{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:11Z","timestamp":1777865291050,"version":"3.51.4"},"reference-count":69,"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\/iccv51701.2025.01448","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"01-12","source":"Crossref","is-referenced-by-count":0,"title":["The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation"],"prefix":"10.1109","author":[{"given":"Aoxiong","family":"Yin","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Moonshot AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Shen","sequence":"additional","affiliation":[{"name":"Moonshot AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichong","family":"Leng","sequence":"additional","affiliation":[{"name":"Moonshot AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Moonshot AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6","volume-title":"Gen-3","year":"2024"},{"key":"ref2","first-page":"6","volume-title":"Hailuo","year":"2024"},{"key":"ref3","first-page":"6","volume-title":"Jimeng","year":"2024"},{"key":"ref4","first-page":"6","volume-title":"Pika 1.0","year":"2024"},{"key":"ref5","first-page":"6","volume-title":"Openai sora","year":"2024"},{"key":"ref6","first-page":"3","volume":"1","author":"Blattmann","year":"2023","journal-title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","first-page":"14","author":"D\u00e9fossez","year":"2022","journal-title":"High Fidelity Neural Audio Compression"},{"key":"ref9","first-page":"14","author":"Dong","year":"2024","journal-title":"Flex Attention: A Programming Model for Generating Optimized Attention Kernels"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","volume":"ICML 2024","author":"Esser","year":"2024"},{"key":"ref13","first-page":"6","author":"Fan","year":"2025","journal-title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"ref15","first-page":"3","author":"Ge","year":"2023","journal-title":"Planting a SEED of Vision in Large Language Model"},{"key":"ref16","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"The Twelfth International Conference on Learning Representations","volume":"ICLR 2024","author":"Guo","year":"2024"},{"key":"ref17","first-page":"6","author":"HaCohen","year":"2024","journal-title":"LTX-Video: Realtime Video Latent Diffusion"},{"key":"ref18","first-page":"7","article-title":"StreamingT2V: Consistent","volume":"3","author":"Henschel","year":"2024","journal-title":"Dynamic, and Extendable Long Video Generation from Text"},{"key":"ref19","first-page":"15","author":"Ho","year":"2022","journal-title":"Classifier-Free Diffusion Guidance"},{"key":"ref20","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","volume":"NeurIPS 2020","author":"Ho","year":"2020"},{"key":"ref21","first-page":"3","article-title":"Imagen video: High definition video generation with diffusion models","volume":"abs\/2210.02303","author":"Ho","year":"2022","journal-title":"CoRR"},{"key":"ref22","first-page":"3","author":"Ho","year":"2022","journal-title":"Video Diffusion Models"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.314"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref25","first-page":"3","author":"Jin","year":"2023","journal-title":"Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization"},{"key":"ref26","first-page":"3","author":"Jin","year":"2024","journal-title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled VisualMotional Tokenization"},{"key":"ref27","first-page":"3","author":"Ju","year":"2024","journal-title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref29","article-title":"Generating images with multimodal language models","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","volume":"NeurIPS 2023","author":"Yu Koh","year":"2023"},{"key":"ref30","article-title":"VideoPoet: A large language model for zero-shot video generation","volume-title":"Forty-First International Conference on Machine Learning","volume":"ICML 2024","author":"Kondratyuk","year":"2024"},{"key":"ref31","first-page":"6","volume":"3","author":"Kong","year":"2024","journal-title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103090"},{"issue":"6","key":"ref33","first-page":"7","volume":"3","author":"Li","year":"2024","journal-title":"ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation"},{"key":"ref34","first-page":"6","volume":"3","author":"Lin","year":"2024","journal-title":"Open-Sora Plan: Open-Source Large Video Generation Model"},{"key":"ref35","first-page":"3","author":"Lin","year":"2024","journal-title":"STIV: Scalable Text and Image Conditioned Video Generation"},{"key":"ref36","first-page":"14","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref37","first-page":"3","author":"Lu","year":"2024","journal-title":"FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref39","first-page":"6","volume":"3","author":"Ma","year":"2024","journal-title":"Latte: Latent Diffusion Transformer for Video Generation"},{"key":"ref40","first-page":"4","author":"Oquab","year":"2024","journal-title":"DINOv2: Learning robust visual features without supervision"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00634"},{"key":"ref43","article-title":"FreeNoise: Tuningfree longer video diffusion via noise rescheduling","volume-title":"The Twelfth International Conference on Learning Representations","volume":"ICLR 2024","author":"Qiu","year":"2024"},{"key":"ref44","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref45","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"issue":"4","key":"ref46","first-page":"13","volume":"2","author":"Shang","year":"2024","journal-title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref48","first-page":"6","author":"Si","year":"2025","journal-title":"RepVideo: Rethinking Cross-Layer Representation for Video Generation"},{"key":"ref49","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"The Eleventh International Conference on Learning Representations","volume":"ICLR 2023","author":"Singer","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref52","first-page":"6","article-title":"Genmo Team","volume-title":"Mochi 1","year":"2024"},{"issue":"6","key":"ref53","first-page":"15","volume":"5","author":"Touvron","year":"2023","journal-title":"LLaMA: Open and Efficient Foundation Language Models"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"2","key":"ref55","first-page":"3","volume":"1","author":"Wang","year":"2024","journal-title":"Emu3: Next-Token Prediction is All You Need"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref57","first-page":"4","author":"Wang","year":"2024","journal-title":"Maskgct: Zero-shot text-to-speech with masked generative codec transformer"},{"key":"ref58","first-page":"3","author":"Yan","year":"2021","journal-title":"VideoGPT: Video Generation using VQ-VAE and Transformers"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"issue":"2","key":"ref60","first-page":"3","volume":"1","author":"Yang","year":"2024","journal-title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer"},{"key":"ref61","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"The Tenth International Conference on Learning Representations","volume":"ICLR 2022","author":"Yu","year":"2022"},{"key":"ref62","article-title":"Language model beats diffusion - tokenizer is key to visual generation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yu","year":"2024"},{"issue":"4","key":"ref63","first-page":"13","volume":"2","author":"Yu","year":"2024","journal-title":"An Image is Worth 32 Tokens for Reconstruction and Generation"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00618"},{"key":"ref65","first-page":"3","author":"Zeng","year":"2023","journal-title":"Make Pixels Dance: HighDynamic Video Generation"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00355"},{"issue":"6","key":"ref68","first-page":"7","volume":"3","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref69","first-page":"3","author":"Zhou","year":"2023","journal-title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models"}],"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\/11444284.pdf?arnumber=11444284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:37Z","timestamp":1777529497000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01448","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}