{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:26Z","timestamp":1777888766468,"version":"3.51.4"},"reference-count":53,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00254","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2642-2652","source":"Crossref","is-referenced-by-count":0,"title":["Is Visual in-Context Learning for Compositional Medical Tasks Within Reach?"],"prefix":"10.1109","author":[{"given":"Simon","family":"Rei\u00df","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zdravko","family":"Marinov","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Jaus","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Constantin","family":"Seibold","sequence":"additional","affiliation":[{"name":"Heidelberg University Hospital"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Saquib","family":"Sarfraz","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erik","family":"Rodner","sequence":"additional","affiliation":[{"name":"University of Applied Sciences Berlin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rainer","family":"Stiefelhagen","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02157"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"key":"ref5","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"International Conference on Learning Representations","author":"Baranchuk","year":"2021"},{"key":"ref6","article-title":"xlstm: Extended long short-term memory","author":"Beck","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2901398"},{"key":"ref8","article-title":"Language models are few-shot learners","author":"Brown","year":"2005","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01960"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref11","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00602"},{"key":"ref13","article-title":"Vision transformers need registers","author":"Darcet","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume":"abs\/1810.04805","author":"Devlin","year":"2018","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref18","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3658136"},{"key":"ref20","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Data-efficient large vision models through sequential autoregression","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03977-3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647307"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1577"},{"key":"ref26","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3452629"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3129870"},{"key":"ref31","article-title":"Supervised transfer learning at scale for medical imaging","author":"Mustafa","year":"2021","journal-title":"arXiv preprint"},{"issue":"8","key":"ref32","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01061"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00941"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_24"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01487"},{"key":"ref37","article-title":"Medical vision generalist: Unifying medical imaging tasks in context","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref39","article-title":"Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter","author":"Sanh","year":"1910","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00535"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3554410"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.161"},{"key":"ref44","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref48","volume-title":"Thinking 11 ms: General instruction following with thought generation","author":"Wu","year":"2024a"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"ref50","article-title":"Imagebrush: Learning visual in-context instructions for exemplar-based image manipulation","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Video in-context learning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0780"}],"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\/11445639.pdf?arnumber=11445639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:56:45Z","timestamp":1777611405000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00254","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}