{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:20:58Z","timestamp":1777890058497,"version":"3.51.4"},"reference-count":31,"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\/iccv51701.2025.01451","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15636-15645","source":"Crossref","is-referenced-by-count":1,"title":["VPO: Aligning Text-to-Video Generation Models with Prompt Optimization"],"prefix":"10.1109","author":[{"given":"Jiale","family":"Cheng","sequence":"first","affiliation":[{"name":"The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiliang","family":"Lyu","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotao","family":"Gu","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiazheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yida","family":"Lu","sequence":"additional","affiliation":[{"name":"The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayan","family":"Teng","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiao","family":"Dong","sequence":"additional","affiliation":[{"name":"The Knowledge Engineering Group (KEG), Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Tang","sequence":"additional","affiliation":[{"name":"The Knowledge Engineering Group (KEG), Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongning","family":"Wang","sequence":"additional","affiliation":[{"name":"The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minlie","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhipu AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A general language assistant as a laboratory for alignment","author":"Askell","year":"2021","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":"10.1109\/CVPR52729.2023.02161"},{"key":"ref4","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref5","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.176"},{"key":"ref7","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","volume-title":"Detoxify","author":"Hanu","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2923"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref13","article-title":"Prompt-a-video: Prompt your video diffusion model via preference-aligned 11 m","author":"Ji","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref15","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"T2vsafetybench: Evaluating the safety of text-to-video generative models","author":"Miao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref18","volume-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"issue":"2","key":"ref20","first-page":"3","article-title":"Hierarchical text-conditional image gener-ation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref23","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2096"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i13.38107"},{"key":"ref28","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","volume-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref30","article-title":"Large language models are human-level prompt engineers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhou","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210080"}],"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\/11443423.pdf?arnumber=11443423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:27Z","timestamp":1777613307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01451","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}