{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:56:54Z","timestamp":1777888614182,"version":"3.51.4"},"reference-count":59,"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\/iccv51701.2025.01724","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18552-18562","source":"Crossref","is-referenced-by-count":0,"title":["TCFG: Truncated Classifier-Free Guidance for Efficient and Scalable Text-to-Image Acceleration"],"prefix":"10.1109","author":[{"given":"Xiaomeng","family":"Fu","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Bayesian online changepoint detection","author":"Adams","year":"2007","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Label-efficient semantic segmentation with diffusion models","volume-title":"International Conference on Learning Representations","author":"Baranchuk"},{"key":"ref3","article-title":"Conditional image generation with score-based diffusion models","author":"Batzolis","year":"2021","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Demystifying mmd gans","volume-title":"International Conference on Learning Representations","author":"Bi\u0144kowski","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00087"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0731"},{"key":"ref10","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gal","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_10"},{"key":"ref12","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2027"},{"key":"ref14","article-title":"Scalecrafter: Tuning-free higher-resolution visual generation with diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"He","year":"2023"},{"key":"ref15","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Why warmup the learning rate? underlying mechanisms and improvements","author":"Kalra","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Karras","year":"2022"},{"key":"ref21","article-title":"Guiding a diffusion model with a bad version of itself","author":"Karras","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref23","article-title":"Bk-sdm: Architecturally compressed stable diffusion for efficient text-to-image generation","volume-title":"Workshop on Efficient Systems for Foundation Models@ ICML2023","author":"Kim","year":"2023"},{"key":"ref24","article-title":"Auto-encoding variational \\{Bayes\\}","volume-title":"The Second International Conference on Learning Representations","author":"Kingma","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1594"},{"key":"ref26","article-title":"Diffusion models already have a semantic latent space","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kwon","year":"2023"},{"key":"ref27","volume-title":"aesthetic-predictor","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"International Conference on Learning Representations","author":"Liu","year":"2020"},{"key":"ref32","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","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref35","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Meng","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3290149"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123231"},{"key":"ref39","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Poole","year":"2023"},{"key":"ref40","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":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3204461"},{"key":"ref45","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"International Conference on Learning Representations","author":"Salimans","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00895"},{"key":"ref48","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref49","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref50","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song","year":"2020"},{"key":"ref51","first-page":"1415","article-title":"Maximum likelihood training of score-based diffusion models","volume":"34","author":"Song","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref52","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Ditfastattn: Attention compression for diffusion transformer models","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Laptop-diff: Layer pruning and normalized distillation for compressing diffusion models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref57","article-title":"Fast sampling of diffusion models with exponential integrator","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0261"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2170"}],"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\/11444511.pdf?arnumber=11444511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:21Z","timestamp":1777611201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01724","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}