{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:11:35Z","timestamp":1780589495142,"version":"3.54.1"},"reference-count":71,"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\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01EB037669"],"award-info":[{"award-number":["R01EB037669"]}],"id":[{"id":"10.13039\/100000002","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\/iccv51701.2025.00779","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8319-8329","source":"Crossref","is-referenced-by-count":2,"title":["Medical World Model"],"prefix":"10.1109","author":[{"given":"Yijun","family":"Yang","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology,Guangzhou"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao-Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuping","family":"Liu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuwen","family":"Sun","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Nanjing Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California,San Francisco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rama","family":"Chellappa","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongwei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Guangzhou"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieneng","family":"Chen","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Claude 3.5 sonnet model card addendum","volume-title":"Claude-3.5 Model Card","year":"2024"},{"key":"ref2","author":"Bai","year":"2025","journal-title":"Qwen2.5-vl technical report"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01472"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102789"},{"key":"ref5","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-024-01246-y"},{"key":"ref7","author":"Bommasani","year":"2021","journal-title":"On the opportunities and risks of foundation models"},{"key":"ref8","article-title":"Genie: Generative interactive environments","volume-title":"Forty-first International Conference on Machine Learning","author":"Bruce","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2024.111827"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.418"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01060"},{"key":"ref12","author":"Chen","year":"2024","journal-title":"Surgsora: Decoupled rgbd-flow diffusion model for controllable surgical video generation"},{"key":"ref13","author":"Chen","year":"2023","journal-title":"Meditron-70b: Scaling medical pretraining for large language models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/00949650212847"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2759102"},{"key":"ref16","author":"Moor","year":"2025","journal-title":"Medgpt"},{"key":"ref17","author":"Du","year":"2023","journal-title":"Video language planning"},{"key":"ref18","article-title":"Video language planning","volume-title":"ICML","author":"Du","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref20","article-title":"Cox proportional-hazards regression for survival data","author":"Fox","year":"2002","journal-title":"An R and S-PLUS companion to applied regression"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref22","author":"Guo","year":"2025","journal-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31635-3_22"},{"key":"ref24","author":"Hafner","year":"2023","journal-title":"Mastering diverse domains through world models"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72086-4_19"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03097-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_45"},{"key":"ref28","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","author":"Hu","year":"2023","journal-title":"Gaia-1: A generative world model for autonomous driving"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00717"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102472"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2025.01.046"},{"key":"ref33","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-018-0482-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2522"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72378-0_4"},{"issue":"1","key":"ref39","first-page":"1","article-title":"A path towards autonomous machine intelligence version 0.9. 2, 2022\u201306-27","volume":"62","author":"LeCun","year":"2022","journal-title":"Open Review"},{"key":"ref40","first-page":"1","article-title":"Deep learning-based prediction of posttreatment survival in hepatocellular carcinoma patients using pre-treatment ct images and clinical data","author":"Lee","year":"2024","journal-title":"Journal of Imaging Informatics in Medicine"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72089-5_22"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.imed.2025.01.001"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2026.3658596"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00635-3"},{"key":"ref45","author":"Lu","year":"2024","journal-title":"Generative world explorer"},{"key":"ref46","author":"Luo","year":"2024","journal-title":"Grounding video models to actions through goal conditioned exploration"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3217501"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180021"},{"key":"ref50","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol","year":"2021"},{"key":"ref51","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref53","first-page":"1332","article-title":"Masked world models for visual control","volume-title":"Conference on Robot Learning","author":"Seo","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03423-7"},{"key":"ref56","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref57","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref60","author":"van Griethuysen","year":"2025","journal-title":"Radiomics-based cox model"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_4"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72104-5_20"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102150"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59713-9_27"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3066161"},{"key":"ref68","first-page":"29001","article-title":"Addressing asynchronicity in clinical multimodal fusion via individualized chest x-ray generation","volume":"37","author":"Yao","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.725"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02318-w"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32239-7_56"}],"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\/11444416.pdf?arnumber=11444416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:11Z","timestamp":1777611971000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00779","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}