{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T09:43:33Z","timestamp":1780998213134,"version":"3.54.1"},"reference-count":58,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00365","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3830-3840","source":"Crossref","is-referenced-by-count":1,"title":["VisNumBench: Evaluating Number Sense of Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Tengjin","family":"Weng","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School,Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Ming","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Claude 3.5 sonnet model card addendum","year":"2024"},{"key":"ref4","article-title":"Januspro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025"},{"key":"ref5","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024"},{"key":"ref6","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.52202\/079017-0504","article-title":"Evaluating large vision-and-language models on children\u2019s mathematical olympiads","author":"Cherian","year":"2024"},{"key":"ref10","article-title":"CLEVR-Math: A dataset for compositional language, visual and mathematical reasoning","volume-title":"16th International Workshop on Neural-Symbolic Learning and Reasoning, NeSy 2022","author":"Lindstr\u00f6m","year":"2022"},{"key":"ref11","article-title":"Teach clip to develop a number sense for ordinal regression","author":"Du","year":"2024"},{"key":"ref12","article-title":"echarts","year":"2025"},{"key":"ref13","article-title":"Mathodyssey: Benchmarking mathematical problem-solving skills in large language models using odyssey math data","author":"Fang","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.05.002"},{"key":"ref15","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref17","article-title":"Google images","year":"2025"},{"key":"ref18","article-title":"Emobench-m: Benchmarking emotional intelligence for multimodal large language models","author":"Hu","year":"2025"},{"key":"ref19","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref20","article-title":"Visonlyqa: Large vision language models still struggle with visual perception of geometric information","author":"Kamoi","year":"2024"},{"key":"ref21","article-title":"Seed-bench-2: Benchmarking multimodal large language models","author":"Li","year":"2023"},{"key":"ref22","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1240"},{"key":"ref24","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2559"},{"key":"ref26","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref28","article-title":"MMBench: Is your multi-modal model an all-around player?","author":"Liu","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"ref30","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1882"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2023.emnlp-main.906","article-title":"UniChart: A universal visionlanguage pretrained model for chart comprehension and reasoning","author":"Masry","year":"2023"},{"key":"ref34","article-title":"Llama 3.2 vision instruct (11b)","year":"2024"},{"key":"ref35","article-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_36"},{"key":"ref37","article-title":"Our next-generation model: Gemini 1.5","author":"Pichai","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/FGR.2006.78"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v9i1.14612"},{"key":"ref40","article-title":"Mathllava: Bootstrapping mathematical reasoning for multimodal large language models","author":"Shi","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref42","article-title":"Qwen2.5-vl","year":"2025"},{"key":"ref43","article-title":"Desktop wallpapers hd, free desktop backgrounds","year":"2025"},{"key":"ref44","article-title":"Measuring multimodal mathematical reasoning with math-vision dataset","author":"Wang","year":"2024"},{"key":"ref45","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref46","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3361"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref49","article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024"},{"key":"ref50","article-title":"SciBench: Evaluating college-level scientific problem-solving abilities of large language models","author":"Wang","year":"2023"},{"key":"ref51","article-title":"Llava-o1: Let vision language models reason step-by-step","author":"Xu","year":"2024"},{"key":"ref52","article-title":"xgen-mm (blip-3): A family of open large multimodal models","author":"Xue","year":"2024"},{"key":"ref53","article-title":"Thinking in space: How multimodal large language models see, remember, and recall spaces","author":"Yang","year":"2024"},{"key":"ref54","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"ref56","article-title":"Mavis: Mathematical visual instruction tuning","author":"Zhang","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"ref58","article-title":"LLaVAR: Enhanced visual instruction tuning for text-rich image understanding","author":"Zhang","year":"2023"}],"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\/11444313.pdf?arnumber=11444313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:05:48Z","timestamp":1777611948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444313\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00365","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}