{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:05:31Z","timestamp":1765343131775,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306041"],"award-info":[{"award-number":["62306041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484488"],"award-info":[{"award-number":["20230484488"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National High Level Hospital Clinical Research Funding","award":["2022-PUMCH-B-002"],"award-info":[{"award-number":["2022-PUMCH-B-002"]}]},{"name":"Beijing Natural Science Foundation","award":["L222012"],"award-info":[{"award-number":["L222012"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758212","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:37:21Z","timestamp":1761377841000},"page":"12729-12736","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SpineBench: Benchmarking Multimodal LLMs for Spinal Pathology Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8541-4488","authenticated-orcid":false,"given":"Chenghanyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1207-1901","authenticated-orcid":false,"given":"Zekun","family":"Li","sequence":"additional","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7963-991X","authenticated-orcid":false,"given":"Peipei","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6788-1920","authenticated-orcid":false,"given":"Xing","family":"Cui","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, BeiJing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0013-9626","authenticated-orcid":false,"given":"Shuhan","family":"Xia","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6530-5687","authenticated-orcid":false,"given":"Weixiang","family":"Yan","sequence":"additional","affiliation":[{"name":"Amazon, Palo Alto, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5925-9031","authenticated-orcid":false,"given":"Yiqiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking Union Medical College Hospital, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5217-1932","authenticated-orcid":false,"given":"Qianyu","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Peking Union Medical College Hospital, Beijing, 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":"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":"Lim Heng Siong, and Anith Khairunnisa Ghazali.","author":"Zaim Ahmad Muhammad Shahrul","year":"2024","unstructured":"Muhammad Shahrul Zaim Ahmad, Nor Azlina Ab Aziz, Lim Heng Siong, and Anith Khairunnisa Ghazali. 2024. Datasets for Artificial Intelligence-based Spine Analysis: A Scoping Review. JOIV (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"Barriers to cross-disciplinary knowledge flow: The case of medical education research. Perspectives on Medical Education","author":"Albert Mathieu","year":"2022","unstructured":"Mathieu Albert, Paula Rowland, Farah Friesen, and Suzanne Laberge. 2022. Barriers to cross-disciplinary knowledge flow: The case of medical education research. Perspectives on Medical Education (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"Part affinity fields and CoordConv for detecting landmarks of lumbar vertebrae and sacrum in X-ray images. Sensors","author":"An Chang-Hyeon","year":"2022","unstructured":"Chang-Hyeon An, Jeong-Sik Lee, Jun-Su Jang, and Hyun-Chul Choi. 2022. Part affinity fields and CoordConv for detecting landmarks of lumbar vertebrae and sacrum in X-ray images. Sensors (2022)."},{"volume-title":"Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku. anthropic","year":"2024","key":"e_1_3_2_1_5_1","unstructured":"Anthropic. 2024. Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku. anthropic (2024). https:\/\/www.anthropic.com\/news\/3-5-models-and-computer-use"},{"key":"e_1_3_2_1_6_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_7_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_8_1","volume-title":"Bmad: Benchmarks for medical anomaly detection. In CVPR.","author":"Bao Jinan","year":"2024","unstructured":"Jinan Bao, Hanshi Sun, Hanqiu Deng, Yinsheng He, Zhaoxiang Zhang, and Xingyu Li. 2024. Bmad: Benchmarks for medical anomaly detection. In CVPR."},{"volume-title":"byteDance","year":"2025","key":"e_1_3_2_1_9_1","unstructured":"ByteDance. 2025. Doubao-1.5-pro. byteDance (2025). https:\/\/seed.bytedance.com\/zh\/special\/doubao_1_5_pro?from=doubao_product_page"},{"key":"e_1_3_2_1_10_1","volume-title":"Xidong Wang, Ruifei Zhang, Zhenyang Cai, Ke Ji, et al.","author":"Chen Junying","year":"2024","unstructured":"Junying Chen, Chi Gui, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Hardy Chen, Xidong Wang, Ruifei Zhang, Zhenyang Cai, Ke Ji, et al., 2024a. Huatuogpt-vision, towards injecting medical visual knowledge into multimodal llms at scale. arXiv preprint arXiv:2406.19280 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"VertXNet: an ensemble method for vertebral body segmentation and identification from cervical and lumbar spinal X-rays. Scientific Reports","author":"Chen Yao","year":"2024","unstructured":"Yao Chen, Yuanhan Mo, Aimee Readie, Gregory Ligozio, Indrajeet Mandal, Faiz Jabbar, Thibaud Coroller, and Bart?omiej W Papie.z. 2024b. VertXNet: an ensemble method for vertebral body segmentation and identification from cervical and lumbar spinal X-rays. Scientific Reports (2024)."},{"key":"e_1_3_2_1_12_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. Science China Information Sciences (2024).","DOI":"10.1007\/s11432-024-4231-5"},{"key":"e_1_3_2_1_13_1","unstructured":"Google. 2025. MedGemma Hugging Face. https:\/\/huggingface.co\/collections\/google\/medgemma-release-680aade845f90bec6a3f60c4."},{"key":"e_1_3_2_1_14_1","volume-title":"googledeepmind","author":"Pro Gemini","year":"2025","unstructured":"GoogleDeepMind. 2025. Gemini 2.5 Pro. googledeepmind (2025). https:\/\/deepmind.google\/models\/gemini\/pro\/"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1430984"},{"key":"e_1_3_2_1_16_1","volume-title":"Pathvqa: 30000 questions for medical visual question answering. arXiv preprint arXiv:2003.10286","author":"He Xuehai","year":"2020","unstructured":"Xuehai He, Yichen Zhang, Luntian Mou, Eric Xing, and Pengtao Xie. 2020. Pathvqa: 30000 questions for medical visual question answering. arXiv preprint arXiv:2003.10286 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Omnimedvqa: A new large-scale comprehensive evaluation benchmark for medical lvlm. In CVPR.","author":"Hu Yutao","year":"2024","unstructured":"Yutao Hu, Tianbin Li, Quanfeng Lu, Wenqi Shao, Junjun He, Yu Qiao, and Ping Luo. 2024. Omnimedvqa: A new large-scale comprehensive evaluation benchmark for medical lvlm. In CVPR."},{"key":"e_1_3_2_1_18_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"BUU-LSPINE: A thai open lumbar spine dataset for spondylolisthesis detection. Applied Sciences","author":"Klinwichit Podchara","year":"2023","unstructured":"Podchara Klinwichit, Watcharaphong Yookwan, Sornsupha Limchareon, Krisana Chinnasarn, Jun-Su Jang, and Athita Onuean. 2023. BUU-LSPINE: A thai open lumbar spine dataset for spondylolisthesis detection. Applied Sciences (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Asma Ben Abacha, and Dina Demner-Fushman","author":"Lau Jason J","year":"2018","unstructured":"Jason J Lau, Soumya Gayen, Asma Ben Abacha, and Dina Demner-Fushman. 2018. A dataset of clinically generated visual questions and answers about radiology images. Scientific data (2018)."},{"key":"e_1_3_2_1_21_1","unstructured":"Anjie Le Henan Liu Yue Wang Zhenyu Liu Rongkun Zhu Taohan Weng Jinze Yu Boyang Wang Yalun Wu Kaiwen Yan et al. 2025. U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding. arXiv preprint arXiv:2505.17779 (2025)."},{"key":"e_1_3_2_1_22_1","volume-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day. NIPS","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. NIPS (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"ICUnet: an Inception-CBAM network based on Unet for MR spine image segmentation. IJMLC","author":"Li Lei","year":"2023","unstructured":"Lei Li, Juan Qin, Lianrong Lv, Mengdan Cheng, Biao Wang, Dan Xia, and Shike Wang. 2023a. ICUnet: an Inception-CBAM network based on Unet for MR spine image segmentation. IJMLC (2023)."},{"key":"e_1_3_2_1_24_1","unstructured":"Sijing Li Tianwei Lin Lingshuai Lin Wenqiao Zhang Jiang Liu Xiaoda Yang Juncheng Li Yucheng He Xiaohui Song Jun Xiao et al. 2025. EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset Benchmark and Model. arXiv preprint arXiv:2504.13650 (2025)."},{"key":"e_1_3_2_1_25_1","volume-title":"Giles Tetteh, Katharina Grau, Eva Niederreiter, et al.","author":"Liebl Hans","year":"2021","unstructured":"Hans Liebl, David Schinz, Anjany Sekuboyina, Luca Malagutti, Maximilian T L\u00f6ffler, Amirhossein Bayat, Malek El Husseini, Giles Tetteh, Katharina Grau, Eva Niederreiter, et al., 2021. A computed tomography vertebral segmentation dataset with anatomical variations and multi-vendor scanner data. Scientific data (2021)."},{"key":"e_1_3_2_1_26_1","unstructured":"Tianwei Lin Wenqiao Zhang Sijing Li Yuqian Yuan Binhe Yu Haoyuan Li Wanggui He Hao Jiang Mengze Li Xiaohui Song et al. 2025. HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation. arXiv preprint arXiv:2502.09838 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In ISBI.","author":"Liu Bo","year":"2021","unstructured":"Bo Liu, Li-Ming Zhan, Li Xu, Lin Ma, Yan Yang, and Xiao-Ming Wu. 2021. Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In ISBI."},{"key":"e_1_3_2_1_28_1","volume-title":"Llavanext: Improved reasoning, ocr, and world knowledge.","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. 2024. Llavanext: Improved reasoning, ocr, and world knowledge."},{"key":"e_1_3_2_1_29_1","volume-title":"Visual instruction tuning. NIPS","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. NIPS (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Revolutionizing edge AI and vision with open, customizable models. meta","author":"Llama","year":"2024","unstructured":"Meta. 2024. Llama 3.2: Revolutionizing edge AI and vision with open, customizable models. meta (2024). https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/"},{"key":"e_1_3_2_1_31_1","unstructured":"Michael Moor Qian Huang Shirley Wu Michihiro Yasunaga Yash Dalmia Jure Leskovec Cyril Zakka Eduardo Pontes Reis and Pranav Rajpurkar. [n.d.]. Med-flamingo: a multimodal medical few-shot learner. In ML4H. PMLR."},{"key":"e_1_3_2_1_32_1","volume-title":"Nunik Afriliana, Hira Meidia, Reyhan Eddy Yunus, and Sud Sudirman.","author":"Natalia Friska","year":"2022","unstructured":"Friska Natalia, Julio Christian Young, Nunik Afriliana, Hira Meidia, Reyhan Eddy Yunus, and Sud Sudirman. 2022. Automated selection of mid-height intervertebral disc slice in traverse lumbar spine MRI using a combination of deep learning feature and machine learning classifier. PLoS One (2022)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Hieu T Nguyen Hieu H Pham Nghia T Nguyen Ha Q Nguyen Thang Q Huynh Minh Dao and Van Vu. 2021. VinDr-SpineXR: A deep learning framework for spinal lesions detection and classification from radiographs. In MICCAI.","DOI":"10.1007\/978-3-030-87240-3_28"},{"key":"e_1_3_2_1_34_1","volume-title":"VinDr-SpineXR: A large annotated medical image dataset for spinal lesions detection and classification from radiographs. PhysioNet","author":"Pham Hieu Huy","year":"2021","unstructured":"Hieu Huy Pham, H Nguyen Trung, and Ha Quy Nguyen. 2021. VinDr-SpineXR: A large annotated medical image dataset for spinal lesions detection and classification from radiographs. PhysioNet (2021)."},{"key":"e_1_3_2_1_35_1","volume-title":"Medical image understanding with pretrained vision language models: A comprehensive study. arXiv preprint arXiv:2209.15517","author":"Qin Ziyuan","year":"2022","unstructured":"Ziyuan Qin, Huahui Yi, Qicheng Lao, and Kang Li. 2022. Medical image understanding with pretrained vision language models: A comprehensive study. arXiv preprint arXiv:2209.15517 (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"Lmod: A large multimodal ophthalmology dataset and benchmark for large vision-language models. arXiv preprint arXiv:2410.01620","author":"Qin Zhenyue","year":"2024","unstructured":"Zhenyue Qin, Yu Yin, Dylan Campbell, Xuansheng Wu, Ke Zou, Yih-Chung Tham, Ninghao Liu, Xiuzhen Zhang, and Qingyu Chen. 2024. Lmod: A large multimodal ophthalmology dataset and benchmark for large vision-language models. arXiv preprint arXiv:2410.01620 (2024)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Yu Ran Wanli Qin Changlong Qin Xiaobin Li Yixing Liu Lin Xu Xiaohong Mu Li Yan Bei Wang Yuxiang Dai et al. 2024. A high-quality dataset featuring classified and annotated cervical spine X-ray atlas. Scientific Data (2024).","DOI":"10.1038\/s41597-024-03383-0"},{"key":"e_1_3_2_1_38_1","volume-title":"RSNA 2024 Lumbar Spine Degenerative Classification. https:\/\/kaggle.com\/competitions\/rsna-2024-lumbar-spine-degenerative-classification.","author":"Richards Tyler","year":"2024","unstructured":"Tyler Richards, Jason Talbott, Robyn Ball, Errol Colak, Adam Flanders, Felipe Kitamura, John Mongan, Luciano Prevedello, and Maryam Vazirabad., 2024. RSNA 2024 Lumbar Spine Degenerative Classification. https:\/\/kaggle.com\/competitions\/rsna-2024-lumbar-spine-degenerative-classification."},{"key":"e_1_3_2_1_39_1","volume-title":"Hussain Mobarak Albarakati, and Aqsa Dastgir","author":"Saeed Muhammad Usman","year":"2024","unstructured":"Muhammad Usman Saeed, Wang Bin, Jinfang Sheng, Hussain Mobarak Albarakati, and Aqsa Dastgir. 2024. MSFF: An automated multi-scale feature fusion deep learning model for spine fracture segmentation using MRI. Biomedical Signal Processing and Control (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"An automated deep learning approach for spine segmentation and vertebrae recognition using computed tomography images. Diagnostics","author":"Saeed Muhammad Usman","year":"2023","unstructured":"Muhammad Usman Saeed, Nikolaos Dikaios, Aqsa Dastgir, Ghulam Ali, Muhammad Hamid, and Fahima Hajjej. 2023. An automated deep learning approach for spine segmentation and vertebrae recognition using computed tomography images. Diagnostics (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Artificial intelligence-driven prediction modeling and decision making in spine surgery using hybrid machine learning models. Journal of Personalized Medicine","author":"Saravi Babak","year":"2022","unstructured":"Babak Saravi, Frank Hassel, Sara \u00dclk\u00fcmen, Alisia Zink, Veronika Shavlokhova, Sebastien Couillard-Despres, Martin Boeker, Peter Obid, and Gernot Michael Lang. 2022. Artificial intelligence-driven prediction modeling and decision making in spine surgery using hybrid machine learning models. Journal of Personalized Medicine (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"MedM-VL: What Makes a Good Medical LVLM? arXiv preprint arXiv:2504.04323","author":"Shi Yiming","year":"2025","unstructured":"Yiming Shi, Shaoshuai Yang, Xun Zhu, Haoyu Wang, Miao Li, and Ji Wu. 2025. MedM-VL: What Makes a Good Medical LVLM? arXiv preprint arXiv:2504.04323 (2025)."},{"key":"e_1_3_2_1_43_1","volume-title":"Internlm: A multilingual language model with progressively enhanced capabilities.","author":"Team LM","year":"2023","unstructured":"InternLM Team. 2023. Internlm: A multilingual language model with progressively enhanced capabilities."},{"key":"e_1_3_2_1_44_1","volume-title":"Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, et al.","author":"Tschannen Michael","year":"2025","unstructured":"Michael Tschannen, Alexey Gritsenko, Xiao Wang, Muhammad Ferjad Naeem, Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, et al., 2025. Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Vladislav Tumko Jack Kim Natalia Uspenskaia Shaun Honig Frederik Abel Darren R Lebl Irene Hotalen Serhii Kolisnyk Mikhail Kochnev Andrej Rusakov et al. 2024. A neural network model for detection and classification of lumbar spinal stenosis on MRI. European Spine Journal (2024).","DOI":"10.1007\/s00586-023-08089-2"},{"key":"e_1_3_2_1_46_1","volume-title":"Matthieu Rutten, Job LC van Susante, Robert Jan Kroeze, Marinus de Kleuver, Bram van Ginneken, and Nikolas Lessmann.","author":"van der Graaf Jasper W","year":"2024","unstructured":"Jasper W van der Graaf, Miranda L van Hooff, Constantinus FM Buckens, Matthieu Rutten, Job LC van Susante, Robert Jan Kroeze, Marinus de Kleuver, Bram van Ginneken, and Nikolas Lessmann. 2024. Lumbar spine segmentation in MR images: a dataset and a public benchmark. Scientific Data (2024)."},{"key":"e_1_3_2_1_47_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang et al. 2024. Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Grok 3 Beta - The Age of Reasoning Agents. xAI","author":"AI.","year":"2025","unstructured":"xAI. 2025. Grok 3 Beta - The Age of Reasoning Agents. xAI (2025). https:\/\/x.ai\/news\/grok-3"},{"key":"e_1_3_2_1_49_1","volume-title":"Cares: A comprehensive benchmark of trustworthiness in medical vision language models. NIPS","author":"Xia Peng","year":"2024","unstructured":"Peng Xia, Ze Chen, Juanxi Tian, Yangrui Gong, Ruibo Hou, Yue Xu, Zhenbang Wu, Zhiyuan Fan, Yiyang Zhou, Kangyu Zhu, et al., 2024. Cares: A comprehensive benchmark of trustworthiness in medical vision language models. NIPS (2024)."},{"key":"e_1_3_2_1_50_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_51_1","volume-title":"Gmai-mmbench: A comprehensive multimodal evaluation benchmark towards general medical ai. NIPS","author":"Ye Jin","year":"2024","unstructured":"Jin Ye, Guoan Wang, Yanjun Li, Zhongying Deng, Wei Li, Tianbin Li, Haodong Duan, Ziyan Huang, Yanzhou Su, Benyou Wang, et al., 2024. Gmai-mmbench: A comprehensive multimodal evaluation benchmark towards general medical ai. NIPS (2024)."},{"key":"e_1_3_2_1_52_1","volume-title":"MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning. arXiv preprint arXiv:2505.16964","author":"Yu Suhao","year":"2025","unstructured":"Suhao Yu, Haojin Wang, Juncheng Wu, Cihang Xie, and Yuyin Zhou. 2025. MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning. arXiv preprint arXiv:2505.16964 (2025)."},{"key":"e_1_3_2_1_53_1","volume-title":"Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. In CVPR.","author":"Yue Xiang","year":"2024","unstructured":"Xiang Yue, Yuansheng Ni, Kai Zhang, Tianyu Zheng, Ruoqi Liu, Ge Zhang, Samuel Stevens, Dongfu Jiang, Weiming Ren, Yuxuan Sun, et al., 2024. Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi. In CVPR."}],"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\/3746027.3758212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:01:58Z","timestamp":1765342918000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758212"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":53,"alternative-id":["10.1145\/3746027.3758212","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758212","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"}}]}}