{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:31:07Z","timestamp":1791567067374,"version":"4.3.4"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Artificial Intelligence National Science and Technology Major Project","award":["2023ZD0121200"],"award-info":[{"award-number":["2023ZD0121200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62222212"],"award-info":[{"award-number":["62222212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["623B2094"],"award-info":[{"award-number":["623B2094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62121002"],"award-info":[{"award-number":["62121002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3653620","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:54:53Z","timestamp":1768856093000},"page":"5910-5927","source":"Crossref","is-referenced-by-count":1,"title":["Toward Accurate Image Generation via Dynamic Generative Image Transformer"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-8126","authenticated-orcid":false,"given":"Zhendong","family":"Mao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9449-4491","authenticated-orcid":false,"given":"Mengqi","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijing","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6102-3407","authenticated-orcid":false,"given":"Quan","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2839-8693","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3012096"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3306436"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3350004"},{"key":"ref4","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref6","first-page":"9256","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127558"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339964"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3321329"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref14","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref15","first-page":"11315","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Chang"},{"key":"ref16","first-page":"4055","article-title":"Muse: Text-to-image generation via masked generative transformers","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Chang"},{"key":"ref17","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref19","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den"},{"key":"ref20","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref21","first-page":"30127","article-title":"Draft-and-revise: Effective image generation with contextual RQ-transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref22","first-page":"23412","article-title":"MOVQ: Modulating quantized vectors for high-fidelity image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_11"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref28","article-title":"Finite scalar quantization: VQ-VAE made simple","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Mentzer","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"issue":"1","key":"ref30","first-page":"142","article-title":"Coding theorems for a discrete source with a fidelity criterion","volume":"4","author":"Shannon","year":"1959","journal-title":"IRE Nat. Conv. Rec"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02164"},{"key":"ref33","article-title":"Vector-quantized image modeling with improved vqgan","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Yu","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0401"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00669"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref43","first-page":"527","article-title":"Adaptive neural networks for efficient inference","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bolukbasi"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00850"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3265198"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00858"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00244"},{"key":"ref50","first-page":"5770","article-title":"Dynamic grained encoder for vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547881"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196959"},{"key":"ref53","first-page":"1920","article-title":"Categorical reparametrization with gumble-softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref58","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref60","first-page":"17480","article-title":"Projected GANs converge faster","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sauer"},{"key":"ref61","first-page":"7958","article-title":"Generating images with sparse representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nash"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00199"},{"key":"ref63","first-page":"3518","article-title":"Imagebart: Bidirectional context with multinomial diffusion for autoregressive image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Esser"},{"key":"ref64","first-page":"11201","article-title":"Soft truncation: A universal training technique of score-based diffusion model for high precision score estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref66","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530738"},{"key":"ref68","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref69","first-page":"2142","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Li"},{"key":"ref70","first-page":"73883","article-title":"Halton scheduler for masked generative image transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Victor"},{"key":"ref71","article-title":"Open-MAGVIT2: An open-source project toward democratizing auto-regressive visual generation","author":"Luo","year":"2024"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2858"},{"key":"ref73","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref76","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01738"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref80","first-page":"10542","article-title":"Large scale adversarial representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Donahue"},{"key":"ref81","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11358752.pdf?arnumber=11358752","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:19Z","timestamp":1775505379000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11358752\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":84,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3653620","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}