{"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":1790995859577,"version":"4.1.0"},"reference-count":55,"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\/iccv51701.2025.01728","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18596-18605","source":"Crossref","is-referenced-by-count":6,"title":["Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation"],"prefix":"10.1109","author":[{"given":"Yuqing","family":"Wang","sequence":"first","affiliation":[{"name":"University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijie","family":"Lin","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Teng","sequence":"additional","affiliation":[{"name":"University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanzhi","family":"Zhu","sequence":"additional","affiliation":[{"name":"École Polytechnique"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhuai","family":"Ren","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref2","article-title":"Language models are fewshot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref4","author":"Chen","year":"2024","journal-title":"Deep compression autoencoder for efficient high-resolution diffusion models"},{"key":"ref5","author":"Chen","year":"2024","journal-title":"Next token prediction towards multimodal intelligence: A comprehensive survey"},{"key":"ref6","first-page":"1691","article-title":"Generative pretraining from pixels","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01467"},{"key":"ref11","author":"Henighan","year":"2020","journal-title":"Scaling laws for autoregressive generative modeling"},{"key":"ref12","first-page":"30","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":"ref13","article-title":"Classifier-free diffusion guidance","volume-title":"NIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref15","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref16","author":"Kondratyuk","year":"2023","journal-title":"Videopoet: A large language model for zero-shot video generation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref18","author":"Li","year":"2024","journal-title":"Autoregressive image generation without vector quantization"},{"key":"ref19","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2018","journal-title":"ICLR"},{"key":"ref20","author":"Luo","year":"2024","journal-title":"Open-magvit2: An open-source project toward democratizing auto-regressive visual generation"},{"key":"ref21","author":"Mentzer","year":"2023","journal-title":"Finite scalar quantization: Vq-vae made simple"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-81897-4_4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref25","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2023"},{"key":"ref26","author":"Radford","year":"2019","journal-title":"Language models are unsupervised multitask learners"},{"key":"ref27","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref28","first-page":"32","article-title":"Generating diverse high-fidelity images with vq-vae-2","author":"Razavi","year":"2019","journal-title":"NeurIPS"},{"key":"ref29","author":"Ren","year":"2024","journal-title":"Flowar: Scale-wise autoregressive image generation meets flow matching"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref33","first-page":"29","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref34","author":"Salimans","year":"2017","journal-title":"Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications"},{"key":"ref35","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"ICLR"},{"key":"ref36","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation"},{"key":"ref37","author":"Team","year":"2024","journal-title":"Chameleon: Mixed-modal early-fusion foundation models"},{"key":"ref38","author":"Tian","year":"2024","journal-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_17"},{"key":"ref40","article-title":"Pixel recurrent neural networks","author":"Van Den Oord","year":"2016","journal-title":"ICML"},{"key":"ref41","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref42","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","author":"Villegas","year":"2022","journal-title":"ICLR"},{"key":"ref43","author":"Wang","year":"2024","journal-title":"Emu3: Next-token prediction is all you need"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01209"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/isit.2019.8849302"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref48","author":"Yu","year":"2021","journal-title":"Vector-quantized image modeling with improved vqgan"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref50","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2024","journal-title":"ICLR"},{"key":"ref51","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3658150"},{"key":"ref53","author":"Zhao","year":"2024","journal-title":"Image and video tokenization with binary spherical quantization"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"},{"key":"ref55","author":"Zhu","year":"2024","journal-title":"Scaling the codebook size of vqgan to 100,000 with a utilization rate of 99%"}],"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\/11445635.pdf?arnumber=11445635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:56:47Z","timestamp":1777611407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01728","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}