{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:09Z","timestamp":1777865409689,"version":"3.51.4"},"reference-count":71,"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":["62322604,62176159"],"award-info":[{"award-number":["62322604,62176159"]}],"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\/iccv51701.2025.02155","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23210-23220","source":"Crossref","is-referenced-by-count":0,"title":["A Token-Level Text Image Foundation Model for Document Understanding"],"prefix":"10.1109","author":[{"given":"Tongkun","family":"Guan","sequence":"first","affiliation":[{"name":"AI Institute, School of Computer Science, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zining","family":"Wang","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Fu","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengtao","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Shen","sequence":"additional","affiliation":[{"name":"AI Institute, School of Computer Science, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Zhou","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiezhu","family":"Yue","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Duan","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianyi","family":"Jiang","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junfeng","family":"Luo","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"AI Institute, School of Computer Science, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Pixtral 12b","author":"Agrawal","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref5","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref6","volume-title":"Internvl2: Better than the best-expanding performance boundaries of open-source multimodal models with the progressive scaling strategy","author":"Chen","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref9","article-title":"Locality alignment improves vision-language models","author":"Covert","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref11","article-title":"On pre-training of multimodal language models customized for chart understanding","author":"Fan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref12","article-title":"Mousi: Poly-visual-expert vision-language models","author":"Fan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4250-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3156390"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01467"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01784"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01784"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3533737"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1090\/psapm\/040\/1059485"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.291"},{"key":"ref29","article-title":"Mini-monkey: Alleviate the sawtooth effect by multi-scale adaptive cropping","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.735"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72967-6_16"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148307"},{"key":"ref34","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref36","article-title":"Doclayllm: An efficient and effective multi-modal extension of large language models for text-rich document understanding","author":"Liao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01471"},{"key":"ref39","volume-title":"Llavanext: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653415"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.379"},{"key":"ref43","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Kosmos-2.5: A multimodal literate model","author":"Lv","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref45","article-title":"KOSMOS-2.5: a multimodal literate model","author":"Lv","year":"2024","journal-title":"arXiv"},{"key":"ref46","article-title":"Alignvlm: Bridging vision and language latent spaces for multimodal understanding","author":"Masry","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Mm1: methods, analysis & insights from multimodal 11 m pre-training","author":"McKinzie","year":"2024","journal-title":"arxiv"},{"key":"ref48","article-title":"Hierarchical visual feature aggregation for OCR-Free document understanding","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Park"},{"key":"ref49","first-page":"8748","volume-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"ref50","volume-title":"Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models","author":"Shao","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3246102"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29874"},{"key":"ref53","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal llms","author":"Tong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01348"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_23"},{"key":"ref57","article-title":"Docgenome: An open largescale scientific document benchmark for training and testing multi-modal large language models","author":"Xia","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"Wukong: A large multimodal model for efficient long pdf reading with end-to-end sparse sampling","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref59","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3495831"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"ref64","article-title":"Texthawk: Exploring efficient finegrained perception of multimodal large language models","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref65","article-title":"Texthawk2: A large vision-language model excels in bilingual ocr and grounding with 16x fewer tokens","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref67","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref68","article-title":"Mm1. 5: Methods, analysis & insights from multimodal 11 m fine-tuning","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33076"},{"key":"ref70","article-title":"Token-level correlation-guided compression for efficient multimodal document understanding","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref72","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv"}],"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\/11445850.pdf?arnumber=11445850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:28:23Z","timestamp":1777530503000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02155","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}