{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T02:59:47Z","timestamp":1790305187989,"version":"4.1.0"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032382351","type":"print"},{"value":"9783032382368","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T00:00:00Z","timestamp":1790380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T00:00:00Z","timestamp":1790380800000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-38236-8_43","type":"book-chapter","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T02:44:48Z","timestamp":1790304288000},"page":"447-457","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SAW: Toward a\u00a0Surgical Action World Model via\u00a0Controllable and\u00a0Scalable Video Generation"],"prefix":"10.1007","author":[{"given":"Sampath","family":"Rapuri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lalithkumar","family":"Seenivasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominik","family":"Schneider","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roger","family":"Soberanis-Mukul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiru","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenhao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyan","family":"Jing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daguang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathias","family":"Unberath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,26]]},"reference":[{"key":"43_CR1","first-page":"57602","volume":"38","author":"Y Bai","year":"2026","unstructured":"Bai, Y., Fang, S., Yu, C., Wang, F., Huang, Q.: GeoVideo: introducing geometric regularization into video generation model. Adv. Neural. Inf. Process. Syst. 38, 57602\u201357622 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"Biagini, D., Navab, N., Farshad, A.: HieraSurg: hierarchy-aware diffusion model for surgical video generation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 310\u2013319. Springer (2025)","DOI":"10.1007\/978-3-032-05114-1_30"},{"issue":"8","key":"43_CR3","first-page":"1","volume":"1","author":"T Brooks","year":"2024","unstructured":"Brooks, T., et al.: Video generation models as world simulators. OpenAI Blog 1(8), 1 (2024)","journal-title":"OpenAI Blog"},{"key":"43_CR4","unstructured":"Bruce, J., et\u00a0al.: Genie: generative interactive environments. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"43_CR5","unstructured":"Carion, N., et\u00a0al.: SAM 3: segment anything with concepts. arXiv preprint arXiv:2511.16719 (2025)"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Chen, T., Yang, S., Wang, J., Bai, L., Ren, H., Zhou, L.: SurgSora: object-aware diffusion model for controllable surgical video generation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 521\u2013531. Springer (2025)","DOI":"10.1007\/978-3-032-05127-1_50"},{"key":"43_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale (2020). arXiv:2010.11929 arXiv preprint"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Fazzari, E., Stefanini, C.: Deep reinforcement learning for surgical robotics with state and image information: a survey (2026)","DOI":"10.21203\/rs.3.rs-8621244\/v1"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"Ge, S., Mahapatra, A., Parmar, G., Zhu, J.Y., Huang, J.B.: On the content bias in fr\u00e9chet video distance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7277\u20137288 (2024)","DOI":"10.1109\/CVPR52733.2024.00695"},{"key":"43_CR10","unstructured":"Ha, D., Schmidhuber, J.: World models. arXiv preprint arXiv:1803.101222(3), \u00a0440 (2018)"},{"key":"43_CR11","unstructured":"HaCohen, Y., et\u00a0al.: LTX-Video: realtime video latent diffusion. arXiv preprint arXiv:2501.00103 (2024)"},{"key":"43_CR12","unstructured":"Huang, L., et al.: In-context LoRA for diffusion transformers (2024). arXiv:2410.23775 arXiv preprint"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Koju, S., et al.: Surgical vision world model. In: MICCAI Workshop on Data Engineering in Medical Imaging, pp. 1\u201310. Springer (2025)","DOI":"10.1007\/978-3-032-08009-7_1"},{"key":"43_CR14","doi-asserted-by":"publisher","first-page":"1551838","DOI":"10.3389\/fsurg.2025.1551838","volume":"12","author":"W Liao","year":"2025","unstructured":"Liao, W., et al.: Artificial intelligence-assisted phase recognition and skill assessment in laparoscopic surgery: a systematic review. Front. Surg. 12, 1551838 (2025)","journal-title":"Front. Surg."},{"key":"43_CR15","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling (2022). arXiv:2210.02747 arXiv preprint"},{"key":"43_CR16","unstructured":"Mittal, M., et al.: Isaac Lab: a GPU-accelerated simulation framework for multi-modal robot learning (2025). arXiv:2511.04831 arXiv preprint"},{"key":"43_CR17","unstructured":"Oh, K.H., et al.: Expanded comprehensive robotic cholecystectomy dataset (CRCD) (2024). arXiv:2412.12238 arXiv preprint"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"P\u00e9rez, P., Gangnet, M., Blake, A.: Poisson image editing. In: Seminal Graphics Papers: pushing the boundaries, vol. 2, pp. 577\u2013582 (2023)","DOI":"10.1145\/3596711.3596772"},{"issue":"2","key":"43_CR19","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1109\/LRA.2022.3227873","volume":"8","author":"PM Scheikl","year":"2022","unstructured":"Scheikl, P.M., et al.: Sim-to-real transfer for visual reinforcement learning of deformable object manipulation for robot-assisted surgery. IEEE Robot. Autom. Lett. 8(2), 560\u2013567 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"6","key":"43_CR20","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1007\/s11548-023-02914-1","volume":"18","author":"S Sharma","year":"2023","unstructured":"Sharma, S., Nwoye, C.I., Mutter, D., Padoy, N.: Rendezvous in time: an attention-based temporal fusion approach for surgical triplet recognition. Int. J. Comput. Assist. Radiol. Surg. 18(6), 1053\u20131059 (2023)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"43_CR21","doi-asserted-by":"crossref","unstructured":"Sivakumar, S.K., Frisch, Y., Ghazaei, G., Mukhopadhyay, A.: SG2Vid: scene graphs enable fine-grained control for video synthesis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 511\u2013521. Springer (2025)","DOI":"10.1007\/978-3-032-05114-1_49"},{"key":"43_CR22","doi-asserted-by":"crossref","unstructured":"Tagliabue, E., Pore, A., Dall\u2019Alba, D., Magnabosco, E., Piccinelli, M., Fiorini, P.: Soft tissue simulation environment to learn manipulation tasks in autonomous robotic surgery. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3261\u20133266. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341710"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6450\u20136459 (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"issue":"1","key":"43_CR24","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De Mathelin, M., Padoy, N.: EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imag. 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imag."},{"key":"43_CR25","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"43_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102770","volume":"86","author":"M Wagner","year":"2023","unstructured":"Wagner, M., M\u00fcller-Stich, B.P., Kisilenko, A., Tran, D., Heger, P., M\u00fcndermann, L., Lubotsky, D.M., M\u00fcller, B., Davitashvili, T., Capek, M., et al.: Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the heichole benchmark. Med. Image Anal. 86, 102770 (2023)","journal-title":"Med. Image Anal."},{"key":"43_CR27","unstructured":"Wang, A., et\u00a0al.: WAN: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.203143(4), \u00a06 (2025)"},{"issue":"4","key":"43_CR28","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"43_CR29","doi-asserted-by":"publisher","first-page":"21875","DOI":"10.52202\/079017-0688","volume":"37","author":"L Yang","year":"2024","unstructured":"Yang, L., et al.: Depth anything V2. Adv. Neural. Inf. Process. Syst. 37, 21875\u201321911 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"43_CR30","unstructured":"Yang, M., Du, Y., Ghasemipour, K., Tompson, J., Schuurmans, D., Abbeel, P.: Learning interactive real-world simulators. arXiv preprint arXiv:2310.061141(2), \u00a06 (2023)"},{"key":"43_CR31","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/RBME.2017.2773521","volume":"11","author":"J Zhang","year":"2017","unstructured":"Zhang, J., Zhong, Y., Gu, C.: Deformable models for surgical simulation: a survey. IEEE Rev. Biomed. Eng. 11, 143\u2013164 (2017)","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"43_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"43_CR33","unstructured":"Zia, A., et al.: Surgical visual understanding (SurgVU) dataset (2025). arXiv:2501.09209 arXiv preprint"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38236-8_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T02:44:51Z","timestamp":1790304291000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38236-8_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,26]]},"ISBN":["9783032382351","9783032382368"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38236-8_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,26]]},"assertion":[{"value":"26 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2026\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}