{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:54:05Z","timestamp":1781538845645,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810881","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"1608-1617","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MixCache: Mixture-of-Cache for Video Diffusion Transformer Acceleration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6551-9274","authenticated-orcid":false,"given":"Yuanxin","family":"Wei","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6193-6126","authenticated-orcid":false,"given":"Lansong","family":"Diao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5704-9861","authenticated-orcid":false,"given":"Bujiao","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7966-2941","authenticated-orcid":false,"given":"Shenggan","family":"Cheng","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0741-9918","authenticated-orcid":false,"given":"Zhengping","family":"Qian","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5641-2452","authenticated-orcid":false,"given":"Wenyuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2166-977X","authenticated-orcid":false,"given":"Nong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3003-0150","authenticated-orcid":false,"given":"Wei","family":"Lin","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4707-9492","authenticated-orcid":false,"given":"Jiangsu","family":"Du","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024, Santa Clara, CA, April 15-17, 2024","author":"Agarwal Shubham","year":"2024","unstructured":"Shubham Agarwal, Subrata Mitra, Sarthak Chakraborty, Srikrishna Karanam, Koyel Mukherjee, and Shiv\u00a0Kumar Saini. 2024. Approximate Caching for Efficiently Serving Text-to-Image Diffusion Models. In 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024, Santa Clara, CA, April 15-17, 2024, Laurent Vanbever and Irene Zhang (Eds.). USENIX Association. https:\/\/www.usenix.org\/conference\/nsdi24\/presentation\/agarwal-shubham"},{"key":"e_1_3_3_1_3_2","unstructured":"Tim Brooks Bill Peebles Connor Holmes Will DePue Yufei Guo Li Jing David Schnurr Joe Taylor Troy Luhman Eric Luhman et\u00a0al. 2024. Video generation models as world simulators. OpenAI Blog 1 (2024) 8."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","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. CoRR abs\/2406.01125 (2024). arXiv:https:\/\/arXiv.org\/abs\/2406.0112510.48550\/ARXIV.2406.01125","DOI":"10.48550\/ARXIV.2406.01125"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Shenggan Cheng Yuanxin Wei Lansong Diao Yong Liu Bujiao Chen Lianghua Huang Yu Liu Wenyuan Yu Jiangsu Du Wei Lin and Yang You. 2025. SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation. CoRR abs\/2505.19151 (2025). arXiv:https:\/\/arXiv.org\/abs\/2505.1915110.48550\/ARXIV.2505.19151","DOI":"10.48550\/ARXIV.2505.19151"},{"key":"e_1_3_3_1_6_2","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=FPnUhsQJ5B"},{"key":"e_1_3_3_1_7_2","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Zeyinzi Jiang Zhen Han Chaojie Mao Jingfeng Zhang Yulin Pan and Yu Liu. 2025. VACE: All-in-One Video Creation and Editing. CoRR abs\/2503.07598 (2025). arXiv:https:\/\/arXiv.org\/abs\/2503.0759810.48550\/ARXIV.2503.07598","DOI":"10.48550\/ARXIV.2503.07598"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Kumara Kahatapitiya Haozhe Liu Sen He Ding Liu Menglin Jia Chenyang Zhang Michael\u00a0S. Ryoo and Tian Xie. 2024. Adaptive Caching for Faster Video Generation with Diffusion Transformers. CoRR abs\/2411.02397 (2024). arXiv:https:\/\/arXiv.org\/abs\/2411.0239710.48550\/ARXIV.2411.02397","DOI":"10.48550\/ARXIV.2411.02397"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"e_1_3_3_1_12_2","unstructured":"Weijie Kong Qi Tian Zijian Zhang Rox Min Zuozhuo Dai Jin Zhou Jiangfeng Xiong Xin Li Bo Wu Jianwei Zhang et\u00a0al. 2024. Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.03603 (2024)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Senmao Li Taihang Hu Fahad\u00a0Shahbaz Khan Linxuan Li Shiqi Yang Yaxing Wang Ming-Ming Cheng and Jian Yang. 2023. Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models. CoRR abs\/2312.09608 (2023). arXiv:https:\/\/arXiv.org\/abs\/2312.0960810.48550\/ARXIV.2312.09608","DOI":"10.48550\/ARXIV.2312.09608"},{"key":"e_1_3_3_1_14_2","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Liu Dong","year":"2025","unstructured":"Dong Liu, Jiayi Zhang, Yifan Li, Yanxuan Yu, Ben Lengerich, and Ying\u00a0Nian Wu. 2025. FastCache: Cache What Matters, Skip What Doesn\u2019t.. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Feng Liu Shiwei Zhang Xiaofeng Wang Yujie Wei Haonan Qiu Yuzhong Zhao Yingya Zhang Qixiang Ye and Fang Wan. 2024. Timestep Embedding Tells: It\u2019s Time to Cache for Video Diffusion Model. CoRR abs\/2411.19108 (2024). arXiv:https:\/\/arXiv.org\/abs\/2411.1910810.48550\/ARXIV.2411.19108","DOI":"10.48550\/ARXIV.2411.19108"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Jinming Lou Wenyang Luo Yufan Liu Bing Li Xinmiao Ding Weiming Hu Jiajiong Cao Yuming Li and Chenguang Ma. 2024. Token Caching for Diffusion Transformer Acceleration. CoRR abs\/2409.18523 (2024). arXiv:https:\/\/arXiv.org\/abs\/2409.1852310.48550\/ARXIV.2409.18523","DOI":"10.48550\/ARXIV.2409.18523"},{"key":"e_1_3_3_1_17_2","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022","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. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, Danielle Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/260a14acce2a89dad36adc8eefe7c59e-Abstract-Conference.html"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Cheng Lu Yuhao Zhou Fan Bao Jianfei Chen Chongxuan Li and Jun Zhu. 2022. DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models. CoRR abs\/2211.01095 (2022). arXiv:https:\/\/arXiv.org\/abs\/2211.0109510.48550\/ARXIV.2211.01095","DOI":"10.48550\/ARXIV.2211.01095"},{"key":"e_1_3_3_1_19_2","unstructured":"Eric Luhman and Troy Luhman. 2021. Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed. CoRR abs\/2101.02388 (2021). arXiv:https:\/\/arXiv.org\/abs\/2101.02388https:\/\/arxiv.org\/abs\/2101.02388"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Zhengyao Lv Chenyang Si Junhao Song Zhenyu Yang Yu Qiao Ziwei Liu and Kwan-Yee\u00a0K. Wong. 2024. FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality. CoRR abs\/2410.19355 (2024). arXiv:https:\/\/arXiv.org\/abs\/2410.1935510.48550\/ARXIV.2410.19355","DOI":"10.48550\/ARXIV.2410.19355"},{"key":"e_1_3_3_1_21_2","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024","author":"Ma Xinyin","year":"2024","unstructured":"Xinyin Ma, Gongfan Fang, Michael\u00a0Bi Mi, and Xinchao Wang. 2024. Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub\u00a0M. Tomczak, and Cheng Zhang (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/f0b1515be276f6ba82b4f2b25e50bef0-Abstract-Conference.html"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"e_1_3_3_1_23_2","unstructured":"Zehong Ma Longhui Wei Feng Wang Shiliang Zhang and Qi Tian. 2025. MagCache: Fast Video Generation with Magnitude-Aware Cache. arxiv:https:\/\/arXiv.org\/abs\/2506.09045\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2506.09045"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_27_2","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","author":"Salimans Tim","year":"2022","unstructured":"Tim Salimans and Jonathan Ho. 2022. Progressive Distillation for Fast Sampling of Diffusion Models. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022. OpenReview.net. https:\/\/openreview.net\/forum?id=TIdIXIpzhoI"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","unstructured":"Pratheba Selvaraju Tianyu Ding Tianyi Chen Ilya Zharkov and Luming Liang. 2024. FORA: Fast-Forward Caching in Diffusion Transformer Acceleration. CoRR abs\/2407.01425 (2024). arXiv:https:\/\/arXiv.org\/abs\/2407.0142510.48550\/ARXIV.2407.01425","DOI":"10.48550\/ARXIV.2407.01425"},{"key":"e_1_3_3_1_29_2","volume-title":"Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning","author":"Shen Mingzhu","year":"2024","unstructured":"Mingzhu Shen, Pengtao Chen, Peng Ye, Guoxuan Xia, Tao Chen, Christos-Savvas Bouganis, and Yiren Zhao. 2024. MD-DiT: Step-aware Mixture-of-Depths for Efficient Diffusion Transformers. In Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning. https:\/\/openreview.net\/forum?id=1jWhiakK7N"},{"key":"e_1_3_3_1_30_2","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"e_1_3_3_1_31_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna\u00a0M. Wallach, Rob Fergus, S.\u00a0V.\u00a0N. Vishwanathan, and Roman Garnett (Eds.). 5998\u20136008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_3_1_32_2","unstructured":"Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang Jianyuan Zeng et\u00a0al. 2025. Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20314 (2025)."},{"key":"e_1_3_3_1_33_2","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023","author":"Wang Xiang","year":"2023","unstructured":"Xiang Wang, Hangjie Yuan, Shiwei Zhang, Dayou Chen, Jiuniu Wang, Yingya Zhang, Yujun Shen, Deli Zhao, and Jingren Zhou. 2023. VideoComposer: Compositional Video Synthesis with Motion Controllability. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/180f6184a3458fa19c28c5483bc61877-Abstract-Conference.html"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Zhou Wang Alan\u00a0C Bovik Hamid\u00a0R Sheikh and Eero\u00a0P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13 4 (2004) 600\u2013612.","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"e_1_3_3_1_37_2","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang Guanting Dong Haoran Wei Huan Lin and etc Jialong\u00a0Tang. 2024. Qwen2 Technical Report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.10671 (2024)."},{"key":"e_1_3_3_1_38_2","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng et\u00a0al. 2024. Cogvideox: Text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06072 (2024)."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","unstructured":"Zichao Yu Zhen Zou Guojiang Shao Chengwei Zhang Shengze Xu Jie Huang Feng Zhao Xiaodong Cun and Wenyi Zhang. 2025. AB-Cache: Training-Free Acceleration of Diffusion Models via Adams-Bashforth Cached Feature Reuse. CoRR abs\/2504.10540 (2025). arXiv:https:\/\/arXiv.org\/abs\/2504.1054010.48550\/ARXIV.2504.10540","DOI":"10.48550\/ARXIV.2504.10540"},{"key":"e_1_3_3_1_40_2","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024","author":"Yuan Zhihang","year":"2024","unstructured":"Zhihang Yuan, Hanling Zhang, Lu Pu, Xuefei Ning, Linfeng Zhang, Tianchen Zhao, Shengen Yan, Guohao Dai, and Yu Wang. 2024. DiTFastAttn: Attention Compression for Diffusion Transformer Models. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024. http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/0267925e3c276e79189251585b4100bf-Abstract-Conference.html"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","unstructured":"Hui Zhang Tingwei Gao Jie Shao and Zuxuan Wu. 2025. BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers. CoRR abs\/2503.15927 (2025). arXiv:https:\/\/arXiv.org\/abs\/2503.1592710.48550\/ARXIV.2503.15927","DOI":"10.48550\/ARXIV.2503.15927"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_1_43_2","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","author":"Zhao Xuanlei","year":"2025","unstructured":"Xuanlei Zhao, Xiaolong Jin, Kai Wang, and Yang You. 2025. Real-Time Video Generation with Pyramid Attention Broadcast. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=hDBrQ4DApF"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","unstructured":"Chang Zou Xuyang Liu Ting Liu Siteng Huang and Linfeng Zhang. 2024. Accelerating Diffusion Transformers with Token-wise Feature Caching. CoRR abs\/2410.05317 (2024). arXiv:https:\/\/arXiv.org\/abs\/2410.0531710.48550\/ARXIV.2410.05317","DOI":"10.48550\/ARXIV.2410.05317"},{"key":"e_1_3_3_1_45_2","unstructured":"Chang Zou Evelyn Zhang Runlin Guo Haohang Xu Conghui He Xuming Hu and Linfeng Zhang. 2024. Accelerating Diffusion Transformers with Dual Feature Caching. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.18911 (2024)."}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:57:53Z","timestamp":1781535473000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":44,"alternative-id":["10.1145\/3805622.3810881","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810881","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}