{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T15:02:30Z","timestamp":1778511750305,"version":"3.51.4"},"reference-count":44,"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\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62402406"],"award-info":[{"award-number":["62402406"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01078","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11590-11599","source":"Crossref","is-referenced-by-count":1,"title":["GameFactorly: Creating New Games with Generative Interactive Videos"],"prefix":"10.1109","author":[{"given":"Jiwen","family":"Yu","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiran","family":"Qin","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xintao","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1873"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1789"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Genie: Generative interactive environments","volume-title":"In Forty-first International Conference on Machine Learning","author":"Bruce"},{"key":"ref5","article-title":"Gamegen-x: Interactive open-world game video generation","volume-title":"In International Conference on Learning Representations","author":"Che"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0759"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"arXiv preprint","author":"Chen","year":"2023"},{"key":"ref9","volume-title":"Oasis: A universe in a transformer","year":"2024"},{"key":"ref10","year":"2024","journal-title":"Genie 2: A large-scale foundation world model"},{"key":"ref11","article-title":"Minedojo: Building open-ended embodied agents with internet-scale knowledge","volume-title":"In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Fan"},{"key":"ref12","article-title":"The matrix: Infinite-horizon world generation with real-time moving control","author":"Feng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref14","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"In International Conference on Learning Representations","author":"Edward"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-08600-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00131"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00576"},{"key":"ref21","volume-title":"Open-sora-plan","author":"Lab","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00993"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00357"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3635705"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref26","volume-title":"Creating video from text","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref29","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref30","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref32","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref33","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref35","article-title":"Diffusion models are real-time game engines","author":"Valevski","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref38","article-title":"Learning interactive real-world simulators","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Playable game generation","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657481"},{"key":"ref41","article-title":"Position: Video as the new language for real-world decision making","volume-title":"In Proceedings of the 41st International Conference on Machine Learning","author":"Yang"},{"key":"ref42","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"}],"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\/11445245.pdf?arnumber=11445245","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:30:54Z","timestamp":1777530654000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445245\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01078","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}