{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T05:38:54Z","timestamp":1782365934039,"version":"3.54.5"},"reference-count":111,"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\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS2443404"],"award-info":[{"award-number":["IIS2443404"]}],"id":[{"id":"10.13039\/100000001","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\/iccv51701.2025.00042","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-13","source":"Crossref","is-referenced-by-count":2,"title":["Scaling Language-Free Visual Representation Learning"],"prefix":"10.1109","author":[{"given":"David","family":"Fan","sequence":"first","affiliation":[{"name":"New York University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengbang","family":"Tong","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiachen","family":"Zhu","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koustuv","family":"Sinha","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuang","family":"Liu","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinlei","family":"Chen","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Rabbat","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Ballas","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yann","family":"LeCun","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Bar","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saining","family":"Xie","sequence":"additional","affiliation":[{"name":"FAIR, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pixtral 12b","author":"Agrawal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"AI@Meta","year":"2024","journal-title":"Llama 3 model card"},{"key":"ref3","article-title":"Smollm2: When smol goes big-data-centric training of a small language model","author":"Ben Allal","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"ref6","article-title":"A cookbook of self-supervised learning","author":"Balestriero","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Stochastic positional embeddings improve masked image modeling","author":"Bar","year":"2024","journal-title":"ICML"},{"key":"ref8","article-title":"ARKitscenes - a diverse real-world dataset for 3d indoor scene understanding using mobile RGB-d data","author":"Baruch","year":"2021","journal-title":"NeurIPS"},{"key":"ref9","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref11","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref13","article-title":"Scaling 4d representations","author":"Carreira","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref16","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref18","article-title":"Pali: A jointly-scaled multilingual language-image model","author":"Chen","year":"2023","journal-title":"ICLR"},{"key":"ref19","article-title":"Bag of image patch embedding behind the success of self-supervised learning","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2024","journal-title":"CVPR"},{"issue":"10","key":"ref22","first-page":"1","author":"Chowdhery","year":"2022","journal-title":"Palm: Scaling language modeling with pathways"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref26","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00517"},{"key":"ref29","article-title":"Data determines distributional robustness in contrastive language image pre-training (clip)","author":"Fang","year":"2022","journal-title":"ICML"},{"key":"ref30","article-title":"Data filtering networks","author":"Fang","year":"2024","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00901"},{"key":"ref32","article-title":"Mme: a comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"corr abs\/2306.13394"},{"key":"ref33","article-title":"Datacomp: In search of the next generation of multimodal datasets","author":"Yitzhak Gadre","year":"2024","journal-title":"NeurIPS"},{"key":"ref34","article-title":"On the duality between contrastive and non-contrastive self-supervised learning","author":"Garrido","year":"2023","journal-title":"ICLR"},{"key":"ref35","article-title":"Planting a seed of vision in large language model","author":"Ge","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref37","article-title":"Unsupervised representation learning by predicting image rotations","author":"Gidaris","year":"2018","journal-title":"ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref40","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref45","article-title":"Natural adversarial examples. 2021 ieee","author":"Hendrycks","year":"2019","journal-title":"CVPR"},{"key":"ref46","article-title":"The many faces of robustness: A critical analysis of out-of-distribution generalization. 2021 ieee","author":"Hendrycks","year":"2020","journal-title":"ICCV"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-020-09517-1"},{"key":"ref48","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2023","journal-title":"NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref50","article-title":"The platonic representation hypothesis","volume-title":"ICML","author":"Huh","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02319"},{"key":"ref52","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref53","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref54","author":"LeCun","year":"1998","journal-title":"The mnist database of handwritten digits"},{"issue":"1","key":"ref55","first-page":"1","article-title":"A path towards autonomous machine intelligence version 0.9. 2","volume":"62","author":"LeCun","year":"2022","journal-title":"Open Review"},{"key":"ref56","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref59","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref61","article-title":"Mmbench: Is your multimodal model an all-around player?","author":"Liu","year":"2024","journal-title":"ECCV"},{"key":"ref62","article-title":"A decade\u2019s battle on dataset bias: Are we there yet?","author":"Liu","year":"2025","journal-title":"ICLR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref64","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","author":"Lu","year":"2022","journal-title":"NeurIPS"},{"key":"ref65","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visualcontexts","author":"Lu","year":"2023","journal-title":"ICLR"},{"key":"ref66","article-title":"Tips: Text-image pretraining with spatial awareness","author":"Maninis","year":"2025","journal-title":"ICLR"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_3"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref72","article-title":"OpenAI","year":"2022","journal-title":"Chatgpt"},{"key":"ref73","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"TMLR"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref75","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref76","article-title":"Imagenet-21k pretraining for the masses","author":"Ridnik","year":"2021","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref78","article-title":"Eagle: Exploring the design space for multimodal 11 ms with mixture of encoders","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00505"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"key":"ref85","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref86","article-title":"Eva-clip18b: Scaling clip to 18 billion parameters","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref87","article-title":"The bitter lesson","author":"Sutton","year":"2019","journal-title":"Incomplete Ideas (blog)"},{"key":"ref88","author":"Tang","year":"2025","journal-title":"Tulip: Towards unified language-image pretraining"},{"key":"ref89","article-title":"What does a visual formal analysis of the world\u2019s 500 most famous paintings tell us about multimodal LLMs?","author":"Tao","year":"2024","journal-title":"The Second Tiny Papers Track at ICLR 2024"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref91","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal llms","author":"Tong","year":"2024","journal-title":"NeurIPS"},{"key":"ref92","article-title":"Metamorph: Multimodal understanding and generation via instruction tuning","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref94","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref95","article-title":"Image captioners are scalable vision learners too","author":"Tschannen","year":"2024","journal-title":"NeurIPS"},{"key":"ref96","article-title":"Locca: Visual pretraining with location-aware captioners","author":"Wan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref98","article-title":"Scaling pre-training to one hundred billion data for vision language models","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref101","year":"2024","journal-title":"xAI. grok"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.05431"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1075"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.5040\/9798881817916.ch-004"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.736"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref112","article-title":"ibot: Image bert pre-training with online tokenizer","author":"Zhou","year":"2021","journal-title":"arXiv preprint"}],"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\/11444555.pdf?arnumber=11444555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:03Z","timestamp":1777613403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":111,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00042","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}