{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:14Z","timestamp":1777889114785,"version":"3.51.4"},"reference-count":65,"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 Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206147"],"award-info":[{"award-number":["62206147"]}],"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\/iccv51701.2025.01735","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18671-18681","source":"Crossref","is-referenced-by-count":0,"title":["Video-T1: Test-Time Scaling for Video Generation"],"prefix":"10.1109","author":[{"given":"Fangfu","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yimo","family":"Cai","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiyan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohang","family":"Zhan","sequence":"additional","affiliation":[{"name":"Tencent"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueqi","family":"Duan","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0759"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref5","article-title":"Universal selfconsistency for large language model generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.721"},{"key":"ref7","article-title":"Autoregressive video generation without vector quantization","author":"Deng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Can we generate images with cot? let\u2019s verify and reinforce image generation step by step","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref15","article-title":"Openai o1 system card","author":"Jaech","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"22185","article-title":"Video-lavit: unified video-language pre-training with decoupled visual-motional tokenization","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Jin","year":"2024"},{"key":"ref18","article-title":"Scaling laws for neural language models","author":"Kaplan","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Scaling laws for neural language models","author":"Kaplan","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Args: Alignment as reward-guided search","author":"Khanov","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","first-page":"25105","article-title":"Videopoet: a large language model for zero-shot video generation","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Kondratyuk","year":"2024"},{"key":"ref22","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"A survey on long video generation: Challenges, methods, and prospects","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","author":"Lifshitz","year":"2025","journal-title":"Multiagent verification: Scaling test-time compute with multiple verifiers"},{"key":"ref25","article-title":"Let\u2019s verify step by step","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lightman","year":"2023"},{"key":"ref26","article-title":"Motionclone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3666733"},{"key":"ref28","article-title":"Physics3d: Learning physical properties of 3d gaussians via video diffusion","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Can 1b llm surpass 405b llm? rethinking compute-optimal test-time scaling","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref31","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Step-video-t2v technical report: The practice, challenges, and future of video foundation model","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref33","author":"Ma","year":"2025","journal-title":"Inference-time scaling for diffusion models beyond scaling denoising steps"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"ref35","author":"Mahan","year":"2024","journal-title":"Generative reward models"},{"key":"ref36","article-title":"Webgpt: Browser-assisted question-answering with human feedback","author":"Nakano","year":"2021","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","first-page":"15841","article-title":"Observational scaling laws and the predictability of langauge model performance","volume":"37","author":"Ruan","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref43","article-title":"Scaling 11 m test-time compute optimally can be more effective than scaling model parameters","author":"Snell","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Scaling 11 m test-time compute optimally can be more effective than scaling model parameters","author":"Snell","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","first-page":"3008","article-title":"Learning to summarize with human feedback","volume":"33","author":"Stiennon","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref46","author":"Sun","year":"2024","journal-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion"},{"key":"ref47","article-title":"Kimi k1. 5: Scaling reinforcement learning with llms","author":"Team","year":"2025","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1247"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"ref51","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Thoughts are all over the place: On the underthinking of o1-like 11 ms","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref54","article-title":"Monte carlo tree search boosts reasoning via iterative preference learning","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00202"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i13.38107"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1221"},{"key":"ref58","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"The dawn of video generation: Preliminary explorations with sora-like models","author":"Zeng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref62","article-title":"Openprm: Building open-domain process-based reward models with preference trees","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref63","author":"Zhang","year":"2025","journal-title":"Generative verifiers: Reward modeling as next-token prediction"},{"key":"ref64","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref65","article-title":"Language agent tree search unifies reasoning acting and planning in language models","author":"Zhou","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\/11444438.pdf?arnumber=11444438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:21Z","timestamp":1777611981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01735","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}