{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:59:51Z","timestamp":1777874391654,"version":"3.51.4"},"reference-count":66,"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\/501100003561","name":"Ministry of Culture, Sports and Tourism","doi-asserted-by":"publisher","award":["RS-2024-00361757"],"award-info":[{"award-number":["RS-2024-00361757"]}],"id":[{"id":"10.13039\/501100003561","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\/iccv51701.2025.01601","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17235-17245","source":"Crossref","is-referenced-by-count":0,"title":["V.I.P.: Iterative Online Preference Distillation for Efficient Video Diffusion Models"],"prefix":"10.1109","author":[{"given":"Jisoo","family":"Kim","sequence":"first","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wooseok","family":"Seo","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junwan","family":"Kim","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungho","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sooyeon","family":"Park","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjae","family":"Yu","sequence":"additional","affiliation":[{"name":"Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref3","article-title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv:2311.15127"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"ref6","article-title":"Edgefusion: On-Device Text-to-Image Generation","author":"Castells","year":"2024","journal-title":"arXiv preprint arXiv:2404.11925"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","article-title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2401.01335"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01451"},{"key":"ref10","article-title":"RLHF Workflow: From Reward Modeling to Online RLHF","author":"Dong","year":"2024","journal-title":"arXiv preprint arXiv:2405.07863"},{"key":"ref11","article-title":"KTO: Model Alignment as Prospect Theoretic Optimization","author":"Ethayarajh","year":"2024","journal-title":"arXiv preprint arXiv:2402.01306"},{"key":"ref12","article-title":"Robust Preference Optimization Through Reward Model Distillation","author":"Fisch","year":"2024","journal-title":"arXiv preprint arXiv:2405.19316"},{"key":"ref13","first-page":"25661","article-title":"A Theory of the Distortion-Perception Tradeoff in Wasserstein Space","volume":"34","author":"Freirich","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00302"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref16","article-title":"Direct Language Model Alignment From Online AI Feedback","author":"Guo","year":"2024","journal-title":"arXiv preprint arXiv:2402.04792"},{"key":"ref17","article-title":"Animatediff: Animate Your Personalized Text-to-Image Diffusion Models Without Specific Tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv:2307.04725"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref21","first-page":"6840","article-title":"Denoising Diffusion Probabilistic Models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.626"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref24","first-page":"36602","article-title":"Unpacking DPO and PPO: Disentangling Best Practices for Learning From Preference Feedback","volume":"37","author":"Ivison","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"HuviDPO: Enhancing Video Generation Through Direct Preference Optimization for Human-Centric Alignment","author":"Jiang","year":"2025","journal-title":"arXiv preprint arXiv:2502.01690"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_22"},{"key":"ref27","author":"Kingma","year":"2013","journal-title":"Auto-Encoding Variational Bayes"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.829"},{"key":"ref29","article-title":"T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model With Mixed Reward Feedback","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2405.18750"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0907"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3483"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3483"},{"key":"ref33","article-title":"Animatediff-Lightning: Cross-Model Diffusion Distillation","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv:2403.12706"},{"key":"ref34","article-title":"SDXL-Lightning: Progressive Adversarial Diffusion Distillation","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv:2402.13929"},{"key":"ref35","article-title":"SDXL-Lightning: Progressive Adversarial Diffusion Distillation","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv:2402.13929"},{"key":"ref36","article-title":"Improving Video Generation With Human Feedback","author":"Liu","year":"2025","journal-title":"arXiv preprint arXiv:2501.13918"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00750"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref39","article-title":"Provably Mitigating Overoptimization in RLHF: Your SFT Loss Is Implicitly an Adversarial Regularizer","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2405.16436"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3946"},{"key":"ref41","article-title":"Posteriormean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration","author":"Ohayon","year":"2024","journal-title":"arXiv preprint arXiv:2410.00418"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref43","article-title":"Smaug: Fixing Failure Modes of Preference Optimisation With DPO-Positive","author":"Pal","year":"2024","journal-title":"arXiv preprint arXiv:2402.13228"},{"key":"ref44","article-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv:2307.01952"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref46","article-title":"Refining Alignment Framework for Diffusion Models With Intermediate-Step Preference Ranking","author":"Ren","year":"2025","journal-title":"arXiv preprint arXiv:2502.01667"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","article-title":"Proximal Policy Optimization Algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28300"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3743093.3770981"},{"key":"ref52","article-title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","author":"Tajwar","year":"2024","journal-title":"arXiv preprint arXiv:2404.14367"},{"key":"ref53","article-title":"Understanding the Performance Gap Between Online and Offline Alignment Algorithms","author":"Tang","year":"2024","journal-title":"arXiv preprint arXiv:2405.08448"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref55","article-title":"Wan: Open and Advanced Large-Scale Video Generative Models","author":"Wan","year":"2025","journal-title":"arXiv preprint arXiv:2503.20314"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_22"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755081"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00237"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.107"},{"key":"ref60","article-title":"UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models Via Training-Free Unified Attention Control","author":"Xia","year":"2024","journal-title":"arXiv preprint arXiv:2403.02332"},{"key":"ref61","article-title":"Tackling the Generative Learning Trilemma With Denoising Diffusion GANs","author":"Xiao","year":"2021","journal-title":"arXiv preprint arXiv:2112.07804"},{"key":"ref62","article-title":"Mobile Video Diffusion","author":"Yahia","year":"2024","journal-title":"arXiv preprint arXiv:2412.07583"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"ref64","article-title":"OnlineVPO: Align Video Diffusion Model With Online Video-Centric Preference Optimization","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv:2412.15159"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_13"},{"key":"ref66","article-title":"Fine-Tuning Language Models From Human Preferences","author":"Ziegler","year":"2019","journal-title":"arXiv preprint arXiv:1909.08593"}],"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\/11446044.pdf?arnumber=11446044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:45:09Z","timestamp":1777578309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446044\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01601","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}