{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:29:05Z","timestamp":1781587745745,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","funder":[{"name":"Key Deployment Program of the Chinese Academy of Sciences, China","award":["Grant KGFZD145-25-39"],"award-info":[{"award-number":["Grant KGFZD145-25-39"]}]},{"name":"Strategic Priority Research Program of Chinese Academy of Science","award":["Grant E1XA310103"],"award-info":[{"award-number":["Grant E1XA310103"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758208","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:39:06Z","timestamp":1761377946000},"page":"12698-12705","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["VER-Bench: Evaluating MLLMs on Reasoning with Fine-Grained Visual Evidence"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5358-8659","authenticated-orcid":false,"given":"Chenhui","family":"Qiang","sequence":"first","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5708-7157","authenticated-orcid":false,"given":"Zhaoyang","family":"Wei","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1636-463X","authenticated-orcid":false,"given":"Xumeng","family":"Han","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0918-5357","authenticated-orcid":false,"given":"Zipeng","family":"Wang","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3386-9502","authenticated-orcid":false,"given":"Siyao","family":"Li","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8564-0346","authenticated-orcid":false,"given":"Xiangyuan","family":"Lan","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3495-5158","authenticated-orcid":false,"given":"Jianbin","family":"Jiao","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9970-5152","authenticated-orcid":false,"given":"Zhenjun","family":"Han","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Spice: Semantic propositional image caption evaluation. In Computer Vision-ECCV 2016: 14th European Conference","author":"Anderson Peter","year":"2016","unstructured":"Peter Anderson, Basura Fernando, Mark Johnson, and Stephen Gould. 2016. Spice: Semantic propositional image caption evaluation. In Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part V 14. Springer, 382-398."},{"key":"e_1_3_2_1_3_1","volume-title":"Model card addendum: Claude 3.5 haiku and upgraded claude 3.5 sonnet. URL https:\/\/api.semanticscholar.org\/CorpusID","author":"Anthropic S","unstructured":"S Anthropic. [n.d.]. Model card addendum: Claude 3.5 haiku and upgraded claude 3.5 sonnet. URL https:\/\/api.semanticscholar.org\/CorpusID, Vol. 273639283 ([n.d.])."},{"key":"e_1_3_2_1_4_1","volume-title":"Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92089-9_22"},{"key":"e_1_3_2_1_6_1","unstructured":"Zheng Cai Maosong Cao Haojiong Chen Kai Chen Keyu Chen Xin Chen Xun Chen Zehui Chen Zhi Chen Pei Chu et al. 2024. Internlm2 technical report. arXiv preprint arXiv:2403.17297 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"e_1_3_2_1_8_1","volume-title":"Are We on the Right Way for Evaluating Large Vision-Language Models? arXiv preprint arXiv:2403.20330","author":"Chen Lin","year":"2024","unstructured":"Lin Chen, Jinsong Li, Xiaoyi Dong, Pan Zhang, Yuhang Zang, Zehui Chen, Haodong Duan, Jiaqi Wang, Yu Qiao, Dahua Lin, and Feng Zhao. 2024a. Are We on the Right Way for Evaluating Large Vision-Language Models? arXiv preprint arXiv:2403.20330 (2024)."},{"key":"e_1_3_2_1_9_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024b. Expanding performance boundaries of open-source multimodal models with model data and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Zhe Chen Weiyun Wang Hao Tian Shenglong Ye Zhangwei Gao Erfei Cui Wenwen Tong Kongzhi Hu Jiapeng Luo Zheng Ma et al. 2024c. How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites. arXiv preprint arXiv:2404.16821 (2024).","DOI":"10.1007\/s11432-024-4231-5"},{"key":"e_1_3_2_1_11_1","unstructured":"Xiaoyi Dong Pan Zhang Yuhang Zang Yuhang Cao Bin Wang Linke Ouyang Xilin Wei Songyang Zhang Haodong Duan Maosong Cao et al. 2024. Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model. arXiv preprint arXiv:2401.16420 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Yuqi Huo, Bingning Wang, Weipeng Chen, Zheng Liu, Zhongyuan Wang, and Ji-Rong Wen.","author":"Du Yifan","year":"2025","unstructured":"Yifan Du, Zikang Liu, Yifan Li, Wayne Xin Zhao, Yuqi Huo, Bingning Wang, Weipeng Chen, Zheng Liu, Zhongyuan Wang, and Ji-Rong Wen. 2025. Virgo: A Preliminary Exploration on Reproducing o1-like MLLM. arXiv preprint arXiv:2501.01904 (2025)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Haodong Duan Junming Yang Yuxuan Qiao Xinyu Fang Lin Chen Yuan Liu Xiaoyi Dong Yuhang Zang Pan Zhang Jiaqi Wang Dahua Lin and Kai Chen. 2024. VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models. arXiv:2407.11691 [cs.CV] https:\/\/arxiv.org\/abs\/2407.11691","DOI":"10.1145\/3664647.3685520"},{"key":"e_1_3_2_1_14_1","volume-title":"Mmbench-video: A long-form multi-shot benchmark for holistic video understanding. NeurIPS","author":"Fang Xinyu","year":"2025","unstructured":"Xinyu Fang, Kangrui Mao, Haodong Duan, Xiangyu Zhao, Yining Li, Dahua Lin, and Kai Chen. 2025. Mmbench-video: A long-form multi-shot benchmark for holistic video understanding. NeurIPS (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32302"},{"key":"e_1_3_2_1_16_1","volume-title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models. arXiv preprint arXiv:2306.13394","author":"Fu Chaoyou","year":"2023","unstructured":"Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, Yunsheng Wu, and Rongrong Ji. 2023. MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models. arXiv preprint arXiv:2306.13394 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Mme-survey: A comprehensive survey on evaluation of multimodal llms. arXiv","author":"Fu Chaoyou","year":"2024","unstructured":"Chaoyou Fu, Yi-Fan Zhang, Shukang Yin, Bo Li, Xinyu Fang, Sirui Zhao, Haodong Duan, Xing Sun, Ziwei Liu, Liang Wang, et al., 2024. Mme-survey: A comprehensive survey on evaluation of multimodal llms. arXiv (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.613"},{"key":"e_1_3_2_1_21_1","unstructured":"Dongzhi Jiang Renrui Zhang Ziyu Guo Yanwei Li Yu Qi Xinyan Chen Liuhui Wang Jianhan Jin Claire Guo Shen Yan et al. 2025. MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality Robustness and Efficiency. arXiv preprint arXiv:2502.09621 (2025)."},{"key":"e_1_3_2_1_22_1","volume-title":"Ting-Hao'Kenneth' Huang, et al.","author":"Kim Jaeyoung","year":"2025","unstructured":"Jaeyoung Kim, Jongho Lee, Hong-Jun Choi, Ting-Yao Hsu, Chieh-Yang Huang, Sungchul Kim, Ryan Rossi, Tong Yu, Clyde Lee Giles, Ting-Hao'Kenneth' Huang, et al., 2025. Multi-LLM Collaborative Caption Generation in Scientific Documents. arXiv preprint arXiv:2501.02552 (2025)."},{"key":"e_1_3_2_1_23_1","unstructured":"Bo Li Yuanhan Zhang Dong Guo Renrui Zhang Feng Li Hao Zhang Kaichen Zhang Yanwei Li Ziwei Liu and Chunyuan Li. 2024c. LLaVA-OneVision: Easy Visual Task Transfer. arXiv:2408.03326 [cs.CV] https:\/\/arxiv.org\/abs\/2408.03326"},{"key":"e_1_3_2_1_24_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Li Wei","year":"2024","unstructured":"Wei Li, Hehe Fan, Yongkang Wong, Yi Yang, and Mohan Kankanhalli. 2024a. Improving context understanding in multimodal large language models via multimodal composition learning. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"e_1_3_2_1_27_1","volume-title":"ECCV 2024","author":"Lin Ziyi","year":"2023","unstructured":"Ziyi Lin, Chris Liu, Renrui Zhang, Peng Gao, Longtian Qiu, Han Xiao, Han Qiu, Chen Lin, Wenqi Shao, Keqin Chen, et al., 2023. Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models. ECCV 2024 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Sphinx-x: Scaling data and parameters for a family of multi-modal large language models. arXiv preprint arXiv:2402.05935","author":"Liu Dongyang","year":"2024","unstructured":"Dongyang Liu, Renrui Zhang, Longtian Qiu, Siyuan Huang, Weifeng Lin, Shitian Zhao, Shijie Geng, Ziyi Lin, Peng Jin, Kaipeng Zhang, et al., 2024b. Sphinx-x: Scaling data and parameters for a family of multi-modal large language models. arXiv preprint arXiv:2402.05935 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"e_1_3_2_1_30_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023b. Visual Instruction Tuning. In NeurIPS."},{"key":"e_1_3_2_1_31_1","volume-title":"MMBench: Is Your Multi-modal Model an All-around Player? arXiv preprint arXiv:2307.06281","author":"Liu Yuan","year":"2023","unstructured":"Yuan Liu, Haodong Duan, Yuanhan Zhang, Bo Li, Songyang Zhang, Wangbo Zhao, Yike Yuan, Jiaqi Wang, Conghui He, Ziwei Liu, Kai Chen, and Dahua Lin. 2023a. MMBench: Is Your Multi-modal Model an All-around Player? arXiv preprint arXiv:2307.06281 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"Jia Qing Tan, Shafiq Joty, and Enamul Hoque.","author":"Masry Ahmed","year":"2022","unstructured":"Ahmed Masry, Do Xuan Long, Jia Qing Tan, Shafiq Joty, and Enamul Hoque. 2022. Chartqa: A benchmark for question answering about charts with visual and logical reasoning. arXiv preprint arXiv:2203.10244 (2022)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_1_34_1","unstructured":"OpenAI. 2024a. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"e_1_3_2_1_35_1","volume-title":"Introducing openai o1","author":"AI.","year":"2024","unstructured":"OpenAI. 2024b. Introducing openai o1, 2024. https:\/\/openai.com\/o1\/"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311-318."},{"key":"e_1_3_2_1_37_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:231591445","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning. https:\/\/api.semanticscholar.org\/CorpusID:231591445"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"e_1_3_2_1_39_1","first-page":"8612","article-title":"Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning","volume":"37","author":"Shao Hao","year":"2024","unstructured":"Hao Shao, Shengju Qian, Han Xiao, Guanglu Song, Zhuofan Zong, Letian Wang, Yu Liu, and Hongsheng Li. 2024. Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning. Advances in Neural Information Processing Systems, Vol. 37 (2024), 8612-8642.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_40_1","volume-title":"European Conference on Computer Vision. Springer, 117-132","author":"Song Kunpeng","year":"2024","unstructured":"Kunpeng Song, Yizhe Zhu, Bingchen Liu, Qing Yan, Ahmed Elgammal, and Xiao Yang. 2024. Moma: Multimodal llm adapter for fast personalized image generation. In European Conference on Computer Vision. Springer, 117-132."},{"key":"e_1_3_2_1_41_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"QVQ: To See the World with Wisdom. https:\/\/qwenlm.github.io\/blog\/qvq-72b-preview\/","author":"Team Qwen","year":"2024","unstructured":"Qwen Team. 2024. QVQ: To See the World with Wisdom. https:\/\/qwenlm.github.io\/blog\/qvq-72b-preview\/"},{"key":"e_1_3_2_1_43_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_45_1","volume-title":"To see is to believe: Prompting gpt-4v for better visual instruction tuning. arXiv preprint arXiv:2311.07574","author":"Wang Junke","year":"2023","unstructured":"Junke Wang, Lingchen Meng, Zejia Weng, Bo He, Zuxuan Wu, and Yu-Gang Jiang. 2023b. To see is to believe: Prompting gpt-4v for better visual instruction tuning. arXiv preprint arXiv:2311.07574 (2023)."},{"key":"e_1_3_2_1_46_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_47_1","volume-title":"Cogvlm: Visual expert for pretrained language models. arXiv preprint arXiv:2311.03079","author":"Wang Weihan","year":"2023","unstructured":"Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wang, Junhui Ji, Zhuoyi Yang, Lei Zhao, Xixuan Song, et al., 2023a. Cogvlm: Visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680886"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01243"},{"key":"e_1_3_2_1_50_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2024. Next-gpt: Any-to-any multimodal llm. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_51_1","unstructured":"XAI. 2024. grok-1.5v. https:\/\/x.ai\/blog\/grok-1.5v"},{"key":"e_1_3_2_1_52_1","volume-title":"Errorradar: Benchmarking complex mathematical reasoning of multimodal large language models via error detection. arXiv","author":"Yan Yibo","year":"2024","unstructured":"Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, Yi-Fan Zhang, Tianlong Xu, Zhendong Chu, et al., 2024. Errorradar: Benchmarking complex mathematical reasoning of multimodal large language models via error detection. arXiv (2024)."},{"key":"e_1_3_2_1_53_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025a. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_54_1","unstructured":"An Yang Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoyan Huang Jiandong Jiang Jianhong Tu Jianwei Zhang Jingren Zhou et al. 2025b. Qwen2. 5-1M Technical Report. arXiv preprint arXiv:2501.15383 (2025)."},{"key":"e_1_3_2_1_55_1","volume-title":"Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800","author":"Yao Yuan","year":"2024","unstructured":"Yuan Yao, Tianyu Yu, Ao Zhang, Chongyi Wang, Junbo Cui, Hongji Zhu, Tianchi Cai, Haoyu Li, Weilin Zhao, Zhihui He, et al., 2024. Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:2408.01800 (2024)."},{"key":"e_1_3_2_1_56_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi et al. 2023. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490","author":"Yu Weihao","year":"2023","unstructured":"Weihao Yu, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Zicheng Liu, Xinchao Wang, and Lijuan Wang. 2023. Mm-vet: Evaluating large multimodal models for integrated capabilities. arXiv preprint arXiv:2308.02490 (2023)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"e_1_3_2_1_59_1","volume-title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans? arXiv preprint arXiv:2408.13257","author":"Zhang Yi-Fan","year":"2024","unstructured":"Yi-Fan Zhang, Huanyu Zhang, Haochen Tian, Chaoyou Fu, Shuangqing Zhang, Junfei Wu, Feng Li, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin, and Tieniu Tan. 2024. MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans? arXiv preprint arXiv:2408.13257 (2024)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","unstructured":"Zicheng Zhang Xiangyu Zhao Xinyu Fang Chunyi Li Xiaohong Liu Xiongkuo Min Haodong Duan Kai Chen and Guangtao Zhai. 2025. Redundancy Principles for MLLMs Benchmarks. arXiv:2501.13953 [cs.CL]","DOI":"10.18653\/v1\/2025.acl-long.612"},{"key":"e_1_3_2_1_61_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."},{"key":"e_1_3_2_1_62_1","unstructured":"Jinguo Zhu Weiyun Wang Zhe Chen Zhaoyang Liu Shenglong Ye Lixin Gu Yuchen Duan Hao Tian Weijie Su Jie Shao et al. 2025. InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models. arXiv preprint arXiv:2504.10479 (2025)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:59:02Z","timestamp":1765310342000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":62,"alternative-id":["10.1145\/3746027.3758208","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758208","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}