{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:36Z","timestamp":1777865376955,"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"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210102801,FT240100820"],"award-info":[{"award-number":["DP210102801,FT240100820"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"MSIT","doi-asserted-by":"publisher","award":["RS-2024-00457882"],"award-info":[{"award-number":["RS-2024-00457882"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-2443404"],"award-info":[{"award-number":["IIS-2443404"]}],"id":[{"id":"10.13039\/100000001","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\/iccv51701.2025.01697","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18262-18272","source":"Crossref","is-referenced-by-count":0,"title":["REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers"],"prefix":"10.1109","author":[{"given":"Xingjian","family":"Leng","sequence":"first","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaskirat","family":"Singh","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunzhong","family":"Hou","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenchang","family":"Xing","sequence":"additional","affiliation":[{"name":"Data61, CSIRO"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saining","family":"Xie","sequence":"additional","affiliation":[{"name":"New York University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zheng","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Improved autoencoders","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref3","first-page":"279","article-title":"Modular learning in neural networks","volume-title":"Proceedings of the sixth National conference on Artificial intelligence-Volume 1","author":"Ballard"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref5","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref11","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02117"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","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":"ref18","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref19","article-title":"The platonic representation hypothesis","volume-title":"International Conference on Machine Learning","author":"Huh"},{"key":"ref20","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01714"},{"key":"ref22","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Eq-vae: Equivariance regularized latent space for improved generative image modeling","author":"Kouzelis","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref25","article-title":"Improved precision and recall metric for assessing generative models","volume":"32","author":"Kynk\u00e4\u00e4nniemi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref26","volume-title":"Flux","year":"2024"},{"key":"ref27","first-page":"56424","article-title":"Autoregressive image generation without vector quantization","volume":"37","author":"Li","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref29","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref31","first-page":"7958","article-title":"Generating images with sparse representations","volume-title":"International Conference on Machine Learning","author":"Nash"},{"key":"ref32","volume-title":"Sora","year":"2024"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-658-47422-5_60","article-title":"W\u00fcrstchen: An efficient architecture for large-scale text-to-image diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Pernias"},{"key":"ref36","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"ref41","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00581"},{"key":"ref43","article-title":"Improving the diffusability of autoencoders","author":"Skorokhodov","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref46","first-page":"11287","article-title":"Score-based generative modeling in latent space","volume-title":"Advances in Neural Information Processing Systems","author":"Vahdat","year":"2021"},{"key":"ref47","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref49","article-title":"Fasterdit: Towards faster diffusion transformers training without architecture modification","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref51","first-page":"128940","article-title":"An image is worth 32 tokens for reconstruction and generation","volume":"37","author":"Yu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref52","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"Languageguided image tokenization for generation","author":"Zha","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"Fast training of diffusion models with masked transformers","author":"Zheng","year":"2023","journal-title":"arXiv preprint arXiv"}],"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\/11445131.pdf?arnumber=11445131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:02Z","timestamp":1777530122000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01697","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}