{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T05:25:20Z","timestamp":1789622720926,"version":"build-2803163510"},"reference-count":44,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B20180,62472393"],"award-info":[{"award-number":["U24B20180,62472393"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01636","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17608-17617","source":"Crossref","is-referenced-by-count":2,"title":["Accelerating Diffusion Transformer via Gradient-Optimized Cache"],"prefix":"10.1109","author":[{"given":"Junxiang","family":"Qiu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinda","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kezhou","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[{"name":"Hefei University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33722"},{"key":"ref3","article-title":"Pixart- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"\\Delta-d i t: A training-free acceleration method tailored for diffusion transformers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","author":"Dong","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/105"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CP.1943-5487.0001034"},{"key":"ref10","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"A signal propagation perspective for pruning neural networks at initialization","author":"Lee","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Faster diffusion: Rethinking the role of unet encoder in diffusion models","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"ref14","article-title":"Brecq: Pushing the limit of posttraining quantization by block reconstruction","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00305"},{"key":"ref17","first-page":"7021","article-title":"Group fisher pruning for practical network compression","volume-title":"International Conference on Machine Learning","author":"Liu","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611784"},{"key":"ref20","article-title":"Damo: Data-and model-aware alignment of multi-modal 11 ms","author":"Lu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Learning-to-cache: Accelerating diffusion transformer via layer caching","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1262"},{"key":"ref24","article-title":"Mass editing memory in a transformer","author":"Meng","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"7197","article-title":"Up or down? adaptive rounding for post-training quantization","volume-title":"International Conference on Machine Learning","author":"Nagel","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.31"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755009"},{"key":"ref29","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Fora: Fast-forward caching in diffusion transformer acceleration","author":"Selvaraju","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Parallel sampling of diffusion models","author":"Shih","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240671"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02678"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"ref37","article-title":"Ptq4dit: Post-training quantization for diffusion transformers","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Token pruning for caching better: 9 times acceleration on stable diffusion for free","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"42390","article-title":"Fast sampling of diffusion models via operator learning","volume-title":"International conference on machine learning","author":"Zheng","year":"2023"},{"key":"ref41","first-page":"92581","article-title":"Dip-go: A diffusion pruner via few-step gradient optimization","volume":"37","author":"Zhu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28614"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0064"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680885"}],"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\/11443565.pdf?arnumber=11443565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:22Z","timestamp":1777612342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01636","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}