{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T17:11:32Z","timestamp":1781975492977,"version":"3.54.5"},"reference-count":54,"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":"NSFC","doi-asserted-by":"publisher","award":["62225603,62206104"],"award-info":[{"award-number":["62225603,62206104"]}],"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\/iccv51701.2025.00086","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"837-847","source":"Crossref","is-referenced-by-count":1,"title":["DocThinker: Explainable Multimodal Large Language Models with Rule-Based Reinforcement Learning for Document Understanding"],"prefix":"10.1109","author":[{"given":"Wenwen","family":"Yu","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibo","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen2.5vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref3","article-title":"Sft memorizes, rl generalizes: A comparative study of foundation model post-training","author":"Chu","year":"2025","journal-title":"ArXiv, abs\/2501.17161"},{"key":"ref4","article-title":"Explainable and interpretable multimodal large language models: A comprehensive survey","author":"Dang","year":"2024","journal-title":"ArXiv"},{"key":"ref5","article-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"Daya Guo","year":"2025","journal-title":"ArXiv, abs\/2501.12948"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4250-y"},{"key":"ref8","article-title":"Refocus: Visual editing as a chain of thought for structured image understanding","author":"Fu","year":"2025","journal-title":"ArXiv, abs\/2501.05452"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41682-8_25"},{"key":"ref10","article-title":"A comprehensive guide to explainable ai: From classical models to llms","author":"Hsieh","year":"2024","journal-title":"ArXiv, abs\/2412.00800"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref13","article-title":"Openai o1 system card","author":"Jaech","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"ref17","article-title":"Imagine while reasoning in space: Multimodal visualization-ofthought","author":"Li","year":"2025","journal-title":"ArXiv, abs\/2501.07542"},{"key":"ref18","article-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"ArXiv, abs\/2311.07575"},{"key":"ref19","article-title":"Focus anywhere for finegrained multi-page document understanding","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Skywork-Reward: Bag of tricks for reward modeling in 11 ms","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653415"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00197"},{"key":"ref25","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2017"},{"key":"ref26","article-title":"Structextv3: An efficient vision-language model for text-rich image perception, comprehension, and beyond","author":"Lyu","year":"2024","journal-title":"ArXiv, abs\/2405.21013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref29","article-title":"ChatGPT","year":"2023"},{"key":"ref30","article-title":"GPT-4","year":"2023"},{"key":"ref31","article-title":"GPT-4V(ision) System Card","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04981-0_32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0965-7"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0275"},{"key":"ref36","article-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models","author":"Shao","year":"2024","journal-title":"ArXiv, abs\/2402.03300"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref39","article-title":"A review of multimodal explainable artificial intelligence: Past, present and future","author":"Sun","year":"2024","journal-title":"ArXiv, abs\/2412.14056"},{"key":"ref40","article-title":"Introduction to reinforcement learning","author":"Sutton","year":"1998","journal-title":"ArXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.463"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_23"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref44","article-title":"Mind\u2019s eye of 11 ms : Visualization-of-thought elicits spatial reasoning in large language models","volume-title":"Neural Information Processing Systems","author":"Wu","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01506"},{"key":"ref46","article-title":"mplug-docowl: Modularized multimodal large language model for document understanding","author":"Ye","year":"2023","journal-title":"ArXiv, abs\/2307.02499"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"ref50","article-title":"A simple yet effective multi-modal reward model","author":"Zang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Read and think: An efficient step-wise multimodal language model for document understanding and reasoning","author":"Zhang","year":"2024","journal-title":"ArXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33076"},{"key":"ref53","article-title":"Llavar: Enhanced visual instruction tuning for text-rich image understanding","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"}],"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\/11445361.pdf?arnumber=11445361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:31:50Z","timestamp":1777613510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445361\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00086","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}