{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:22Z","timestamp":1777865302178,"version":"3.51.4"},"reference-count":73,"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":["62125603,62321005,62336004,62441616"],"award-info":[{"award-number":["62125603,62321005,62336004,62441616"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L247009"],"award-info":[{"award-number":["L247009"]}],"id":[{"id":"10.13039\/501100004826","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\/iccv51701.2025.01470","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15842-15852","source":"Crossref","is-referenced-by-count":0,"title":["SpectralAR: Spectral Autoregressive Visual Generation"],"prefix":"10.1109","author":[{"given":"Yuanhui","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiliang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzhao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueqi","family":"Duan","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1974.223784"},{"key":"ref2","article-title":"The analytical theory of heat","author":"Baptiste","year":"2003","journal-title":"Courier Corporation"},{"key":"ref3","volume-title":"Large scale gan training for high fidelity natural image synthesis","author":"Brock","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref5","first-page":"1691","article-title":"Generative pretraining from pixels","author":"Chen","year":"2020","journal-title":"pages"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/070710111"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NIPS","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref9","article-title":"An image is worth 16 times 16 words: Transformers for image recognition at scale.","volume":"6","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref11","article-title":"Spectral image tokenizer","author":"Esteves","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"3247","article-title":"Leveraging frequency analysis for deep fake image recognition","author":"Frank","year":"2020","journal-title":"ICML"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00445"},{"key":"ref14","first-page":"2","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/83.846246"},{"key":"ref16","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Han","year":"2024"},{"key":"ref17","first-page":"6","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":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NIPS"},{"issue":"47","key":"ref20","first-page":"133","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"JMLR"},{"key":"ref21","first-page":"2","article-title":"Owl1: Omni world model for consistent long video generation","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref24","author":"Diederik","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref25","author":"Kondratyuk","year":"2023","journal-title":"Videopoet: A large language model for zero-shot video generation"},{"key":"ref26","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref30","article-title":"Selfconditioned image generation via generating representations","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref31","first-page":"56424","article-title":"Autoregressive image generation without vector quantization","volume":"37","author":"Li","year":"2025","journal-title":"NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01488"},{"key":"ref34","article-title":"Open-magvit2: An open-source project toward democratizing auto-regressive visual generation","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref36","author":"Ma","year":"2024","journal-title":"Star: Scale-wise text-toimage generation via auto-regressive representations"},{"key":"ref37","author":"Mentzer","year":"2023","journal-title":"Finite scalar quantization: Vq-vae made simple"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.97.2.307"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref40","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref41","volume":"34","author":"Rao","year":"2021","journal-title":"Global filter networks for image classification. Advances in neural information processing systems"},{"key":"ref42","article-title":"Generating diverse high-fidelity images with vq-vae-2","author":"Razavi","year":"2019","journal-title":"NIPS"},{"key":"ref43","author":"Roheda","year":"2024","journal-title":"Cart: Compositional auto-regressive transformer for image generation"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","first-page":"1","article-title":"Styleganxl: Scaling stylegan to large diverse datasets.","volume-title":"In ACM SIGGRAPH 2022 conference proceedings","author":"Sauer"},{"key":"ref46","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models. arXiv preprint"},{"key":"ref47","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation. arXiv preprint"},{"key":"ref48","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation. arXiv preprint"},{"key":"ref49","year":"2024","journal-title":"Chameleon Team. Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint"},{"key":"ref50","first-page":"84839","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","volume":"37","author":"Tian","year":"2025","journal-title":"NIPS"},{"key":"ref51","first-page":"29","article-title":"Conditional image generation with pixelcnn decoders","author":"Van den Oord","year":"2016","journal-title":"NIPS"},{"key":"ref52","first-page":"30","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"NIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"ref56","author":"Wang","year":"2024","journal-title":"Emu3: Next-token prediction is all you need. arXiv preprint"},{"key":"ref57","author":"Wang","year":"2024","journal-title":"Loong: Generating minute-level long videos with autoregressive language models. arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01210"},{"key":"ref60","author":"Xie","year":"2024","journal-title":"Show-o: One single transformer to unify multimodal understanding and generation. arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_1"},{"key":"ref62","author":"Yu","year":"2021","journal-title":"Vector-quantized image modeling with improved vqgan. arXiv preprint"},{"key":"ref63","author":"Yu","year":"2021","journal-title":"Vector-quantized image modeling with improved vqgan. arXiv preprint"},{"issue":"3","key":"ref64","volume":"2","author":"Yu","year":"2022","journal-title":"Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint"},{"key":"ref65","author":"Yu","year":"2024","journal-title":"Randomized autoregressive visual generation. arXiv preprint"},{"key":"ref66","first-page":"128940","article-title":"An image is worth 32 tokens for reconstruction and generation","volume":"37","author":"Yu","year":"2025","journal-title":"NIPS"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01385"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.375"},{"key":"ref69","article-title":"Var-clip: Text-to-image generator with visual auto-regressive modeling","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref71","author":"Zhang","year":"2023","journal-title":"Llama-adapter: Efficient finetuning of language models with zero-init attention. arXiv preprint"},{"key":"ref72","first-page":"23412","article-title":"Movq: Modulating quantized vectors for highfidelity image generation","volume":"35","author":"Zheng","year":"2022","journal-title":"NIPS"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_4"}],"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\/11445098.pdf?arnumber=11445098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:13:44Z","timestamp":1777529624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01470","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}