{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:06:09Z","timestamp":1789038369204,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373618","type":"print"},{"value":"9783032373625","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37362-5_26","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:08:22Z","timestamp":1789034902000},"page":"483-501","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["IC-World: In-Context Generation for Shared World Modeling"],"prefix":"10.1007","author":[{"given":"Fan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruibo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyou","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deheng","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"26_CR1","unstructured":"Agarwal, N., et\u00a0al.: Cosmos world foundation model platform for physical AI. arXiv preprint arXiv:2501.03575 (2025)"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Bai, J., et\u00a0al.: Recammaster: camera-controlled generative rendering from a single video. arXiv preprint arXiv:2503.11647 (2025)","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"26_CR3","unstructured":"Bai, S., et al.: Qwen2.5-VL Technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"26_CR4","unstructured":"Bai, S., et al.: Univg-r1: reasoning guided universal visual grounding with reinforcement learning. arXiv preprint arXiv:2505.14231 (2025)"},{"key":"26_CR5","unstructured":"Chen, H., et\u00a0al.: Videocrafter1: open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512 (2023)"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Chen, H., et al.: Videocrafter2: overcoming data limitations for high-quality video diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7310\u20137320 (2024)","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"26_CR7","unstructured":"Chu, Z., et al.: Sora detector: a unified hallucination detection for large text-to-video models. arXiv preprint arXiv:2405.04180 (2024)"},{"key":"26_CR8","unstructured":"Contributors, L.: Lightx2v: light video generation inference framework (2025). https:\/\/github.com\/ModelTC\/lightx2v"},{"key":"26_CR9","unstructured":"Deng, et al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Fang, R., et al.: Got: unleashing reasoning capability of multimodal large language model for visual generation and editing. arXiv preprint arXiv:2503.10639 (2025)","DOI":"10.52202\/085713-2270"},{"key":"26_CR11","unstructured":"Fei, Z., Qiu, D., Li, D., Yu, C., Fan, M.: Video diffusion transformers are in-context learners. arXiv preprint arXiv:2412.10783 (2024)"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Feng, K., et al.: Video-r1: reinforcing video reasoning in MLLMs. arXiv preprint arXiv:2503.21776 (2025)","DOI":"10.52202\/085713-3310"},{"key":"26_CR13","unstructured":"Guo, D., et\u00a0al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"26_CR14","unstructured":"HaCohen, Y., et al.: Ltx-video: realtime video latent diffusion. arXiv preprint arXiv:2501.00103 (2024)"},{"key":"26_CR15","unstructured":"He, H., et al.: Cameractrl: enabling camera control for text-to-video generation. arXiv preprint arXiv:2404.02101 (2024)"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a reference free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"26_CR17","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local Nash equilibrium. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"26_CR18","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: Cogvideo: large-scale pretraining for text-to-video generation via transformers. arXiv preprint arXiv:2205.15868 (2022)"},{"issue":"2","key":"26_CR19","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"key":"26_CR20","unstructured":"Huang, L., et al.: In-context lora for diffusion transformers. arXiv preprint arXiv:2410.23775 (2024)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: Vbench: comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"26_CR22","unstructured":"Kong, W., et\u00a0al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Kuang, Z., et al.: Collaborative video diffusion: consistent multi-video generation with camera control. In: arXiv (2024)","DOI":"10.52202\/079017-0518"},{"key":"26_CR24","doi-asserted-by":"publisher","first-page":"75692","DOI":"10.52202\/079017-2410","volume":"37","author":"J Li","year":"2024","unstructured":"Li, J., et al.: T2v-turbo: breaking the quality bottleneck of video consistency model with mixed reward feedback. Adv. Neural. Inf. Process. Syst. 37, 75692\u201375726 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., Harada, T.: Lepard: learning partial point cloud matching in rigid and deformable scenes. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00547"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Ling, L., et\u00a0al.: Dl3dv-10k: a large-scale scene dataset for deep learning-based 3D vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22160\u201322169 (2024)","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Liu, R., et al.: Videodpo: Omnipreference alignment for video diffusion generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8009\u20138019 (2025)","DOI":"10.1109\/CVPR52734.2025.00750"},{"key":"26_CR28","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"26_CR29","unstructured":"Qwen-Image, T.: Qwen-image Technical report (2025). https:\/\/arxiv.org\/abs\/2508.02324"},{"key":"26_CR30","unstructured":"Russell, L., et al.: Gaia-2: a controllable multi-view generative world model for autonomous driving. arXiv preprint arXiv:2503.20523 (2025)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Sahoo, P., Meharia, P., Ghosh, A., Saha, S., Jain, V., Chadha, A.: A comprehensive survey of hallucination in large language, image, video and audio foundation models. arXiv preprint arXiv:2405.09589 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.685"},{"key":"26_CR32","unstructured":"Wan, T.: Wan: open and advanced large-scale video generative models. arxiv preprint arXiv:2503.20314 (2025)"},{"key":"26_CR33","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: 4real-video: learning generalizable photo-realistic 4D video diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17723\u201317732 (2025)","DOI":"10.1109\/CVPR52734.2025.01651"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: Time-r1: post-training large vision language model for temporal video grounding. arXiv preprint arXiv:2503.13377 (2025)","DOI":"10.52202\/085713-2793"},{"key":"26_CR35","unstructured":"Wang, Y., et al.: $$\\pi ^3$$: scalable permutation-equivariant visual geometry learning (2025). https:\/\/arxiv.org\/abs\/2507.13347"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Wu, R., et al.: Cat4d: create anything in 4d with multi-view video diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26057\u201326068 (2025)","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"26_CR37","unstructured":"Wu, W., et al.: Drivescape: towards high-resolution controllable multi-view driving video generation. arXiv preprint arXiv:2409.05463 (2024)"},{"key":"26_CR38","unstructured":"Xiao, Y., et al.: Spatialtrackerv2: 3D point tracking made easy. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025). https:\/\/arxiv.org\/abs\/2507.12462"},{"key":"26_CR39","unstructured":"Xie, Y., Yao, C.H., Voleti, V., Jiang, H., Jampani, V.: Sv4d: dynamic 3D content generation with multi-frame and multi-view consistency. arXiv preprint arXiv:2407.17470 (2024)"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Xing, J., et al.: Dynamicrafter: animating open-domain images with video diffusion priors. arXiv preprint arXiv:2310.12190 (2023)","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"26_CR41","unstructured":"Xu, J., et al.: Easyanimate: a high-performance long video generation method based on transformer architecture. arXiv preprint arXiv:2405.18991 (2024)"},{"key":"26_CR42","unstructured":"Xue, Z., et\u00a0al.: Dancegrpo: unleashing GRPO on visual generation. arXiv preprint arXiv:2505.07818 (2025)"},{"key":"26_CR43","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"26_CR44","doi-asserted-by":"publisher","first-page":"73366","DOI":"10.52202\/079017-2334","volume":"37","author":"H Yuan","year":"2024","unstructured":"Yuan, H., Chen, Z., Ji, K., Gu, Q.: Self-play fine-tuning of diffusion models for text-to-image generation. Adv. Neural. Inf. Process. Syst. 37, 73366\u201373398 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR45","unstructured":"Zhang, J., et al.: Onlinevpo: align video diffusion model with online video-centric preference optimization. arXiv preprint arXiv:2412.15159 (2024)"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, J., Lu, Y., Yang, Z., Yang, Y.: In-context edit: enabling instructional image editing with in-context generation in large scale diffusion transformer. arXiv preprint arXiv:2504.20690 (2025)","DOI":"10.52202\/085713-4646"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Zhao, G., Wang, X., Zhu, Z., Chen, X., Huang, G., Bao, X., Wang, X.: Drivedreamer-2: LLM-enhanced world models for diverse driving video generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 10412\u201310420 (2025)","DOI":"10.1609\/aaai.v39i10.33130"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Zheng, W., Song, R., Guo, X., Zhang, C., Chen, L.: Genad: generative end-to-end autonomous driving. In: European Conference on Computer Vision, pp. 87\u2013104. Springer (2024)","DOI":"10.1007\/978-3-031-73650-6_6"},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, S., Yang, P., Wang, J., Luo, Y., Loy, C.C.: Upscale-a-video: Temporalconsistent diffusion model for real-world video super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2535\u20132545 (2024)","DOI":"10.1109\/CVPR52733.2024.00245"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37362-5_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:08:40Z","timestamp":1789034920000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37362-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373618","9783032373625"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37362-5_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}