{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:25Z","timestamp":1777865305299,"version":"3.51.4"},"reference-count":38,"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\/iccv51701.2025.00053","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers"],"prefix":"10.1109","author":[{"given":"Yang","family":"Tian","sequence":"first","affiliation":[{"name":"School of AI, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Lu","sequence":"additional","affiliation":[{"name":"School of AI, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingqi","family":"Gao","sequence":"additional","affiliation":[{"name":"School of AI, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"BAAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of AI, Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"The claude 3 model family: Opus, sonnet, haiku"},{"key":"ref2","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume-title":"arXiv preprint","author":"Abdin","year":"2024"},{"key":"ref3","article-title":"Qwen2. 5-vl technical report","volume-title":"arXiv preprint","author":"Bai","year":"2025"},{"key":"ref4","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","volume-title":"arXiv preprint","author":"Chen","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref6","article-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","volume-title":"arXiv preprint","author":"Deitke","year":"2024"},{"key":"ref7","volume-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools","author":"Team","year":"2024"},{"key":"ref8","article-title":"Efficient multimodal learning from data-centric perspective","volume-title":"arXiv preprint","author":"He","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.70675\/802872a7z8092z4556za1fdz2c7af45f0e72"},{"key":"ref10","article-title":"mplug-docow12: High-resolution compressing for ocrfree multi-page document understanding","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Minicpm: Unveiling the potential of small language models with scalable training strategies","volume-title":"arXiv preprint","author":"Hu","year":"2024"},{"key":"ref12","article-title":"Gpt-4o system card","volume-title":"arXiv preprint","author":"Hurst","year":"2024"},{"key":"ref13","article-title":"Financebench: A new benchmark for financial question answering","volume-title":"arXiv preprint","author":"Islam","year":"2023"},{"key":"ref14","article-title":"Building and better understanding visionlanguage models: insights and future directions.","volume-title":"Workshop on Responsibly Building the Next Generation of Multimodal Foundational Models","author":"Lauren\u00e7on","year":"2024"},{"key":"ref15","article-title":"Llava-onevision: Easy visual task transfer","volume-title":"arXiv preprint","author":"Li","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref18","article-title":"Mmsci: A dataset for graduate-level multi-discipline multimodal scientific understanding","volume-title":"arXiv preprint","author":"Li","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653415"},{"key":"ref21","article-title":"Mmlongbench-doc: Benchmarking long-context document understanding with visualizations","volume-title":"arXiv preprint","author":"Ma","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref25","year":"2024, 2024","journal-title":"AI Meta. Llama 3.2: Revolutionizing edge ai and vision with open, customizable models. Meta AI Blog"},{"key":"ref26","article-title":"Rethinking comprehensive benchmark for chart understanding: A perspective from scientific literature","volume-title":"arXiv preprint","author":"Shen","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"ref28","article-title":"Gemini: a family of highly capable multimodal models","volume-title":"arXiv preprint","author":"Team","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109834"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"ref31","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","volume-title":"arXiv preprint","author":"Wang","year":"2024"},{"key":"ref32","article-title":"Charxiv: Charting gaps in realistic chart understanding in multimodal 11 ms","volume-title":"arXiv preprint","author":"Wang","year":"2024"},{"key":"ref33","article-title":"Deepseek-vl2: Mixture-ofexperts vision-language models for advanced multimodal understanding","volume-title":"arXiv preprint","author":"Wu","year":"2024"},{"key":"ref34","article-title":"Qwen2","volume-title":"5 technical report. arXiv preprint","author":"Yang","year":"2024"},{"key":"ref35","article-title":"mplug-owl3: Towards long image-sequence understanding in multi-modal large language models","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Yi: Open foundation models by 01","volume-title":"ai. arXiv preprint","author":"Young","year":"2024"},{"key":"ref37","article-title":"Internlm-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output","volume-title":"arXiv preprint","author":"Zhang","year":"2024"},{"key":"ref38","article-title":"Llava-read: Enhancing reading ability of multimodal language models","volume-title":"arXiv preprint","author":"Zhang","year":"2024"}],"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\/11444545.pdf?arnumber=11444545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:50Z","timestamp":1777529510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00053","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}