{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:11:55Z","timestamp":1777889515620,"version":"3.51.4"},"reference-count":68,"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\/iccv51701.2025.01460","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15737-15747","source":"Crossref","is-referenced-by-count":0,"title":["FullDiT: Video Generative Foundation Models with Multimodal Control via Full Attention"],"prefix":"10.1109","author":[{"given":"Xuan","family":"Ju","sequence":"first","affiliation":[{"name":"Kling Team, Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weicai","family":"Ye","sequence":"additional","affiliation":[{"name":"Kling Team, Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quande","family":"Liu","sequence":"additional","affiliation":[{"name":"Kling Team, Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiulin","family":"Wang","sequence":"additional","affiliation":[{"name":"Kling Team, Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xintao","family":"Wang","sequence":"additional","affiliation":[{"name":"Kling Team, Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kling Team, Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kling Team, Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Gai","sequence":"additional","affiliation":[{"name":"Kling Team, Kuaishou Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"arXiv preprint","year":"2024"},{"key":"ref2","article-title":"Vd3d: Taming large video diffusion transformers for 3d camera control","author":"Bahmani","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref4","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00572"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01166"},{"key":"ref9","article-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Delta tuning: A comprehen-sive study of parameter efficient methods for pre-trained language models","author":"Ding","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref12","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref16","article-title":"Photorealistic video generation with diffusion models","author":"Gupta","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Cameractrl: Enabling camera control for text-to-video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Id-animator: Zero-shot identity-preserving human video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2024"},{"key":"ref20","article-title":"Videocontrolnet: A motion-guided video-to-video translation framework by using diffusion model with controlnet","author":"Hu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","author":"Huang","year":"2024","journal-title":"Group diffusion transformers are unsupervised multitask learners"},{"key":"ref22","article-title":"Conceptmaster: Multi-concept video customization on diffusion transformer models without test-time tuning","author":"Huang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref24","article-title":"Miradata: A large-scale video dataset with long durations and structured captions","author":"Ju","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Videopoet: A large language model for zero-shot video generation","author":"Kondratyuk","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00255"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02602"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01230"},{"key":"ref30","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01285"},{"key":"ref32","article-title":"Ctrladapter: An efficient and versatile framework for adapting diverse controls to any diffusion model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Motionclone: Training-free motion cloning for controllable video generation","author":"Ling","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lu","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92808-6_2"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref40","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref44","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref46","article-title":"Chameleon: Mixed-modal early-fusion foundation models","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref48","article-title":"Generating videos with scene dynamics","author":"Vondrick","year":"2016","journal-title":"Advances in neural information processing systems, 29"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref50","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00625"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01210"},{"key":"ref54","article-title":"Motionbooth: Motion-aware customized text-to-video generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01241"},{"key":"ref56","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Omnicontrol: Control any joint at any time for human motion generation","author":"Xie","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Ctrlora: An extensible and efficient framework for controllable image generation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref60","article-title":"Identitypreserving text-to-video generation by frequency decomposition","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Moonshot: Towards controllable video generation and editing with multimodal conditions","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref63","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Magic mirror: Id-preserved video generation in video diffusion transformers","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Cami2v: Camera-controlled image-to-video diffusion model","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","author":"Zhou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33167"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"}],"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\/11444609.pdf?arnumber=11444609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:11:58Z","timestamp":1777612318000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01460","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}