{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:40Z","timestamp":1777865380038,"version":"3.51.4"},"reference-count":61,"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":["62376245"],"award-info":[{"award-number":["62376245"]}],"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\/iccv51701.2025.00442","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4647-4658","source":"Crossref","is-referenced-by-count":1,"title":["2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"],"prefix":"10.1109","author":[{"given":"Wenqi","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"DAMO Academy,Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiashuo","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongliang","family":"Shen","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Lu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deli","family":"Zhao","sequence":"additional","affiliation":[{"name":"DAMO Academy,Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lidong","family":"Bing","sequence":"additional","affiliation":[{"name":"DAMO Academy,Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Phi-4 technical report","author":"Abdin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-loras","author":"Abouelenin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref6","article-title":"Openflamingo: An opensource framework for training large autoregressive visionlanguage models","author":"Awadalla","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1160"},{"key":"ref8","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","volume-title":"Coyo-700m: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00756"},{"key":"ref11","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref13","article-title":"Videollama 2: Advancing spatialtemporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Infinity-mm: Scaling multimodal performance with large-scale and high-quality instruction data","author":"Gu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Textbooks are all you need","author":"Gunasekar","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Video-mmmu: Evaluating knowledge acquisition from multi-discipline professional videos","author":"Hu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3155"},{"issue":"3","key":"ref18","first-page":"3","article-title":"Phi-2: The surprising power of small language models","volume":"1","author":"Javaheripi","year":"2023","journal-title":"Microsoft Research Blog"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia","year":"2021"},{"key":"ref20","article-title":"Mantis: Interleaved multi-image instruction tuning","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Building and better understanding visionlanguage models: insights and future directions","author":"Lauren\u00e7on","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"What matters when building vision-language models?","author":"Lauren\u00e7on","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","author":"Lauren\u00e7on","year":"2023","journal-title":"Obelics: An open webscale filtered dataset of interleaved image-text documents"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref25","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref26","article-title":"Omnicorpus: An unified multimodal corpus of 10 billion-level images interleaved with text","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Textbooks are all you need ii: phi-1.5 technical report","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Towards general text embeddings with multi-stage contrastive learning","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02520"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref33","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref37","article-title":"Mm1: Methods, analysis & insights from multimodal 11 m pre-training","author":"McKinzie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00272"},{"key":"ref39","first-page":"11054","article-title":"True fewshot learning with language models","volume":"34","author":"Perez","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref40","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":"ref41","article-title":"How2: a large-scale dataset for multimodal language understanding","author":"Sanabria","year":"2018","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"LAION400 M: open dataset of clip-filtered 400 million image-text pairs","volume":"abs\/2111.02114","author":"Schuhmann","year":"2021","journal-title":"CoRR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref46","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.09396"},{"key":"ref48","first-page":"1596315974","article-title":"Mobileclip: Fast image-text models through multi-modal reinforced training","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Kumar","year":"2024"},{"key":"ref49","article-title":"Pin: A knowledge-intensive dataset for paired and interleaved multimodal documents","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","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":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref52","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref54","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"mplug-owl3: Towards long image-sequence understanding in multi-modal large language models","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref59","article-title":"Embodied-reasoner: Synergizing visual search, reasoning, and action for embodied interactive tasks","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Multimodal c4: An open, billion-scale corpus of images interleaved with text","volume":"36","author":"Zhu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11443544.pdf?arnumber=11443544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:58Z","timestamp":1777530178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443544\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00442","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}