{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:33Z","timestamp":1777865433990,"version":"3.51.4"},"reference-count":33,"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\/iccv51701.2025.01547","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["TITAN-Guide: Taming Inference-Time Alignment for Guided Text-to-Video Diffusion Models"],"prefix":"10.1109","author":[{"given":"Christian","family":"Simon","sequence":"first","affiliation":[{"name":"Sony Group Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Ishii","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akio","family":"Hayakawa","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Zhong","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shusuke","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Shibuya","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref3","first-page":"2, 3, 5","article-title":"Gradients without backpropagation","author":"Baydin","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref5","first-page":"6","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref6","first-page":"2","article-title":"Flatten: optical flowguided attention for consistent text-to-video editing","author":"Cong","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2011.tm11181"},{"key":"ref8","first-page":"10249","article-title":"Can forward gradient match backpropagation?","volume-title":"International Conference on Machine Learning","author":"Fournier","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref10","first-page":"4, 6, 8","article-title":"Animatediff: Animate your personalized text-toimage diffusion models without specific tuning","volume-title":"International Conference on Learning Representations","author":"Guo","year":"2024"},{"key":"ref11","first-page":"2, 4, 6, 7, 8","article-title":"Manifold preserving guided diffusion","volume-title":"The Twelfth International Conference on Learning Representations","author":"He","year":"2024"},{"key":"ref12","first-page":"2","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arxiv preprint arxiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01906"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01906"},{"key":"ref16","first-page":"2, 4","article-title":"Ditto: Diffusion inference-time t optimization for music generation","author":"Novack","year":"2024","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref18","first-page":"5","article-title":"Scaling forward gradient with local losses","author":"Ren","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref19","first-page":"2","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arxiv preprint arxiv"},{"key":"ref20","first-page":"3248332498","article-title":"Loss-guided diffusion models for plug-and-play controllable generation","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Song","year":"2023"},{"key":"ref21","first-page":"2, 4","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arxiv preprint arxiv"},{"key":"ref22","first-page":"6","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arxiv preprint arxiv"},{"key":"ref23","first-page":"2","article-title":"Edict: Exact diffusion inversion via coupled transformations","author":"Wallace","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00669"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref27","first-page":"6","volume-title":"Cvpr 2023 text guided video editing competition","author":"Wu","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"ref29","first-page":"4, 6","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28486"},{"key":"ref31","first-page":"2,3,4,5,6,7,8","volume-title":"Tfg: Unified training-free guidance for diffusion models","author":"Ye","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"}],"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\/11444381.pdf?arnumber=11444381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:32:41Z","timestamp":1777530761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01547","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}