{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:56Z","timestamp":1777889696784,"version":"3.51.4"},"reference-count":54,"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\/iccv51701.2025.01645","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17708-17718","source":"Crossref","is-referenced-by-count":0,"title":["Towards Stabilized and Efficient Diffusion Transformers Through Long-Skip-Connections With Spectral Constraints"],"prefix":"10.1109","author":[{"given":"Guanjie","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"The University of North Carolina at Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yucheng","family":"Zhou","sequence":"additional","affiliation":[{"name":"4SKL-IOTSC, CIS, University of Macau"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoye","family":"Qu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianlong","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of North Carolina at Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref3","author":"Betker","journal-title":"Improving image generation with better captions"},{"key":"ref4","author":"Chen","year":"2023","journal-title":"Pixart-a: Fast training of diffusion transformer for photorealistic text-to-image synthesis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02636"},{"key":"ref6","author":"Chen","year":"2024","journal-title":"Delta-dit: A training-free acceleration method tailored for diffusion transformers"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Ho","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3084"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref11","author":"Kahatapitiya","year":"2024","journal-title":"Adaptive caching for faster video generation with diffusion transformers"},{"key":"ref12","year":"2024","journal-title":"PKU-Yuan Lab and Tuzhan AI etc. Open-sora-plan"},{"key":"ref13","author":"Li","year":"2023","journal-title":"Faster diffusion: Rethinking the role of unet encoder in diffusion models"},{"key":"ref14","author":"Li","year":"2024","journal-title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00689"},{"key":"ref17","first-page":"15762","volume-title":"Deepcache: Accelerating diffusion models for free. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Ma","year":"2023"},{"key":"ref18","author":"Ma","year":"2024","journal-title":"Latte: Latent diffusion transformer for video generation"},{"key":"ref19","article-title":"Spectral normalization for generative adversarial networks","volume-title":"6th International Conference on Learning Representations, ICLR 2018","author":"Miyato","year":"2018"},{"key":"ref20","volume-title":"OpenAI. Sora: Creating video from text","year":"2024"},{"key":"ref21","article-title":"On buggy resizing libraries and surprising subtleties in FID calculation","author":"Parmar","year":"2021","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref24","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref25","author":"Polyak","year":"2024","journal-title":"Movie Gen: A Cast of Media Foundation Models"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref28","article-title":"Faceforensics: A large-scale video dataset for forgery detection in human faces","author":"R\u00f6ssler","year":"2018","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref30","author":"Selvaraju","year":"2024","journal-title":"Fora: Fast-forward caching in diffusion transformer acceleration"},{"key":"ref31","first-page":"7135","article-title":"First order motion model for image animation","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","author":"Siarohin","year":"2019"},{"key":"ref32","author":"So","year":"2023","journal-title":"Frdiff: Feature reuse for exquisite zero-shot acceleration of diffusion models"},{"key":"ref33","article-title":"Denoising diffusion implicit models. In 9th International Conference on Learning Representations","volume-title":"ICLR 2021","author":"Song","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref35","author":"Su","year":"2025","journal-title":"Openthinkimg: Learning to think with images via visual tool reinforcement learning"},{"key":"ref36","author":"Su","year":"2025","journal-title":"Thinking with images for multimodal reasoning: Foundations, methods, and future frontiers"},{"key":"ref37","volume-title":"U-dits: Downsample tokens in u-shaped diffusion transformers. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS","author":"Tian","year":"2024"},{"key":"ref38","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"CoRR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/97.995823"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00251"},{"key":"ref43","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1787"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref46","article-title":"Spectral norm regularization for improving the generalizability of deep learning","author":"Yoshida","year":"2017","journal-title":"CoRR"},{"key":"ref47","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","volume-title":"International Conference on Learning Representations","author":"Yu","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref49","article-title":"Cross-attention makes inference cumbersome in text-to-image diffusion models","author":"Zhang","year":"2024","journal-title":"CoRR"},{"key":"ref50","author":"Zhang","year":"2024","journal-title":"Cross-attention makes inference cumbersome in text-to-image diffusion models"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00740"},{"key":"ref52","author":"Zhao","year":"2024","journal-title":"Dynamic diffusion transformer"},{"key":"ref53","author":"Zhao","year":"2024","journal-title":"Realtime video generation with pyramid attention broadcast"},{"key":"ref54","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"}],"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\/11445753.pdf?arnumber=11445753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:16:52Z","timestamp":1777612612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445753\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01645","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}