{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:01Z","timestamp":1777865341180,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371350"],"award-info":[{"award-number":["62371350"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00445","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4681-4690","source":"Crossref","is-referenced-by-count":0,"title":["ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for Mllm-Based Process Judges"],"prefix":"10.1109","author":[{"given":"Jiaxin","family":"Ai","sequence":"first","affiliation":[{"name":"Wuhan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaopan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"USTC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zizhen","family":"Li","sequence":"additional","affiliation":[{"name":"NKU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwen","family":"Sun","sequence":"additional","affiliation":[{"name":"NKU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukang","family":"Feng","sequence":"additional","affiliation":[{"name":"NKU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baojin","family":"Huang","sequence":"additional","affiliation":[{"name":"HZAU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Wuhan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"4","volume":"1","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref2","volume-title":"Learning to reason with 11 ms","year":"2024"},{"key":"ref3","first-page":"5","volume":"2","year":"2024","journal-title":"Gemini 2.0 flash experimental"},{"key":"ref4","year":"2024","journal-title":"Qvq: To see the world with wisdom"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref6","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Measuring mathematical problem solving with the math dataset","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","volume":"1","author":"Hendrycks"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0607"},{"key":"ref9","article-title":"Evaluating mathematical reasoning beyond accuracy","volume":"1","author":"Xia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Solving math word problems with process-and outcome-based feedback","author":"Uesato","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"3","article-title":"Let\u2019s verify step by step","volume":"1","author":"Lightman","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","first-page":"3","article-title":"Mr-gsm8k: A meta-reasoning bench-mark for large language model evaluation","volume":"2","author":"Zeng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.91"},{"issue":"1","key":"ref14","article-title":"Is your model really a good math reasoner? evaluating mathematical reasoning with checklist","volume":"2","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"3","article-title":"Processbench: Identifying process errors in mathematical reasoning","volume":"2","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1230"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.73"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_10"},{"issue":"3","key":"ref19","article-title":"Mme-cot: Benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency","volume":"1","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"issue":"3","key":"ref20","article-title":"Mpbench: A comprehensive multimodal reasoning benchmark for process errors identification","volume":"2","author":"Xu","year":"2025","journal-title":"arXiv preprint"},{"issue":"4","key":"ref21","first-page":"6","volume":"2","year":"2025","journal-title":"Qwen2.5-vl"},{"key":"ref22","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"issue":"1","key":"ref23","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","volume":"2","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"issue":"1","key":"ref24","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"The Twelfth International Conference on Learning Representations","volume":"2","author":"Lu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_22"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01245"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3507000"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref29","article-title":"Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi","volume-title":"Forty-first International Conference on Machine Learning","author":"Ying"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.983"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.983"},{"key":"ref36","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"},{"issue":"1","key":"ref37","first-page":"113569","article-title":"CharXiv: Charting gaps in realistic chart understanding in multimodal 11 ms","volume":"37","author":"Wang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","year":"2023","journal-title":"Gpt-4v(ision) system card."},{"key":"ref39","article-title":"Math-shepherd: Verify and reinforce 11 ms step-by-step without human annotations","volume":"abs\/2312.08935","author":"Wang","year":"2023","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.211"},{"issue":"6","key":"ref41","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","volume":"4","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Llava-onevision: Easy visual task transfer","volume":"4","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"issue":"6","key":"ref43","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","volume":"4","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","volume":"4","year":"2024","journal-title":"Qwen2.5: A party of foundation models"},{"key":"ref45","article-title":"Camel: Communicative agents for \u201cmind\u201d exploration of large language model society","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","volume":"4","author":"Li"},{"key":"ref46","volume":"5","year":"2025","journal-title":"Gemini 2.0 flash thinking."},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref48","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","volume":"8","author":"Edward"}],"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\/11445423.pdf?arnumber=11445423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:43Z","timestamp":1777529923000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00445","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}