{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T16:29:16Z","timestamp":1789144156555,"version":"build-2803163510"},"reference-count":52,"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\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00336454"],"award-info":[{"award-number":["RS-2024-00336454"]}],"id":[{"id":"10.13039\/501100003725","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\/iccv51701.2025.01665","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17920-17929","source":"Crossref","is-referenced-by-count":1,"title":["Free\n                    <sup>2<\/sup>\n                    Guide: Training-Free Text-to-Video Alignment Using Image LVLM"],"prefix":"10.1109","author":[{"given":"Jaemin","family":"Kim","sequence":"first","affiliation":[{"name":"Kim Jaechul Graduate School of AI, KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryan Sangwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Kim Jaechul Graduate School of AI, KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong Chul","family":"Ye","sequence":"additional","affiliation":[{"name":"Kim Jaechul Graduate School of AI, KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Training diffusion models with reinforcement learning","author":"Black","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","volume-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref5","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"International Conference on Learning Representations","author":"Chung","year":"2023"},{"key":"ref6","article-title":"Directly fine-tuning diffusion models on differentiable rewards","author":"Clark","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Advances in Neural Information Processing Systems","author":"Dhariwal","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2011.tm11181"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00355-011-0603-9"},{"key":"ref10","article-title":"Reinforcement learning for fine-tuning text-to-image diffusion models","volume":"36","author":"Fan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref12","article-title":"Benchmarking spatial relationships in text-to-image generation","author":"Gokhale","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref17","article-title":"Symbolic music generation with non-differentiable rule guided diffusion","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref19","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2005\/11\/P11011"},{"key":"ref21","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proc. NeurIPS","author":"Karras","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3517625"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref25","article-title":"Llm-grounded video diffusion models","author":"Lian","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3003837"},{"key":"ref27","article-title":"Latent consistency models: Synthesizing highresolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref29","article-title":"Diffusion models for adversarial purification","author":"Nie","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Aligning text-to-image diffusion models with reward backpropagation","author":"Prabhudesai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Video diffusion alignment via reward gradients","author":"Prabhudesai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International Conference on Machine Learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref35","article-title":"Denoising diffusion implicit models","volume-title":"9th International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref36","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref38","article-title":"T2v-compbench: A comprehensive benchmark for compositional text-to-video generation","author":"Sun","year":"2024","journal-title":"arXiv"},{"key":"ref39","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"Theodorou","year":"2010","journal-title":"The Journal of Machine Learning Research"},{"key":"ref40","article-title":"Understanding reinforcement learning-based fine-tuning of diffusion models: A tutorial and review","author":"Uehara","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Fine-tuning of continuous-time diffusion models as entropy-regularized control","author":"Uehara","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00669"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref44","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang","year":"2023"},{"key":"ref45","volume-title":"Diffusions, Markov processes, and martingales.","author":"Williams","year":"1979"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref47","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":"ref48","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xu","year":"2024"},{"key":"ref49","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal 11 ms","volume-title":"Forty-first International Conference on Machine Learning","author":"Yang","year":"2024"},{"key":"ref50","article-title":"Training-free diffusion model alignment with sampling demons","author":"Yeh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Ensemble kalman diffusion guidance: A derivative-free method for inverse problems","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"}],"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\/11445928.pdf?arnumber=11445928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:16Z","timestamp":1777613596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01665","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}