{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:20Z","timestamp":1777865360710,"version":"3.51.4"},"reference-count":56,"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\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"publisher","award":["AISG3-RP-2022-030"],"award-info":[{"award-number":["AISG3-RP-2022-030"]}],"id":[{"id":"10.13039\/501100001381","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\/iccv51701.2025.00222","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2303-2312","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization"],"prefix":"10.1109","author":[{"given":"Kesen","family":"Zhao","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beier","family":"Zhu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianru","family":"Sun","sequence":"additional","affiliation":[{"name":"Singapore Management University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.592"},{"key":"ref2","article-title":"A general theoretical paradigm to understand learning from human preferences","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Gheshlaghi Azar","year":"2024"},{"key":"ref3","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"ref5","article-title":"Towards reasoning era: A survey of long chain-of-thought for reasoning large language models","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","author":"David","year":"1963","journal-title":"The method of paired comparisons. London"},{"key":"ref7","article-title":"Kto: Model alignment as prospect theoretic optimization","author":"Ethayarajh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3100"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3100"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3497725"},{"key":"ref11","article-title":"Mini-monkey: Alleviating the semantic sawtooth effect for lightweight mllms via complementary image pyramid","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref14","article-title":"G3: an effective and adaptive framework for worldwide geolocalization using large multimodality models","volume-title":"NeurIPS","author":"Jia","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02328"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","article-title":"Large language models are zero-shot reasoners","volume-title":"NeurIPS","author":"Kojima","year":"2022"},{"key":"ref18","article-title":"Step-dpo: Step-wise preference optimization for long-chain reasoning of 11 ms","author":"Lai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","author":"Lee","year":"2023","journal-title":"Rlaif: Scaling reinforcement learning from human feedback with ai feedback"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref22","article-title":"Visual instruction tuning","volume-title":"NeurIPS","author":"Liu","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3695461"},{"key":"ref24","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","author":"Maddison","year":"2017","journal-title":"Gumbel machinery"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref28","year":"2023","journal-title":"Chatgpt"},{"key":"ref29","article-title":"Precise localization of memories: A fine-grained neuron-level knowledge editing technique for 11 ms","volume-title":"ICLR","author":"Pan","year":"2025"},{"key":"ref30","article-title":"Iterative reasoning preference optimization","author":"Yuanzhe Pang","year":"2025","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref32","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref33","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume-title":"NeurIPS","author":"Rafailov","year":"2023"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning","volume-title":"NeurIPS","author":"Shao","year":"2025"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref37","article-title":"Aligning large multimodal models with factually augmented rlhf","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01789"},{"key":"ref40","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"NeurIPS","author":"Wei","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"ref42","article-title":"Llava-o1: Let vision language models reason step-by-step","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Mm-react: Prompting chatgpt for multimodal reasoning and action","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Reformulating vision-language foundation models and datasets towards universal multimodal assistants","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"ref47","article-title":"Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Notellm-2: Multimodal large representation models for recommendation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Automatic chain of thought prompting in large language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Multimodal chain-ofthought reasoning in language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00319"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28614"},{"key":"ref53","article-title":"Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting","volume-title":"NeurIPS","author":"Zhu","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680885"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref56","article-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2019","journal-title":"arXiv preprint"}],"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\/11444604.pdf?arnumber=11444604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:21Z","timestamp":1777529961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444604\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00222","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}