{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T08:09:59Z","timestamp":1761811799786,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032043382","type":"print"},{"value":"9783032043399","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-032-04339-9_17","type":"book-chapter","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T08:06:36Z","timestamp":1761811596000},"page":"263-279","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Investigating Zero-Shot Diagnostic Pathology in\u00a0Vision-Language Models with\u00a0Efficient Prompt Design"],"prefix":"10.1007","author":[{"given":"Vasudev","family":"Sharma","sequence":"first","affiliation":[]},{"given":"Ahmed","family":"Alagha","sequence":"additional","affiliation":[]},{"given":"Abdelhakim","family":"Khellaf","sequence":"additional","affiliation":[]},{"given":"Vincent Quoc-Huy","family":"Trinh","sequence":"additional","affiliation":[]},{"given":"Mahdi S.","family":"Hosseini","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,31]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"17_CR2","unstructured":"Chanda, D., Aryal, M., Soltani, N.Y., Ganji, M.: A new era in computational pathology: a survey on foundation and vision-language models. arXiv preprint arXiv:2408.14496 (2024)"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Chen, R.J., et al.: Scaling vision transformers to gigapixel images via hierarchical self-supervised learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16144\u201316155 (2022)","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"17_CR4","unstructured":"Chen, R.J., et\u00a0al.: A general-purpose self-supervised model for computational pathology. arXiv preprint arXiv:2308.15474 (2023)"},{"issue":"1","key":"17_CR5","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1038\/s41467-024-55631-x","volume":"16","author":"J Clusmann","year":"2025","unstructured":"Clusmann, J., et al.: Prompt injection attacks on vision language models in oncology. Nat. Commun. 16(1), 1239 (2025)","journal-title":"Nat. Commun."},{"issue":"4","key":"17_CR6","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1038\/s41374-020-00514-0","volume":"101","author":"M Cui","year":"2021","unstructured":"Cui, M., Zhang, D.Y.: Artificial intelligence and computational pathology. Lab. Invest. 101(4), 412\u2013422 (2021)","journal-title":"Lab. Invest."},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR9","first-page":"126725","volume":"37","author":"Y Du","year":"2024","unstructured":"Du, Y., Sun, W., Snoek, C.: Ipo: interpretable prompt optimization for vision-language models. Adv. Neural. Inf. Process. Syst. 37, 126725\u2013126766 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR10","unstructured":"Gu, J., Beirami, A., Wang, X., Beutel, A., Torr, P., Qin, Y.: Towards robust prompts on vision-language models. arXiv preprint arXiv:2304.08479 (2023)"},{"key":"17_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpi.2023.100357","volume":"15","author":"MS Hosseini","year":"2024","unstructured":"Hosseini, M.S., et al.: Computational pathology: a survey review and the way forward. J. Pathol. Inform. 15, 100357 (2024)","journal-title":"J. Pathol. Inform."},{"key":"17_CR12","first-page":"37995","volume":"36","author":"W Ikezogwo","year":"2023","unstructured":"Ikezogwo, W., et al.: Quilt-1m: one million image-text pairs for histopathology. Adv Neural Inform. Process. Syst. 36, 37995\u201338017 (2023)","journal-title":"Adv Neural Inform. Process. Syst."},{"key":"17_CR13","first-page":"28541","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":"17_CR14","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Lu, M.Y., et\u00a0al.: Visual language pretrained multiple instance zero-shot transfer for histopathology images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19764\u201319775 (2023)","DOI":"10.1109\/CVPR52729.2023.01893"},{"issue":"3","key":"17_CR16","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","volume":"30","author":"MY Lu","year":"2024","unstructured":"Lu, M.Y., et al.: A visual-language foundation model for computational pathology. Nat. Med. 30(3), 863\u2013874 (2024)","journal-title":"Nat. Med."},{"key":"17_CR17","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"17_CR18","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"8","key":"17_CR19","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"17_CR20","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Seyfioglu, M.S., et\u00a0al.: Quilt-llava: visual instruction tuning by extracting localized narratives from open-source histopathology videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13183\u201313192 (2024)","DOI":"10.1109\/CVPR52733.2024.01252"},{"key":"17_CR22","unstructured":"Sun, S., et\u00a0al.: Dr-llava: visual instruction tuning with symbolic clinical grounding. arXiv preprint arXiv:2405.19567 (2024)"},{"key":"17_CR23","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"17_CR24","unstructured":"Vorontsov, E., et\u00a0al.: Virchow: A million-slide digital pathology foundation model. arXiv preprint arXiv:2309.07778 (2023)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Wang, B., Liu, J., Karimnazarov, J., Thompson, N.: Task supportive and personalized human-large language model interaction: a user study. In: Proceedings of the 2024 Conference on Human Information Interaction and Retrieval, pp. 370\u2013375 (2024)","DOI":"10.1145\/3627508.3638344"},{"key":"17_CR26","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"}],"container-title":["Communications in Computer and Information Science","Deep Learning Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04339-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T08:06:48Z","timestamp":1761811608000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04339-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783032043382","9783032043399"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04339-9_17","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"31 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DeLTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Deep Learning Theory and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"delta2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/delta.scitevents.org\/?y=2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}