{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:13Z","timestamp":1777890193994,"version":"3.51.4"},"reference-count":63,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC3602601"],"award-info":[{"award-number":["2022YFC3602601"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.01766","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19000-19010","source":"Crossref","is-referenced-by-count":0,"title":["Neighboring Autoregressive Modeling for Efficient Visual Generation"],"prefix":"10.1109","author":[{"given":"Yefei","family":"He","sequence":"first","affiliation":[{"name":"Zhejiang University,China"}]},{"given":"Yuanyu","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}]},{"given":"Shaoxuan","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Adelaide,Australia"}]},{"given":"Hong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}]},{"given":"Kaipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}]},{"given":"Bohan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Laion-coco: 600 m synthetic captions from laion-2b-en"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00338"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.17487\/rfc2083"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767851"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","author":"Chen","journal-title":"Pixelsnail: An improved autoregressive generative model"},{"key":"ref7","article-title":"Januspro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"issue":"70","key":"ref8","first-page":"1","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.901238"},{"key":"ref10","article-title":"Autoregressive video generation without vector quantization","author":"Deng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref12","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref16","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Han","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref19","article-title":"Zipar: Accelerating autoregressive image generation through spatial locality","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012","journal-title":"NeurIPS"},{"issue":"7","key":"ref22","doi-asserted-by":"crossref","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"Kuznetsova","year":"2020","journal-title":"International journal of computer vision"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref24","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Controlvar: Exploring controllable visual autoregressive modeling","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00090"},{"key":"ref27","article-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref30","article-title":"Merge, ensemble, and cooperate a survey on collaborative strategies in the era of large language models","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Videofusion: Decomposed diffusion models for high-quality video generation","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref34","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref35","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"issue":"8","key":"ref36","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref37","article-title":"You only look once: unified, real-time object detection (2015)","author":"Redmon","year":"2015","journal-title":"arXiv preprint arXiv:1506.02640, 825"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","article-title":"Painting outside the box: Image outpainting with gans","author":"Sabini","year":"2018","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint arXiv:2209.14792"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00723"},{"key":"ref43","first-page":"271","author":"Sobel","year":"1973","journal-title":"A3 \u00d7 3 Isotropic Gradient Operator for Image Processing"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref45","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Accelerating autoregressive text-to-image generation with training-free speculative jacobi decoding","author":"Teng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","journal-title":"2024. 2, 4, 5"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1998.710815"},{"key":"ref50","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Conditional image generation with pixelcnn decoders","author":"Van den Oord","year":"2016","journal-title":"Advances in neural information processing systems, 29"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"ref55","article-title":"Larp: Tokenizing videos with a learned autoregressive generative prior","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Omnitokenizer: A joint image-video tokenizer for visual generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2409.12191"},{"key":"ref58","article-title":"Emu 3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01209"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref62","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20252"}],"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\/11445208.pdf?arnumber=11445208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:47Z","timestamp":1777613507000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01766","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}