{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:01Z","timestamp":1777888801085,"version":"3.51.4"},"reference-count":60,"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\/iccv51701.2025.01740","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18725-18735","source":"Crossref","is-referenced-by-count":0,"title":["Prompt-A-Video: Prompt your Video Diffusion Model via Preference-Aligned LLM"],"prefix":"10.1109","author":[{"given":"Yatai","family":"Ji","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiacheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shilong","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoufa","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongjian","family":"Ge","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peize","family":"Sun","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqi","family":"Shao","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefeng","family":"Xiao","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weilin","family":"Huang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"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":"Qwen-vl: A frontier large vision-language model with versatile abilities","volume":"abs\/2308.12966","author":"Bai","year":"2023","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref4","article-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models","author":"Bao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref6","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref8","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref9","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref11","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","volume":"abs\/2305.13840","author":"Chen","year":"2023","journal-title":"CoRR"},{"key":"ref12","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume":"abs\/2312.14238","author":"Chen","year":"2023","journal-title":"CoRR"},{"key":"ref13","article-title":"The llama 3 herd of models","volume":"abs\/2407.21783","author":"Dubey","year":"2024","journal-title":"CoRR"},{"key":"ref14","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Connecting large language models with evolutionary algorithms yields powerful prompt optimizers","author":"Guo","year":"2024","journal-title":"ICLR"},{"key":"ref16","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2923"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref19","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00656"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02228"},{"key":"ref24","article-title":"IDA-VLM: towards movie understanding via id-aware large vision-language model","volume":"abs\/2407.07577","author":"Ji","year":"2024","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref26","article-title":"Evolution through large models","volume":"abs\/2206.08896","author":"Lehman","year":"2022","journal-title":"CoRR"},{"key":"ref27","article-title":"Prompt optimization with human feedback","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501825"},{"key":"ref30","article-title":"Are large language models good prompt optimizers?","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Improving text-to-image consistency via automatic prompt optimization","author":"Ma\u00f1as","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02514"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/0144929x.2023.2286532"},{"key":"ref34","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref35","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2023","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/math12060929"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref39","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"ref41","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Global and local semantic completion learning for visionlanguage pre-training","volume":"abs\/2306.07096","author":"Tu","year":"2023","journal-title":"CoRR"},{"key":"ref43","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","author":"Villegas","year":"2023","journal-title":"ICLR"},{"key":"ref44","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"On discrete prompt optimization for diffusion models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref47","article-title":"Diffusiondb: A large-scale prompt gallery dataset for text-toimage generative models","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref49","article-title":"Human preference score v 2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.351"},{"key":"ref51","article-title":"Easyanimate: A high-performance long video generation method based on transformer architecture","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","volume":"abs\/2404.16994","author":"Xu","year":"2024","journal-title":"CoRR"},{"key":"ref53","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Chatglm: A family of large language models from GLM-130B to GLM-4 all tools","volume":"abs\/2406.12793","author":"Zeng","year":"2024","journal-title":"CoRR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.53"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2009.2014613"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00766"},{"key":"ref58","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"ref60","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","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\/11446279.pdf?arnumber=11446279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:37Z","timestamp":1777611517000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01740","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}