{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:05:51Z","timestamp":1784228751713,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62441231, 62472065, U23B2010"],"award-info":[{"award-number":["62441231, 62472065, U23B2010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811208","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3867-0920","authenticated-orcid":false,"given":"BaoLu","family":"Li","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9753-4943","authenticated-orcid":false,"given":"Yiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6908-5485","authenticated-orcid":false,"given":"Qinghe","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0814-9876","authenticated-orcid":false,"given":"Liqian","family":"Ma","sequence":"additional","affiliation":[{"name":"ZMO AI Inc., San Jose, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3696-4442","authenticated-orcid":false,"given":"Xiaoyu","family":"Shi","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6585-8604","authenticated-orcid":false,"given":"Xintao","family":"Wang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9281-1529","authenticated-orcid":false,"given":"Pengfei","family":"Wan","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8666-1103","authenticated-orcid":false,"given":"Zhenfei","family":"Yin","sequence":"additional","affiliation":[{"name":"Oxford University, Oxford, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4288-4516","authenticated-orcid":false,"given":"Yunzhi","family":"Zhuge","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6668-9758","authenticated-orcid":false,"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3168-3505","authenticated-orcid":false,"given":"Xu","family":"Jia","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","unstructured":"2025. Gen-3. Accessed June 17 2025 [Online] https:\/\/runwayml.com\/research\/introducing-gen-3-alpha. https:\/\/runwayml.com\/research\/introducing-gen-3-alpha"},{"key":"e_1_3_3_2_3_1","unstructured":"2025. Higgsfield. Accessed June 1 2025 [Online] https:\/\/higgsfield.ai\/. https:\/\/higgsfield.ai\/"},{"key":"e_1_3_3_2_4_1","unstructured":"2025. Minmax Team. Accessed June 31 2025 [Online] https:\/\/hailuoai.com\/. https:\/\/hailuoai.com\/"},{"key":"e_1_3_3_2_5_1","unstructured":"2025. Pixverse: AI-powered Image and Video Editing Platform. Accessed June 1 2025 [Online] https:\/\/app.pixverse.ai\/. https:\/\/app.pixverse.ai\/"},{"key":"e_1_3_3_2_6_1","unstructured":"2025. Sora. Accessed July 15 2025 [Online] https:\/\/openai.com\/sora\/. https:\/\/openai.com\/sora\/"},{"key":"e_1_3_3_2_7_1","unstructured":"2025. Veo3. Accessed June 18 2025 [Online] https:\/\/veo3.im\/. https:\/\/veo3.im\/"},{"key":"e_1_3_3_2_8_1","unstructured":"Niket Agarwal Arslan Ali Maciej Bala Yogesh Balaji Erik Barker Tiffany Cai Prithvijit Chattopadhyay Yongxin Chen Yin Cui Yifan Ding et\u00a0al. 2025. Cosmos world foundation model platform for physical ai. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.03575 (2025)."},{"key":"e_1_3_3_2_9_1","unstructured":"Jianhong Bai Menghan Xia Xiao Fu Xintao Wang Lianrui Mu Jinwen Cao Zuozhu Liu Haoji Hu Xiang Bai Pengfei Wan et\u00a0al. 2025. Recammaster: Camera-controlled generative rendering from a single video. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.11647 (2025)."},{"key":"e_1_3_3_2_10_1","unstructured":"Jianhong Bai Menghan Xia Xintao Wang Ziyang Yuan Xiao Fu Zuozhu Liu Haoji Hu Pengfei Wan and Di Zhang. 2024. Syncammaster: Synchronizing multi-camera video generation from diverse viewpoints. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.07760 (2024)."},{"key":"e_1_3_3_2_11_1","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et\u00a0al. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning multimodality long context and next generation agentic capabilities. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.06261 (2025)."},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Tao Du Kui Wu Pingchuan Ma Sebastien Wah Andrew Spielberg Daniela Rus and Wojciech Matusik. 2021. Diffpd: Differentiable projective dynamics. ACM Transactions on Graphics (ToG) 41 2 (2021) 1\u201321.","DOI":"10.1145\/3490168"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00010"},{"key":"e_1_3_3_2_14_1","unstructured":"Zekai Gu Rui Yan Jiahao Lu Peng Li Zhiyang Dou Chenyang Si Zhen Dong Qifeng Liu Cheng Lin Ziwei Liu Wenping Wang and Yuan Liu. 2025. Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.03847 (2025)."},{"key":"e_1_3_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681516"},{"key":"e_1_3_3_2_16_1","unstructured":"Yoav HaCohen Nisan Chiprut Benny Brazowski Daniel Shalem Dudu Moshe Eitan Richardson Eran Levin Guy Shiran Nir Zabari Ori Gordon Poriya Panet Sapir Weissbuch Victor Kulikov Yaki Bitterman Zeev Melumian and Ofir Bibi. 2024. LTX-Video: Realtime Video Latent Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.00103 (2024)."},{"key":"e_1_3_3_2_17_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_2_18_1","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang Weizhu Chen et\u00a0al. 2022. Lora: Low-rank adaptation of large language models. ICLR 1 2 (2022) 3."},{"key":"e_1_3_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00682"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Zeyinzi Jiang Zhen Han Chaojie Mao Jingfeng Zhang Yulin Pan and Yu Liu. 2025. Vace: All-in-one video creation and editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.07598 (2025).","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"e_1_3_3_2_22_1","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.6114 (2013)."},{"key":"e_1_3_3_2_23_1","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_2_24_1","unstructured":"Xinyu Liu Ailing Zeng Wei Xue Harry Yang Wenhan Luo Qifeng Liu and Yike Guo. 2025. VFX Creator: Animated Visual Effect Generation with Controllable Diffusion Transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.05979 (2025)."},{"key":"e_1_3_3_2_25_1","unstructured":"Guoqing Ma Haoyang Huang Kun Yan Liangyu Chen Nan Duan Shengming Yin Changyi Wan Ranchen Ming Xiaoniu Song Xing Chen et\u00a0al. 2025b. Step-video-t2v technical report: The practice challenges and future of video foundation model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.10248 (2025)."},{"key":"e_1_3_3_2_26_1","unstructured":"Yue Ma Kunyu Feng Zhongyuan Hu Xinyu Wang Yucheng Wang Mingzhe Zheng Xuanhua He Chenyang Zhu Hongyu Liu Yingqing He et\u00a0al. 2025a. Controllable video generation: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.16869 (2025)."},{"key":"e_1_3_3_2_27_1","unstructured":"Fangyuan Mao Aiming Hao Jintao Chen Dongxia Liu Xiaokun Feng Jiashu Zhu Meiqi Wu Chubin Chen Jiahong Wu and Xiangxiang Chu. 2025. Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.07981 (2025)."},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_2_29_1","unstructured":"Bohao Peng Jian Wang Yuechen Zhang Wenbo Li Ming-Chang Yang and Jiaya Jia. 2024. ControlNeXt: Powerful and Efficient Control for Image and Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06070 (2024)."},{"key":"e_1_3_3_2_30_1","unstructured":"Adam Polyak Amit Zohar Andrew Brown Andros Tjandra Animesh Sinha Ann Lee Apoorv Vyas Bowen Shi Chih-Yao Ma Ching-Yao Chuang et\u00a0al. 2024. Movie gen: A cast of media foundation models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.13720 (2024)."},{"key":"e_1_3_3_2_31_1","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter\u00a0J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21 140 (2020) 1\u201367."},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_2_33_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2020a. Denoising diffusion implicit models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.02502 (2020)."},{"key":"e_1_3_3_2_34_1","unstructured":"Yang Song Jascha Sohl-Dickstein Diederik\u00a0P Kingma Abhishek Kumar Stefano Ermon and Ben Poole. 2020b. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2011.13456 (2020)."},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"crossref","unstructured":"Jianlin Su Murtadha Ahmed Yu Lu Shengfeng Pan Wen Bo and Yunfeng Liu. 2024. Roformer: Enhanced transformer with rotary position embedding. Neurocomputing 568 (2024) 127063.","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_3_2_36_1","unstructured":"Thomas Unterthiner Sjoerd Van\u00a0Steenkiste Karol Kurach Raphael Marinier Marcin Michalski and Sylvain Gelly. 2018. Towards accurate generative models of video: A new metric & challenges. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.01717 (2018)."},{"key":"e_1_3_3_2_37_1","unstructured":"Team Wan Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang 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_2_38_1","unstructured":"Qinghe Wang Xu Jia Xiaomin Li Taiqing Li Liqian Ma Yunzhi Zhuge and Huchuan Lu. 2024. Stableidentity: Inserting anybody into anywhere at first sight. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.15975 (2024)."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730755"},{"key":"e_1_3_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730604"},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"crossref","unstructured":"Xindi Yang Baolu Li Yiming Zhang Zhenfei Yin Lei Bai Liqian Ma Zhiyong Wang Jianfei Cai Tien-Tsin Wong Huchuan Lu et\u00a0al. 2025b. VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.23368 (2025).","DOI":"10.1109\/ICCV51701.2025.01149"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"crossref","unstructured":"Yuxue Yang Lue Fan Zuzeng Lin Feng Wang and Zhaoxiang Zhang. 2025a. LayerAnimate: Layer-level Control for Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.08295 (2025).","DOI":"10.1109\/ICCV51701.2025.01011"},{"key":"e_1_3_3_2_43_1","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_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00251"},{"key":"e_1_3_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730683"}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:22:50Z","timestamp":1784226170000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":45,"alternative-id":["10.1145\/3799902.3811208","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811208","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}