{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:39:20Z","timestamp":1786120760879,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817506","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"8636-8647","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AutoDavis: Automatic and Dynamic Evaluation Protocol of Large Vision-Language Models on Visual Question-Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6977-3486","authenticated-orcid":false,"given":"Han","family":"Bao","sequence":"first","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8315-7972","authenticated-orcid":false,"given":"Yue","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8780-7705","authenticated-orcid":false,"given":"Yanbo","family":"Wang","sequence":"additional","affiliation":[{"name":"Independent Researcher, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5415-8713","authenticated-orcid":false,"given":"Jiayi","family":"Ye","sequence":"additional","affiliation":[{"name":"Independent Researcher, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5065-9051","authenticated-orcid":false,"given":"Xiangqi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6633-0796","authenticated-orcid":false,"given":"Xiuying","family":"Chen","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Masdar city, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3401-4921","authenticated-orcid":false,"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Southern California, Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5348-0632","authenticated-orcid":false,"given":"Tianyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Masdar city, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9659-1551","authenticated-orcid":false,"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology, Thuwal, Makkah, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3574-5665","authenticated-orcid":false,"given":"Xiangliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Yushi Bai Jiahao Ying Yixin Cao Xin Lv Yuze He Xiaozhi Wang Jifan Yu Kaisheng Zeng Yijia Xiao Haozhe Lyu et al. 2024. Benchmarking foundation models with language-model-as-an-examiner. Advances in Neural Information Processing Systems V36 (2024).","DOI":"10.52202\/075280-3414"},{"key":"e_1_3_2_1_3_1","unstructured":"Dongping Chen Yue Huang Siyuan Wu Jingyu Tang Liuyi Chen Yilin Bai Zhigang He Chenlong Wang Huichi Zhou Yiqiang Li et al. 2024a. GUI-WORLD: A Dataset for GUI-oriented Multimodal LLM-based Agents. arXiv preprint arXiv:2406.10819 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Lin Chen Jinsong Li Xiaoyi Dong Pan Zhang Yuhang Zang Zehui Chen Haodong Duan Jiaqi Wang Yu Qiao Dahua Lin et al. 2024b. Are We on the Right Way for Evaluating Large Vision-Language Models? arXiv preprint arXiv:2403.20330 (2024).","DOI":"10.52202\/079017-0850"},{"key":"e_1_3_2_1_5_1","volume-title":"Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward. arXiv preprint arXiv:2504.16727","author":"Fan Zhiyuan","year":"2025","unstructured":"Zhiyuan Fan, Yumeng Wang, Sandeep Polisetty, and Yi R Fung. 2025. Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward. arXiv preprint arXiv:2504.16727 (2025)."},{"key":"e_1_3_2_1_6_1","volume-title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models. arXiv preprint arXiv:2306.13394","author":"Fu Chaoyou","year":"2024","unstructured":"Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, et al., 2024. MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models. arXiv preprint arXiv:2306.13394 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"V105","author":"Geetha AV","year":"2024","unstructured":"AV Geetha, T Mala, D Priyanka, and E Uma. 2024. Multimodal Emotion Recognition with deep learning: advancements, challenges, and future directions. Information Fusion, V105 (2024), 102218."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3617592","article-title":"Deep learning approaches on image captioning: A review","volume":"56","author":"Ghandi Taraneh","year":"2023","unstructured":"Taraneh Ghandi, Hamidreza Pourreza, and Hamidreza Mahyar. 2023. Deep learning approaches on image captioning: A review. Comput. Surveys, V56, 3 (2023), 1-39.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500830"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"e_1_3_2_1_12_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=F5R0lG74Tu","author":"Huang Yue","year":"2025","unstructured":"Yue Huang, Siyuan Wu, Chujie Gao, Dongping Chen, Qihui Zhang, Yao Wan, Tianyi Zhou, Chaowei Xiao, Jianfeng Gao, Lichao Sun, and Xiangliang Zhang. 2025. DataGen: Unified Synthetic Dataset Generation via Large Language Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=F5R0lG74Tu"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_14_1","unstructured":"Black Forest Labs. 2023. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_1_15_1","volume-title":"Aligning text-to-image models using human feedback. arXiv preprint arXiv:2302.12192","author":"Lee Kimin","year":"2023","unstructured":"Kimin Lee, Hao Liu, Moonkyung Ryu, Olivia Watkins, Yuqing Du, Craig Boutilier, Pieter Abbeel, Mohammad Ghavamzadeh, and Shixiang Shane Gu. 2023. Aligning text-to-image models using human feedback. arXiv preprint arXiv:2302.12192 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"SEED-Bench-2: Benchmarking Multimodal Large Language Models. arXiv preprint arXiv:2311.17092","author":"Li Bohao","year":"2023","unstructured":"Bohao Li, Yuying Ge, Yixiao Ge, Guangzhi Wang, Rui Wang, Ruimao Zhang, and Ying Shan. 2023a. SEED-Bench-2: Benchmarking Multimodal Large Language Models. arXiv preprint arXiv:2311.17092 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension. arXiv preprint arXiv:2307.16125","author":"Li Bohao","year":"2023","unstructured":"Bohao Li, Rui Wang, Guangzhi Wang, Yuying Ge, Yixiao Ge, and Ying Shan. 2023b. SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension. arXiv preprint arXiv:2307.16125 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Preference leakage: A contamination problem in llm-as-a-judge. arXiv preprint arXiv:2502.01534","author":"Li Dawei","year":"2025","unstructured":"Dawei Li, Renliang Sun, Yue Huang, Ming Zhong, Bohan Jiang, Jiawei Han, Xiangliang Zhang, Wei Wang, and Huan Liu. 2025. Preference leakage: A contamination problem in llm-as-a-judge. arXiv preprint arXiv:2502.01534 (2025)."},{"key":"e_1_3_2_1_19_1","volume-title":"Percy Liang, and Tatsunori Hashimoto.","author":"Li Xiang Lisa","year":"2024","unstructured":"Xiang Lisa Li, Evan Zheran Liu, Percy Liang, and Tatsunori Hashimoto. 2024. AutoBencher: Creating Salient, Novel, Difficult Datasets for Language Models. arXiv preprint arXiv:2407.08351 (2024)."},{"key":"e_1_3_2_1_20_1","first-page":"740","volume-title":"Zurich","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740-755."},{"key":"e_1_3_2_1_21_1","volume-title":"V36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024a. Visual instruction tuning. Advances in neural information processing systems, V36 (2024)."},{"key":"e_1_3_2_1_22_1","volume-title":"Best Practices and Lessons Learned on Synthetic Data. In First Conference on Language Modeling.","author":"Liu Ruibo","year":"2024","unstructured":"Ruibo Liu, Jerry Wei, Fangyu Liu, Chenglei Si, Yanzhe Zhang, Jinmeng Rao, Steven Zheng, Daiyi Peng, Diyi Yang, Denny Zhou, et al., 2024b. Best Practices and Lessons Learned on Synthetic Data. In First Conference on Language Modeling."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Lin Long Rui Wang Ruixuan Xiao Junbo Zhao Xiao Ding Gang Chen and Haobo Wang. 2024. On LLMs-Driven Synthetic Data Generation Curation and Evaluation: A Survey. In ACL (Findings).","DOI":"10.18653\/v1\/2024.findings-acl.658"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14156831"},{"key":"e_1_3_2_1_26_1","volume-title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models. arXiv preprint arXiv:2408.02718","author":"Meng Fanqing","year":"2024","unstructured":"Fanqing Meng, Jin Wang, Chuanhao Li, Quanfeng Lu, Hao Tian, Jiaqi Liao, Xizhou Zhu, Jifeng Dai, Yu Qiao, Ping Luo, and Wenqi Shao. 2024. MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models. arXiv preprint arXiv:2408.02718 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Qin Yujia","year":"2023","unstructured":"Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, et al., 2023. ToolLLM: Facilitating Large Language Models to Master 16000 Real-world APIs. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_28_1","volume-title":"Semantic memory","author":"Quillian M Ross","unstructured":"M Ross Quillian. 1966. Semantic memory. Air Force Cambridge Research Laboratories, Office of Aerospace Research \u2026."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision V115 (2015) 211-252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2621980"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03359-y"},{"key":"e_1_3_2_1_32_1","volume-title":"UniGen: A Unified Framework for Textual Dataset Generation Using Large Language Models. arXiv preprint arXiv:2406.18966","author":"Wu Siyuan","year":"2024","unstructured":"Siyuan Wu, Yue Huang, Chujie Gao, Dongping Chen, Qihui Zhang, Yao Wan, Tianyi Zhou, Xiangliang Zhang, Jianfeng Gao, Chaowei Xiao, and Lichao Sun. 2024. UniGen: A Unified Framework for Textual Dataset Generation Using Large Language Models. arXiv preprint arXiv:2406.18966 (2024)."},{"key":"e_1_3_2_1_33_1","volume-title":"Mme-unify: A comprehensive benchmark for unified multimodal understanding and generation models. arXiv preprint arXiv:2504.03641","author":"Xie Wulin","year":"2025","unstructured":"Wulin Xie, Yi-Fan Zhang, Chaoyou Fu, Yang Shi, Bingyan Nie, Hongkai Chen, Zhang Zhang, Liang Wang, and Tieniu Tan. 2025. Mme-unify: A comprehensive benchmark for unified multimodal understanding and generation models. arXiv preprint arXiv:2504.03641 (2025)."},{"key":"e_1_3_2_1_34_1","volume-title":"Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models","author":"Xu Peng","year":"2024","unstructured":"Peng Xu, Wenqi Shao, Kaipeng Zhang, Peng Gao, Shuo Liu, Meng Lei, Fanqing Meng, Siyuan Huang, Yu Qiao, and Ping Luo. 2024a. Lvlm-ehub: A comprehensive evaluation benchmark for large vision-language models. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Benchmarking benchmark leakage in large language models. arXiv preprint arXiv:2404.18824","author":"Xu Ruijie","year":"2024","unstructured":"Ruijie Xu, Zengzhi Wang, Run-Ze Fan, and Pengfei Liu. 2024b. Benchmarking benchmark leakage in large language models. arXiv preprint arXiv:2404.18824 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Yang Yue","unstructured":"Yue Yang, Shuibo Zhang, Kaipeng Zhang, Yi Bin, Yu Wang, Ping Luo, and Wenqi Shao. [n.d.]. Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_37_1","volume-title":"LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models. arXiv preprint arXiv:2505.15616","author":"Yao Ruilin","year":"2025","unstructured":"Ruilin Yao, Bo Zhang, Jirui Huang, Xinwei Long, Yifang Zhang, Tianyu Zou, Yufei Wu, Shichao Su, Yifan Xu, Wenxi Zeng, et al., 2025. LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models. arXiv preprint arXiv:2505.15616 (2025)."},{"key":"e_1_3_2_1_38_1","unstructured":"Jiayi Ye Yanbo Wang Yue Huang Dongping Chen Qihui Zhang Nuno Moniz Tian Gao Werner Geyer Chao Huang Pin-Yu Chen et al. 2024. Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge. arXiv preprint arXiv:2410.02736 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. Advances in Neural Information Processing Systems, V36","author":"Yin Zhenfei","year":"2024","unstructured":"Zhenfei Yin, Jiong Wang, Jianjian Cao, Zhelun Shi, Dingning Liu, Mukai Li, Xiaoshui Huang, Zhiyong Wang, Lu Sheng, Lei Bai, et al., 2024. Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark. Advances in Neural Information Processing Systems, V36 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI. In Forty-first International Conference on Machine Learning.","author":"Ying Kaining","year":"2024","unstructured":"Kaining Ying, Fanqing Meng, Jin Wang, Zhiqian Li, Han Lin, Yue Yang, Hao Zhang, Wenbo Zhang, Yuqi Lin, Shuo Liu, et al., 2024. MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_41_1","volume-title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities. In Forty-first International Conference on Machine Learning.","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. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_42_1","volume-title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities. arXiv preprint arXiv:2408.00765","author":"Yu Weihao","year":"2024","unstructured":"Weihao Yu, Zhengyuan Yang, Linfeng Ren, Linjie Li, Jianfeng Wang, Kevin Lin, Chung-Ching Lin, Zicheng Liu, Lijuan Wang, and Xinchao Wang. 2024. MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities. arXiv preprint arXiv:2408.00765 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"e_1_3_2_1_44_1","volume-title":"V7","author":"Zar Jerrold H","year":"2005","unstructured":"Jerrold H Zar. 2005. Spearman rank correlation. Encyclopedia of biostatistics, V7 (2005)."},{"key":"e_1_3_2_1_45_1","volume-title":"Task Me Anything. arXiv preprint arXiv:2406.11775","author":"Zhang Jieyu","year":"2024","unstructured":"Jieyu Zhang, Weikai Huang, Zixian Ma, Oscar Michel, Dong He, Tanmay Gupta, Wei-Chiu Ma, Ali Farhadi, Aniruddha Kembhavi, and Ranjay Krishna. 2024a. Task Me Anything. arXiv preprint arXiv:2406.11775 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Debiasing Multimodal Large Language Models. arXiv preprint arXiv:2403.05262","author":"Zhang Yi-Fan","year":"2024","unstructured":"Yi-Fan Zhang, Weichen Yu, Qingsong Wen, Xue Wang, Zhang Zhang, Liang Wang, Rong Jin, and Tieniu Tan. 2024b. Debiasing Multimodal Large Language Models. arXiv preprint arXiv:2403.05262 (2024)."},{"key":"e_1_3_2_1_47_1","volume-title":"PuzzleBench: A Fully Dynamic Evaluation Framework for Large Multimodal Models on Puzzle Solving. arXiv preprint arXiv:2504.10885","author":"Zhang Zeyu","year":"2025","unstructured":"Zeyu Zhang, Zijian Chen, Zicheng Zhang, Yuze Sun, Yuan Tian, Ziheng Jia, Chunyi Li, Xiaohong Liu, Xiongkuo Min, and Guangtao Zhai. 2025. PuzzleBench: A Fully Dynamic Evaluation Framework for Large Multimodal Models on Puzzle Solving. arXiv preprint arXiv:2504.10885 (2025)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems V36 (2023) 46595-46623.","DOI":"10.52202\/075280-2020"},{"key":"e_1_3_2_1_49_1","volume-title":"MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis. arXiv preprint arXiv:2411.11235","author":"Zhou Yingjie","year":"2024","unstructured":"Yingjie Zhou, Zicheng Zhang, Jiezhang Cao, Jun Jia, Yanwei Jiang, Farong Wen, Xiaohong Liu, Xiongkuo Min, and Guangtao Zhai. 2024. MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis. arXiv preprint arXiv:2411.11235 (2024)."},{"key":"e_1_3_2_1_50_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Zhu Kaijie","year":"2023","unstructured":"Kaijie Zhu, Jiaao Chen, Jindong Wang, Neil Zhenqiang Gong, Diyi Yang, and Xing Xie. 2023. Dyval: Dynamic evaluation of large language models for reasoning tasks. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_51_1","volume-title":"Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=DwTgy1hXXo","author":"Zhu Kaijie","year":"2024","unstructured":"Kaijie Zhu, Jindong Wang, Qinlin Zhao, Ruochen Xu, and Xing Xie. 2024. Dynamic Evaluation of Large Language Models by Meta Probing Agents. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=DwTgy1hXXo"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:20:10Z","timestamp":1786065610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817506"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":52,"alternative-id":["10.1145\/3770855.3817506","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817506","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}