{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T23:04:43Z","timestamp":1789254283419,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375551","type":"print"},{"value":"9783032375568","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37556-8_32","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:12:26Z","timestamp":1789251146000},"page":"588-604","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MMBU: A Massive Multi-modal Biomedical Understanding Benchmark to\u00a0Probe the\u00a0Perception Capabilities of\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Ryan","family":"D\u2019 Cunha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"Lozano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxiao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Vela Jarquin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min Woo","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josiah","family":"Aklilu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Burgess","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paola","family":"Avila Robayo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongying","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjun","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Tibshirani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey J.","family":"Nirschl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Serena","family":"Yeung-Levy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"32_CR1","unstructured":"Burgess, J., et al.: Microvqa: a multimodal reasoning benchmark for microscopy-based scientific research (2025). https:\/\/arxiv.org\/abs\/2503.13399"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Chen, P., et al.: Gmai-mmbench: a comprehensive multimodal evaluation benchmark towards general medical ai (2024). https:\/\/arxiv.org\/abs\/2408.03361","DOI":"10.52202\/079017-2992"},{"key":"32_CR3","unstructured":"Gu, Y., et\u00a0al.: The illusion of readiness: stress testing large frontier models on multimodal medical benchmarks. arXiv preprint arXiv:2509.18234 (2025)"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering (2020). https:\/\/arxiv.org\/abs\/2003.10286","DOI":"10.36227\/techrxiv.13127537"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Omnimedvqa: a new large-scale comprehensive evaluation benchmark for medical LVLM (2024). https:\/\/arxiv.org\/abs\/2402.09181","DOI":"10.1109\/CVPR52733.2024.02093"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Jeong, D.P., Mani, P., Garg, S., Lipton, Z.C., Oberst, M.: The limited impact of medical adaptation of large language and vision-language models. arXiv preprint arXiv:2411.08870 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.677"},{"key":"32_CR7","doi-asserted-by":"publisher","unstructured":"Lau, J.J., Gayen, S., Ben\u00a0Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5 (2018). https:\/\/doi.org\/10.1038\/sdata.2018.251. https:\/\/www.nature.com\/articles\/sdata2018251","DOI":"10.1038\/sdata.2018.251"},{"key":"32_CR8","unstructured":"Le, A., et al.: U2-bench: benchmarking large vision-language models on ultrasound understanding (2025). https:\/\/arxiv.org\/abs\/2505.17779"},{"key":"32_CR9","doi-asserted-by":"publisher","first-page":"28541","DOI":"10.52202\/075280-1240","volume":"36","author":"C Li","year":"2023","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. Adv. Neural. Inf. Process. Syst. 36, 28541\u201328564 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. Adv. Neural Inf. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-1240"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering (2021). https:\/\/arxiv.org\/abs\/2102.09542","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2024). https:\/\/arxiv.org\/abs\/2310.03744","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"32_CR13","unstructured":"Lozano, A., et al.: $$\\{$$$$\\backslash $$mu$$\\}$$-bench: a vision-language benchmark for microscopy understanding. arXiv preprint arXiv:2407.01791 (2024)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Lozano, A., et al.: Micro-bench: a vision-language benchmark for microscopy understanding. In: Proceedings of the 38th International Conference on Neural Information Processing Systems, pp. 30670\u201330685 (2024)","DOI":"10.52202\/079017-0965"},{"key":"32_CR15","doi-asserted-by":"publisher","first-page":"131035","DOI":"10.52202\/079017-4165","volume":"37","author":"M Maruf","year":"2024","unstructured":"Maruf, M., et al.: Vlm4bio: a benchmark dataset to evaluate pretrained vision-language models for trait discovery from biological images. Adv. Neural. Inf. Process. Syst. 37, 131035\u2013131071 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR16","unstructured":"OpenAI: GPT-4.1 mini. https:\/\/developers.openai.com\/api\/docs\/models\/gpt-4.1-mini (2025). openAI API model documentation. Model ID: gpt-4.1-mini; snapshot: gpt-4.1-mini-2025-04-14. Accessed: 2026-05-27"},{"key":"32_CR17","unstructured":"OpenAI: GPT-5.4 mini. https:\/\/developers.openai.com\/api\/docs\/models\/gpt-5.4-mini (2026). openAI API model documentation. Model ID: gpt-5.4-mini; snapshot: gpt-5.4-mini-2026-03-17. Accessed: 2026-05-27"},{"key":"32_CR18","unstructured":"Ossowski, T., et al.: Octomed: data recipes for state-of-the-art multimodal medical reasoning. arXiv preprint arXiv:2511.23269 (2025)"},{"key":"32_CR19","unstructured":"Qwen, et al.: Qwen2.5 Technical report (2025). https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"32_CR20","unstructured":"Saab, K., et al.: Capabilities of Gemini models in medicine. arXiv preprint arXiv:2404.18416 (2024)"},{"key":"32_CR21","unstructured":"Sellergren, A., et al.: Medgemma Technical report. arXiv preprint arXiv:2507.05201 (2025)"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Shi, L., Ma, C., Liang, W., Diao, X., Ma, W., Vosoughi, S.: Judging the judges: a systematic study of position bias in LLM-as-a-judge. In: Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pp. 292\u2013314 (2025)","DOI":"10.18653\/v1\/2025.ijcnlp-long.18"},{"key":"32_CR23","unstructured":"Team, G.: Gemma 3 Technical report (2025). https:\/\/arxiv.org\/abs\/2503.19786"},{"issue":"1","key":"32_CR24","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1038\/s41746-022-00592-y","volume":"5","author":"G Varoquaux","year":"2022","unstructured":"Varoquaux, G., Cheplygina, V.: Machine learning for medical imaging: methodological failures and recommendations for the future. NPJ Digital Med. 5(1), 48 (2022)","journal-title":"NPJ Digital Med."},{"key":"32_CR25","unstructured":"Wang, W., et al.: Internvl3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency (2025). https:\/\/arxiv.org\/abs\/2508.18265"},{"issue":"2","key":"32_CR26","doi-asserted-by":"publisher","first-page":"e131","DOI":"10.1016\/j.radi.2015.12.010","volume":"22","author":"C Wright","year":"2016","unstructured":"Wright, C., Reeves, P.: Radbench: benchmarking image interpretation skills. Radiography 22(2), e131\u2013e136 (2016)","journal-title":"Radiography"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Xu, W., et\u00a0al.: Lingshu: a generalist foundation model for unified multimodal medical understanding and reasoning. arXiv preprint arXiv:2506.07044 (2025)","DOI":"10.1109\/TPAMI.2026.3730310"},{"key":"32_CR28","unstructured":"Yang, A., et al.: Qwen3 Technical report (2025). https:\/\/arxiv.org\/abs\/2505.09388"},{"issue":"10","key":"32_CR29","doi-asserted-by":"publisher","first-page":"2838","DOI":"10.1038\/s41591-024-03113-4","volume":"30","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Zhang, H., Gichoya, J.W., Katabi, D., Ghassemi, M.: The limits of fair medical imaging ai in real-world generalization. Nat. Med. 30(10), 2838\u20132848 (2024)","journal-title":"Nat. Med."},{"key":"32_CR30","unstructured":"Yue, X., et al.: Mmmu: a massive multi-discipline multimodal understanding and reasoning benchmark for expert Agi (2024). https:\/\/arxiv.org\/abs\/2311.16502"},{"key":"32_CR31","unstructured":"Zhang, S., et\u00a0al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, J., Li, H., Chen, S., Chen, Z., Han, Z., Gao, X.: Large language models in biomedicine and healthcare. NPJ Artif. Intell. 1(1), 44 (2025)","DOI":"10.1038\/s44387-025-00047-1"},{"key":"32_CR33","doi-asserted-by":"publisher","unstructured":"Zhou, Y., et al.: Evaluating GPT-4v (GPT-4 with vision) on detection of radiologic findings on chest radiographs. Radiology 311(2) (2024). https:\/\/doi.org\/10.1148\/radiol.233270. https:\/\/pubs.rsna.org\/doi\/full\/10.1148\/radiol.233270. PMID: 38712869","DOI":"10.1148\/radiol.233270"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37556-8_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:12:30Z","timestamp":1789251150000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37556-8_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375551","9783032375568"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37556-8_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}