{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:58:28Z","timestamp":1783439908015,"version":"3.54.6"},"reference-count":52,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202199"],"award-info":[{"award-number":["62202199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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\/iccv51701.2025.01615","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17390-17400","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis"],"prefix":"10.1109","author":[{"given":"Peng","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junke","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Trustworthy Embodied AI, Fudan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhou","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computing and Data Science, The University of Hong Kon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02641"},{"key":"ref4","article-title":"Flow matching in latent space","author":"Dao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","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":"ref7","article-title":"Fluid: Scaling autoregressive text-to-image generative models with continuous tokens","author":"Fan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02117"},{"key":"ref9","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00729"},{"key":"ref11","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","author":"Han","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref13","article-title":"Acdit: Interpolating autoregressive conditional modeling and diffusion transformer","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","volume-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref16","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":"ref17","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref20","article-title":"Inference-time scaling for diffusion models beyond scaling denoising steps","author":"Ma","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref21","first-page":"2773027744","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref24","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","article-title":"Tokenflow: Unified image tokenizer for multimodal understanding and generation","author":"Qu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Flowar: Scale-wise autoregressive image generation meets flow matching","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","article-title":"Taming scalable visual tokenizer for autoregressive image generation","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Llamafusion: Adapting pretrained language models for multimodal generation","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref31","article-title":"Hart: Efficient visual generation with hybrid autoregressive transformer","author":"Tang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref34","first-page":"84839","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","volume":"37","author":"Tian","year":"2025","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Metamorph: Multimodal understanding and generation via instruction tuning","author":"Tong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01209"},{"key":"ref39","article-title":"Maskbit: Embedding-free image generation via bit tokens","author":"Weber","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01210"},{"key":"ref41","article-title":"Vila-u: a unified foundation model integrating visual understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref44","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref45","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref46","article-title":"Randomized autoregressive visual generation","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref47","first-page":"128940128966","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":"ref48","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"E-car: Efficient continuous autoregressive image generation via multistage modeling","author":"Yuan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Fast training of diffusion models with masked transformers","author":"Zheng","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref51","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","article-title":"Scaling the codebook size of vqgan to 100,000 with a utilization rate of 99 %","author":"Zhu","year":"2024","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\/11444798.pdf?arnumber=11444798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:00Z","timestamp":1777611240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01615","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}