{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:51:06Z","timestamp":1765309866585,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","award":["AISG-NMLP-2024-002"],"award-info":[{"award-number":["AISG-NMLP-2024-002"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B20181"],"award-info":[{"award-number":["U24B20181"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Pilot Program for Basic Research - Fudan University","award":["21TQ1400100 (22TQ018)"],"award-info":[{"award-number":["21TQ1400100 (22TQ018)"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754805","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:17Z","timestamp":1761375257000},"page":"5355-5364","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["<i>MCM-DPO<\/i>\n                    : Multifaceted Cross-Modal Direct Preference Optimization for Alt-text Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0370-1238","authenticated-orcid":false,"given":"Jinlan","family":"Fu","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5740-6744","authenticated-orcid":false,"given":"Shenzhen","family":"Huangfu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3026-6347","authenticated-orcid":false,"given":"Hao","family":"Fei","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4004-8564","authenticated-orcid":false,"given":"Yichong","family":"Huang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0217-2469","authenticated-orcid":false,"given":"Xiaoyu","family":"Shen","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7163-5247","authenticated-orcid":false,"given":"Xipeng","family":"Qiu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6565-7511","authenticated-orcid":false,"given":"See-Kiong","family":"Ng","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Artificial Intelligence and Statistics","volume":"4455","author":"Azar Mohammad Gheshlaghi","year":"2024","unstructured":"Mohammad Gheshlaghi Azar, Zhaohan Daniel Guo, Bilal Piot, R\u00e9mi Munos, Mark Rowland, Michal Valko, and Daniele Calandriello. 2024. A General Theoretical Paradigm to Understand Learning from Human Preferences. In International Conference on Artificial Intelligence and Statistics, 2-4 May 2024, Palau de Congressos, Valencia, Spain (Proceedings of Machine Learning Research, Vol. 238), Sanjoy Dasgupta, Stephan Mandt, and Yingzhen Li (Eds.). PMLR, 4447-4455. https:\/\/proceedings.mlr.press\/v238\/gheshlaghi-azar24a.html"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.12966"},{"key":"e_1_3_2_1_3_1","volume-title":"Umayangani Wickramaratne, and Humphrey O Obie.","author":"Belle Aspen","year":"2022","unstructured":"Aspen Belle, Vanessa Goh, Akshay Kumar, Richard Pranjatno, Pui Man Yip, Umayangani Wickramaratne, and Humphrey O Obie. 2022. Alt-Texify: A Pipeline to Generate Alt-text from SVG Visualizations.. In ENASE. 275-281."},{"key":"e_1_3_2_1_4_1","volume-title":"Gregory P Meyer, Yuning Chai, Dennis Park, and Yong Jae Lee.","author":"Cai Mu","year":"2023","unstructured":"Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P Meyer, Yuning Chai, Dennis Park, and Yong Jae Lee. 2023. Making large multimodal models understand arbitrary visual prompts. arXiv preprint arXiv:2312.00784 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3544796"},{"key":"e_1_3_2_1_6_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven C. H. Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven C. H. Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"volume-title":"CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs. In The Thirteenth International Conference on Learning Representations.","author":"Fu Jinlan","key":"e_1_3_2_1_8_1","unstructured":"Jinlan Fu, Hao Fei, Xiaoyu Shen, Bryan Hooi, Xipeng Qiu, See-Kiong Ng, et al., [n.d.]. CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376728"},{"volume-title":"https:\/\/deepmind.google\/technologies\/gemini\/flash\/","year":"2024","key":"e_1_3_2_1_10_1","unstructured":"Google. 2024. Gemmi. (2024). https:\/\/deepmind.google\/technologies\/gemini\/flash\/"},{"key":"e_1_3_2_1_11_1","volume-title":"Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"e_1_3_2_1_13_1","volume-title":"Minicpm: Unveiling the potential of small language models with scalable training strategies. arXiv preprint arXiv:2404.06395","author":"Hu Shengding","year":"2024","unstructured":"Shengding Hu, Yuge Tu, Xu Han, Chaoqun He, Ganqu Cui, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Weilin Zhao, et al., 2024. Minicpm: Unveiling the potential of small language models with scalable training strategies. arXiv preprint arXiv:2404.06395 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.EMNLP-MAIN.443"},{"key":"e_1_3_2_1_15_1","volume-title":"Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency. arXiv preprint arXiv:2505.14405","author":"Liang Jiafeng","year":"2025","unstructured":"Jiafeng Liang, Shixin Jiang, Xuan Dong, Ning Wang, Zheng Chu, Hui Su, Jinlan Fu, Ming Liu, See-Kiong Ng, and Bing Qin. 2025. Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency. arXiv preprint arXiv:2505.14405 (2025)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"e_1_3_2_1_17_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2023. Improved Baselines with Visual Instruction Tuning. arXiv:2310.03744 [cs.CV]"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.14734"},{"key":"e_1_3_2_1_19_1","volume-title":"Context-Aware Image Descriptions for Web Accessibility. arXiv preprint arXiv:2409.03054","author":"Mohanbabu Ananya Gubbi","year":"2024","unstructured":"Ananya Gubbi Mohanbabu and Amy Pavel. 2024. Context-Aware Image Descriptions for Web Accessibility. arXiv preprint arXiv:2409.03054 (2024)."},{"key":"e_1_3_2_1_20_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR Vol. abs\/2303.08774 (2023)."},{"key":"e_1_3_2_1_21_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_22_1","volume-title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization. CoRR","author":"Pi Renjie","year":"2024","unstructured":"Renjie Pi, Tianyang Han, Wei Xiong, Jipeng Zhang, Runtao Liu, Rui Pan, and Tong Zhang. 2024. Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization. CoRR, Vol. abs\/2403.08730 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","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 International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_24_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Rafailov Rafael","year":"2024","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2024. Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_25_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_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.16681"},{"key":"e_1_3_2_1_27_1","volume-title":"Mitigating Object Hallucination via Data Augmented Contrastive Tuning. CoRR","author":"Sarkar Pritam","year":"1865","unstructured":"Pritam Sarkar, Sayna Ebrahimi, Ali Etemad, Ahmad Beirami, Sercan \u00d6. Arik, and Tomas Pfister. 2024. Mitigating Object Hallucination via Data Augmented Contrastive Tuning. CoRR, Vol. abs\/2405.18654 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Alt-Text with Context: Improving Accessibility for Images on Twitter. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Srivatsan Nikita","year":"2024","unstructured":"Nikita Srivatsan, Sof\u00eda Samaniego, Omar Florez, and Taylor Berg-Kirkpatrick. 2024. Alt-Text with Context: Improving Accessibility for Images on Twitter. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=97Dl82avFs"},{"key":"e_1_3_2_1_29_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_30_1","volume-title":"Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818","author":"Team Chameleon","year":"2024","unstructured":"Chameleon Team. 2024a. Chameleon: Mixed-modal early-fusion foundation models. arXiv preprint arXiv:2405.09818 (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"https:\/\/deepmind.google\/technologies\/gemini\/flash\/","author":"Team Pinterest","year":"2024","unstructured":"Pinterest Team. 2024b. Pinterest. (2024). https:\/\/deepmind.google\/technologies\/gemini\/flash\/"},{"key":"e_1_3_2_1_32_1","volume-title":"https:\/\/deepmind.google\/technologies\/gemini\/flash\/","author":"Team Twitter","year":"2024","unstructured":"Twitter Team. 2024c. Twitter. (2024). https:\/\/deepmind.google\/technologies\/gemini\/flash\/"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_34_1","first-page":"3156","volume-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Vinyals Oriol","year":"2014","unstructured":"Oriol Vinyals, Alexander Toshev, Samy Bengio, and D. Erhan. 2014. Show and tell: A neural image caption generator. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014), 3156-3164. https:\/\/api.semanticscholar.org\/CorpusID:1169492"},{"key":"e_1_3_2_1_35_1","volume-title":"mDPO: Conditional Preference Optimization for Multimodal Large Language Models. arXiv preprint arXiv:2406.11839","author":"Wang Fei","year":"2024","unstructured":"Fei Wang, Wenxuan Zhou, James Y Huang, Nan Xu, Sheng Zhang, Hoifung Poon, and Muhao Chen. 2024. mDPO: Conditional Preference Optimization for Multimodal Large Language Models. arXiv preprint arXiv:2406.11839 (2024)."},{"key":"e_1_3_2_1_36_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. 2023. An llm-free multi-dimensional benchmark for mllms hallucination evaluation. arXiv preprint arXiv:2311.07397 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning. arXiv preprint arXiv:2503.10480","author":"Wang Siyin","year":"2025","unstructured":"Siyin Wang, Zhaoye Fei, Qinyuan Cheng, Shiduo Zhang, Panpan Cai, Jinlan Fu, and Xipeng Qiu. 2025. World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning. arXiv preprint arXiv:2503.10480 (2025)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998364"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2405.00675"},{"key":"e_1_3_2_1_40_1","volume-title":"Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Xu Haoran","year":"2024","unstructured":"Haoran Xu, Amr Sharaf, Yunmo Chen, Weiting Tan, Lingfeng Shen, Benjamin Van Durme, Kenton Murray, and Young Jin Kim. 2024. Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=51iwkioZpn"},{"key":"e_1_3_2_1_41_1","volume-title":"Attend and Tell: Neural Image Caption Generation with Visual Attention. In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"2057","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. In Proceedings of the 32nd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 37), Francis Bach and David Blei (Eds.). PMLR, Lille, France, 2048-2057. https:\/\/proceedings.mlr.press\/v37\/xuc15.html"},{"key":"e_1_3_2_1_42_1","volume-title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone. arXiv preprint 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, Qianyu Chen, Huarong Zhou, Zhensheng Zou, Haoye Zhang, Shengding Hu, Zhi Zheng, Jie Zhou, Jie Cai, Xu Han, Guoyang Zeng, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2024. MiniCPM-V: A GPT-4V Level MLLM on Your Phone. arXiv preprint 2408.01800 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"e_1_3_2_1_44_1","volume-title":"Self-Rewarding Language Models. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Yuan Weizhe","year":"2024","unstructured":"Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, and Jason Weston. 2024. Self-Rewarding Language Models. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=0NphYCmgua"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.475"},{"key":"e_1_3_2_1_46_1","volume-title":"Beyond one-preference-for-all: Multi-objective direct preference optimization. arXiv preprint arXiv:2310.03708","author":"Zhou Zhanhui","year":"2023","unstructured":"Zhanhui Zhou, Jie Liu, Chao Yang, Jing Shao, Yu Liu, Xiangyu Yue, Wanli Ouyang, and Yu Qiao. 2023. Beyond one-preference-for-all: Multi-objective direct preference optimization. arXiv preprint arXiv:2310.03708 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754805","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:47:00Z","timestamp":1765309620000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754805"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":46,"alternative-id":["10.1145\/3746027.3754805","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754805","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"}}]}}