{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:41:10Z","timestamp":1784310070284,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"name":"Young Elite Scientists Sponsorship Program by CAST","award":["2023QNRC001"],"award-info":[{"award-number":["2023QNRC001"]}]},{"name":"National Key R&D Program of China","award":["2023YFB4502200"],"award-info":[{"award-number":["2023YFB4502200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376024, 62325405, 62104128, 62203257, 62031017, 62406159, U21B2031"],"award-info":[{"award-number":["62376024, 62325405, 62104128, 62203257, 62031017, 62406159, U21B2031"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Tsinghua University Initiative Scientific Research Program"},{"name":"Beijing National Research Center for Information Science, Technology","award":["BNR2024TD03001"],"award-info":[{"award-number":["BNR2024TD03001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755118","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"3555-3564","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6049-603X","authenticated-orcid":false,"given":"Yudong","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China and Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-5647","authenticated-orcid":false,"given":"Ruobing","family":"Xie","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3222-0901","authenticated-orcid":false,"given":"Xingwu","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2143-3329","authenticated-orcid":false,"given":"Yiqing","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2040-7938","authenticated-orcid":false,"given":"Jiansheng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5151-4222","authenticated-orcid":false,"given":"Zhanhui","family":"Kang","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, Guandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6713-1638","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6108-5157","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, 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","unstructured":"Ayush Agrawal Mirac Suzgun Lester Mackey and Adam Kalai. 2024. Do Language Models Know When They're Hallucinating References?. In EACL (Findings)."},{"key":"e_1_3_2_1_2_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al., 2022. Flamingo: a visual language model for few-shot learning. NeurIPS, Vol. 35 (2022), 23716-23736.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_3_1","volume-title":"Hallucination Detection in LLMs: Fast and Memory-Efficient Finetuned Models. arXiv preprint arXiv:2409.02976","author":"Arteaga Gabriel Y","year":"2024","unstructured":"Gabriel Y Arteaga, Thomas B Sch\u00f6n, and Nicolas Pielawski. 2024. Hallucination Detection in LLMs: Fast and Memory-Efficient Finetuned Models. arXiv preprint arXiv:2409.02976 (2024)."},{"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","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_6_1","volume-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478","author":"Chen Jun","year":"2023","unstructured":"Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, and Mohamed Elhoseiny. 2023. Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al., 2024. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198."},{"key":"e_1_3_2_1_8_1","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys.org (accessed","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E Gonzalez, et al., 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys.org (accessed 14 April 2023), Vol. 2, 3 (2023), 6."},{"key":"e_1_3_2_1_9_1","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung Hyung Won","year":"2024","unstructured":"Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al., 2024. Scaling instruction-finetuned language models. Journal of Machine Learning Research, Vol. 25, 70 (2024), 1-53.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_10_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2024","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2024. Instructblip: Towards general-purpose vision-language models with instruction tuning. NeurIPS, Vol. 36 (2024)."},{"key":"e_1_3_2_1_11_1","first-page":"19358","article-title":"Eva: Exploring the limits of masked visual representation learning at scale","author":"Fang Yuxin","year":"2023","unstructured":"Yuxin Fang, Wen Wang, Binhui Xie, Quan Sun, Ledell Wu, Xinggang Wang, Tiejun Huang, Xinlong Wang, and Yue Cao. 2023. Eva: Exploring the limits of masked visual representation learning at scale. In CVPR. 19358-19369.","journal-title":"CVPR."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07421-0"},{"key":"e_1_3_2_1_13_1","unstructured":"Peng Gao Jiaming Han Renrui Zhang Ziyi Lin Shijie Geng Aojun Zhou Wei Zhang Pan Lu Conghui He Xiangyu Yue et al. 2023. Llama-adapter v2: Parameter-efficient visual instruction model. arXiv preprint arXiv:2304.15010 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"e_1_3_2_1_15_1","volume-title":"CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following.","author":"Hu Hongyu","year":"2023","unstructured":"Hongyu Hu, Jiyuan Zhang, Minyi Zhao, and Zhenbang Sun. 2023. CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following."},{"key":"e_1_3_2_1_16_1","volume-title":"Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, and Nenghai Yu.","author":"Huang Qidong","year":"2023","unstructured":"Qidong Huang, Xiaoyi Dong, Pan zhang, Bin Wang, Conghui He, Jiaqi Wang, Dahua Lin, Weiming Zhang, and Nenghai Yu. 2023. OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation. arXiv preprint arXiv:2311.17911 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Vcoder: Versatile vision encoders for multimodal large language models. arXiv preprint arXiv:2312.14233","author":"Jain Jitesh","year":"2023","unstructured":"Jitesh Jain, Jianwei Yang, and Humphrey Shi. 2023. Vcoder: Versatile vision encoders for multimodal large language models. arXiv preprint arXiv:2312.14233 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Hallucination augmented contrastive learning for multimodal large language model. arXiv preprint arXiv:2312.06968","author":"Jiang Chaoya","year":"2023","unstructured":"Chaoya Jiang, Haiyang Xu, Mengfan Dong, Jiaxing Chen, Wei Ye, Ming Yan, Qinghao Ye, Ji Zhang, Fei Huang, and Shikun Zhang. 2023. Hallucination augmented contrastive learning for multimodal large language model. arXiv preprint arXiv:2312.06968 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Faithscore: Evaluating hallucinations in large vision-language models. arXiv preprint arXiv:2311.01477","author":"Jing Liqiang","year":"2023","unstructured":"Liqiang Jing, Ruosen Li, Yunmo Chen, Mengzhao Jia, and Xinya Du. 2023. Faithscore: Evaluating hallucinations in large vision-language models. arXiv preprint arXiv:2311.01477 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Mitigating object hallucinations in large vision-language models through visual contrastive decoding. arXiv preprint arXiv:2311.16922","author":"Leng Sicong","year":"2023","unstructured":"Sicong Leng, Hang Zhang, Guanzheng Chen, Xin Li, Shijian Lu, Chunyan Miao, and Lidong Bing. 2023. Mitigating object hallucinations in large vision-language models through visual contrastive decoding. arXiv preprint arXiv:2311.16922 (2023)."},{"key":"e_1_3_2_1_21_1","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023b. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In ICML. PMLR, 19730-19742.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_22_1","volume-title":"Evaluating Object Hallucination in Large Vision-Language Models. In The 2023 Conference on Empirical Methods in Natural Language Processing.","author":"Li Yifan","year":"2023","unstructured":"Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Xin Zhao, and Ji-Rong Wen. 2023a. Evaluating Object Hallucination in Large Vision-Language Models. In The 2023 Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_1_23_1","volume-title":"Monkey: Image resolution and text label are important things for large multi-modal models. arXiv preprint arXiv:2311.06607","author":"Li Zhang","year":"2023","unstructured":"Zhang Li, Biao Yang, Qiang Liu, Zhiyin Ma, Shuo Zhang, Jingxu Yang, Yabo Sun, Yuliang Liu, and Xiang Bai. 2023c. Monkey: Image resolution and text label are important things for large multi-modal models. arXiv preprint arXiv:2311.06607 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Microsoft coco: Common objects in context","author":"Lin Tsung-Yi","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 ECCV. Springer, 740-755."},{"key":"e_1_3_2_1_25_1","unstructured":"Fuxiao Liu Kevin Lin Linjie Li Jianfeng Wang Yaser Yacoob and Lijuan Wang. 2023b. Mitigating hallucination in large multi-modal models via robust instruction tuning. In ICLR."},{"key":"e_1_3_2_1_26_1","volume-title":"Improved Baselines with Visual Instruction Tuning. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following.","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Yuheng Li, and Yong Jae Lee. 2023a. Improved Baselines with Visual Instruction Tuning. In NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following."},{"key":"e_1_3_2_1_27_1","volume-title":"NeurIPS","volume":"36","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024a. Visual instruction tuning. NeurIPS, Vol. 36 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"European Conference on Computer Vision. Springer, 125-140","author":"Liu Shi","year":"2024","unstructured":"Shi Liu, Kecheng Zheng, and Wei Chen. 2024b. Paying more attention to image: A training-free method for alleviating hallucination in lvlms. In European Conference on Computer Vision. Springer, 125-140."},{"key":"e_1_3_2_1_29_1","volume-title":"Negative object presence evaluation (nope) to measure object hallucination in vision-language models. arXiv preprint arXiv:2310.05338","author":"Lovenia Holy","year":"2023","unstructured":"Holy Lovenia, Wenliang Dai, Samuel Cahyawijaya, Ziwei Ji, and Pascale Fung. 2023. Negative object presence evaluation (nope) to measure object hallucination in vision-language models. arXiv preprint arXiv:2310.05338 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Evaluation and mitigation of agnosia in multimodal large language models. arXiv preprint arXiv:2309.04041","author":"Lu Jiaying","year":"2023","unstructured":"Jiaying Lu, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Baochen Sun, Carl Yang, and Jie Yang. 2023. Evaluation and mitigation of agnosia in multimodal large language models. arXiv preprint arXiv:2309.04041 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Cand\u00e8s, and Tatsunori Hashimoto.","author":"Muennighoff Niklas","year":"2025","unstructured":"Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Cand\u00e8s, and Tatsunori Hashimoto. 2025. s1: Simple test-time scaling. arXiv preprint arXiv:2501.19393 (2025)."},{"key":"e_1_3_2_1_32_1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","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, et al., 2021. Learning transferable visual models from natural language supervision. In ICML. PMLR, 8748-8763.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_33_1","volume-title":"Kaylee Burns, Trevor Darrell, and Kate Saenko.","author":"Rohrbach Anna","year":"2018","unstructured":"Anna Rohrbach, Lisa Anne Hendricks, Kaylee Burns, Trevor Darrell, and Kate Saenko. 2018. Object hallucination in image captioning. arXiv preprint arXiv:1809.02156 (2018)."},{"key":"e_1_3_2_1_34_1","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon Nisan","year":"2020","unstructured":"Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learning to summarize with human feedback. NeurIPS, Vol. 33 (2020), 3008-3021.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_35_1","unstructured":"Zhiqing Sun Sheng Shen Shengcao Cao Haotian Liu Chunyuan Li Yikang Shen Chuang Gan Liang-Yan Gui Yu-Xiong Wang Yiming Yang et al. 2023. Aligning large multimodal models with factually augmented rlhf. arXiv preprint arXiv:2309.14525 (2023)."},{"key":"e_1_3_2_1_36_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_37_1","volume-title":"An llm-free multi-dimensional benchmark for mllms hallucination evaluation. arXiv preprint arXiv:2311.07397","author":"Wang Junyang","year":"2023","unstructured":"Junyang Wang, Yuhang Wang, Guohai Xu, Jing Zhang, Yukai Gu, Haitao Jia, Ming Yan, Ji Zhang, and Jitao Sang. 2023a. An llm-free multi-dimensional benchmark for mllms hallucination evaluation. arXiv preprint arXiv:2311.07397 (2023)."},{"key":"e_1_3_2_1_38_1","unstructured":"Junyang Wang Yiyang Zhou Guohai Xu Pengcheng Shi Chenlin Zhao Haiyang Xu Qinghao Ye Ming Yan Ji Zhang Jihua Zhu et al. 2023b. Evaluation and analysis of hallucination in large vision-language models. arXiv preprint arXiv:2308.15126 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Xintong Wang Jingheng Pan Liang Ding and Chris Biemann. 2024. Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding. In ACL (Findings).","DOI":"10.18653\/v1\/2024.findings-acl.937"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00563"},{"key":"e_1_3_2_1_41_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_1_42_1","volume-title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity. In ICLR.","author":"You Haoxuan","year":"2023","unstructured":"Haoxuan You, Haotian Zhang, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao, Shih-Fu Chang, and Yinfei Yang. 2023. Ferret: Refer and Ground Anything Anywhere at Any Granularity. In ICLR."},{"key":"e_1_3_2_1_43_1","volume-title":"Halle-switch: Rethinking and controlling object existence hallucinations in large vision language models for detailed caption. arXiv preprint arXiv:2310.01779","author":"Zhai Bohan","year":"2023","unstructured":"Bohan Zhai, Shijia Yang, Xiangchen Zhao, Chenfeng Xu, Sheng Shen, Dongdi Zhao, Kurt Keutzer, Manling Li, Tan Yan, and Xiangjun Fan. 2023. Halle-switch: Rethinking and controlling object existence hallucinations in large vision language models for detailed caption. arXiv preprint arXiv:2310.01779 (2023)."},{"key":"e_1_3_2_1_44_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al., 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i21.34425"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685510"},{"key":"e_1_3_2_1_47_1","volume-title":"Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs. arXiv preprint arXiv:2506.01064","author":"Zhang Yudong","year":"2025","unstructured":"Yudong Zhang, Ruobing Xie, Yiqing Huang, Jiansheng Chen, Xingwu Sun, Zhanhui Kang, Di Wang, and Yu Wang. 2025b. Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs. arXiv preprint arXiv:2506.01064 (2025)."},{"key":"e_1_3_2_1_48_1","volume-title":"The Security Threat of Compressed Projectors in Large Vision-Language Models. arXiv preprint arXiv:2506.00534","author":"Zhang Yudong","year":"2025","unstructured":"Yudong Zhang, Ruobing Xie, Xingwu Sun, Jiansheng Chen, Zhanhui Kang, Di Wang, and Yu Wang. 2025c. The Security Threat of Compressed Projectors in Large Vision-Language Models. arXiv preprint arXiv:2506.00534 (2025)."},{"key":"e_1_3_2_1_49_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_50_1","volume-title":"Connector-S: A Survey of Connectors in Multi-modal Large Language Models. arXiv preprint arXiv:2502.11453","author":"Zhu Xun","year":"2025","unstructured":"Xun Zhu, Zheng Zhang, Xi Chen, Yiming Shi, Miao Li, and Ji Wu. 2025. Connector-S: A Survey of Connectors in Multi-modal Large Language Models. arXiv preprint arXiv:2502.11453 (2025)."},{"key":"e_1_3_2_1_51_1","volume-title":"Segment everything everywhere all at once. Advances in neural information processing systems","author":"Zou Xueyan","year":"2023","unstructured":"Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li, Linjie Li, Jianfeng Wang, Lijuan Wang, Jianfeng Gao, and Yong Jae Lee. 2023. Segment everything everywhere all at once. Advances in neural information processing systems, Vol. 36 (2023), 19769-19782."}],"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\/3746027.3755118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:07:12Z","timestamp":1765310832000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":51,"alternative-id":["10.1145\/3746027.3755118","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755118","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"}}]}}