{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:21:47Z","timestamp":1765308107570,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755083","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"10925-10934","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7658-2959","authenticated-orcid":false,"given":"Jiaqi","family":"Xu","sequence":"first","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6047-2827","authenticated-orcid":false,"given":"Kunzhe","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0628-3715","authenticated-orcid":false,"given":"Xinyi","family":"Zou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4691-8696","authenticated-orcid":false,"given":"Yunkuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0405-3818","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7603-9787","authenticated-orcid":false,"given":"Mengli","family":"Cheng","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7706-7081","authenticated-orcid":false,"given":"Jun","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5946-3187","authenticated-orcid":false,"given":"Xing","family":"Shi","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"e_1_3_2_1_2_1","volume-title":"Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150","author":"Beltagy Iz","year":"2020","unstructured":"Iz Beltagy, Matthew E Peters, and Arman Cohan. 2020. Longformer: The long-document transformer. arXiv preprint arXiv:2004.05150 (2020)."},{"key":"e_1_3_2_1_3_1","unstructured":"James Betker Gabriel Goh Li Jing Tim Brooks Jianfeng Wang Linjie Li Long Ouyang Juntang Zhuang Joyce Lee Yufei Guo et al. 2023. Improving image generation with better captions. Computer Science. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf Vol. 2 3 (2023) 8."},{"key":"e_1_3_2_1_4_1","volume-title":"Training Diffusion Models with Reinforcement Learning. In The Twelfth International Conference on Learning Representations.","author":"Black Kevin","year":"2023","unstructured":"Kevin Black, Michael Janner, Yilun Du, Ilya Kostrikov, and Sergey Levine. 2023. Training Diffusion Models with Reinforcement Learning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_5_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts et al. 2023. Stable video diffusion: Scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"Allava: Harnessing gpt4v-synthesized data for lite vision-language models. arXiv preprint arXiv:2402.11684","author":"Chen Guiming Hardy","year":"2024","unstructured":"Guiming Hardy Chen, Shunian Chen, Ruifei Zhang, Junying Chen, Xiangbo Wu, Zhiyi Zhang, Zhihong Chen, Jianquan Li, Xiang Wan, and Benyou Wang. 2024a. Allava: Harnessing gpt4v-synthesized data for lite vision-language models. arXiv preprint arXiv:2402.11684 (2024)."},{"key":"e_1_3_2_1_7_1","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang et al. 2023a. Videocrafter1: Open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512 (2023)."},{"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","unstructured":"Junsong Chen Jincheng Yu Chongjian Ge Lewei Yao Enze Xie Yue Wu Zhongdao Wang James Kwok Ping Luo Huchuan Lu and Zhenguo Li. 2023b. PixArt-\u03b1: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis. arXiv:2310.00426 [cs.CV]"},{"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","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198","author":"Chen Zhe","year":"2024","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al., 2024c. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24185-24198."},{"key":"e_1_3_2_1_12_1","volume-title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards. In The Twelfth International Conference on Learning Representations.","author":"Clark Kevin","year":"2024","unstructured":"Kevin Clark, Paul Vicol, Kevin Swersky, and David J Fleet. 2024. Directly Fine-Tuning Diffusion Models on Differentiable Rewards. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","volume-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in neural information processing systems","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in neural information processing systems, Vol. 35 (2022), 16344-16359."},{"key":"e_1_3_2_1_14_1","unstructured":"Aesthetic Predictor V2.5 Developers. [n. d.] a. Aesthetic predictor v2.5. https:\/\/github.com\/discus0434\/aesthetic-predictor-v2-5."},{"key":"e_1_3_2_1_15_1","unstructured":"FFmpeg Developers. [n. d.] b. FFmpeg. https:\/\/github.com\/FFmpeg\/FFmpeg."},{"key":"e_1_3_2_1_16_1","unstructured":"OpenCV Developers. [n. d.] c. OpenCV. https:\/\/github.com\/opencv\/opencv."},{"key":"e_1_3_2_1_17_1","unstructured":"PySceneDetect Developers. [n. d.] d. Pyscenedetect. https:\/\/github.com\/Breakthrough\/PySceneDetect."},{"key":"e_1_3_2_1_18_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Forty-first international conference on machine learning.","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, et al., 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45103-X_50"},{"key":"e_1_3_2_1_21_1","volume-title":"The Twelfth International Conference on Learning Representations.","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 The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","volume-title":"Ltx-video: Realtime video latent diffusion. arXiv preprint arXiv:2501.00103","author":"HaCohen Yoav","year":"2025","unstructured":"Yoav HaCohen, Nisan Chiprut, Benny Brazowski, Daniel Shalem, Dudu Moshe, Eitan Richardson, Eran Levin, Guy Shiran, Nir Zabari, Ori Gordon, et al., 2025. Ltx-video: Realtime video latent diffusion. arXiv preprint arXiv:2501.00103 (2025)."},{"key":"e_1_3_2_1_23_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_24_1","volume-title":"International Conference on Learning Representations.","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models.. In International Conference on Learning Representations."},{"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","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_27_1","first-page":"48955","article-title":"Miradata: A large-scale video dataset with long durations and structured captions","volume":"37","author":"Ju Xuan","year":"2024","unstructured":"Xuan Ju, Yiming Gao, Zhaoyang Zhang, Ziyang Yuan, Xintao Wang, Ailing Zeng, Yu Xiong, Qiang Xu, and Ying Shan. 2024. Miradata: A large-scale video dataset with long durations and structured captions. Advances in Neural Information Processing Systems, Vol. 37 (2024), 48955-48970.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_29_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_30_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_31_1","volume-title":"Videodpo: Omni-preference alignment for video diffusion generation. arXiv preprint arXiv:2412.14167","author":"Liu Runtao","year":"2024","unstructured":"Runtao Liu, Haoyu Wu, Zheng Ziqiang, Chen Wei, Yingqing He, Renjie Pi, and Qifeng Chen. 2024. Videodpo: Omni-preference alignment for video diffusion generation. arXiv preprint arXiv:2412.14167 (2024)."},{"volume-title":"The Eleventh International Conference on Learning Representations.","author":"Liu Xingchao","key":"e_1_3_2_1_32_1","unstructured":"Xingchao Liu, Chengyue Gong, and qiang liu. 2023. Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.","author":"Luo Zhengxiong","year":"2023","unstructured":"Zhengxiong Luo, Dayou Chen, Yingya Zhang, Yan Huang, Liang Wang, Yujun Shen, Deli Zhao, Jingren Zhou, and Tieniu Tan. 2023. VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_34_1","volume-title":"Latte: Latent Diffusion Transformer for Video Generation. Transactions on Machine Learning Research","author":"Ma Xin","year":"2025","unstructured":"Xin Ma, Yaohui Wang, Xinyuan Chen, Gengyun Jia, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, and Yu Qiao. 2025. Latte: Latent Diffusion Transformer for Video Generation. Transactions on Machine Learning Research (2025)."},{"key":"e_1_3_2_1_35_1","unstructured":"OpenAI. 2024. Video Generation Models as World Simulators. https:\/\/openai.com\/index\/video-generation-models-as-world-simulators\/."},{"key":"e_1_3_2_1_36_1","unstructured":"Maxime Oquab Timoth\u00e9e Darcet Th\u00e9o Moutakanni Huy Vo Marc Szafraniec Vasil Khalidov Pierre Fernandez Daniel Haziza Francisco Massa Alaaeldin El-Nouby et al. 2024. DINOv2: Learning Robust Visual Features without Supervision. Transactions on Machine Learning Research Journal (2024) 1-31."},{"key":"e_1_3_2_1_37_1","unstructured":"Pexels. [n.d.]. Pexels. https:\/\/www.pexels.com\/"},{"key":"e_1_3_2_1_38_1","unstructured":"Adam Polyak Amit Zohar Andrew Brown Andros Tjandra Animesh Sinha Ann Lee Apoorv Vyas Bowen Shi Chih-Yao Ma Ching-Yao Chuang David Yan Dhruv Choudhary Dingkang Wang Geet Sethi Guan Pang Haoyu Ma Ishan Misra Ji Hou Jialiang Wang Kiran Jagadeesh Kunpeng Li Luxin Zhang Mannat Singh Mary Williamson Matt Le Matthew Yu Mitesh Kumar Singh Peizhao Zhang Peter Vajda Quentin Duval Rohit Girdhar Roshan Sumbaly Sai Saketh Rambhatla Sam Tsai Samaneh Azadi Samyak Datta Sanyuan Chen Sean Bell Sharadh Ramaswamy Shelly Sheynin Siddharth Bhattacharya Simran Motwani Tao Xu Tianhe Li Tingbo Hou Wei-Ning Hsu Xi Yin Xiaoliang Dai Yaniv Taigman Yaqiao Luo Yen-Cheng Liu Yi-Chiao Wu Yue Zhao Yuval Kirstain Zecheng He Zijian He Albert Pumarola Ali Thabet Artsiom Sanakoyeu Arun Mallya Baishan Guo Boris Araya Breena Kerr Carleigh Wood Ce Liu Cen Peng Dimitry Vengertsev Edgar Schonfeld Elliot Blanchard Felix Juefei-Xu Fraylie Nord Jeff Liang John Hoffman Jonas Kohler Kaolin Fire Karthik Sivakumar Lawrence Chen Licheng Yu Luya Gao Markos Georgopoulos Rashel Moritz Sara K. Sampson Shikai Li Simone Parmeggiani Steve Fine Tara Fowler Vladan Petrovic and Yuming Du. 2024. Movie Gen: A Cast of Media Foundation Models. arXiv preprint arXiv: 2410.13720 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"Aligning text-to-image diffusion models with reward backpropagation. arXiv preprint arXiv:2310.03739","author":"Prabhudesai Mihir","year":"2023","unstructured":"Mihir Prabhudesai, Anirudh Goyal, Deepak Pathak, and Katerina Fragkiadaki. 2023. Aligning text-to-image diffusion models with reward backpropagation. arXiv preprint arXiv:2310.03739 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Video diffusion alignment via reward gradients. arXiv preprint arXiv:2407.08737","author":"Prabhudesai Mihir","year":"2024","unstructured":"Mihir Prabhudesai, Russell Mendonca, Zheyang Qin, Katerina Fragkiadaki, and Deepak Pathak. 2024. Video diffusion alignment via reward gradients. arXiv preprint arXiv:2407.08737 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Machine Learning. 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. 8748-8763."},{"key":"e_1_3_2_1_42_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1-67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"e_1_3_2_1_45_1","unstructured":"Christoph Schuhmann Romain Beaumont Richard Vencu Cade Gordon Ross Wightman Mehdi Cherti Theo Coombes Aarush Katta Clayton Mullis Mitchell Wortsman et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in neural information processing systems Vol. 35 (2022) 25278-25294."},{"volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP)","author":"Su J","key":"e_1_3_2_1_46_1","unstructured":"J Su, H Zhang, X Li, J Zhang, and Y RoFormer Li. 2021. Enhanced transformer with rotary position embedding. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP), Association for Computational Linguistics, Online. 1-6."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00787"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems. 49659-49678","author":"Sun Keqiang","year":"2023","unstructured":"Keqiang Sun, Junting Pan, Yuying Ge, Hao Li, Haodong Duan, Xiaoshi Wu, Renrui Zhang, Aojun Zhou, Zipeng Qin, Yi Wang, et al., 2023. JourneyDB: a benchmark for generative image understanding. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 49659-49678."},{"key":"e_1_3_2_1_49_1","unstructured":"Genmo Team. 2024. Mochi 1. https:\/\/github.com\/genmoai\/models."},{"key":"e_1_3_2_1_50_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.898"},{"key":"e_1_3_2_1_52_1","volume-title":"Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571","author":"Wang Jiuniu","year":"2023","unstructured":"Jiuniu Wang, Hangjie Yuan, Dayou Chen, Yingya Zhang, Xiang Wang, and Shiwei Zhang. 2023. Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)."},{"key":"e_1_3_2_1_53_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_54_1","volume-title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation. In The Twelfth International Conference on Learning Representations.","author":"Wang Yi","year":"2024","unstructured":"Yi Wang, Yinan He, Yizhuo Li, Kunchang Li, Jiashuo Yu, Xin Ma, Xinhao Li, Guo Chen, Xinyuan Chen, Yaohui Wang, et al., 2024b. InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_55_1","volume-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341","author":"Wu Xiaoshi","year":"2023","unstructured":"Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, and Hongsheng Li. 2023. Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Visionreward: Fine-grained multi-dimensional human preference learning for image and video generation. arXiv preprint arXiv:2412.21059","author":"Xu Jiazheng","year":"2024","unstructured":"Jiazheng Xu, Yu Huang, Jiale Cheng, Yuanming Yang, Jiajun Xu, Yuan Wang, Wenbo Duan, Shen Yang, Qunlin Jin, Shurun Li, et al., 2024. Visionreward: Fine-grained multi-dimensional human preference learning for image and video generation. arXiv preprint arXiv:2412.21059 (2024)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"e_1_3_2_1_58_1","volume-title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. In The Thirteenth International Conference on Learning Representations.","author":"Yang Zhuoyi","year":"2025","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, et al., 2025. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00618"},{"key":"e_1_3_2_1_60_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Zhang Biao","year":"2019","unstructured":"Biao Zhang and Rico Sennrich. 2019. Root mean square layer normalization. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00766"},{"key":"e_1_3_2_1_62_1","volume-title":"Open-sora: Democratizing efficient video production for all. arXiv preprint arXiv:2412.20404","author":"Zheng Zangwei","year":"2024","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. arXiv preprint arXiv:2412.20404 (2024)."}],"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\/3746027.3755083","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:00Z","timestamp":1765308000000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":62,"alternative-id":["10.1145\/3746027.3755083","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755083","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"}}]}}