{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:04:17Z","timestamp":1777889057185,"version":"3.51.4"},"reference-count":60,"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":["92470203"],"award-info":[{"award-number":["92470203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L242022"],"award-info":[{"award-number":["L242022"]}],"id":[{"id":"10.13039\/501100004826","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\/iccv51701.2025.00855","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9147-9157","source":"Crossref","is-referenced-by-count":0,"title":["ReCot: Reflective Self-Correction Training for Mitigating Confirmation Bias in Large Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Mengxue","family":"Qu","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibo","family":"Hu","sequence":"additional","affiliation":[{"name":"NIO,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunyang","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunchao","family":"Wei","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Bai","year":"2023","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_11"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685523"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01350"},{"key":"ref7","article-title":"Self-play fine-tuning converts weak language models to strong language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref10","article-title":"Vision-language models can self-improve reasoning via reflection","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"DeepSeek-AI","year":"2025","journal-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00847"},{"key":"ref13","article-title":"Think thrice before you act: Progressive thought refinement in large language models","author":"Du","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","author":"Fu","year":"2024","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref15","article-title":"G-llava: Solving geometric problem with multi-modal large language model","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Rose: Revolutionizing open-set dense segmentation with patch-wise perceptual large multimodal model","author":"Han","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.507"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3720546"},{"key":"ref19","article-title":"Intent3d: 3d object detection in rgb-d scans based on human intention","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Kang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.99"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00245"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.440"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02520"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref26","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref27","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"The 36th Conference on Neural Information Processing Systems (NeurIPS)","author":"Lu","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"ref30","article-title":"OpenAI","year":"2024","journal-title":"Openai o1 system card"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2024.3513992"},{"key":"ref32","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"ArXiv, abs\/2306"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1865"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00191"},{"key":"ref35","article-title":"Qwen2-vl: To see the world more clearly","year":"2024","journal-title":"Wwen Blog"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref38","article-title":"Training language models with language feedback at scale","author":"Scheurer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref40","author":"Shao","year":"2024","journal-title":"Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models"},{"key":"ref41","first-page":"3008","article-title":"Learning to summarize with human feedback","author":"Stiennon","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02321"},{"key":"ref43","article-title":"Qwen Team","year":"2024","journal-title":"Qvq: To see the world with wisdom"},{"key":"ref44","article-title":"The all-seeing project: Towards panoptic visual recognition and understanding of the open world","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref46","article-title":"Generating sequences by learning to self-correct","volume-title":"The Eleventh International Conference on Learning Representations","author":"Welleck","year":"2023"},{"key":"ref47","author":"Xie","year":"2024","journal-title":"Monte carlo tree search boosts reasoning via iterative preference learning"},{"key":"ref48","author":"Xu","year":"2024","journal-title":"Llava-cot: Let vision language models reason step-by-step"},{"key":"ref49","article-title":"Mathglm-vision: Solving mathematical problems with multi-modal large language model","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Mulberry: Empowering mllm with o1-like reasoning and reflection via collective monte carlo tree search","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref52","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Agent-r: Training language model agents to reflect via iterative self-training","author":"Yuan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1126"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2066"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_12"},{"key":"ref57","article-title":"Mavis: Mathematical visual instruction tuning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Improve vision language model chain-ofthought reasoning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref60","article-title":"Least-to-most prompting enables complex reasoning in large language models","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhou"}],"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\/11444328.pdf?arnumber=11444328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:05:55Z","timestamp":1777611955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444328\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00855","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}