{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:02Z","timestamp":1777865342481,"version":"3.51.4"},"reference-count":63,"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":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192782,62302501,62403462"],"award-info":[{"award-number":["62192782,62302501,62403462"]}],"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\/iccv51701.2025.00116","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1162-1172","source":"Crossref","is-referenced-by-count":0,"title":["VisionMath: Vision-Form Mathematical Problem-Solving"],"prefix":"10.1109","author":[{"given":"Zongyang","family":"Ma","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Chen","sequence":"additional","affiliation":[{"name":"ARC Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongang","family":"Oi","sequence":"additional","affiliation":[{"name":"vivo Mobile Communication Co.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunfeng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaojie","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tencent PCG,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengxiang","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Tencent PCG,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Liu","sequence":"additional","affiliation":[{"name":"ARC Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zang","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent PCG,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"ARC Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,China"}],"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":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","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":"ref4","article-title":"Numinamath 7b cot","author":"Beeching","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-14-170"},{"key":"ref6","article-title":"Tabfact: A large-scale dataset for table-based fact verification","author":"Chen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref9","first-page":"24185","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2024"},{"key":"ref10","article-title":"R-cot: Reverse chain-of-thought problem generation for geometric reasoning in large multimodal models","author":"Deng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3542700.3542709"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref13","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","author":"Gao","year":"2023","journal-title":"G-llava: Solving geometric problem with multi-modal large language model"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref17","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref19","article-title":"Figureqa: An annotated figure dataset for visual reasoning","author":"Kahou","year":"2017","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.526"},{"key":"ref22","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref24","article-title":"Large languagegeometry model: When 11 m meets equivariance","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Star-r1: Spatial transformation reasoning by reinforcing multimodal 11 ms","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Mmc: Advancing multimodal chart understanding with large-scale instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","author":"Liu","year":"2023","journal-title":"Improved baselines with visual instruction tuning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref29","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref31","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lu","year":"2024"},{"key":"ref33","article-title":"Ursa: Understanding and verifying chain-of-thought reasoning in multimodal mathematics","author":"Luo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"ref41","article-title":"Multimath: Bridging visual and mathematical reasoning for large language models","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.268"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_36"},{"key":"ref44","author":"Sun","year":"2023","journal-title":"Generative multimodal models are in-context learners."},{"key":"ref45","author":"Sun","year":"2023","journal-title":"Generative pretraining in multimodality."},{"key":"ref46","year":"2020","journal-title":"Deepform: Understand structured documents at scale."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17635"},{"key":"ref48","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","author":"Team","year":"2025","journal-title":"Qwen2.5-vl"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41682-8_22"},{"key":"ref52","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":"ref53","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Vary: Scaling up the vision vocabulary for large vision-language models","author":"Wei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Qwen2.5math technical report: Toward mathematical expert model via self-improvement","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Mathglm-vision: Solving mathematical problems with multi-modal large language model","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"ref60","author":"Zhang","year":"2024","journal-title":"Mavis: Mathematical visual instruction tuning"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00442"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34815"}],"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\/11444743.pdf?arnumber=11444743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:07Z","timestamp":1777529827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00116","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}