{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:11Z","timestamp":1777888931692,"version":"3.51.4"},"reference-count":47,"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\/iccv51701.2025.01618","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17422-17431","source":"Crossref","is-referenced-by-count":0,"title":["Latent Diffusion Models With Masked Autoencoders"],"prefix":"10.1109","author":[{"given":"Junho","family":"Lee","sequence":"first","affiliation":[{"name":"Seoul National University,Seoul,Korea"}]},{"given":"Jeongwoo","family":"Shin","sequence":"additional","affiliation":[{"name":"Seoul National University,Seoul,Korea"}]},{"given":"Hyungwook","family":"Choi","sequence":"additional","affiliation":[{"name":"Seoul National University,Seoul,Korea"}]},{"given":"Joonseok","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Seoul,Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref2","author":"Chen","year":"2025","journal-title":"Masked autoencoders are effective tokenizers for diffusion models"},{"key":"ref3","author":"Chen","year":"2024","journal-title":"Deep compression autoencoder for efficient high-resolution diffusion models"},{"key":"ref4","article-title":"Do not escape from the manifold: Discovering the local coordinates on the latent space of gans","author":"Choi","year":"2021","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023","journal-title":"arXiv"},{"key":"ref6","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"In Proc. of the International Conference on Machine Learning (ICML)","author":"Dehghani"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","article-title":"Diffusion models beat gans on image synthesis","volume-title":"In Advances in Neural Information Processing Systems (NeurIPS)","author":"Dhariwal","year":"2021"},{"key":"ref9","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"In Proc. of the International Conference on Machine Learning (ICML)","author":"Esser"},{"key":"ref12","article-title":"Isometric representation learning for disentangled latent space of diffusion models","author":"Hahm","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"ref15","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref16","article-title":"\u03b2-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"In Proc. of the International Conference on Learning Representations","author":"Higgins"},{"key":"ref17","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref18","article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"In Proc. of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Karras"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref20","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref21","article-title":"Improved precision and recall metric for assessing generative models","author":"Kynk\u00e4\u00e4nniemi","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref22","volume-title":"Labs. Flux","author":"Forest","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref25","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","author":"Lu","year":"2022","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00878"},{"key":"ref28","article-title":"Generating images with sparse representations","author":"Nash","year":"2021","journal-title":"arXiv"},{"key":"ref29","article-title":"Improved denoising diffusion probabilistic models","volume-title":"In Proc. of the International Conference on Machine Learning (ICML)","author":"Quinn Nichol"},{"key":"ref30","article-title":"What do self-supervised vision transformers learn? arXiv:2305","author":"Park","year":"2023","journal-title":"00729"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21236\/ada164453"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0128"},{"key":"ref35","article-title":"Improved techniques for training GANs","volume-title":"In Advances in Neural Information Processing Systems (NIPS)","author":"Salimans","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1879"},{"key":"ref37","article-title":"Latent space disentanglement in diffusion transformers enables precise zero-shot semantic editing","author":"Shuai","year":"2024","journal-title":"arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1409.1556"},{"key":"ref39","article-title":"Denoising diffusion implicit models","volume-title":"In Proc. of the International Conference on Learning Representations (ICLR)","author":"Song"},{"key":"ref40","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref41","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"In Proc. of the International Conference on Learning Representations (ICLR)","author":"Song"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref43","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"In Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref45","article-title":"Reconstruction vs","author":"Yao","year":"2025","journal-title":"generation: Taming optimization dilemma in latent diffusion models"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"}],"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\/11445820.pdf?arnumber=11445820","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:43Z","timestamp":1777611763000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445820\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01618","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}