{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:07:02Z","timestamp":1765339622691,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0117103"],"award-info":[{"award-number":["2022ZD0117103"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Outstanding Youth Science Foundation of Shaanxi Province","award":["2025JC-JCQN-083"],"award-info":[{"award-number":["2025JC-JCQN-083"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172222; 62302354"],"award-info":[{"award-number":["62172222; 62302354"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Shaanxi Province","award":["2025CY-YBXM-047; 2024GX-YBXM-039"],"award-info":[{"award-number":["2025CY-YBXM-047; 2024GX-YBXM-039"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["QTZX23084"],"award-info":[{"award-number":["QTZX23084"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754507","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:56:43Z","timestamp":1761371803000},"page":"2606-2615","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0382-2715","authenticated-orcid":false,"given":"Xiao","family":"Liang","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0759-7459","authenticated-orcid":false,"given":"Jiawei","family":"Hu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8027-4287","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2045-4822","authenticated-orcid":false,"given":"Zhi","family":"Ma","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8756-2027","authenticated-orcid":false,"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1890-7845","authenticated-orcid":false,"given":"Ronghan","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3410-9560","authenticated-orcid":false,"given":"Bo","family":"Wan","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6913-8604","authenticated-orcid":false,"given":"Quan","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"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":"Sam Ade Jacobs, and Ammar Ahmad Awan et al","author":"Abdin Marah","year":"2024","unstructured":"Marah Abdin, Sam Ade Jacobs, and Ammar Ahmad Awan et al., 2024. Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone. ArXiv, Vol. abs\/2404.14219 (2024). https:\/\/api.semanticscholar.org\/CorpusID:269293048"},{"key":"e_1_3_2_1_2_1","volume-title":"Tackeun Kim, and Edward Choi.","author":"Bae Seongsu","year":"2023","unstructured":"Seongsu Bae, Daeun Kyung, Jaehee Ryu, Eunbyeol Cho, Gyubok Lee, Sunjun Kweon, Jungwoo Oh, Lei Ji, Eric I-Chao Chang, Tackeun Kim, and Edward Choi. 2023. EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images. ArXiv, Vol. abs\/2310.18652 (2023). https:\/\/api.semanticscholar.org\/CorpusID:264590453"},{"key":"e_1_3_2_1_3_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_4_1","first-page":"12914","volume-title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023","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. ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023), 12914-12923. https:\/\/api.semanticscholar.org\/CorpusID:265551875"},{"key":"e_1_3_2_1_5_1","volume-title":"Xidong Wang, Ruifei Zhang, Zhenyang Cai, Ke Ji, Guangjun Yu, Xiang Wan, and Benyou Wang.","author":"Chen Junying","year":"2024","unstructured":"Junying Chen, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Hardy Chen, Xidong Wang, Ruifei Zhang, Zhenyang Cai, Ke Ji, Guangjun Yu, Xiang Wan, and Benyou Wang. 2024. HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale. arXiv:2406.19280 [cs.CV] https:\/\/arxiv.org\/abs\/2406.19280"},{"key":"e_1_3_2_1_6_1","volume-title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models. CoRR","author":"Chuang Yung-Sung","year":"2023","unstructured":"Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, and Pengcheng He. 2023. DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models. CoRR, Vol. abs\/2309.03883 (2023). arXiv:2309.03883 http:\/\/arxiv.org\/abs\/2309.03883"},{"key":"e_1_3_2_1_7_1","volume-title":"Biomedical Visual Instruction Tuning with Clinician Preference Alignment. Advances in neural information processing systems","author":"Cui Hejie","year":"2024","unstructured":"Hejie Cui, Lingjun Mao, Xin Liang, Jieyu Zhang, Hui Ren, Quanzheng Li, Xiang Li, and Carl Yang. 2024. Biomedical Visual Instruction Tuning with Clinician Preference Alignment. Advances in neural information processing systems, Vol. 37 (2024), 96449-96467. https:\/\/api.semanticscholar.org\/CorpusID:270619462"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2502.14560"},{"key":"e_1_3_2_1_9_1","volume-title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples. ArXiv","author":"Gao Chengqian","year":"2025","unstructured":"Chengqian Gao, Haonan Li, Liu Liu, Zeke Xie, Peilin Zhao, and Zhiqiang Xu. 2025. Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples. ArXiv, Vol. abs\/2502.09650 (2025). https:\/\/api.semanticscholar.org\/CorpusID:276394867"},{"key":"e_1_3_2_1_10_1","volume-title":"Arne Edward Michalson, Christian Bluethgen, Hyun Joo Shin, Curtis Langlotz, et al.","author":"Hein Dennis","year":"2024","unstructured":"Dennis Hein, Zhihong Chen, Sophie Ostmeier, Justin Xu, Maya Varma, Eduardo Pontes Reis, Arne Edward Michalson, Christian Bluethgen, Hyun Joo Shin, Curtis Langlotz, et al., 2024. Preference fine-tuning for factuality in Chest X-Ray interpretation models without human Feedback. arXiv preprint arXiv:2410.07025 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. ArXiv","author":"Hu J. Edward","year":"2021","unstructured":"J. Edward Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. ArXiv, Vol. abs\/2106.09685 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235458009"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599819"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"e_1_3_2_1_17_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Li Chunyuan","year":"2023","unstructured":"Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2023b. LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day. 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, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/5abcdf8ecdcacba028c6662789194572-Abstract-Datasets_and_Benchmarks.html"},{"key":"e_1_3_2_1_18_1","volume-title":"Contrastive Learning with Counterfactual Explanations for Radiology Report Generation. In European Conference on Computer Vision. https:\/\/api.semanticscholar.org\/CorpusID:271310426","author":"Li Mingjie","year":"2024","unstructured":"Mingjie Li, Haokun Lin, Liang Qiu, Xiaodan Liang, Ling Chen, Abdulmotaleb Elsaddik, and Xiaojun Chang. 2024. Contrastive Learning with Counterfactual Explanations for Radiology Report Generation. In European Conference on Computer Vision. https:\/\/api.semanticscholar.org\/CorpusID:271310426"},{"key":"e_1_3_2_1_19_1","volume-title":"Visual Instruction Tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual 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, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/6dcf277ea32ce3288914faf369fe6de0-Abstract-Conference.html"},{"key":"e_1_3_2_1_20_1","volume-title":"Yuhang Cao, Haodong Duan, Dahua Lin, and Jiaqi Wang.","author":"Liu Ziyu","year":"2025","unstructured":"Ziyu Liu, Zeyi Sun, Yuhang Zang, Xiao wen Dong, Yuhang Cao, Haodong Duan, Dahua Lin, and Jiaqi Wang. 2025. Visual-RFT: Visual Reinforcement Fine-Tuning. https:\/\/api.semanticscholar.org\/CorpusID:276768091"},{"key":"e_1_3_2_1_21_1","volume-title":"Pan Zhang, Yuhang Cao, Haodong Duan, Conghui He, Yuanjun Xiong, Dahua Lin, and Jiaqi Wang.","author":"Liu Ziyu","year":"2024","unstructured":"Ziyu Liu, Yuhang Zang, Xiao wen Dong, Pan Zhang, Yuhang Cao, Haodong Duan, Conghui He, Yuanjun Xiong, Dahua Lin, and Jiaqi Wang. 2024. MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models. ArXiv, Vol. abs\/2410.17637 (2024). https:\/\/api.semanticscholar.org\/CorpusID:273532785"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.ACL-LONG.250"},{"key":"e_1_3_2_1_23_1","volume-title":"Uncertainty Estimation in Autoregressive Structured Prediction. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:231895728","author":"Malinin Andrey","year":"2021","unstructured":"Andrey Malinin and Mark John Francis Gales. 2021. Uncertainty Estimation in Autoregressive Structured Prediction. In International Conference on Learning Representations. https:\/\/api.semanticscholar.org\/CorpusID:231895728"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 3rd Machine Learning for Health Symposium (Proceedings of Machine Learning Research","volume":"367","author":"Moor Michael","year":"2023","unstructured":"Michael Moor, Qian Huang, Shirley Wu, Michihiro Yasunaga, Yash Dalmia, Jure Leskovec, Cyril Zakka, Eduardo Pontes Reis, and Pranav Rajpurkar. 2023. Med-Flamingo: a Multimodal Medical Few-shot Learner. In Proceedings of the 3rd Machine Learning for Health Symposium (Proceedings of Machine Learning Research, Vol. 225), Stefan Hegselmann, Antonio Parziale, Divya Shanmugam, Shengpu Tang, Mercy Nyamewaa Asiedu, Serina Chang, Tom Hartvigsen, and Harvineet Singh (Eds.). PMLR, 353-367. https:\/\/proceedings.mlr.press\/v225\/moor23a.html"},{"key":"e_1_3_2_1_25_1","volume-title":"Filtered Direct Preference Optimization. ArXiv","author":"Morimura Tetsuro","year":"2024","unstructured":"Tetsuro Morimura, Mitsuki Sakamoto, Yuu Jinnai, Kenshi Abe, and Kaito Air. 2024. Filtered Direct Preference Optimization. ArXiv, Vol. abs\/2404.13846 (2024). https:\/\/api.semanticscholar.org\/CorpusID:269293711"},{"key":"e_1_3_2_1_26_1","volume-title":"ChEX: Interactive Localization and Region Description in Chest X-rays. In European Conference on Computer Vision. https:\/\/api.semanticscholar.org\/CorpusID:269362121","author":"M\u00fcller Philip","year":"2024","unstructured":"Philip M\u00fcller, Georgios Kaissis, and Daniel Rueckert. 2024. ChEX: Interactive Localization and Region Description in Chest X-rays. In European Conference on Computer Vision. https:\/\/api.semanticscholar.org\/CorpusID:269362121"},{"key":"e_1_3_2_1_27_1","volume-title":"Abdelrahman Shaker and Fahad Shahbaz Khan","author":"Mullappilly Hisham Cholakkal Rao Sahal Shaji","year":"2023","unstructured":"Sahal Shaji Mullappilly Hisham Cholakkal Rao Muhammad Anwer Salman Khan Jorma Laaksonen Omkar Thawkar, Abdelrahman Shaker and Fahad Shahbaz Khan. 2023. XrayGPT: Chest Radiographs Summarization using Large Medical Vision-Language Models. arXiv: 2306.07971 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"GPT-4o System Card. arXiv preprint arXiv:2410.21276","author":"AI.","year":"2024","unstructured":"OpenAI. 2024. GPT-4o System Card. arXiv preprint arXiv:2410.21276 (2024). https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_2_1_29_1","volume-title":"CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs. ArXiv","author":"Ouali Yassine","year":"2024","unstructured":"Yassine Ouali, Adrian Bulat, Brais Mart\u00ednez, and Georgios Tzimiropoulos. 2024. CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs. ArXiv, Vol. abs\/2408.10433 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271909100"},{"key":"e_1_3_2_1_30_1","unstructured":"PhysioNet. [n.d.]. PhysioNet. https:\/\/physionet.org\/. Accessed: 2025-04-07."},{"key":"e_1_3_2_1_31_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_32_1","volume-title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model. ArXiv","author":"Rafailov Rafael","year":"1829","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. ArXiv, Vol. abs\/2305.18290 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258959321"},{"key":"e_1_3_2_1_33_1","volume-title":"Yaofei Duan and Tao Tan","author":"Patrick Pang Rongsheng Wang Junrong Li","year":"2023","unstructured":"Junrong Li Patrick Pang Rongsheng Wang, Yaofei Duan and Tao Tan. 2023. XrayGLM: The first Chinese Medical Multimodal Model that Chest Radiographs Summarization. https:\/\/github.com\/WangRongsheng\/XrayGLM."},{"key":"e_1_3_2_1_34_1","volume-title":"STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering. arXiv preprint arXiv:2406.19973","author":"Sun Guohao","year":"2024","unstructured":"Guohao Sun, Can Qin, Huazhu Fu, Linwei Wang, and Zhiqiang Tao. 2024. STLLaVA-Med: Self-Training Large Language and Vision Assistant for Medical Question-Answering. arXiv preprint arXiv:2406.19973 (2024)."},{"key":"e_1_3_2_1_35_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104-3112."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"e_1_3_2_1_37_1","volume-title":"Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data. CoRR","author":"Wu Chaoyi","year":"2023","unstructured":"Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2023. Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data. CoRR, Vol. abs\/2308.02463 (2023). arXiv:2308.02463 http:\/\/arxiv.org\/abs\/2308.02463"},{"key":"e_1_3_2_1_38_1","volume-title":"Jasper Seth Yao, Edward Christopher Dee, William Mitchell, Satyananda Kashyap, Andrea Giovannini, Leo Anthony Celi, and Mehdi Moradi.","author":"Wu Joy T.","year":"2021","unstructured":"Joy T. Wu, Nkechinyere N. Agu, Ismini Lourentzou, Arjun Sharma, Joseph Alexander Paguio, Jasper Seth Yao, Edward Christopher Dee, William Mitchell, Satyananda Kashyap, Andrea Giovannini, Leo Anthony Celi, and Mehdi Moradi. 2021. Chest ImaGenome Dataset for Clinical Reasoning. ArXiv, Vol. abs\/2108.00316 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235420881"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.62"},{"key":"e_1_3_2_1_40_1","volume-title":"Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key. ArXiv","author":"Yang Zhihe","year":"2025","unstructured":"Zhihe Yang, Xufang Luo, Dongqi Han, Yunjian Xu, and Dongsheng Li. 2025. Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key. ArXiv, Vol. abs\/2501.09695 (2025). https:\/\/api.semanticscholar.org\/CorpusID:275570496"},{"key":"e_1_3_2_1_41_1","volume-title":"Robert Tinn, Sam Preston, Rajesh N. Rao, Mu-Hsin Wei, Naveen Valluri, Cliff Wong, Matthew P. Lungren, Tristan Naumann, and Hoifung Poon.","author":"Zhang Sheng","year":"2023","unstructured":"Sheng Zhang, Yanbo Xu, Naoto Usuyama, Jaspreet Kaur Bagga, Robert Tinn, Sam Preston, Rajesh N. Rao, Mu-Hsin Wei, Naveen Valluri, Cliff Wong, Matthew P. Lungren, Tristan Naumann, and Hoifung Poon. 2023. BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. https:\/\/api.semanticscholar.org\/CorpusID:257280046"},{"key":"e_1_3_2_1_42_1","unstructured":"Yiyang Zhou Chenhang Cui Rafael Rafailov Chelsea Finn and Huaxiu Yao. 2024. Aligning Modalities in Vision Large Language Models via Preference Fine-tuning. arXiv:2402.11411 [cs.LG] https:\/\/arxiv.org\/abs\/2402.11411"},{"key":"e_1_3_2_1_43_1","volume-title":"MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization. ArXiv","author":"Zhu Kangyu","year":"2024","unstructured":"Kangyu Zhu, Peng Xia, Yun Li, Hongtu Zhu, Sheng Wang, and Huaxiu Yao. 2024. MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization. ArXiv, Vol. abs\/2412.06141 (2024). https:\/\/api.semanticscholar.org\/CorpusID:274597778"}],"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\/3746027.3754507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:03:34Z","timestamp":1765339414000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754507"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":43,"alternative-id":["10.1145\/3746027.3754507","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754507","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"}}]}}