{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:08Z","timestamp":1777865288845,"version":"3.51.4"},"reference-count":54,"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\/iccv51701.2025.01024","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11006-11015","source":"Crossref","is-referenced-by-count":0,"title":["Latent Swap Joint Diffusion for 2D Long-Form Latent Generation"],"prefix":"10.1109","author":[{"given":"Yusheng","family":"Dai","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kewei","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Sun","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqing","family":"Gao","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiefeng","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","volume-title":"International Conference on Machine Learning","author":"Bar-Tal"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_14"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2203"},{"key":"ref4","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv"},{"key":"ref6","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv"},{"key":"ref7","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv"},{"key":"ref8","article-title":"Gen-l-video: Multitext to long video generation via temporal co-denoising","author":"Wang","year":"2023","journal-title":"arXiv"},{"key":"ref9","article-title":"Freenoise: Tuning-free longer video diffusion via noise rescheduling","author":"Qiu","year":"2023","journal-title":"arXiv"},{"key":"ref10","article-title":"2405.11473","author":"Kim","year":"2024","journal-title":"Fifo-diffusion: Generating infinite videos from text without training"},{"key":"ref11","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref12","article-title":"Text-to-audio generation using instructiontuned 11 m and latent diffusion model","author":"Ghosal","year":"2023","journal-title":"arXiv"},{"key":"ref13","article-title":"Make-an-audio 2: Temporal-enhanced text-to-audio generation","author":"Huang","year":"2023","journal-title":"ArXiv"},{"key":"ref14","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024","journal-title":"ICML 2024"},{"key":"ref15","article-title":"Noise2music: Textconditioned music generation with diffusion models","volume":"abs\/2302.03917","author":"Huang","year":"2023","journal-title":"ArXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1126"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29332"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref20","article-title":"Fifo-diffusion: Generating infinite videos from text without training","volume":"abs\/2405.11473","author":"Kim","year":"2024","journal-title":"ArXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_9"},{"key":"ref22","article-title":"Mixture of diffusers for scene composition and high resolution image generation","author":"Jim\u00e9nez","year":"2023","journal-title":"arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00982"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref25","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022","journal-title":"arXiv"},{"key":"ref26","article-title":"Long-form music generation with latent diffusion","author":"Evans","year":"2024","journal-title":"arXiv"},{"key":"ref27","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv"},{"key":"ref28","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv"},{"key":"ref29","article-title":"Simple and controllable music generation","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Copet"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2467"},{"key":"ref32","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"arXiv"},{"key":"ref33","article-title":"Text-to-audio generation using instruction tuned 11 m and latent diffusion model","author":"Ghosal","year":"2023","journal-title":"arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3016"},{"key":"ref38","article-title":"Stochsync: Stochastic diffusion synchronization for image generation in arbitrary spaces","author":"Yeo","year":"2025","journal-title":"arXiv"},{"key":"ref39","article-title":"Scalecrafter: Tuning-free higherresolution visual generation with diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"He"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00589"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"issue":"70","key":"ref46","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref47","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref48","article-title":"Leveraging early-stage robustness in diffusion models for efficient and high-quality image synthesis","volume":"36","author":"Kim","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref50","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref51","article-title":"Demystifying mmd gans","author":"Bi\u0144kowski","year":"2018","journal-title":"arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"}],"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\/11444280.pdf?arnumber=11444280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:42Z","timestamp":1777529502000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01024","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}