{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:21Z","timestamp":1777889661590,"version":"3.51.4"},"reference-count":48,"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":["62272411"],"award-info":[{"award-number":["62272411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018735","name":"Ant Group","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018735","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\/iccv51701.2025.00168","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1718-1728","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program"],"prefix":"10.1109","author":[{"given":"Minghe","family":"Gao","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongqi","family":"Yue","sequence":"additional","affiliation":[{"name":"Chalmers University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Wu","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Openflamingo: An opensource framework for training large autoregressive visionlanguage models","author":"Awadalla","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.446"},{"key":"ref3","volume-title":"Mj-bench: Is your multimodal reward model really a good judge for text-to-image generation?","author":"Chen","year":"2024"},{"key":"ref4","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","volume-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2025"},{"key":"ref6","article-title":"DeepSeek-AI","author":"Guo","year":"2025","journal-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning"},{"key":"ref7","volume-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681552"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681082"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681488"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00916"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.483"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0529"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3274139"},{"key":"ref18","volume-title":"Fine-tuning multimodal 11 ms to follow zero-shot demonstrative instructions","author":"Li","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02296"},{"key":"ref20","article-title":"Vlrewardbench: A challenging benchmark for vision-language generative reward models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref22","volume-title":"Let\u2019s verify step by step","author":"Lightman","year":"2023"},{"key":"ref23","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1882"},{"key":"ref25","volume-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2024"},{"key":"ref26","article-title":"OpenAI","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref27","article-title":"OpenAI","year":"2024","journal-title":"Learning to reason with 11 ms"},{"key":"ref28","volume-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","author":"Qian","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00312"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0275"},{"key":"ref31","volume-title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters","author":"Snell","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1230"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref34","volume-title":"Solving math word problems with process- and outcome-based feedback","author":"Uesato","year":"2022"},{"key":"ref35","volume-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"ref37","volume-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2023"},{"key":"ref38","volume-title":"Multimodal preference data synthetic alignment with reward model","author":"Wijaya","year":"2024"},{"key":"ref39","volume-title":"Deepseek-proverv1.5: Harnessing proof assistant feedback for reinforcement learning and monte-carlo tree search","author":"Xin","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref41","volume-title":"Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi","author":"Ying","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00913"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.340"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.340"},{"key":"ref46","volume-title":"Cocot: Contrastive chain-of-thought prompting for large multimodal models with multiple image inputs","author":"Zhang","year":"2024"},{"key":"ref47","article-title":"Least-to-most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Rmb: Comprehensively benchmarking reward models in 11 m alignment","author":"Zhou","year":"2024","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\/11445043.pdf?arnumber=11445043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:18:49Z","timestamp":1777612729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00168","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}