{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:21:53Z","timestamp":1778606513843,"version":"3.51.4"},"reference-count":80,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"publisher","award":["#162327"],"award-info":[{"award-number":["#162327"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02217","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23912-23923","source":"Crossref","is-referenced-by-count":1,"title":["Modaltune: Fine-Tuning Slide-Level Foundation Models with Multi-Modal Information for Multi-Task Learning in Digital Pathology"],"prefix":"10.1109","author":[{"given":"Vishwesh","family":"Ramanathan","sequence":"first","affiliation":[{"name":"Sunnybrook Research Institute,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tony","family":"Xu","sequence":"additional","affiliation":[{"name":"Sunnybrook Research Institute,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pushpak","family":"Pati","sequence":"additional","affiliation":[{"name":"Independent Researcher"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faruk","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Google Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maged","family":"Goubran","sequence":"additional","affiliation":[{"name":"Sunnybrook Research Institute,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne L.","family":"Martel","sequence":"additional","affiliation":[{"name":"Sunnybrook Research Institute,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pathalign: A vision-language model for whole slide images in histopathology","author":"Ahmed","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Learning from randomly initialized neural network features","author":"Amid","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00317"},{"key":"ref4","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae316"},{"key":"ref6","article-title":"Random projections for $k$-means clustering","volume":"23","author":"Boutsidis","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-58796-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3021387"},{"key":"ref9","first-page":"339","article-title":"Whole slide images are 2d point clouds: Context-aware survival prediction using patch-based graph convolutional networks","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Richard"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00398"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02857-3"},{"key":"ref12","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100198"},{"key":"ref14","article-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01317"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43987-2_60"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-025-03982-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2017.7950668"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03922-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102652"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/bcr426"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2546221"},{"issue":"6","key":"ref23","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1038\/s41587-020-0546-8","article-title":"Visualizing and interpreting cancer genomics data via the xena platform","volume":"38","author":"Mary","year":"2020","journal-title":"Nature biotechnology"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102685"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"issue":"2","key":"ref26","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00341-z"},{"key":"ref28","first-page":"2127","article-title":"Attention-based deep multiple instance learning","volume-title":"International conference on machine learning","author":"Ilse"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00920"},{"key":"ref30","author":"Jaume","year":"2024","journal-title":"Transcriptomicsguided slide representation learning in computational pathology-CVPR 2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73414-4_2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43987-2_49"},{"issue":"189\u2013206","key":"ref34","first-page":"1","article-title":"Extensions of lipschitz mappings into a hilbert space","volume":"26","author":"William","year":"1984","journal-title":"Contemporary mathematics"},{"key":"ref35","article-title":"Self-normalizing neural networks","volume":"30","author":"Klambauer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1242\/jcs.02397"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.20.00108"},{"key":"ref38","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6970-9"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02513"},{"key":"ref41","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/nrc2248"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02856-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07618-3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S1534-5807(03)00153-9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1717139115"},{"key":"ref47","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/cancers12123557"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1201.0490"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72087-2_43"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"ref52","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of Machine Learning Research","volume":"139","author":"Radford"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72086-4_25"},{"key":"ref55","first-page":"6","article-title":"On random weights and unsupervised feature learning","author":"Andrew","year":"2011","journal-title":"In ICML"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/ijms21218127"},{"key":"ref57","article-title":"Prism: A multi-modal generative foundation model for slide-level histopathology","author":"Shaikovski","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3362852"},{"key":"ref59","first-page":"2136","article-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Shao","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref60","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"International conference on machine learning","author":"Sundararajan"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_41"},{"key":"ref62","first-page":"24261","article-title":"MLP-Mixer: An all-MLP Architecture for Vision","volume":"29","author":"Tolstikhin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.5114\/wo.2014.47136"},{"key":"ref64","article-title":"Molecular-driven foundation model for oncologic pathology","author":"Vaidya","year":"2025","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccr.2009.12.020"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/S0074-7696(07)65003-7"},{"key":"ref68","article-title":"When an image is worth $1,024 \\times 1,024$ words: A case study in computational pathology","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102559"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1136\/jcp.s3-8.1.48"},{"key":"ref71","article-title":"Multimodal multitask representation learning for pathology biobank metadata prediction","author":"Weng","year":"2019","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07441-w"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01942"},{"key":"ref74","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0819"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00645"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/5468858"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25471"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3176598"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72083-3_35"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444568.pdf?arnumber=11444568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:48Z","timestamp":1777613388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02217","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}