{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:59Z","timestamp":1777865519673,"version":"3.51.4"},"reference-count":82,"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\/iccv51701.2025.01012","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10875-10885","source":"Crossref","is-referenced-by-count":0,"title":["AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction"],"prefix":"10.1109","author":[{"given":"Junhao","family":"Cheng","sequence":"first","affiliation":[{"name":"City University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuying","family":"Ge","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixiao","family":"Ge","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Liao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Decart AI","year":"2024","journal-title":"Oasis: The future engine of virtual worlds"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3649921.3650010"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Genie: Generative interactive environments","volume-title":"Forty-first International Conference on Machine Learning","author":"Bruce","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.658"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","author":"Carse","year":"1986","journal-title":"Finite and infinite games: A vision of life as play and possibility"},{"key":"ref8","article-title":"Gamegen-x: Interactive open-world game video generation","author":"Che","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref10","author":"Cheng","year":"2024","journal-title":"Autostudio: Crafting consistent subjects in multi-turn interactive image generation"},{"key":"ref11","author":"Cheng","year":"2024","journal-title":"Theatergen: Character management with 11 m for consistent multi-turn image generation"},{"issue":"240","key":"ref12","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676352"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01804"},{"key":"ref15","article-title":"Ai-based game design: Enabling new playable experiences","volume-title":"UC Santa Cruz Baskin School of Engineering","volume":"2","author":"Eladhari","year":"2011"},{"key":"ref16","author":"Ennabili","year":"2023","journal-title":"A comparison of traditional game design vs. ai-driven game design"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1333"},{"key":"ref18","article-title":"Dreamsim: Learning new dimensions of human visual similarity using synthetic data","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Exploring novel game spaces with fluidic games","author":"Gaudl","year":"2018","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Divot: Diffusion powers video tokenizer for comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v12i1.12861"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v14i1.13022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3060005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3600149"},{"key":"ref26","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CoG60054.2024.10645597"},{"key":"ref28","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"A survey on large language model-based game agents","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Mistral 7b","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/141"},{"key":"ref32","article-title":"Lyfe agents: Generative agents for low-cost real-time social interactions","author":"Kaiya","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080431"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00131"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v15i1.7418"},{"key":"ref37","article-title":"Black Forest Labs","volume-title":"Flux","year":"2024"},{"key":"ref38","article-title":"Mini-dalle3: Interactive text to image by prompting large language models","author":"Lai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Unbounded: A generative infinite game of character life simulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05383-8"},{"key":"ref41","article-title":"Rl-gpt: Integrating reinforcement learning and code-as-policy","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Videodrafter: Content-consistent multi-scene video generation with 11 m","author":"Long","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11210189"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CoG57401.2023.10333197"},{"key":"ref45","article-title":"OpenAI","year":"2023","journal-title":"Openai models"},{"key":"ref46","article-title":"Sakuga- 42 m dataset: Scaling up cartoon research","author":"Pan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"issue":"140","key":"ref49","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"ref51","article-title":"Blending levels from different games using 1stms","volume-title":"AIIDE Workshops","author":"Sarkar","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3069833"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-42716-4"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1380"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v10i3.12748"},{"key":"ref56","article-title":"Experiments in map generation using markov chains","author":"Snodgrass","year":"2014","journal-title":"FDG"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2016.2623560"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2361"},{"key":"ref59","article-title":"Super mario as a string: Platformer level generation via 1stms","author":"Summerville","year":"2016","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2846639"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v19i1.27539"},{"key":"ref62","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3582437.3587211"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/2538528.2538537"},{"key":"ref65","author":"Treanor","year":"2015","journal-title":"Ai-based game design patterns"},{"key":"ref66","article-title":"Diffusion models are real-time game engines","author":"Valevski","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205517"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02309-y"},{"key":"ref69","article-title":"Pandora: Towards general world model with natural language actions and video states","author":"Xiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01781"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3397712"},{"key":"ref72","article-title":"Playable game generation","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00197"},{"key":"ref74","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Gamefactory: Creating new games with generative interactive videos","author":"Yu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Envgen: Generating and adapting environments via 11 ms for training embodied agents","author":"Zala","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","article-title":"Moviedreamer: Hierarchical generation for coherent long visual sequence","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"ref79","article-title":"Steve-eye: Equipping 11 m-based embodied agents with visual perception in open worlds","author":"Zheng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3649921.3650001"},{"key":"ref81","first-page":"110315","article-title":"Storydiffusion: Consistent selfattention for long-range image and video generation","volume":"37","author":"Zhou","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref82","article-title":"Vl-gpt: A generative pre-trained transformer for vision and language understanding and generation","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"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\/11446246.pdf?arnumber=11446246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:45:44Z","timestamp":1777531544000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01012","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}