{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T02:50:59Z","timestamp":1790995859532,"version":"4.1.0"},"reference-count":75,"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\/iccv51701.2025.01676","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18034-18045","source":"Crossref","is-referenced-by-count":2,"title":["DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer"],"prefix":"10.1109","author":[{"given":"Yecheng","family":"Wu","sequence":"first","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyu","family":"Chen","sequence":"additional","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enze","family":"Xie","sequence":"additional","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jincheng","family":"Yu","sequence":"additional","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junsong","family":"Chen","sequence":"additional","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyi","family":"Hu","sequence":"additional","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Han","sequence":"additional","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Cai","sequence":"additional","affiliation":[{"name":"MIT NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Flextok: Resampling images into 1d token sequences of flexible length","author":"Bachmann","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Meissonic: Revitalizing masked generative transformers for efficient high-resolution text-to-image synthesis","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref4","year":"2024","journal-title":"BlackForest Labs. Flux"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01587"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00687"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref8","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02641"},{"key":"ref10","article-title":"Masked autoencoders are effective tokenizers for diffusion models","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Deep compression autoencoder for efficient high-resolution diffusion models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref13","article-title":"Pixart- $\\{\\backslash \\operatorname{delta}\\}$: Fast and controllable image generation with latent consistency models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref15","article-title":"Maskmamba: A hybrid mamba-transformer model for masked image generation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Januspro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02173"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","first-page":"41714186","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers)","author":"Devlin","year":"2019"},{"key":"ref21","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume":"34","author":"Ding","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref24","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref25","article-title":"Fluid: Scaling autoregressive text-to-image generative models with continuous tokens","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref28","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","author":"Han","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","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":"ref30","article-title":"Lantern: Accelerating visual autoregressive models with relaxed speculative decoding","author":"Jang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01714"},{"key":"ref32","article-title":"Videopoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2024","journal-title":"ICML"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref35","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":"ref36","article-title":"Controlvar: Exploring controllable visual autoregressive modeling","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"26689","article-title":"Vila: On pre-training for vi-sual language models","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Lin"},{"key":"ref38","article-title":"Playground v3: Improving text-to-image alignment with deep-fusion large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"World model on million-length video and language with blockwise ringattention","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Exploring the role of large language models in prompt encoding for diffusion models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Ma"},{"key":"ref42","article-title":"Star: Scale-wise text-toimage generation via auto-regressive representations","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","year":"2024","journal-title":"OpenAI. Hello gpt-4o"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref45","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":"ref46","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00243"},{"issue":"140","key":"ref48","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref49","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2161"},{"key":"ref52","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Hart: Efficient visual generation with hybrid autoregressive transformer","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","volume-title":"Auraflow Team. Introducing auraflow v0. 1, an open exploration of large rectified flow models","volume":"4","year":"2024"},{"key":"ref55","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"K Team. Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref58","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref59","article-title":"Phenaki: Variable length video generation from open domain textual description","author":"Villegas","year":"2022","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01209"},{"key":"ref62","article-title":"Maskbit: Embedding-free image generation via bit tokens","author":"Weber","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref63","article-title":"Janus: Decoupling visual encoding for unified multimodal understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Vila-u: a unified foundation model integrating visual understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","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":"ref67","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Car: Controllable autoregressive modeling for visual generation","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"issue":"128940128966","key":"ref71","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":"ref72","article-title":"Shieldgemma: Generative ai content moderation based on gemma","author":"Zeng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Languageguided image tokenization for generation","author":"Zha","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Var-clip: Text-to-image generator with visual auto-regressive modeling","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"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\/11444288.pdf?arnumber=11444288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:36:44Z","timestamp":1777531004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01676","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}