{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:20Z","timestamp":1777657460677,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"name":"the Local Science and Technology Program","award":["2024CSJGG00800"],"award-info":[{"award-number":["2024CSJGG00800"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755009","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:47:42Z","timestamp":1761371262000},"page":"9588-9597","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Accelerating Diffusion Transformer via Error-Optimized Cache"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1257-1268","authenticated-orcid":false,"given":"Junxiang","family":"Qiu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4881-9344","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7322-9942","authenticated-orcid":false,"given":"Jinda","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4363-7907","authenticated-orcid":false,"given":"Lin","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6599-3572","authenticated-orcid":false,"given":"Houcheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5225-7770","authenticated-orcid":false,"given":"Xingyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0695-1566","authenticated-orcid":false,"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00356"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00087"},{"key":"e_1_3_2_1_4_1","volume-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426","author":"Chen Junsong","year":"2023","unstructured":"Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, et al., 2023. Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis. arXiv preprint arXiv:2310.00426 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"A Training-Free Acceleration Method Tailored for Diffusion Transformers. arXiv preprint arXiv:2406.01125","author":"Chen Pengtao","year":"2024","unstructured":"Pengtao Chen, Mingzhu Shen, Peng Ye, Jianjian Cao, Chongjun Tu, Christos-Savvas Bouganis, Yiren Zhao, and Tao Chen. 2024. \u0394-DiT$: A Training-Free Acceleration Method Tailored for Diffusion Transformers. arXiv preprint arXiv:2406.01125 (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","volume-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon. Advances in neural information processing systems","author":"Dong Xin","year":"2017","unstructured":"Xin Dong, Shangyu Chen, and Sinno Pan. 2017. Learning to prune deep neural networks via layer-wise optimal brain surgeon. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i16.33823"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680768"},{"key":"e_1_3_2_1_10_1","volume-title":"Parameter-efficient transfer learning with diff pruning. arXiv preprint arXiv:2012.07463","author":"Guo Demi","year":"2020","unstructured":"Demi Guo, Alexander M Rush, and Yoon Kim. 2020. Parameter-efficient transfer learning with diff pruning. arXiv preprint arXiv:2012.07463 (2020)."},{"key":"e_1_3_2_1_11_1","first-page":"744","article-title":"Dense Temporal Convolution Network for Sign Language Translation","author":"Guo Dan","year":"2019","unstructured":"Dan Guo, Shuo Wang, Qi Tian, and Meng Wang. 2019. Dense Temporal Convolution Network for Sign Language Translation. In IJCAI. 744-750.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)CP.1943-5487.0001034"},{"key":"e_1_3_2_1_13_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_14_1","volume-title":"A signal propagation perspective for pruning neural networks at initialization. arXiv preprint arXiv:1906.06307","author":"Lee Namhoon","year":"2019","unstructured":"Namhoon Lee, Thalaiyasingam Ajanthan, Stephen Gould, and Philip HS Torr. 2019. A signal propagation perspective for pruning neural networks at initialization. arXiv preprint arXiv:1906.06307 (2019)."},{"key":"e_1_3_2_1_15_1","volume-title":"DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=AhcYq4CnfF","author":"Li Jinghan","year":"2025","unstructured":"Jinghan Li, Yuan Gao, Jinda Lu, Junfeng Fang, Congcong Wen, Hui Lin, and Xiang Wang. 2025. DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=AhcYq4CnfF"},{"key":"e_1_3_2_1_16_1","volume-title":"Linxuan Li, Shiqi Yang, Yaxing Wang, Ming-Ming Cheng, and Jian Yang.","author":"Li Senmao","year":"2023","unstructured":"Senmao Li, Taihang Hu, Fahad Shahbaz Khan, Linxuan Li, Shiqi Yang, Yaxing Wang, Ming-Ming Cheng, and Jian Yang. 2023a. Faster diffusion: Rethinking the role of unet encoder in diffusion models. CoRR (2023)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"e_1_3_2_1_18_1","volume-title":"Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426","author":"Li Yuhang","year":"2021","unstructured":"Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, and Shi Gu. 2021. Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426 (2021)."},{"key":"e_1_3_2_1_19_1","first-page":"740","volume-title":"Switzerland","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer vision-ECCV 2014: 13th European conference, zurich, Switzerland, September 6-12, 2014, proceedings, part v 13. Springer, 740-755."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00689"},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Machine Learning. PMLR, 7021-7032","author":"Liu Liyang","year":"2021","unstructured":"Liyang Liu, Shilong Zhang, Zhanghui Kuang, Aojun Zhou, Jing-Hao Xue, Xinjiang Wang, Yimin Chen, Wenming Yang, Qingmin Liao, and Wayne Zhang. 2021. Group fisher pruning for practical network compression. In International Conference on Machine Learning. PMLR, 7021-7032."},{"key":"e_1_3_2_1_22_1","volume-title":"Rethinking the value of network pruning. arXiv preprint arXiv:1810.05270","author":"Liu Zhuang","year":"2018","unstructured":"Zhuang Liu, Mingjie Sun, Tinghui Zhou, Gao Huang, and Trevor Darrell. 2018. Rethinking the value of network pruning. arXiv preprint arXiv:1810.05270 (2018)."},{"key":"e_1_3_2_1_23_1","first-page":"5775","article-title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","volume":"35","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022. Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps. Advances in Neural Information Processing Systems, Vol. 35 (2022), 5775-5787.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611784"},{"key":"e_1_3_2_1_25_1","volume-title":"DAMO: Data-and Model-aware Alignment of Multi-modal LLMs. arXiv preprint arXiv:2502.01943","author":"Lu Jinda","year":"2025","unstructured":"Jinda Lu, Junkang Wu, Jinghan Li, Xiaojun Jia, Shuo Wang, YiFan Zhang, Junfeng Fang, Xiang Wang, and Xiangnan He. 2025. DAMO: Data-and Model-aware Alignment of Multi-modal LLMs. arXiv preprint arXiv:2502.01943 (2025)."},{"key":"e_1_3_2_1_26_1","volume-title":"Knowledge distillation in iterative generative models for improved sampling speed. arXiv preprint arXiv:2101.02388","author":"Luhman Eric","year":"2021","unstructured":"Eric Luhman and Troy Luhman. 2021. Knowledge distillation in iterative generative models for improved sampling speed. arXiv preprint arXiv:2101.02388 (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"Fastercache: Training-free video diffusion model acceleration with high quality. arXiv preprint arXiv:2410.19355","author":"Lv Zhengyao","year":"2024","unstructured":"Zhengyao Lv, Chenyang Si, Junhao Song, Zhenyu Yang, Yu Qiao, Ziwei Liu, and Kwan-Yee K Wong. 2024. Fastercache: Training-free video diffusion model acceleration with high quality. arXiv preprint arXiv:2410.19355 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Michael Bi Mi, and Xinchao Wang","author":"Ma Xinyin","year":"2024","unstructured":"Xinyin Ma, Gongfan Fang, Michael Bi Mi, and Xinchao Wang. 2024b. Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching. arXiv preprint arXiv:2406.01733 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"e_1_3_2_1_31_1","first-page":"17359","article-title":"Locating and editing factual associations in GPT","volume":"35","author":"Meng Kevin","year":"2022","unstructured":"Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in GPT. Advances in Neural Information Processing Systems, Vol. 35 (2022), 17359-17372.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_1","volume-title":"Mar\u00eda Dolores Garc\u00eda, and Antonio Su\u00e1rez","author":"Montero Gustavo","year":"2002","unstructured":"Gustavo Montero, L Gonz\u00e1lez, Elizabeth Fl\u00f3rez, Mar\u00eda Dolores Garc\u00eda, and Antonio Su\u00e1rez. 2002. Approximate inverse computation using Frobenius inner product. Numerical linear algebra with applications, Vol. 9, 3 (2002), 239-247."},{"key":"e_1_3_2_1_33_1","volume-title":"International Conference on Machine Learning. PMLR, 7197-7206","author":"Nagel Markus","year":"2020","unstructured":"Markus Nagel, Rana Ali Amjad, Mart Van Baalen, Christos Louizos, and Tijmen Blankevoort. 2020. Up or down? adaptive rounding for post-training quantization. In International Conference on Machine Learning. PMLR, 7197-7206."},{"key":"e_1_3_2_1_34_1","volume-title":"Markov chains. Number 2","author":"Norris James R","unstructured":"James R Norris. 1998. Markov chains. Number 2. Cambridge university press."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.31"},{"key":"e_1_3_2_1_37_1","volume-title":"Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512","author":"Salimans Tim","year":"2022","unstructured":"Tim Salimans and Jonathan Ho. 2022. Progressive distillation for fast sampling of diffusion models. arXiv preprint arXiv:2202.00512 (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Fora: Fast-forward caching in diffusion transformer acceleration. arXiv preprint arXiv:2407.01425","author":"Selvaraju Pratheba","year":"2024","unstructured":"Pratheba Selvaraju, Tianyu Ding, Tianyi Chen, Ilya Zharkov, and Luming Liang. 2024. Fora: Fast-forward caching in diffusion transformer acceleration. arXiv preprint arXiv:2407.01425 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Shih Andy","year":"2024","unstructured":"Andy Shih, Suneel Belkhale, Stefano Ermon, Dorsa Sadigh, and Nima Anari. 2024. Parallel sampling of diffusion models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"So Junhyuk","year":"2024","unstructured":"Junhyuk So, Jungwon Lee, Daehyun Ahn, Hyungjun Kim, and Eunhyeok Park. 2024. Temporal dynamic quantization for diffusion models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_1_42_1","volume-title":"Consistency models. arXiv preprint arXiv:2303.01469","author":"Song Yang","year":"2023","unstructured":"Yang Song, Prafulla Dhariwal, Mark Chen, and Ilya Sutskever. 2023. Consistency models. arXiv preprint arXiv:2303.01469 (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240671"},{"key":"e_1_3_2_1_44_1","volume-title":"Lavie: High-quality video generation with cascaded latent diffusion models. International Journal of Computer Vision","author":"Wang Yaohui","year":"2024","unstructured":"Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, et al., 2024. Lavie: High-quality video generation with cascaded latent diffusion models. International Journal of Computer Vision (2024), 1-20."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02678"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"e_1_3_2_1_47_1","volume-title":"PTQ4DiT: Post-training Quantization for Diffusion Transformers. arXiv preprint arXiv:2405.16005","author":"Wu Junyi","year":"2024","unstructured":"Junyi Wu, Haoxuan Wang, Yuzhang Shang, Mubarak Shah, and Yan Yan. 2024. PTQ4DiT: Post-training Quantization for Diffusion Transformers. arXiv preprint arXiv:2405.16005 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xu Jiazheng","year":"2024","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2024. Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"e_1_3_2_1_50_1","volume-title":"Real-time video generation with pyramid attention broadcast. arXiv preprint arXiv:2408.12588","author":"Zhao Xuanlei","year":"2024","unstructured":"Xuanlei Zhao, Xiaolong Jin, Kai Wang, and Yang You. 2024. Real-time video generation with pyramid attention broadcast. arXiv preprint arXiv:2408.12588 (2024)."},{"key":"e_1_3_2_1_51_1","volume-title":"International conference on machine learning. PMLR, 42390-42402","author":"Zheng Hongkai","year":"2023","unstructured":"Hongkai Zheng, Weili Nie, Arash Vahdat, Kamyar Azizzadenesheli, and Anima Anandkumar. 2023. Fast sampling of diffusion models via operator learning. In International conference on machine learning. PMLR, 42390-42402."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28614"},{"key":"e_1_3_2_1_53_1","first-page":"2001","article-title":"Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting","volume":"37","author":"Zhu Xingyu","year":"2024","unstructured":"Xingyu Zhu, Beier Zhu, Yi Tan, Shuo Wang, Yanbin Hao, and Hanwang Zhang. 2024b. Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting. Advances in Neural Information Processing Systems, Vol. 37 (2024), 2001-2025.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680885"},{"key":"e_1_3_2_1_55_1","volume-title":"Accelerating diffusion transformers with token-wise feature caching. arXiv preprint arXiv:2410.05317","author":"Zou Chang","year":"2024","unstructured":"Chang Zou, Xuyang Liu, Ting Liu, Siteng Huang, and Linfeng Zhang. 2024. Accelerating diffusion transformers with token-wise feature caching. arXiv preprint arXiv:2410.05317 (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:18:21Z","timestamp":1765307901000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755009"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":55,"alternative-id":["10.1145\/3746027.3755009","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755009","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}