{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:03:10Z","timestamp":1777888990953,"version":"3.51.4"},"reference-count":75,"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\/iccv51701.2025.01516","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16333-16344","source":"Crossref","is-referenced-by-count":0,"title":["Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models"],"prefix":"10.1109","author":[{"given":"Zerui","family":"Tao","sequence":"first","affiliation":[{"name":"RIKEN AIP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhta","family":"Takida","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoki","family":"Murata","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qibin","family":"Zhao","sequence":"additional","affiliation":[{"name":"RIKEN AIP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Tqcompressor: improving tensor decomposition methods in neural networks via permutations","author":"V","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA61862.2024.00085"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0438"},{"key":"ref4","article-title":"Ether: Efficient finetuning of large-scale models with hyperplane reflections","volume-title":"In Forty-first International Conference on Machine Learning. 3","author":"Bini"},{"key":"ref5","first-page":"2","article-title":"Foura: Fourier low rank adaptation","author":"Borse","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref7","first-page":"3","article-title":"Para: Personalizing text-to-image diffusion via parameter rank reduction","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Chen"},{"key":"ref8","first-page":"2","article-title":"Quanta: Efficient highrank fine-tuning of 11 ms with quantum-informed tensor adaptation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2200000059"},{"key":"ref10","first-page":"2","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"In Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref11","first-page":"2","article-title":"A note on lora","author":"Fomenko","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"2","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"In The Eleventh International Conference on Learning Representations","author":"Gal"},{"key":"ref13","first-page":"2","article-title":"Parameter-efficient fine-tuning with discrete fourier transform","volume-title":"In Forty-first International Conference on Machine Learning","author":"Gao"},{"key":"ref14","first-page":"3","article-title":"Ultimate tensorization: compressing convolutional and fc layers alike","author":"Garipov","year":"2016","journal-title":"arXiv preprint"},{"key":"ref15","volume-title":"Deep learning book notation.","author":"Goodfellow"},{"key":"ref16","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref17","first-page":"2","article-title":"Mix-of-show: Decentralized lowrank adaptation for multi-concept customization of diffusion models","volume":"36","author":"Gu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref19","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"In International conference on machine learning","author":"Houlsby"},{"key":"ref20","first-page":"2","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"In International Conference on Learning Representations","author":"Hu"},{"key":"ref21","first-page":"3","article-title":"SaRA: High-efficient diffusion model fine-tuning with progressive sparse low-rank adaptation","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Hu"},{"key":"ref22","first-page":"3","article-title":"HiRA: Parameter-efficient hadamard high-rank adaptation for large language models","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Huang"},{"key":"ref23","first-page":"3","article-title":"Fedpara: Low-rank hadamard product for communicationefficient federated learning","volume-title":"In International Conference on Learning Representations","author":"Hyeon-Woo"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"ref25","article-title":"Vera: Vector-based random matrix adaptation","volume-title":"In The Twelfth International Conference on Learning Representations.","author":"Kopiczko"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref27","first-page":"6","article-title":"Direct consistency optimization for compositional text-to-image personalization","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref29","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref31","first-page":"2","article-title":"DoRA: Weight-decomposed low-rank adaptation","volume-title":"In Forty-first International Conference on Machine Learning","author":"Liu"},{"key":"ref32","first-page":"2","article-title":"Parameter-efficient orthogonal finetuning via butterfly factorization","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Liu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0786"},{"key":"ref34","article-title":"Parameter efficient quasi-orthogonal finetuning via givens rotation","volume-title":"In Forty-first International Conference on Machine Learning. 3","author":"Ma"},{"key":"ref35","first-page":"3","article-title":"A tensorized transformer for language modeling","volume":"32","author":"Ma","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref36","volume-title":"Peft: State-of-the-art parameter-efficient fine-tuning methods","author":"Mangrulkar","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01067"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref39","first-page":"2","article-title":"RoSA: Accurate parameter-efficient fine-tuning via robust adaptation","volume-title":"In Forty-first International Conference on Machine Learning","author":"Nikdan"},{"key":"ref40","first-page":"3","article-title":"Vetrov","volume":"28","author":"Novikov","year":"2015","journal-title":"Tensorizing neural networks. Advances in neural information processing systems"},{"key":"ref41","first-page":"1","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/090752286"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1817"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014683"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16014-1_59"},{"key":"ref46","first-page":"2","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3472"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"issue":"2","key":"ref49","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref51","first-page":"3","article-title":"Rb-modulation: Training-free personalization of diffusion models using stochastic optimal control","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref54","first-page":"2","article-title":"Structured unrestricted-rank matrices for parameter efficient fine-tuning","author":"Sehanobish","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","first-page":"13714","article-title":"Convolutional tensortrain 1stm for spatio-temporal learning","volume":"33","author":"Su","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref56","volume-title":"The Diffusers team. SD-XL inpainting 0.1 model card."},{"key":"ref57","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00972"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref60","first-page":"12077","article-title":"Alvarez, and Ping Luo","volume":"34","author":"Xie","year":"2021","journal-title":"Segformer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00390"},{"key":"ref62","article-title":"Raphael: Text-to-image generation via large mixture of diffusion paths","volume":"36","author":"Xue","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref63","article-title":"A spectral condition for feature learning","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","first-page":"3","article-title":"Tensortrain recurrent neural networks for video classification","volume-title":"In International Conference on Machine Learning, pages 38913900. PMLR","author":"Yang"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.174"},{"key":"ref66","first-page":"3","article-title":"Navigating text-to-image customization: From lyCORIS fine-tuning to model evaluation","volume-title":"In The Twelfth International Conference on Learning Representations","author":"YEH"},{"key":"ref67","first-page":"3","article-title":"Bridging the gap between low-rank and orthogonal adaptation via householder reflection adaptation","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref69","first-page":"3","article-title":"Adaptive budget allocation for parameter-efficient finetuning","volume-title":"In International Conference on Learning Representations. Openreview","author":"Zhang"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00458"},{"key":"ref72","article-title":"Galore: Memoryefficient llm training by gradient low-rank projection","volume-title":"In International Conference on Machine Learning, pages 6112161143. PMLR","author":"Zhao"},{"key":"ref73","first-page":"2","article-title":"Tensor ring decomposition","author":"Zhao","year":"2016","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2351"}],"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\/11446275.pdf?arnumber=11446275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:34Z","timestamp":1777611874000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01516","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}