{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:35:34Z","timestamp":1780500934257,"version":"3.54.1"},"reference-count":83,"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 R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160102"],"award-info":[{"award-number":["2022ZD0160102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206272"],"award-info":[{"award-number":["62206272"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01863","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20031-20042","source":"Crossref","is-referenced-by-count":3,"title":["Lumina-Image 2.0: a Unified and Efficient Image Generative Framework"],"prefix":"10.1109","author":[{"given":"Qi","family":"Qin","sequence":"first","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Xin","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoyi","family":"Du","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Fu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiting","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyue","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Will","family":"Beddow","sequence":"additional","affiliation":[{"name":"Krea AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erwann","family":"Millon","sequence":"additional","affiliation":[{"name":"Krea AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor","family":"Perez","sequence":"additional","affiliation":[{"name":"Krea AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Xu","sequence":"additional","affiliation":[{"name":"The University of Sydney"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization","author":"Bai","year":"2023","journal-title":"Text Reading, and Beyond"},{"key":"ref3","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Imagen 3","author":"Baldridge","year":"2024","journal-title":"arXiv preprint"},{"issue":"3","key":"ref5","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref6","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Chen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref9","author":"Chen","year":"2025","journal-title":"Janus-pro: Unified multimodal understanding and generation with data and model scaling"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref11","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Dehghani"},{"key":"ref12","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"The rating of chessplayers: Past and present","author":"Elo","year":"1978","journal-title":"Arco Pub"},{"key":"ref14","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Esser"},{"key":"ref15","article-title":"Lumina-t2x: Transforming text into any modality, resolution, and duration via flow-based large diffusion transformers","author":"Gao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref18","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Han","year":"2024"},{"key":"ref19","article-title":"Classifier-free diffusion guidance","volume-title":"Advances in Neural Information Processing Systems Workshops (NeurIPS Workshops)","author":"Ho","year":"2021"},{"key":"ref20","article-title":"Ella: Equip diffusion models with llm for enhanced semantic alignment","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00982"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"ref23","article-title":"Openai o1 system card","author":"Jaech","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref26","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","volume-title":"Flux","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00825"},{"key":"ref29","article-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Pixwizard: Versatile image-to-image visual assistant with open-language instructions","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Stiv: Scalable text and image conditioned video generation","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Sphinx-x: Scaling data and parameters for a family of multi-modal large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Lumina-video: Efficient and flexible video generation with multi-scale next-dit","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00689"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref38","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref42","article-title":"Exploring the role of large language models in prompt encoding for diffusion models","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Step-video-t2v technical report: The practice, challenges, and future of video foundation model","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Inference-time scaling for diffusion models beyond scaling denoising steps","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00725"},{"key":"ref46","year":"2022","journal-title":"Chatgpt: Optimizing language models for dialogue"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref48","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref49","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref50","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref53","article-title":"Scaling $l l m$ test-time compute optimally can be more effective than scaling model parameters","author":"Snell","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref55","article-title":"Augmenting self-attention with persistent memory","author":"Sukhbaatar","year":"2019","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Hart: Efficient visual generation with hybrid autoregressive transformer","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Chameleon: Mixed-modal early-fusion foundation models","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Gemma 2: Improving open language models at a practical size","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","volume-title":"Kuaishou Technology. Kolors","year":"2024"},{"key":"ref63","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01241"},{"key":"ref70","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Xie"},{"key":"ref71","article-title":"Sana 1.5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer","author":"Xie","year":"2025","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Lumina-mgpt 2.0: Stand-alone autoregressive image modeling","author":"Xin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Resurrect mask autoregressive modeling for efficient and scalable image generation","author":"Xin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1757"},{"key":"ref77","article-title":"Root mean square layer normalization","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref78","article-title":"Towards building specialized generalist ai with system 1 and system 2 fusion","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref80","article-title":"Internlm-xcomposer: A visionlanguage large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref81","article-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling","author":"Zhang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4172"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01422"}],"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\/11444580.pdf?arnumber=11444580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:00:09Z","timestamp":1777611609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01863","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}