{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:05:42Z","timestamp":1784228742356,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":68,"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 Key Research and Development Program of China","award":["2023YFF0905104"],"award-info":[{"award-number":["2023YFF0905104"]}]},{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM101"],"award-info":[{"award-number":["JYB2025XDXM101"]}]},{"name":"Natural Science Foundation of China","award":["62132012"],"award-info":[{"award-number":["62132012"]}]},{"name":"Natural Science Foundation of China","award":["62361146854"],"award-info":[{"award-number":["62361146854"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811088","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9433-1980","authenticated-orcid":false,"given":"Tian-Xing","family":"Xu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7291-6198","authenticated-orcid":false,"given":"Zi-Xuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2388-0716","authenticated-orcid":false,"given":"Guangyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9666-6872","authenticated-orcid":false,"given":"Li","family":"Hu","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5648-1255","authenticated-orcid":false,"given":"Zhongyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3704-051X","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9529-0184","authenticated-orcid":false,"given":"Bang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongyi Lab, Alibaba, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0460-1586","authenticated-orcid":false,"given":"Song-Hai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"crossref","unstructured":"Eloi Alonso Adam Jelley Vincent Micheli Anssi Kanervisto Amos\u00a0J Storkey Tim Pearce and Fran\u00e7ois Fleuret. 2024. Diffusion for world modeling: Visual details matter in atari. Advances in Neural Information Processing Systems 37 (2024) 58757\u201358791.","DOI":"10.52202\/079017-1873"},{"key":"e_1_3_3_2_3_1","unstructured":"Genesis Authors. 2024. Genesis: A universal and generative physics engine for robotics and beyond December 2024. URL https:\/\/github. com\/Genesis-Embodied-AI\/Genesis 9 (2024)."},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02130"},{"key":"e_1_3_3_2_5_1","unstructured":"Jianhong Bai Menghan Xia Xiao Fu Xintao Wang Lianrui Mu Jinwen Cao Zuozhu Liu Haoji Hu Xiang Bai Pengfei Wan et\u00a0al. 2025b. 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_6_1","unstructured":"Yunpeng Bai Haoxiang Li and Qixing Huang. 2025a. Positional encoding field. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.20385 (2025)."},{"key":"e_1_3_3_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01472"},{"key":"e_1_3_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763842"},{"key":"e_1_3_3_2_10_1","unstructured":"Haoxuan Che Xuanhua He Quande Liu Cheng Jin and Hao Chen. 2024. Gamegen-x: Interactive open-world game video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.00769 (2024)."},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Boyuan Chen Diego Mart\u00ed\u00a0Mons\u00f3 Yilun Du Max Simchowitz Russ Tedrake and Vincent Sitzmann. 2024. Diffusion forcing: Next-token prediction meets full-sequence diffusion. Advances in Neural Information Processing Systems 37 (2024) 24081\u201324125.","DOI":"10.52202\/079017-0759"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_3_2_13_1","doi-asserted-by":"crossref","unstructured":"Yanran Dai Jing Li Yuqi Jiang Haidong Qin Bang Liang Shikuan Hong Haozhe Pan and Tao Yang. 2024. Real-time distance field acceleration based free-viewpoint video synthesis for large sports fields. Computational Visual Media 10 2 (2024) 331\u2013353.","DOI":"10.1007\/s41095-022-0323-3"},{"key":"e_1_3_3_2_14_1","unstructured":"Etched Decart Quinn McIntyre Spruce Campbell Xinlei Chen and Robert Wachen. 2024. Oasis: A universe in a transformer. URL: https:\/\/oasis-model. github. io (2024)."},{"key":"e_1_3_3_2_15_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\u00a0al. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In Forty-first international conference on machine learning."},{"key":"e_1_3_3_2_16_1","unstructured":"Wanquan Feng Jiawei Liu Pengqi Tu Tianhao Qi Mingzhen Sun Tianxiang Ma Songtao Zhao Siyu Zhou and Qian He. 2024. I2vcontrol-camera: Precise video camera control with adjustable motion strength. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.06525 (2024)."},{"key":"e_1_3_3_2_17_1","unstructured":"Jianxiong Gao Zhaoxi Chen Xian Liu Junhao Zhuang Chengming Xu Jianfeng Feng Yu Qiao Yanwei Fu Chenyang Si and Ziwei Liu. 2025a. LongVie 2: Multimodal Controllable Ultra-Long Video World Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.13604 (2025)."},{"key":"e_1_3_3_2_18_1","unstructured":"Yu Gao Haoyuan Guo Tuyen Hoang Weilin Huang Lu Jiang Fangyuan Kong Huixia Li Jiashi Li Liang Li Xiaojie Li et\u00a0al. 2025b. Seedance 1.0: Exploring the Boundaries of Video Generation Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.09113 (2025)."},{"key":"e_1_3_3_2_19_1","unstructured":"Yuchao Gu Weijia Mao and Mike\u00a0Zheng Shou. 2025a. Long-context autoregressive video modeling with next-frame prediction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.19325 (2025)."},{"key":"e_1_3_3_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730607"},{"key":"e_1_3_3_2_21_1","unstructured":"Xiangyu Guo Zhanqian Wu Kaixin Xiong Ziyang Xu Lijun Zhou Gangwei Xu Shaoqing Xu Haiyang Sun Bing Wang Guang Chen et\u00a0al. 2025. Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.07497 (2025)."},{"key":"e_1_3_3_2_22_1","unstructured":"Hao He Yinghao Xu Yuwei Guo Gordon Wetzstein Bo Dai Hongsheng Li and Ceyuan Yang. 2024. Cameractrl: Enabling camera control for text-to-video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.02101 (2024)."},{"key":"e_1_3_3_2_23_1","doi-asserted-by":"crossref","unstructured":"Hao He Ceyuan Yang Shanchuan Lin Yinghao Xu Meng Wei Liangke Gui Qi Zhao Gordon Wetzstein Lu Jiang and Hongsheng Li. 2025. Cameractrl ii: Dynamic scene exploration via camera-controlled video diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.10592 (2025).","DOI":"10.1109\/ICCV51701.2025.01246"},{"key":"e_1_3_3_2_24_1","unstructured":"Martin Heusel Hubert Ramsauer Thomas Unterthiner Bernhard Nessler and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_2_25_1","doi-asserted-by":"publisher","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. CoRR abs\/2207.12598 (2022). arXiv:https:\/\/arXiv.org\/abs\/2207.1259810.48550\/ARXIV.2207.12598","DOI":"10.48550\/ARXIV.2207.12598"},{"key":"e_1_3_3_2_26_1","unstructured":"Xun Huang Zhengqi Li Guande He Mingyuan Zhou and Eli Shechtman. 2025. Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.08009 (2025)."},{"key":"e_1_3_3_2_27_1","doi-asserted-by":"crossref","unstructured":"Xinyi Jing Tao Yu Renyuan He Yu-Kun Lai and Kun Li. 2025. Frnerf: Fusion and regularization fields for dynamic view synthesis. Computational Visual Media (2025).","DOI":"10.26599\/CVM.2025.9450405"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"crossref","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 37 (2024) 48955\u201348970.","DOI":"10.52202\/079017-1551"},{"key":"e_1_3_3_2_29_1","doi-asserted-by":"crossref","unstructured":"Anssi Kanervisto Dave Bignell Linda\u00a0Yilin Wen Martin Grayson Raluca Georgescu Sergio Valcarcel\u00a0Macua Shan\u00a0Zheng Tan Tabish Rashid Tim Pearce Yuhan Cao et\u00a0al. 2025. World and human action models towards gameplay ideation. Nature 638 8051 (2025) 656\u2013663.","DOI":"10.1038\/s41586-025-08600-3"},{"key":"e_1_3_3_2_30_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_31_1","doi-asserted-by":"crossref","unstructured":"Arno Knapitsch Jaesik Park Qian-Yi Zhou and Vladlen Koltun. 2017. Tanks and temples: Benchmarking large-scale scene reconstruction. ACM Transactions on Graphics (ToG) 36 4 (2017) 1\u201313.","DOI":"10.1145\/3072959.3073599"},{"key":"e_1_3_3_2_32_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_33_1","unstructured":"Yushi Lan Yihang Luo Fangzhou Hong Shangchen Zhou Honghua Chen Zhaoyang Lyu Shuai Yang Bo Dai Chen\u00a0Change Loy and Xingang Pan. 2025. Stream3r: Scalable sequential 3d reconstruction with causal transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.10893 (2025)."},{"key":"e_1_3_3_2_34_1","unstructured":"Runjia Li Philip Torr Andrea Vedaldi and Tomas Jakab. 2025a. VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.18903 (2025)."},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02673"},{"key":"e_1_3_3_2_36_1","unstructured":"Haotong Lin Sili Chen Junhao Liew Donny\u00a0Y Chen Zhenyu Li Guang Shi Jiashi Feng and Bingyi Kang. 2025. Depth anything 3: Recovering the visual space from any views. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.10647 (2025)."},{"key":"e_1_3_3_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"e_1_3_3_2_38_1","unstructured":"Tianran Liu Shengwen Zhao and Nicholas Rhinehart. 2025b. Towards foundational LiDAR world models with efficient latent flow matching. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.23434 (2025)."},{"key":"e_1_3_3_2_39_1","unstructured":"Yifan Liu Zhiyuan Min Zhenwei Wang Junta Wu Tengfei Wang Yixuan Yuan Yawei Luo and Chunchao Guo. 2025a. Worldmirror: Universal 3d world reconstruction with any-prior prompting. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.10726 (2025)."},{"key":"e_1_3_3_2_40_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1711.05101 (2017)."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00194"},{"key":"e_1_3_3_2_42_1","unstructured":"J Parker-Holder P Ball J Bruce V Dasagi K Holsheimer C Kaplanis A Moufarek G Scully J Shar J Shi et\u00a0al. 2024. Genie 2: A large-scale foundation world model. URL: https:\/\/deepmind. google\/discover\/blog\/genie-2-a-large-scale-foundation-world-model (2024)."},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"e_1_3_3_2_45_1","unstructured":"Kiwhan Song Boyuan Chen Max Simchowitz Yilun Du Russ Tedrake and Vincent Sitzmann. 2025. History-guided video diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.06764 (2025)."},{"key":"e_1_3_3_2_46_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_47_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_48_1","unstructured":"Dani Valevski Yaniv Leviathan Moab Arar and Shlomi Fruchter. 2024. Diffusion models are real-time game engines. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.14837 (2024)."},{"key":"e_1_3_3_2_49_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_50_1","unstructured":"Jiahao Wang Yufeng Yuan Rujie Zheng Youtian Lin Jian Gao Lin-Zhuo Chen Yajie Bao Yi Zhang Chang Zeng Yanxi Zhou et\u00a0al. 2025. Spatialvid: A large-scale video dataset with spatial annotations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.09676 (2025)."},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"crossref","unstructured":"Zhou Wang and Alan\u00a0C Bovik. 2002. A universal image quality index. IEEE signal processing letters 9 3 (2002) 81\u201384.","DOI":"10.1109\/97.995823"},{"key":"e_1_3_3_2_52_1","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_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"e_1_3_3_2_54_1","unstructured":"Tong Wu Shuai Yang Ryan Po Yinghao Xu Ziwei Liu Dahua Lin and Gordon Wetzstein. 2025. Video World Models with Long-term Spatial Memory. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.05284 (2025)."},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Tong Wu Yu-Jie Yuan Ling-Xiao Zhang Jie Yang Yan-Pei Cao Ling-Qi Yan and Lin Gao. 2024. Recent advances in 3d gaussian splatting. Computational Visual Media 10 4 (2024) 613\u2013642.","DOI":"10.1007\/s41095-024-0436-y"},{"key":"e_1_3_3_2_56_1","unstructured":"Zeqi Xiao Yushi Lan Yifan Zhou Wenqi Ouyang Shuai Yang Yanhong Zeng and Xingang Pan. 2025. Worldmem: Long-term consistent world simulation with memory. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.12369 (2025)."},{"key":"e_1_3_3_2_57_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_58_1","unstructured":"Meng You Zhiyu Zhu Hui Liu and Junhui Hou. 2024. Nvs-solver: Video diffusion model as zero-shot novel view synthesizer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.15364 (2024)."},{"key":"e_1_3_3_2_59_1","unstructured":"Jiwen Yu Jianhong Bai Yiran Qin Quande Liu Xintao Wang Pengfei Wan Di Zhang and Xihui Liu. 2025. Context as memory: Scene-consistent interactive long video generation with memory retrieval. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.03141 (2025)."},{"key":"e_1_3_3_2_60_1","unstructured":"Mark YU Wenbo Hu Jinbo Xing and Ying Shan. 2025. Trajectorycrafter: Redirecting camera trajectory for monocular videos via diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.05638 (2025)."},{"key":"e_1_3_3_2_61_1","unstructured":"Wangbo Yu Jinbo Xing Li Yuan Wenbo Hu Xiaoyu Li Zhipeng Huang Xiangjun Gao Tien-Tsin Wong Ying Shan and Yonghong Tian. 2024. Viewcrafter: Taming video diffusion models for high-fidelity novel view synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.02048 (2024)."},{"key":"e_1_3_3_2_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.29"},{"key":"e_1_3_3_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02498"},{"key":"e_1_3_3_2_64_1","unstructured":"Cheng Zhang Boying Li Meng Wei Yan-Pei Cao Camilo\u00a0Cruz Gambardella Dinh Phung and Jianfei Cai. 2025. Unified Camera Positional Encoding for Controlled Video Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.07237 (2025)."},{"key":"e_1_3_3_2_65_1","unstructured":"Junyi Zhang Charles Herrmann Junhwa Hur Chen Sun Ming-Hsuan Yang Forrester Cole Trevor Darrell and Deqing Sun. 2026. LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2603.03269 (2026)."},{"key":"e_1_3_3_2_66_1","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2025. Packing input frame context in next-frame prediction models for video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.12626 (2025)."},{"key":"e_1_3_3_2_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_3_2_68_1","unstructured":"Tinghui Zhou Richard Tucker John Flynn Graham Fyffe and Noah Snavely. 2018. Stereo magnification: Learning view synthesis using multiplane images. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1805.09817 (2018)."},{"key":"e_1_3_3_2_69_1","unstructured":"Zheng Zhu Xiaofeng Wang Wangbo Zhao Chen Min Bohan Li Nianchen Deng Min Dou Yuqi Wang Botian Shi Kai Wang et\u00a0al. 2024. Is sora a world simulator? a comprehensive survey on general world models and beyond. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.03520 (2024)."}],"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":"2026-07-16T18:21:44Z","timestamp":1784226104000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811088"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":68,"alternative-id":["10.1145\/3799902.3811088","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811088","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"}}]}}