{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:44Z","timestamp":1777888664532,"version":"3.51.4"},"reference-count":46,"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\/iccv51701.2025.01423","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs"],"prefix":"10.1109","author":[{"given":"Teng","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongchuan","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"ref3","first-page":"1737","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","volume-title":"International Conference on Machine Learning","author":"Bar-Tal","year":"2023"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00677"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128167"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555447"},{"issue":"70","key":"ref9","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","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":"Advances in neural information processing systems"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3541625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-024-3814-0"},{"key":"ref16","article-title":"Streammultidiffusion: Real-time interactive generation with region-based semantic control","author":"Lee","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2203"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0957"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02570-9"},{"key":"ref20","article-title":"Controlvar: Exploring controllable visual autoregressive modeling","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_14"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"issue":"1\u20134","key":"ref26","first-page":"259","article-title":"Rudin, Stanley Osher, and Emad Fatemi","volume":"60","author":"Leonid","year":"1992","journal-title":"Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena"},{"key":"ref27","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref29","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref30","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref31","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref33","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"Gomez, \u0141ukasz Kaiser, and Illia Polosukhin","volume":"30","author":"Vaswani","year":"2017","journal-title":"Attention is all you need. Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612508"},{"key":"ref38","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref40","article-title":"Panodiffusion: 360-degree panorama outpainting via diffusion","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wu","year":"2024"},{"key":"ref41","article-title":"Autoregressive models in vision: A survey","author":"Xiong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref43","article-title":"Language model beats diffusion - tokenizer is key to visual generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yu","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref45","article-title":"Multi-scale diffusion: Enhancing spatial layout in high-resolution panoramic image generation","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240512"}],"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\/11444678.pdf?arnumber=11444678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:44Z","timestamp":1777611224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01423","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}