{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T02:05:01Z","timestamp":1773194701600,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/pcs65673.2025.11417611","type":"proceedings-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:56:18Z","timestamp":1773086178000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Autoregressive Vision Foundation Models for Image Compression"],"prefix":"10.1109","author":[{"given":"Huu-Tai","family":"Phung","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Yu-Hsiang","family":"Lin","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Yen-Kuan","family":"Ho","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]},{"given":"Wen-Hsiao","family":"Peng","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Variational image compression with a scale hyperprior","volume-title":"International Conference on Learning Representations","author":"Ball\u00e9"},{"key":"ref2","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint arXiv:2501.03575"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3515874"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849863"},{"key":"ref5","article-title":"Revisiting feature prediction for learning visual representations from video","author":"Bardes","year":"2024","journal-title":"arXiv:2404.08471"},{"key":"ref6","article-title":"Gigatok: Scaling visual tokenizers to 3 billion parameters for autoregressive image generation","author":"Xiong","year":"2025","journal-title":"arXiv preprint arXiv:2504.08736"},{"key":"ref7","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv:2406.06525"},{"key":"ref8","article-title":"Neural discrete representation learning","volume":"30","author":"van den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01268"},{"key":"ref10","article-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2408.02657"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref14","first-page":"25426","article-title":"Improving statistical fidelity for neural image compression with implicit local likelihood models","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"202","author":"Muckley"},{"key":"ref15","article-title":"High-fidelity generative image compression","author":"Mentzer","year":"2020","journal-title":"arXiv preprint arXiv:2006.09965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2835"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28733"},{"key":"ref18","article-title":"Kodak lossless true color image suite (photocd pcd0992)","author":"Kodak","year":"1993"},{"key":"ref19","article-title":"Workshop and challenge on learned image compression (clic)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref23","article-title":"VTM-17.0","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2023.3245919"},{"key":"ref25","article-title":"Perco (SD): Open perceptual compression","volume-title":"Workshop on Machine Learning and Compression","author":"Karber"}],"event":{"name":"2025 Picture Coding Symposium (PCS)","location":"Aachen, Germany","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 Picture Coding Symposium (PCS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11417472\/11417493\/11417611.pdf?arnumber=11417611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:28:20Z","timestamp":1773120500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/pcs65673.2025.11417611","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}