{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T02:23:54Z","timestamp":1790562234179,"version":"4.1.0"},"reference-count":52,"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\/iccv51701.2025.01535","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16535-16544","source":"Crossref","is-referenced-by-count":6,"title":["Deeply Supervised Flow-Based Generative Models"],"prefix":"10.1109","author":[{"given":"Inkyu","family":"Shin","sequence":"first","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenglin","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang-Chieh","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Albergo","year":"2023","journal-title":"Stochastic interpolants: A unifying framework for flows and diffusions"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","article-title":"Neural ordinary differential equations","volume-title":"Proc. of Neural Information Processing Systems (NeurIPS)","author":"Chen","year":"2018"},{"key":"ref5","author":"Chen","year":"2015","journal-title":"Microsoft coco captions: Data collection and evaluation server"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Proc. of Neural Information Processing Systems (NeurIPS)","author":"Dhariwal","year":"2021"},{"key":"ref8","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. of Int\u2019l Conf. on Machine Learning (ICML)","author":"Esser","year":"2024"},{"key":"ref9","article-title":"Lumina-t2x: Scalable flow-based large diffusion transformer for flexible resolution generation","volume-title":"Proc. of Int\u2019l Conf. on Learning Representations (ICLR)","author":"Gao","year":"2025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01544"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. of Neural Information Processing Systems (NeurIPS)","author":"Ho","year":"2020"},{"key":"ref15","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref16","article-title":"Simple diffusion: End-to-end diffusion for high resolution images","volume-title":"Proc. of Int\u2019l Conf. on Machine Learning (ICML)","author":"Hoogeboom","year":"2023"},{"key":"ref17","author":"Jin","year":"2024","journal-title":"Pyramidal flow matching for efficient video generative modeling"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01714"},{"key":"ref19","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref20","article-title":"Deeply-supervised nets","volume-title":"Proc. of Artificial Intelligence and Statistics (AISTATS)","author":"Lee","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","article-title":"Flow matching for generative modeling","volume-title":"Proc. of Int\u2019l Conf. on Learning Representations (ICLR)","author":"Lipman","year":"2023"},{"key":"ref23","author":"Lipman","year":"2024","journal-title":"Flow matching guide and code"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4254"},{"key":"ref25","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proc. of Int\u2019l Conf. on Learning Representations (ICLR)","author":"Liu","year":"2023"},{"key":"ref26","article-title":"Instaflow: One step is enough for high-quality diffusion-based text-to-image generation","volume-title":"Proc. of Int\u2019l Conf. on Learning Representations (ICLR)","author":"Liu","year":"2023"},{"key":"ref27","author":"Luo","year":"2024","journal-title":"Open-magvit2: An opensource project toward democratizing auto-regressive visual generation"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref29","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. of Int\u2019l Conf. on Machine Learning (ICML)","author":"Nichol","year":"2021"},{"key":"ref30","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref31","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Proc. of Neural Information Processing Systems (NeurIPS)","author":"Paszke","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref33","article-title":"W\u00fcrstchen: An efficient architecture for large-scale text-to-image diffusion models","volume-title":"Proc. of Int\u2019l Conf. on Learning Representations (ICLR)","author":"Pernias","year":"2024"},{"key":"ref34","author":"Ren","year":"2024","journal-title":"Flowar: Scale-wise autoregressive image generation meets flow matching"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01464"},{"key":"ref36","author":"Ren","year":"2025","journal-title":"Grouping first, attending smartly: Training-free acceleration for diffusion transformers"},{"key":"ref37","article-title":"Variational inference with normalizing flows","volume-title":"Proc. of Int\u2019l Conf. on Machine Learning (ICML)","author":"Rezende","year":"2015"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref40","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. of Neural Information Processing Systems (NeurIPS)","author":"Song","year":"2020"},{"key":"ref41","article-title":"Scorebased generative modeling through stochastic differential equations","volume-title":"Proc. of Int\u2019l Conf. on Learning Representations (ICLR)","author":"Song","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0165"},{"key":"ref43","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_17"},{"key":"ref45","article-title":"Attention is all you need","volume-title":"Proc. of Neural Information Processing Systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"ref46","author":"Weber","year":"2024","journal-title":"Maskbit: Embedding-free image generation via bit tokens"},{"key":"ref47","author":"Yang","year":"2024","journal-title":"1.58-bit flux"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref49","article-title":"Language model beats diffusion-tokenizer is key to visual generation","volume-title":"Proc. of Int\u2019l Conf. on Learning Representations (ICLR)","author":"Yu","year":"2024"},{"key":"ref50","author":"Yu","year":"2024","journal-title":"Randomized autoregressive visual generation"},{"key":"ref51","article-title":"An image is worth 32 tokens for reconstruction and generation","volume-title":"Proc. of Neural Information Processing Systems (NeurIPS)","author":"Yu","year":"2024"},{"key":"ref52","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","volume-title":"Proc. of Int\u2019l Conf. on Learning Representations (ICLR)","author":"Yu","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\/11445814.pdf?arnumber=11445814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:39:41Z","timestamp":1777531181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01535","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}