{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:50Z","timestamp":1758672890464,"version":"3.44.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Text-to-image diffusion models can generate high-quality images but lack fine-grained control of visual concepts, limiting their creativity. Thus, we introduce component-controllable personalization, a new task that enables users to customize and reconfigure individual components within concepts. This task faces two challenges: semantic pollution, where undesired elements disrupt the target concept, and semantic imbalance, which causes disproportionate learning of the target concept and component. To address these, we design MagicTailor, a framework that uses Dynamic Masked Degradation to adaptively perturb unwanted visual semantics and Dual-Stream Balancing for more balanced learning of desired visual semantics. The experimental results show that MagicTailor achieves superior performance in this task and enables more personalized and creative image generation.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/1136","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"10225-10233","source":"Crossref","is-referenced-by-count":0,"title":["MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models"],"prefix":"10.24963","author":[{"given":"Donghao","family":"Zhou","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Jiancheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences"}]},{"given":"Jinbin","family":"Bai","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"given":"Jiaze","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]},{"given":"Guangyong","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang Lab"}]},{"given":"Xiaowei","family":"Hu","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}]},{"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:36:14Z","timestamp":1758627374000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/1136"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/1136","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}