{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:02:12Z","timestamp":1782576132231,"version":"3.54.5"},"reference-count":40,"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":["62132017,62302435,62402434"],"award-info":[{"award-number":["62132017,62302435,62402434"]}],"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\/iccv51701.2025.00229","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2376-2385","source":"Crossref","is-referenced-by-count":7,"title":["R1-Onevision: Advancing Generalized Multimodal Reasoning Through Cross-Modal Formalization"],"prefix":"10.1109","author":[{"given":"Yi","family":"Yang","sequence":"first","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxuan","family":"He","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongkun","family":"Pan","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiyan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Deng","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingtao","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Lu","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Yin","sequence":"additional","affiliation":[{"name":"Tencent Inc.,WeChat Vision"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengyun","family":"Rao","sequence":"additional","affiliation":[{"name":"Tencent Inc.,WeChat Vision"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minfeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-srw.17"},{"key":"ref2","author":"Bai","year":"2025","journal-title":"Qwen2. 5-vl technical report"},{"key":"ref3","author":"Chen","year":"2021","journal-title":"Evaluating large language models trained on code"},{"key":"ref4","author":"Chen","year":"2024","journal-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling"},{"key":"ref5","author":"Cobbe","year":"2021","journal-title":"Training verifiers to solve math word problems"},{"key":"ref6","year":"2023","journal-title":"Opencompass: A universal evaluation platform for foundation models"},{"key":"ref7","article-title":"Cruxeval: A benchmark for code reasoning, understanding and execution","volume-title":"International Conference on Machine Learning","author":"Gu","year":"2024"},{"key":"ref8","author":"Guo","year":"2025","journal-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.680"},{"key":"ref10","article-title":"Measuring mathematical problem solving with the MATH dataset","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","author":"Hendrycks","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref13","article-title":"Lawrence Zitnick, and Ross Girshick","author":"Johnson","year":"2016","journal-title":"Clevr: A diagnostic dataset for compositional language and elementary visual reasoning"},{"key":"ref14","volume-title":"Figureqa: An annotated figure dataset for visual reasoning","author":"Ebrahimi Kahou","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref16","article-title":"LLaVA-onevision: Easy visual task transfer","author":"Li","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref17","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lu","year":"2024"},{"issue":"2024","key":"ref18","article-title":"Llama 3.2: Revolutionizing edge ai and vision with open, customizable models","volume":"20","author":"Meta","year":"2024","journal-title":"Meta AI Blog. Retrieved December"},{"key":"ref19","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.70777\/si.v2i1.13973"},{"key":"ref21","author":"Plaat","year":"2024","journal-title":"Reasoning with large language models, a survey"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.983"},{"key":"ref23","author":"Roberts","year":"2025","journal-title":"Zerobench: An impossible visual benchmark for contemporary large multimodal models"},{"key":"ref24","author":"Thawakar","year":"2025","journal-title":"Llamavo1: Rethinking step-by-step visual reasoning in 11 ms"},{"key":"ref25","first-page":"95095","article-title":"Measuring multimodal mathematical reasoning with math-vision dataset","volume":"37","author":"Wang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.167"},{"key":"ref30","author":"Wu","year":"2024","journal-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding"},{"key":"ref31","author":"Xu","year":"2024","journal-title":"Llava-o1: Let vision language models reason step-by-step"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00202"},{"key":"ref33","author":"Yao","year":"2024","journal-title":"Mulberry: Empowering mllm with o1-like reasoning and reflection via collective monte carlo tree search"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref35","author":"Yao","year":"2024","journal-title":"Minicpm-v: A gpt-4v level mllm on your phone"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00546"},{"key":"ref37","author":"Zhang","year":"2024","journal-title":"Humaneval-v: Evaluating visual understanding and reasoning abilities of large multimodal models through coding tasks"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"ref39","author":"Zhang","year":"2023","journal-title":"Cumulative reasoning with large language models"},{"key":"ref40","author":"Zou","year":"2024","journal-title":"Dynamath: A dynamic visual benchmark for evaluating mathematical reasoning robustness of vision language models"}],"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\/11444300.pdf?arnumber=11444300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:48:49Z","timestamp":1777610929000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00229","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}