{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:25:30Z","timestamp":1765308330589,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","funder":[{"name":"General Research Fund of the Research Grants Council in the Hong Kong SAR","award":["17203023"],"award-info":[{"award-number":["17203023"]}]},{"name":"Collaborative Research Fund of the Research Grants Council in the Hong Kong SAR","award":["C5052-23G"],"award-info":[{"award-number":["C5052-23G"]}]},{"name":"NSFC\/RGC Collaborative Research Scheme of the Research Grants Council in the Hong Kong SAR","award":["CRS_HKU703\/24"],"award-info":[{"award-number":["CRS_HKU703\/24"]}]},{"name":"UBTECH Robotics"},{"name":"JC STEM Lab of Multimedia and Machine Learning funded by The Hong Kong Jockey Club Charities Trust"},{"name":"NSFC Fund","award":["62202431"],"award-info":[{"award-number":["62202431"]}]},{"name":"Zhejiang Leading Innovative and Entrepreneur Team Introduction Program","award":["2024R01007"],"award-info":[{"award-number":["2024R01007"]}]},{"name":"Key Research and Development Program of Zhejiang Province","award":["2025C01026"],"award-info":[{"award-number":["2025C01026"]}]},{"name":"Scientific Research Project of Westlake University","award":["WU2025WF003"],"award-info":[{"award-number":["WU2025WF003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755081","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"9714-9723","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9866-669X","authenticated-orcid":false,"given":"Yiming","family":"Wu","sequence":"first","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0155-4462","authenticated-orcid":false,"given":"Zhenghao","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Newcastle, Newcastle, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-901X","authenticated-orcid":false,"given":"Huan","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2775-9730","authenticated-orcid":false,"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Kling AI. 2023. Kling AI. https:\/\/klingai.com\/."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"e_1_3_2_1_3_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023a. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Cristian Bucilut Rich Caruana and Alexandru Niculescu-Mizil. 2006. Model compression.","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_2_1_6_1","volume-title":"Jae Gon Kim, and Tae-Ho Kim","author":"Castells Thibault","year":"2024","unstructured":"Thibault Castells, Hyoung-Kyu Song, Tairen Piao, Shinkook Choi, Bo-Kyeong Kim, Hanyoung Yim, Changgwun Lee, Jae Gon Kim, and Tae-Ho Kim. 2024a. EdgeFusion: On-Device Text-to-Image Generation. arXiv preprint arXiv:2404.11925 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Jae Gon Kim, and Tae-Ho Kim","author":"Castells Thibault","year":"2024","unstructured":"Thibault Castells, Hyoung-Kyu Song, Tairen Piao, Shinkook Choi, Bo-Kyeong Kim, Hanyoung Yim, Changgwun Lee, Jae Gon Kim, and Tae-Ho Kim. 2024b. EdgeFusion: On-Device Text-to-Image Generation. arXiv preprint arXiv:2404.11925 (2024)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00749"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140608"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00598"},{"key":"e_1_3_2_1_13_1","first-page":"8543","article-title":"Neural video compression with spatio-temporal cross-covariance transformers","author":"Chen Zhenghao","year":"2023","unstructured":"Zhenghao Chen, Lucas Relic, Roberto Azevedo, Yang Zhang, Markus Gross, Dong Xu, Luping Zhou, and Christopher Schroers. 2023. Neural video compression with spatio-temporal cross-covariance transformers. In Proc. ACM Multimedia. 8543-8551.","journal-title":"Proc. ACM Multimedia."},{"key":"e_1_3_2_1_14_1","first-page":"11022","article-title":"Group-aware parameter-efficient updating for content-adaptive neural video compression","author":"Chen Zhenghao","year":"2024","unstructured":"Zhenghao Chen, Luping Zhou, Zhihao Hu, and Dong Xu. 2024c. Group-aware parameter-efficient updating for content-adaptive neural video compression. In Proc. ACM Multimedia. 11022-11031.","journal-title":"Proc. ACM Multimedia."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"e_1_3_2_1_16_1","volume-title":"Proc. NeurIPS.","author":"Fang Gongfan","year":"2023","unstructured":"Gongfan Fang, Xinyin Ma, and Xinchao Wang. 2023a. Structural Pruning for Diffusion Models. In Proc. NeurIPS."},{"key":"e_1_3_2_1_17_1","volume-title":"Proc. IEEE Conf. CVPR. 7277-7288","author":"Ge Songwei","year":"2024","unstructured":"Songwei Ge, Aniruddha Mahapatra, Gaurav Parmar, Jun-Yan Zhu, and Jia-Bin Huang. 2024. On the Content Bias in Fr\u00e9chet Video Distance. In Proc. IEEE Conf. CVPR. 7277-7288."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_19_1","volume-title":"Proc. ICLR.","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. In Proc. ICLR."},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. NeurIPS.","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William J Dally. 2015. Learning both weights and connections for efficient neural network. In Proc. NeurIPS."},{"key":"e_1_3_2_1_21_1","volume-title":"Proc. NeurIPS Workshop.","author":"Hinton Geoffrey","year":"2014","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2014. Distilling the knowledge in a neural network. In Proc. NeurIPS Workshop."},{"key":"e_1_3_2_1_22_1","volume-title":"Proc. NeurIPS Workshop.","author":"Ho Jonathan","year":"2021","unstructured":"Jonathan Ho and Tim Salimans. 2021. Classifier-Free Diffusion Guidance. In Proc. NeurIPS Workshop."},{"key":"e_1_3_2_1_23_1","first-page":"8633","article-title":"Video diffusion models","volume":"35","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Tim Salimans, Alexey Gritsenko, William Chan, Mohammad Norouzi, and David J Fleet. 2022. Video diffusion models. In Proc. NeurIPS, Vol. 35. 8633-8646.","journal-title":"Proc. NeurIPS"},{"key":"e_1_3_2_1_24_1","first-page":"1","volume-title":"JMLR","volume":"22","author":"Hoefler Torsten","year":"2021","unstructured":"Torsten Hoefler, Dan Alistarh, Tal Ben-Nun, Nikoli Dryden, and Alexandra Peste. 2021. Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks. JMLR, Vol. 22, 241 (2021), 1-124."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_2_1_26_1","volume-title":"Vbench: Comprehensive and versatile benchmark suite for video generative models. arXiv preprint arXiv:2411.13503","author":"Huang Ziqi","year":"2024","unstructured":"Ziqi Huang, Fan Zhang, Xiaojie Xu, Yinan He, Jiashuo Yu, Ziyue Dong, Qianli Ma, Nattapol Chanpaisit, Chenyang Si, Yuming Jiang, et al., 2024b. Vbench: Comprehensive and versatile benchmark suite for video generative models. arXiv preprint arXiv:2411.13503 (2024)."},{"key":"e_1_3_2_1_27_1","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras Tero","year":"2022","unstructured":"Tero Karras, Miika Aittala, Timo Aila, and Samuli Laine. 2022. Elucidating the design space of diffusion-based generative models. In Proc. NeurIPS, Vol. 35. 26565-26577.","journal-title":"Proc. NeurIPS"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02282"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. ECCV.","author":"Kim Bo-Kyeong","year":"2024","unstructured":"Bo-Kyeong Kim, Hyoung-Kyu Song, Thibault Castells, and Shinkook Choi. 2024. BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion. In Proc. ECCV."},{"key":"e_1_3_2_1_31_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_32_1","volume-title":"Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603","author":"Kong Weijie","year":"2024","unstructured":"Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong, Xin Li, Bo Wu, Jianwei Zhang, et al., 2024. Hunyuanvideo: A systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","unstructured":"PKU-Yuan Lab and Tuzhan AI etc. 2024. Open-Sora-Plan. doi:10.5281\/zenodo.10948109","DOI":"10.5281\/zenodo.10948109"},{"key":"e_1_3_2_1_34_1","unstructured":"Luma Labs. 2024. Dream Machine. https:\/\/lumalabs.ai\/dream-machine."},{"key":"e_1_3_2_1_35_1","volume-title":"Proc. ICLR.","author":"Li Hao","year":"2017","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2017. Pruning filters for efficient convnets. In Proc. ICLR."},{"key":"e_1_3_2_1_36_1","volume-title":"T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design. arXiv preprint arXiv:2410.05677","author":"Li Jiachen","year":"2024","unstructured":"Jiachen Li, Qian Long, Jian Zheng, Xiaofeng Gao, Robinson Piramuthu, Wenhu Chen, and William Yang Wang. 2024. T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design. arXiv preprint arXiv:2410.05677 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. NeurIPS.","author":"Li Yanyu","year":"2023","unstructured":"Yanyu Li, Huan Wang, Qing Jin, Ju Hu, Pavlo Chemerys, Yun Fu, Yanzhi Wang, Sergey Tulyakov, and Jian Ren. 2023. SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds. In Proc. NeurIPS."},{"key":"e_1_3_2_1_38_1","unstructured":"Bin Lin Yunyang Ge Xinhua Cheng Zongjian Li Bin Zhu Shaodong Wang Xianyi He Yang Ye Shenghai Yuan Liuhan Chen et al. 2024. Open-sora plan: Open-source large video generation model. arXiv preprint arXiv:2412.00131 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Proc. ICLR.","author":"Lipman Yaron","year":"2023","unstructured":"Yaron Lipman, Ricky TQ Chen, Heli Ben-Hamu, Maximilian Nickel, and Matthew Le. 2023. Flow Matching for Generative Modeling. In Proc. ICLR."},{"key":"e_1_3_2_1_40_1","volume-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378","author":"Luo Simian","year":"2023","unstructured":"Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, and Hang Zhao. 2023. Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Proc. IEEE Conf. CVPR.","author":"Mao Xiaofeng","year":"2024","unstructured":"Xiaofeng Mao, Zhengkai Jiang, Fu-Yun Wang, Wenbing Zhu, Jiangning Zhang, Hao Chen, Mingmin Chi, and Yabiao Wang. 2024. Osv: One step is enough for high-quality image to video generation. In Proc. IEEE Conf. CVPR."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"e_1_3_2_1_44_1","volume-title":"Proc. ICLR.","author":"Molchanov Pavlo","year":"2017","unstructured":"Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, and Jan Kautz. 2017. Pruning Convolutional Neural Networks for Resource Efficient Inference. In Proc. ICLR."},{"key":"e_1_3_2_1_45_1","volume-title":"Proc. NeurIPS.","author":"Mozer Michael C","year":"1988","unstructured":"Michael C Mozer and Paul Smolensky. 1988. Skeletonization: A technique for trimming the fat from a network via relevance assessment. In Proc. NeurIPS."},{"key":"e_1_3_2_1_46_1","volume-title":"Openvid-1m: A large-scale high-quality dataset for text-to-video generation. arXiv preprint arXiv:2407.02371","author":"Nan Kepan","year":"2024","unstructured":"Kepan Nan, Rui Xie, Penghao Zhou, Tiehan Fan, Zhenheng Yang, Zhijie Chen, Xiang Li, Jian Yang, and Ying Tai. 2024. Openvid-1m: A large-scale high-quality dataset for text-to-video generation. arXiv preprint arXiv:2407.02371 (2024)."},{"key":"e_1_3_2_1_47_1","unstructured":"OpenAI. 2024. Sora. https:\/\/openai.com\/index\/video-generation-models-as-world-simulators\/."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.248452"},{"key":"e_1_3_2_1_50_1","volume-title":"Proc. ICLR.","author":"Salimans Tim","year":"2022","unstructured":"Tim Salimans and Jonathan Ho. 2022. Progressive Distillation for Fast Sampling of Diffusion Models. In Proc. ICLR."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"e_1_3_2_1_52_1","volume-title":"Proc. ICLR.","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021a. Denoising diffusion implicit models. Proc. ICLR."},{"key":"e_1_3_2_1_53_1","volume-title":"Proc. ICLR.","author":"Song Yang","year":"2024","unstructured":"Yang Song and Prafulla Dhariwal. 2024. Improved Techniques for Training Consistency Models. In Proc. ICLR."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-1329-2_9"},{"key":"e_1_3_2_1_55_1","volume-title":"Proc. ICLR. https:\/\/openreview.net\/forum?id=PxTIG12RRHS","author":"Song Yang","year":"2021","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2021b. Score-Based Generative Modeling through Stochastic Differential Equations. In Proc. ICLR. https:\/\/openreview.net\/forum?id=PxTIG12RRHS"},{"key":"e_1_3_2_1_56_1","volume-title":"VidGen-1M: A Large-Scale Dataset for Text-to-video Generation. arXiv preprint arXiv:2408.02629","author":"Tan Zhiyu","year":"2024","unstructured":"Zhiyu Tan, Xiaomeng Yang, Luozheng Qin, and Hao Li. 2024. VidGen-1M: A Large-Scale Dataset for Text-to-video Generation. arXiv preprint arXiv:2408.02629 (2024)."},{"key":"e_1_3_2_1_57_1","unstructured":"Genmo Team. 2024. Mochi 1. https:\/\/github.com\/genmoai\/models."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Fu-Yun Wang Zhaoyang Huang Xiaoyu Shi Weikang Bian Guanglu Song Yu Liu and Hongsheng Li. 2024. AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data. SIGGRAPH ASIA TCS.","DOI":"10.1145\/3681758.3698013"},{"key":"e_1_3_2_1_59_1","volume-title":"Proc. ICLR.","author":"Wang Huan","year":"2021","unstructured":"Huan Wang, Can Qin, Yulun Zhang, and Yun Fu. 2021. Neural Pruning via Growing Regularization. In Proc. ICLR."},{"key":"e_1_3_2_1_60_1","volume-title":"Proc. ICLR.","author":"Wang Zhendong","year":"2023","unstructured":"Zhendong Wang, Huangjie Zheng, Pengcheng He, Weizhu Chen, and Mingyuan Zhou. 2023. Diffusion-GAN: Training GANs with Diffusion. In Proc. ICLR."},{"key":"e_1_3_2_1_61_1","volume-title":"Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:2503.20314","author":"Wang Ang","year":"2025","unstructured":"WanTeam, Ang Wang, Baole Ai, Bin Wen, Chaojie Mao, Chen-Wei Xie, Di Chen, Feiwu Yu, Haiming Zhao, Jianxiao Yang, Jianyuan Zeng, Jiayu Wang, Jingfeng Zhang, Jingren Zhou, Jinkai Wang, Jixuan Chen, Kai Zhu, Kang Zhao, Keyu Yan, Lianghua Huang, Mengyang Feng, Ningyi Zhang, Pandeng Li, Pingyu Wu, Ruihang Chu, Ruili Feng, Shiwei Zhang, Siyang Sun, Tao Fang, Tianxing Wang, Tianyi Gui, Tingyu Weng, Tong Shen, Wei Lin, Wei Wang, Wei Wang, Wenmeng Zhou, Wente Wang, Wenting Shen, Wenyuan Yu, Xianzhong Shi, Xiaoming Huang, Xin Xu, Yan Kou, Yangyu Lv, Yifei Li, Yijing Liu, Yiming Wang, Yingya Zhang, Yitong Huang, Yong Li, You Wu, Yu Liu, Yulin Pan, Yun Zheng, Yuntao Hong, Yupeng Shi, Yutong Feng, Zeyinzi Jiang, Zhen Han, Zhi-Fan Wu, and Ziyu Liu. 2025. Wan: Open and Advanced Large-Scale Video Generative Models. arXiv preprint arXiv:2503.20314 (2025)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00237"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"e_1_3_2_1_64_1","unstructured":"Zhuoyi Yang Jiayan Teng Wendi Zheng Ming Ding Shiyu Huang Jiazheng Xu Yuanming Yang Wenyi Hong Xiaohan Zhang Guanyu Feng et al. 2024. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. arXiv preprint arXiv:2408.06072 (2024)."},{"volume-title":"Proc. NeurIPS.","author":"Zhai Yuanhao","key":"e_1_3_2_1_65_1","unstructured":"Yuanhao Zhai, Kevin Lin, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Chung-Ching Lin, David Doermann, Junsong Yuan, and Lijuan Wang. [n.d.]. Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation. In Proc. NeurIPS."},{"key":"e_1_3_2_1_66_1","volume-title":"Proc. ICLR.","author":"Zhang Yabo","year":"2024","unstructured":"Yabo Zhang, Yuxiang Wei, Dongsheng Jiang, XIAOPENG ZHANG, Wangmeng Zuo, and Qi Tian. 2024b. ControlVideo: Training-free Controllable Text-to-video Generation. In Proc. ICLR."},{"key":"e_1_3_2_1_67_1","volume-title":"Proc. NeurIPS.","author":"Zhang Zhixing","year":"2024","unstructured":"Zhixing Zhang, Yanyu Li, Yushu Wu, Yanwu Xu, Anil Kag, Ivan Skorokhodov, Willi Menapace, Aliaksandr Siarohin, Junli Cao, Dimitris Metaxas, et al., 2024a. SF-V: Single Forward Video Generation Model. In Proc. NeurIPS."},{"key":"e_1_3_2_1_68_1","volume-title":"Mobilediffusion: Subsecond text-to-image generation on mobile devices. arXiv preprint arXiv:2311.16567","author":"Zhao Yang","year":"2023","unstructured":"Yang Zhao, Yanwu Xu, Zhisheng Xiao, and Tingbo Hou. 2023. Mobilediffusion: Subsecond text-to-image generation on mobile devices. arXiv preprint arXiv:2311.16567 (2023)."},{"key":"e_1_3_2_1_69_1","unstructured":"Zangwei Zheng Xiangyu Peng Tianji Yang Chenhui Shen Shenggui Li Hongxin Liu Yukun Zhou Tianyi Li and Yang You. 2024. Open-Sora: Democratizing Efficient Video Production for All. https:\/\/github.com\/hpcaitech\/Open-Sora"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:37Z","timestamp":1765308037000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755081"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":69,"alternative-id":["10.1145\/3746027.3755081","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755081","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"}}]}}