{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:10Z","timestamp":1777865410445,"version":"3.51.4"},"reference-count":64,"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\/iccv51701.2025.00303","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3163-3173","source":"Crossref","is-referenced-by-count":0,"title":["VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models"],"prefix":"10.1109","author":[{"given":"Jiacheng","family":"Ruan","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzhen","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Guo","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daoxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Xu","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Hu","sequence":"additional","affiliation":[{"name":"Xiaohongshu Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhuo","family":"Fu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","volume-title":"arXiv preprint","author":"Abdin","year":"2024"},{"key":"ref2","first-page":"2","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint","author":"Achiam","year":"2023"},{"key":"ref3","year":"2025","journal-title":"Claude 3.5: Sonnet"},{"key":"ref4","first-page":"2","article-title":"Qwen2. 5-vl technical report","volume-title":"arXiv preprint","author":"Bai","year":"2025"},{"key":"ref5","article-title":"Constitutional ai: Harmlessness from ai feedback","author":"Bai","year":"2022","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Internlm2 technical report","volume-title":"arXiv preprint","author":"Cai","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref8","article-title":"Self-play fine-tuning converts weak language models to strong language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00847"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref12","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Length-controlled alpacaeval: A simple way to debias automatic evaluators","author":"Dubois","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref16","article-title":"Mantis: Interleaved multiimage instruction tuning","author":"Jiang","year":"2024","journal-title":"Transactions on Machine Learning Research, 2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2025.3531360"},{"key":"ref18","article-title":"Solar 10.7 b: Scaling large language models with simple yet effective depth up-scaling","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"2","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\/2024.emnlp-main.358"},{"key":"ref22","article-title":"Benchmark evaluations, applications, and challenges of large vision language models: A survey","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"2","article-title":"Let\u2019s verify step by step","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Lightman","year":"2023"},{"key":"ref24","article-title":"Criticbench: Benchmarking 11 ms for critique-correct reasoning","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Skywork-reward: Bag of tricks for reward modeling in 11 ms","author":"Yuhao Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"A survey on hallucination in large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Rm-bench: Benchmarking reward models of language models with subtlety and style","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Uncertainty-aware reward model: Teaching reward models to know what is unknown","author":"Lou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Let\u2019s reward step by step: Step-level reward model as the navigators for reasoning","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","year":"2024","journal-title":"Introducing meta llama 3: The most capable openly available llm to date. Meta AI"},{"key":"ref33","year":"2025","journal-title":"Minicpm o: A gpt-4o-level mllm for vision, speech, and multimodal live streaming on your phone"},{"key":"ref34","first-page":"2773027744","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref36","article-title":"Illusionvqa: A challenging optical illusion dataset for vision language models","author":"Sameen Shahgir","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1230"},{"key":"ref38","article-title":"Gemini: a family of highly capable multimodal models.","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","first-page":"2","year":"2024","journal-title":"Qvq: To see the world with wisdom"},{"key":"ref40","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"A survey on data selection for llm instruction tuning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"95095","article-title":"Measuring multimodal mathematical reasoning with math-vision dataset","volume":"37","author":"Wang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref43","article-title":"Large language models are not fair evaluators","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","first-page":"3","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Selftaught evaluators","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Helpsteer2-preference: Complementing ratings with preferences","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","first-page":"5","article-title":"Boosting multimodal reasoning with mcts-automated structured thinking","volume":"1","author":"Wu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Scaling inference-time search with vision value model for improved visual comprehension","author":"Xiyao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Qwen2 technical report","volume-title":"arXiv preprint","author":"Yang","year":"2024"},{"key":"ref50","article-title":"Qwen2. 5 technical report","volume-title":"arXiv preprint","author":"Yang","year":"2024"},{"key":"ref51","first-page":"1","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":"ref52","first-page":"2","article-title":"Multimodal rewardbench: Holistic evaluation of reward models for vision language models","author":"Yasunaga","year":"2025","journal-title":"arXiv preprint"},{"key":"ref53","first-page":"1","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":"ref54","article-title":"Mr-gsm8k: A meta-reasoning benchmark for large language model evaluation","author":"Zeng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Mr-ben: A meta-reasoning benchmark for evaluating system- 2 thinking in 11 ms","author":"Zeng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.020"},{"key":"ref57","article-title":"Critic-v: Vlm critics help catch vlm errors in multimodal reasoning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.547"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.50"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3402136"},{"key":"ref63","article-title":"Is your model really a good math rea-soner? evaluating mathematical reasoning with checklist","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Dynamath: A dynamic visual benchmark for evaluating mathematical reasoning robustness of vision language models","author":"Zou","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\/11445931.pdf?arnumber=11445931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:28:33Z","timestamp":1777530513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00303","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}