{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:44:25Z","timestamp":1781797465274,"version":"3.54.5"},"reference-count":60,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01681","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18090-18100","source":"Crossref","is-referenced-by-count":1,"title":["Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation"],"prefix":"10.1109","author":[{"given":"Tuna Han Salih","family":"Meral","sequence":"first","affiliation":[{"name":"Virginia Tech"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enis","family":"Simsar","sequence":"additional","affiliation":[{"name":"ETH Zurich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[{"name":"TUM"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pinar","family":"Yanardag","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref4","first-page":"1737","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","volume-title":"In International Conference on Machine Learning","author":"Bar-Tal","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref7","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"In International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_8"},{"key":"ref9","volume-title":"Civitai","year":"2020"},{"key":"ref10","author":"Couairon","year":"2022","journal-title":"Diffedit: Diffusion-based semantic image editing with mask guidance"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596771"},{"key":"ref12","author":"Gal","year":"2022","journal-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref16","author":"Gu","year":"2023","journal-title":"Mix-of-show: Decentralized lowrank adaptation for multi-concept customization of diffusion models"},{"key":"ref17","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref18","author":"Hertz","year":"2022","journal-title":"Prompt-to-prompt image editing with cross attention control"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596770"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","author":"Hu","year":"2021","journal-title":"Lora: Low-rank adaptation of large language models"},{"key":"ref22","author":"Huang","year":"2023","journal-title":"Lorahub: Efficient cross-task generalization via dynamic lora composition"},{"key":"ref23","volume-title":"Composer: Creative and controllable image synthesis with composable conditions","author":"Huang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599557"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_15"},{"key":"ref31","author":"Korshunov","year":"2018","journal-title":"Deepfakes: a new threat to face recognition? assessment and detection"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3283551"},{"key":"ref34","author":"Li","year":"2023","journal-title":"Divide & bind your attention for improved generative semantic nursing"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref36","author":"Luo","year":"2024","journal-title":"Stylus: Automatic adapter selection for diffusion models"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1163\/9789004337862_lgbo_com_030721"},{"key":"ref38","author":"Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00761"},{"key":"ref41","volume-title":"Prolific. Prolific","year":"2025"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref43","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","first-page":"234","article-title":"Unet: Convolutional networks for biomedical image segmentation","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference","author":"Ronneberger","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref47","author":"Ryu","year":"2023","journal-title":"Low-rank adaptation for fast text-to-image diffusion fine-tuning"},{"key":"ref48","author":"Saharia","year":"2022","journal-title":"Photorealistic text-to-image diffusion models with deep language understanding"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01231"},{"key":"ref51","author":"Sohn","year":"2023","journal-title":"Styledrop: Text-to-image generation in any style"},{"key":"ref52","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"ref54","article-title":"Mole: Mixture of lora experts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wu","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3633153"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00456"},{"key":"ref59","author":"Zhong","year":"2024","journal-title":"Multi-lora composition for image generation"},{"key":"ref60","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11444429.pdf?arnumber=11444429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:20Z","timestamp":1777611980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444429\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01681","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}