{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:19Z","timestamp":1777865359984,"version":"3.51.4"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031777","name":"CUP","doi-asserted-by":"publisher","award":["C93C22005250001"],"award-info":[{"award-number":["C93C22005250001"]}],"id":[{"id":"10.13039\/100031777","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01497","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16132-16142","source":"Crossref","is-referenced-by-count":0,"title":["LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation"],"prefix":"10.1109","author":[{"given":"Donald","family":"Shenaj","sequence":"first","affiliation":[{"name":"Samsung R&D Institute UK (SRUK)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ondrej","family":"Bohdal","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute UK (SRUK)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mete","family":"Ozay","sequence":"additional","affiliation":[{"name":"Samsung R&D Institute UK (SRUK)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pietro","family":"Zanuttigh","sequence":"additional","affiliation":[{"name":"University of Padova"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umberto","family":"Michieli","sequence":"additional","affiliation":[{"name":"University of Padova"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01164"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618173"},{"key":"ref3","article-title":"Non-linear fusion in federated learning: A hypernetwork approach to federated domain generalization","author":"Bartholet","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.929"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10862-8"},{"key":"ref6","article-title":"Mllm-as-a-judge: Assessing multimodal 11 m -as-a-judge with vision-language benchmark","volume-title":"International Conference on Machine Learning","author":"Chen","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref8","volume-title":"Civitai: The Home of Open-Source Generative AI","year":"2024"},{"key":"ref9","volume-title":"Low-rank adaptation for fast text-toimage diffusion finetuning","year":"2022"},{"key":"ref10","article-title":"Dreamartist: Towards controllable one-shot text-to-image generation via positivenegative prompt-tuning","author":"Dong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref12","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"International Conference on Learning Representations","author":"Gal","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.36"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0699"},{"key":"ref16","article-title":"Hypernetworks","volume-title":"International Conference on Learning Representations","author":"Ha","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.762"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref19","article-title":"Vico: Plug-and-play visual condition for personalized text-toimage generation","author":"Hao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2021"},{"key":"ref22","volume-title":"Hugging Face - The AI community building the future","year":"2024"},{"key":"ref23","article-title":"Editing models with task arithmetic","volume-title":"International Conference on Learning Representations","author":"Ilharco","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref25","article-title":"Imagenhub: Standardizing the evaluation of conditional image generation models","volume-title":"International Conference on Learning Representations","author":"Ku","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1634"},{"key":"ref28","article-title":"Blip-diffusion: Pre-trained subject representation for controllable text-toimage generation and editing","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657469"},{"key":"ref30","article-title":"Kosmos-g: Generating images in context with multimodal large language models","volume-title":"International Conference on Learning Representations","author":"Pan","year":"2024"},{"key":"ref31","article-title":"\\lambda-ECLIPSE: Multi-concept personalized text-to-image diffusion models by leveraging CLIP latent space","author":"Patel","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref32","article-title":"Dreambench++: A human-aligned benchmark for personalized image generation","volume-title":"International Conference on Learning Representations","author":"Peng","year":"2025"},{"key":"ref33","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"International Conference on Learning Representations","author":"Podell","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91907-7_15"},{"key":"ref35","article-title":"Rb-modulation: Training-free stylization using reference-based modulation","volume-title":"International Conference on Learning Representations","author":"Rout","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2920"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591506"},{"key":"ref41","article-title":"p+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref43","article-title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","volume-title":"International Conference on Machine Learning","author":"Wortsman","year":"2022"},{"key":"ref44","article-title":"Difflora: Generating personalized low-rank adaptation weights with diffusion","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Llavacritic: Learning to evaluate multimodal models","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Xiong","year":"2025"},{"key":"ref46","article-title":"Break-for-make: Modular low-rank adaptations for composable content-style customization","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Freetuner: Any subject in any style with training-free diffusion","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Ties-merging: Resolving interference when merging models","author":"Yadav","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","article-title":"Model merging in 11 ms, mllms, and beyond: Methods, theories, applications and opportunities","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Controllable textual inversion for personalized text-to-image generation","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3633153"},{"key":"ref52","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Language models are super mario: Absorbing abilities from homologous models as a free lunch","volume-title":"International Conference on Machine Learning","author":"Yu","year":"2024"},{"key":"ref54","volume-title":"Can MLLMs perform text-to-image in-context learning? In Conference on Language Modeling","author":"Zeng"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00648"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00877"},{"key":"ref58","article-title":"Toffee: Efficient million-scale dataset construction for subject-driven text-to-image generation","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"VL-ICL bench: The devil in the details of multimodal incontext learning","volume-title":"International Conference on Learning Representations","author":"Zong","year":"2025"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444369.pdf?arnumber=11444369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:42Z","timestamp":1777530042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01497","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}