{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:15Z","timestamp":1778048355970,"version":"3.51.4"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00594","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6142-6152","source":"Crossref","is-referenced-by-count":0,"title":["Align Video Diffusion Model with Online Video-Centric Preference Optimization"],"prefix":"10.1109","author":[{"given":"Jiacheng","family":"Zhang","sequence":"first","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":"Weifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yatai","family":"Ji","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"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":"Kai","family":"Han","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","first-page":"4447","article-title":"A general theoretical paradigm to understand learning from human preferences","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Azar"},{"key":"ref3","article-title":"Constitutional ai: Harmlessness from ai feedback","author":"Bai","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref5","article-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models","author":"Bao","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref7","article-title":"Revisiting feature prediction for learning visual representations from video","author":"Bardes","year":"2024"},{"key":"ref8","article-title":"Training diffusion models with reinforcement learning","volume-title":"ICLR","author":"Black"},{"key":"ref9","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref11","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref12","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref14","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.221"},{"key":"ref16","article-title":"Raft: Reward ranked finetuning for generative foundation model alignment","author":"Dong","year":"2023"},{"key":"ref17","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref18","article-title":"Kto: Model alignment as prospect theoretic optimization","volume-title":"ICML","author":"Ethayarajh"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3497"},{"key":"ref20","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"ICLR","author":"Guo"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref22","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref23","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"ICLR","author":"Hong"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref27","article-title":"Subjective-aligned dateset and metric for text-to-video quality assessment","volume-title":"ACMMM","author":"Kou"},{"key":"ref28","article-title":"Rlaif: Scaling reinforcement learning from human feedback with ai feedback","author":"Lee","year":"2023"},{"key":"ref29","article-title":"Aligning textto-image models using human feedback","author":"Lee","year":"2023"},{"key":"ref30","article-title":"T2v-turbo: Breaking the quality bottleneck of video consistency model with mixed reward feedback","author":"Li","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00750"},{"key":"ref32","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref33","article-title":"Training language models to follow instructions with human feedback","volume-title":"NeurIPS","author":"Ouyang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref35","article-title":"Video diffusion alignment via reward gradients","author":"Prabhudesai","year":"2024"},{"key":"ref36","author":"Rafailov","year":"2024","journal-title":"Direct preference optimization: Your language model is secretly a reward model"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref39","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer"},{"key":"ref40","article-title":"Defining and characterizing reward gaming","volume-title":"NeurIPS","author":"Skalse"},{"key":"ref41","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref42","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref44","volume-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref46","article-title":"Q-align: Teaching lmms for visual scoring via discrete text-defined levels","volume-title":"ICML","author":"Wu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref48","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023"},{"key":"ref49","article-title":"Better aligning text-to-image models with human preference","author":"Wu","year":"2023"},{"key":"ref50","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"NeurIPS","author":"Xu"},{"key":"ref51","article-title":"Easyanimate: A high-performance long video generation method based on transformer architecture","author":"Xu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"ref53","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00618"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00766"},{"key":"ref56","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref57","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022"},{"key":"ref58","article-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2019"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492063.pdf?arnumber=11492063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:54Z","timestamp":1778046834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00594","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}