{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T08:50:32Z","timestamp":1782377432477,"version":"3.54.5"},"reference-count":33,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T00:00:00Z","timestamp":1782000000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114283","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T23:20:19Z","timestamp":1781911219000},"page":"114283","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Fine-grained alignment in medical pathology vision-language models via variational distillation"],"prefix":"10.1016","volume":"180","author":[{"given":"Runlin","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haowei","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weipeng","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiu-ming","family":"Cheung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongmin","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9501-0321","authenticated-orcid":false,"given":"Weifeng","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114283_b1","series-title":"Icml","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"9","key":"10.1016\/j.patcog.2026.114283_b2","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114283_b3","series-title":"Cvpr","first-page":"19113","article-title":"Maple: Multi-modal prompt learning","author":"Khattak","year":"2023"},{"key":"10.1016\/j.patcog.2026.114283_b4","series-title":"Cvpr","first-page":"15190","article-title":"Self-regulating prompts: Foundational model adaptation without forgetting","author":"Khattak","year":"2023"},{"key":"10.1016\/j.patcog.2026.114283_b5","series-title":"Iclr","article-title":"Consistency-guided prompt learning for vision-language models","author":"Roy","year":"2024"},{"key":"10.1016\/j.patcog.2026.114283_b6","series-title":"Advancing textual prompt learning with anchored attributes. arxiv","author":"Li","year":"2025"},{"key":"10.1016\/j.patcog.2026.114283_b7","series-title":"International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.patcog.2026.114283_b8","series-title":"Eccv","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"issue":"8","key":"10.1016\/j.patcog.2026.114283_b9","doi-asserted-by":"crossref","first-page":"5822","DOI":"10.1007\/s11263-025-02451-1","article-title":"Supplementary prompt learning for vision-language models","volume":"133","author":"Zeng","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2026.114283_b10","article-title":"Cluster-aware prompt ensemble learning for few-shot vision\u2013language model adaptation","author":"Chen","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114283_b11","article-title":"Decouple before align: Visual disentanglement enhances prompt tuning","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114283_b12","doi-asserted-by":"crossref","unstructured":"T. Koleilat, H. Asgariandehkordi, H. Rivaz, Y. Xiao, Biomedcoop: Learning to prompt for biomedical vision-language models, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 14766\u201314776.","DOI":"10.1109\/CVPR52734.2025.01376"},{"key":"10.1016\/j.patcog.2026.114283_b13","unstructured":"X. Cui, J. Zhang, J. Hou, D. Lu, H. Zhang, R. Wang, BiomedCCPL: Causal Conditional Prompt Learning for Biomedical Vision-Language Models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2026, pp. 40812\u201340821."},{"key":"10.1016\/j.patcog.2026.114283_b14","series-title":"Conference on Health, Inference, and Learning","first-page":"117","article-title":"Multi-modal pre-training for medical vision-language understanding and generation: An empirical study with a new benchmark","author":"Xu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114283_b15","first-page":"1","article-title":"A visual\u2013language foundation model for pathology image analysis using medical Twitter","author":"Huang","year":"2023","journal-title":"Nature Med."},{"key":"10.1016\/j.patcog.2026.114283_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111646","article-title":"Vision-language foundation model for generalizable nasal disease diagnosis using unlabeled endoscopic records","volume":"165","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114283_b17","unstructured":"C. Zhang, R. Wu, T. Zhou, Y. Zhou, MedKCO: Medical Vision-Language Pretraining via Knowledge-Driven Cognitive Orchestration, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2026, pp. 35260\u201335269."},{"key":"10.1016\/j.patcog.2026.114283_b18","doi-asserted-by":"crossref","first-page":"7321","DOI":"10.1109\/TIP.2025.3628469","article-title":"Local alignment for medical vision-language pre-training","volume":"34","author":"Yan","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114283_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111484","article-title":"GAD: Domain generalized diabetic retinopathy grading by grade-aware de-stylization","volume":"164","author":"Bi","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114283_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111564","article-title":"An information bottleneck approach for feature selection","volume":"164","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114283_b21","series-title":"The information bottleneck method","author":"Tishby","year":"2000"},{"key":"10.1016\/j.patcog.2026.114283_b22","series-title":"Iclr","article-title":"Deep variational information bottleneck","author":"Alemi","year":"2017"},{"key":"10.1016\/j.patcog.2026.114283_b23","series-title":"The dual information bottleneck","author":"Piran","year":"2020"},{"key":"10.1016\/j.patcog.2026.114283_b24","series-title":"Cvpr","first-page":"7497","article-title":"Label information bottleneck for label enhancement","author":"Zheng","year":"2023"},{"key":"10.1016\/j.patcog.2026.114283_b25","series-title":"Cvpr","first-page":"27435","article-title":"Differentiable information bottleneck for deterministic multi-view clustering","author":"Yan","year":"2024"},{"key":"10.1016\/j.patcog.2026.114283_b26","series-title":"Icml","first-page":"16049","article-title":"How does information bottleneck help deep learning?","author":"Kawaguchi","year":"2023"},{"key":"10.1016\/j.patcog.2026.114283_b27","article-title":"Variational distillation for multi-view learning","author":"Tian","year":"2023","journal-title":"Tpami"},{"key":"10.1016\/j.patcog.2026.114283_b28","article-title":"A survey on information bottleneck","author":"Hu","year":"2024","journal-title":"Tpami"},{"key":"10.1016\/j.patcog.2026.114283_b29","series-title":"Pannuke dataset extension, insights and baselines","author":"Gamper","year":"2020"},{"key":"10.1016\/j.patcog.2026.114283_b30","series-title":"Collection of Textures in Colorectal Cancer Histology","author":"Kather","year":"2016"},{"key":"10.1016\/j.patcog.2026.114283_b31","doi-asserted-by":"crossref","first-page":"27988","DOI":"10.1038\/srep27988","article-title":"Multi-class texture analysis in colorectal cancer histology","volume":"6","author":"Kather","year":"2016","journal-title":"Sci. Rep."},{"issue":"1","key":"10.1016\/j.patcog.2026.114283_b32","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/s41597-022-01721-8","article-title":"Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification","volume":"10","author":"Yang","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.patcog.2026.114283_b33","series-title":"2017 IEEE Symposium Series on Computational Intelligence","first-page":"1","article-title":"A comparative study of CNN, BoVW and LBP for classification of histopathological images","author":"Kumar","year":"2017"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012483?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012483?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T08:33:00Z","timestamp":1782376380000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":33,"alternative-id":["S0031320326012483"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114283","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Fine-grained alignment in medical pathology vision-language models via variational distillation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114283","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"114283"}}