{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T06:31:32Z","timestamp":1784874692714,"version":"3.55.0"},"reference-count":68,"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\/iccv51701.2025.00202","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2087-2098","source":"Crossref","is-referenced-by-count":18,"title":["LlaVA-CoT: Let Vision Language Models Reason Step-By-Step"],"prefix":"10.1109","author":[{"given":"Guowei","family":"Xu","sequence":"first","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Jin","sequence":"additional","affiliation":[{"name":"Shenzhen Graduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziang","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen Graduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Graduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibing","family":"Song","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lichao","family":"Sun","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Lehigh University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shenzhen Graduate School, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Detailed results on openvlm leaderboard"},{"key":"ref2","first-page":"3","year":"2024","journal-title":"Claude 3.5 sonnet"},{"key":"ref3","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref4","author":"Amini","year":"2024","journal-title":"Variational best-of-n alignment"},{"key":"ref5","first-page":"279","article-title":"Neuro-symbolic visual reasoning: Disentangling","volume-title":"International Conference on Machine Learning","author":"Amizadeh","year":"2020"},{"key":"ref6","article-title":"Foundational models defining a new era in vision: A survey and outlook","author":"Awais","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"1511","article-title":"An augmented benchmark dataset for geometric question answering through dual parallel text encoding","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Cao","year":"2022"},{"key":"ref8","author":"Cesista","year":"2024","journal-title":"Multimodal structured generation: Cvpr\u2019s 2nd mmfm challenge technical report"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.65"},{"key":"ref14","first-page":"28","article-title":"Clevr-math: A dataset for compositional language, visual and mathematical reasoning","volume-title":"International Joint Conference on Learning and Reasoning, 16th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy 2022), Windsor, UK","author":"Lindstr\u00f6m","year":"2022"},{"key":"ref15","author":"Guo","year":"2025","journal-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00370"},{"key":"ref18","author":"Zeng","year":"2024","journal-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools"},{"key":"ref19","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.288"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00916"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.67"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref29","author":"Lanham","year":"2023","journal-title":"Measuring faithfulness in chain-of-thought reasoning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3276570"},{"key":"ref31","author":"Li","year":"2017","journal-title":"People in social context (pisc) dataset"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02491-7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1580"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref37","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":"ref38","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":"ref39","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024","journal-title":"arXiv:2405.20797"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.11.011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref43","first-page":"3","article-title":"Meta AI","year":"2024","journal-title":"Llama 3.2: Revolutionizing edge ai and vision with open, customizable models"},{"key":"ref44","article-title":"OpenAI","volume-title":"Gpt-4o mini: advancing cost-efficient intelligence","year":"2024"},{"key":"ref45","author":"Qiao","journal-title":"Prism: A framework for decoupling and assessing the capabilities of vlms, 2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.51644\/9781771120920-031"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-tutorials.7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref49","author":"Shao","journal-title":"Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning, 2024"},{"key":"ref50","article-title":"Rethinking data selection for supervised finetuning","author":"Shen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","author":"Snell","journal-title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters, 2024"},{"key":"ref52","author":"Sutskever","year":"2014","journal-title":"Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems. Curran Associates, Inc."},{"key":"ref53","author":"Turpin","year":"2023","journal-title":"Language models don\u2019t always say what they think: Unfaithful explanations in chain-of-thought prompting"},{"key":"ref54","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref55","author":"Wang","year":"2024","journal-title":"Improved value alignment in large language models using variational best-of-n techniques"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref57","author":"Wu","year":"2024","journal-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29544"},{"key":"ref59","author":"Yang","year":"2023","journal-title":"The dawn of lmms: Preliminary explorations with gpt-4v(ision)"},{"key":"ref60","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Evagaussians: Event stream assisted gaussian splatting from blurry images","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities","volume-title":"International conference on machine learning. PMLR","author":"Yu","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"ref64","article-title":"Internlm-xcomposer2","author":"Zang","year":"2025","journal-title":"5-reward: A simple yet effective multi-modal reward model. arXiv preprint arXiv:2501.12368"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.82"},{"key":"ref67","author":"Zhao","year":"2024","journal-title":"Marco-o1: Towards open reasoning models for openended solutions"},{"key":"ref68","author":"Zhong","year":"2024","journal-title":"Evaluation of openai o1: Opportunities and challenges of agi"}],"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\/11445580.pdf?arnumber=11445580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:01Z","timestamp":1777529701000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00202","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}