{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T05:29:42Z","timestamp":1781501382493,"version":"3.54.1"},"reference-count":61,"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\/iccv51701.2025.01471","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15853-15863","source":"Crossref","is-referenced-by-count":2,"title":["From Reusing to Forecasting: Accelerating Diffusion Models With Taylorseers"],"prefix":"10.1109","author":[{"given":"Jiacheng","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Zou","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanhuiyi","family":"Lyu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linfeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref4","article-title":"Pixart-$\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref5","article-title":"$\\delta$-dit: A training-free acceleration method tailored for diffusion transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","author":"Cheng","year":"2025","journal-title":"Cat pruning: Cluster-aware token pruning for text-to-image diffusion models"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0731"},{"key":"ref9","article-title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","author":"Hessel","year":"2022","journal-title":"arXiv:2104.08718 [cs]"},{"key":"ref10","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","author":"Heusel","year":"2018","journal-title":"arXiv:1706.08500 [cs]"},{"key":"ref11","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","year":"2020","journal-title":"arXiv:2006.11239 [cs]"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","author":"Huang","year":"2023","journal-title":"arXiv:2311.17982 [cs]"},{"key":"ref14","author":"Kahatapitiya","year":"2024","journal-title":"Adaptive Caching for Faster Video Generation with Diffusion Transformers"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00035"},{"key":"ref17","volume-title":"Black Forest Labs. Flux","year":"2024"},{"key":"ref18","article-title":"Faster diffusion: Rethinking the role of unet encoder in diffusion models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01608"},{"key":"ref20","article-title":"Snapfusion: Text-to-image diffusion model on mobile devices within two seconds","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","author":"Li","journal-title":"HunyuanDiT: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00689"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755331"},{"key":"ref24","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu"},{"key":"ref25","author":"Liu","year":"2025","journal-title":"Region-adaptive sampling for diffusion transformers"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref28","author":"Lv","year":"2025","journal-title":"FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01374"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref37","article-title":"Moghadam, and Ahmad Nickabadi","author":"Saghatchian","year":"2025","journal-title":"Cached adaptive token merging: Dynamic token reduction and redundant computation elimination in diffusion model"},{"key":"ref38","author":"Saharia","journal-title":"Photorealistic Text-toImage Diffusion Models with Deep Language Understanding"},{"key":"ref39","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Fora: Fast-forward caching in diffusion transformer acceleration","author":"Selvaraju","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"ref42","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"In International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref43","article-title":"Denoising diffusion implicit models","volume-title":"In International Conference on Learning Representations","author":"Song"},{"key":"ref44","first-page":"32211","article-title":"Consistency models","volume-title":"In International Conference on Machine Learning","author":"Song"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3743093.3770981"},{"key":"ref46","article-title":"Hunyuan-large: An open-source MoE model with 52 billion activated parameters by tencent","author":"Sun","journal-title":"5"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref48","article-title":"ImageReward: Learning and Evaluating Human Preferences for Text-toImage Generation","author":"Xu","year":"2023","journal-title":"arXiv:2304.05977 [cs]"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01623"},{"key":"ref50","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","volume-title":"In The Thirteenth International Conference on Learning Representations","author":"Yang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0037"},{"key":"ref52","author":"Zhang","year":"2024","journal-title":"Token pruning for caching better: 9 times acceleration on stable diffusion for free"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33071"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref55","article-title":"Real-time video generation with pyramid attention broadcast","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2423"},{"key":"ref57","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755479"},{"key":"ref59","author":"Zhu","year":"2024","journal-title":"Dip-go: A diffusion pruner via few-step gradient optimization"},{"key":"ref60","author":"Zou","year":"2024","journal-title":"Accelerating diffusion transformers with dual feature caching"},{"key":"ref61","article-title":"Accelerating diffusion transformers with token-wise feature caching","volume-title":"Proceedings of the 13th International Conference on Learning Representations (ICLR 2025)","author":"Zou"}],"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\/11444758.pdf?arnumber=11444758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:13Z","timestamp":1777613413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01471","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}