi-agent collaboration","author":"Hu","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01640"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02334-x"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref31","article-title":"Flux","author":"Labs","year":"2024"},{"key":"ref32","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_14"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680718"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3553024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72907-2_23"},{"key":"ref40","first-page":"32100","article-title":"Dora: Weight-decomposed low-rank adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2024"},{"key":"ref41","article-title":"C-CLIP: Multimodal continual learning for vision-language model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2508"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00614"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01031"},{"key":"ref45","article-title":"Representational continuity for unsupervised continual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Madaan","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00069"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00774"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01242"},{"key":"ref50","first-page":"1862","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Podell","year":"2024"},{"key":"ref51","article-title":"Dreamfusion: Text-to-3D using 2D diffusion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Poole","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01726"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"ref54","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"ref60","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with c-LoRA","author":"Smith","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/208"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3382753"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01403"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00202"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01538"},{"key":"ref67","article-title":"MS-Diffusion: Multi-subject zero-shot image personalization with layout guidance","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32868"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00625"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02015"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00268"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32904"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1082"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01689"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32914"},{"key":"ref78","article-title":"Mixture of LoRA experts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2024"},{"key":"ref79","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xie","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681391"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3587105"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3633153"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00272"},{"key":"ref84","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00251"},{"key":"ref86","article-title":"Lifelong learning with dynamically expandable networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yoon","year":"2018"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00648"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"ref90","article-title":"Multi-LoRA composition for image generation","author":"Zhong","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00877"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33187"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11554072.pdf?arnumber=11554072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:18:45Z","timestamp":1790270325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11554072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":92,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3700787","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}