{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:53:11Z","timestamp":1779382391512,"version":"3.53.1"},"reference-count":73,"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\/iccv51701.2025.01714","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18442-18452","source":"Crossref","is-referenced-by-count":5,"title":["Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens"],"prefix":"10.1109","author":[{"given":"Dongwon","family":"Kim","sequence":"first","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ju","family":"He","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihang","family":"Yu","sequence":"additional","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":"Xiaohui","family":"Shen","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suha","family":"Kwak","sequence":"additional","affiliation":[{"name":"POSTECH"}],"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","volume-title":"LAION2B-en-aesthetic"},{"key":"ref2","volume-title":"LAION-art"},{"key":"ref3","volume-title":"LAION-pop"},{"key":"ref4","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Meissonic: Revitalizing masked generative transformers for efficient high-resolution text-to-image synthesis","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"issue":"3","key":"ref7","volume-title":"Improving image generation with better captions. Computer Science","volume":"2","author":"Betker","year":"2023"},{"key":"ref8","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref10","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref12","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref13","article-title":"Generative pretraining from pixels","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref14","article-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","article-title":"Bert: Pre-training of deep bidirectional trans-formers for language understanding","author":"Devlin","year":"2018","journal-title":"NAACL"},{"key":"ref17","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref18","volume-title":"XWAVE, and SilentAntagonist. Dalle3 1 Million+ High Quality Captions","author":"Egan","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref20","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"ICML"},{"key":"ref21","article-title":"Fluid: Scaling autoregressive text-to-image generative models with continuous tokens","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Datacomp: In search of the next generation of multimodal datasets","author":"Gadre","year":"2023","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref24","article-title":"Geneval: An object-focused framework for evaluating text-toimage alignment","author":"Ghosh","year":"2023","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref26","article-title":"Deep autoregressive networks","author":"Gregor","year":"2014","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01544"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref33","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23161-2_300919"},{"key":"ref35","article-title":"Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image generation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref37","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref38","article-title":"Alleviating distortion in image generation via multi-resolution diffusion models","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref39","article-title":"Open-magvit2: An open-source project toward democratizing auto-regressive visual generation","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Image transformer","author":"Parmar","year":"2018","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref42","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref44","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"JMLR"},{"key":"ref45","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01464"},{"key":"ref47","article-title":"Flowar: Scale-wise autoregressive image generation meets flow matching","author":"Ren","year":"2025","journal-title":"ICML"},{"key":"ref48","article-title":"Grouping first, attending smartly: Trainingfree acceleration for diffusion transformers","author":"Ren","year":"2025","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref50","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref51","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref52","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01535"},{"key":"ref54","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015","journal-title":"ICLR"},{"key":"ref55","volume-title":"stabilityai","year":"2023"},{"key":"ref56","article-title":"Journeydb: A benchmark for generative image understanding","author":"Sun","year":"2023","journal-title":"NeurIPS"},{"key":"ref57","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00783"},{"key":"ref60","article-title":"Conditional image generation with pixelcnn decoders","author":"Van den Oord","year":"2016","journal-title":"NeurIPS"},{"key":"ref61","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref62","article-title":"Maskbit: Embedding-free image generation via bit tokens","author":"Weber","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"1.58-bit flux","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2022","journal-title":"ICLR"},{"key":"ref66","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"TMLR"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref68","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2024","journal-title":"ICLR"},{"key":"ref69","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"NeurIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01713"},{"key":"ref71","article-title":"Making convolutional networks shiftinvariant again","author":"Zhang","year":"2019","journal-title":"ICML"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"}],"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\/11445053.pdf?arnumber=11445053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:06Z","timestamp":1777613466000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01714","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}