{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:39:59Z","timestamp":1778258399299,"version":"3.51.4"},"reference-count":37,"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\/iccv51701.2025.01825","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space"],"prefix":"10.1109","author":[{"given":"Junyu","family":"Chen","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongyun","family":"Zou","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenkun","family":"He","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsong","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enze","family":"Xie","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Han","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Cai","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01587"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00687"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02641"},{"key":"ref6","article-title":"Masked autoencoders are effective tokenizers for diffusion models","volume-title":"arXiv preprint","author":"Chen","year":"2025"},{"key":"ref7","article-title":"Deep compression autoencoder for efficient high-resolution diffusion models","volume-title":"arXiv preprint","author":"Chen","year":"2024"},{"key":"ref8","article-title":"Pixart- \u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref9","article-title":"Very deep vaes generalize autoregressive models and can outperform them on images","volume-title":"arXiv preprint","author":"Child","year":"2020"},{"key":"ref10","article-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","volume-title":"arXiv preprint","author":"Dai","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref13","article-title":"Classifier-free diffusion guidance","volume-title":"arXiv preprint","author":"Ho","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"ref16","article-title":"Eq-vae: Equivariance regularized latent space for improved generative image modeling","volume-title":"arXiv preprint","author":"Kouzelis","year":"2025"},{"key":"ref17","article-title":"Improved precision and recall metric for assessing generative models","volume-title":"Advances in neural information processing systems","volume":"32","author":"Kynk\u00e4\u00e4nniemi","year":"2019"},{"key":"ref18","article-title":"Applying guidance in a limited interval improves sample and distribution quality in diffusion models","volume-title":"arXiv preprint","author":"Kynk\u00e4\u00e4nniemi","year":"2024"},{"key":"ref19","article-title":"Labs","volume-title":"Flux. Online","author":"Forest","year":"2024"},{"key":"ref20","article-title":"Autoregressive image generation without vector quantization","volume-title":"arXiv preprint","author":"Li","year":"2024"},{"key":"ref21","article-title":"Playground v3: Improving text-to-image alignment with deep-fusion large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.08500"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","article-title":"Improved techniques for training gans","volume-title":"Advances in neural information processing systems, 29","author":"Salimans","year":"2016"},{"key":"ref27","first-page":"20141","article-title":"Bit prioritization in variational autoencoders via progressive coding","volume-title":"ICML","author":"Shu","year":"2022"},{"key":"ref28","article-title":"Improving the diffusability of autoencoders","volume-title":"arXiv preprint","author":"Skorokhodov","year":"2025"},{"key":"ref29","article-title":"Hq-vae: Hierarchical discrete representation learning with variational bayes","volume-title":"arXiv preprint","author":"Takida","year":"2023"},{"key":"ref30","first-page":"19667","article-title":"Nvae: A deep hierarchical variational autoencoder","volume":"33","author":"Vahdat","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","volume-title":"arXiv preprint","author":"Xie","year":"2024"},{"key":"ref32","article-title":"Sana 1.5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer","author":"Xie","year":"2025","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref34","article-title":"Language model beats diffusion-tokenizer is key to visual generation","volume-title":"arXiv preprint","author":"Yu","year":"2023"},{"key":"ref35","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","volume-title":"arXiv preprint","author":"Yu","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref37","article-title":"Designing a better asymmetric vqgan for stablediffusion","volume-title":"arXiv preprint","author":"Zhu","year":"2023"}],"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\/11444013.pdf?arnumber=11444013","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:44Z","timestamp":1777613324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444013\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01825","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}