{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:04:59Z","timestamp":1765339499427,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754495","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:54:15Z","timestamp":1761375255000},"page":"7142-7151","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Uni-Sight: An E2E Vision-Language-Action System Unifying Multi-View Alignment and Multi-Modal Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8689-6929","authenticated-orcid":false,"given":"Daixun","family":"Li","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9704-1209","authenticated-orcid":false,"given":"Sibo","family":"He","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7394-1851","authenticated-orcid":false,"given":"Jiayun","family":"Tian","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2179-2665","authenticated-orcid":false,"given":"Yusi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8310-024X","authenticated-orcid":false,"given":"Weiying","family":"Xie","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1892-3645","authenticated-orcid":false,"given":"Mingxiang","family":"Cao","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7047-5762","authenticated-orcid":false,"given":"Donglai","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6589-0478","authenticated-orcid":false,"given":"Zirui","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5178-9309","authenticated-orcid":false,"given":"Tianlin","family":"Hui","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3368-1688","authenticated-orcid":false,"given":"Rui","family":"Huang","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0234-6270","authenticated-orcid":false,"given":"Yunsong","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, Shaanxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Anthony Brohan Noah Brown Justice Carbajal Yevgen Chebotar Joseph Dabis Chelsea Finn Keerthana Gopalakrishnan Karol Hausman Alex Herzog Jasmine Hsu et al. 2022. Rt-1: Robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2022).","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"e_1_3_2_1_4_1","unstructured":"Zhe Chen Weiyun Wang Yue Cao Yangzhou Liu Zhangwei Gao Erfei Cui Jinguo Zhu Shenglong Ye Hao Tian Zhaoyang Liu et al. 2024. Expanding performance boundaries of open-source multimodal models with model data and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"European Conference on Computer Vision (ECCV). Springer, 352-367","author":"Ding Pengxiang","year":"2024","unstructured":"Pengxiang Ding, Han Zhao, Wenjie Zhang, Wenxuan Song, Min Zhang, Siteng Huang, Ningxi Yang, and Donglin Wang. 2024. Quar-vla: Vision-language-action model for quadruped robots. In European Conference on Computer Vision (ECCV). Springer, 352-367."},{"key":"e_1_3_2_1_6_1","first-page":"9156","article-title":"Learning universal policies via text-guided video generation","volume":"36","author":"Du Yilun","year":"2023","unstructured":"Yilun Du, Sherry Yang, Bo Dai, Hanjun Dai, Ofir Nachum, Josh Tenenbaum, Dale Schuurmans, and Pieter Abbeel. 2023. Learning universal policies via text-guided video generation. Advances in Neural Information Processing Systems (NeurIPS) 36 (2023), 9156-9172.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01827"},{"key":"e_1_3_2_1_8_1","first-page":"59636","article-title":"Grounded decoding: Guiding text generation with grounded models for embodied agents","volume":"36","author":"Huang Wenlong","year":"2023","unstructured":"Wenlong Huang, Fei Xia, Dhruv Shah, Danny Driess, Andy Zeng, Yao Lu, Pete Florence, Igor Mordatch, Sergey Levine, Karol Hausman, et al. 2023. Grounded decoding: Guiding text generation with grounded models for embodied agents. Advances in Neural Information Processing Systems (NeurIPS) 36 (2023), 59636-59661.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_9_1","volume-title":"Vima: General robot manipulation with multimodal prompts. arXiv preprint arXiv:2210.03094 2, 3","author":"Jiang Yunfan","year":"2022","unstructured":"Yunfan Jiang, Agrim Gupta, Zichen Zhang, Guanzhi Wang, Yongqiang Dou, Yanjun Chen, Li Fei-Fei, Anima Anandkumar, Yuke Zhu, and Linxi Fan. 2022. Vima: General robot manipulation with multimodal prompts. arXiv preprint arXiv:2210.03094 2, 3 (2022), 6."},{"key":"e_1_3_2_1_10_1","volume-title":"Openvla: An open-source vision-language-action model. arXiv preprint arXiv:2406.09246","author":"Kim Moo Jin","year":"2024","unstructured":"Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao, Ashwin Balakrishna, Suraj Nair, Rafael Rafailov, Ethan Foster, Grace Lam, Pannag Sanketi, et al. 2024. Openvla: An open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"FusionSAM: Latent Space driven Segment Anything Model for Multimodal Fusion and Segmentation. arXiv preprint arXiv:2408.13980","author":"Li Daixun","year":"2024","unstructured":"Daixun Li, Weiying Xie, Mingxiang Cao, Yunke Wang, Jiaqing Zhang, Yunsong Li, Leyuan Fang, and Chang Xu. 2024. FusionSAM: Latent Space driven Segment Anything Model for Multimodal Fusion and Segmentation. arXiv preprint arXiv:2408.13980 (2024)."},{"key":"e_1_3_2_1_12_1","first-page":"8653","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","volume":"38","author":"Li Daixun","year":"2024","unstructured":"Daixun Li, Weiying Xie, Jiaqing Zhang, and Yunsong Li. 2024. MDFL: Multidomain diffusion-driven feature learning. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Vol. 38. 8653-8660."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"e_1_3_2_1_15_1","first-page":"44776","article-title":"Libero: Benchmarking knowledge transfer for lifelong robot learning","volume":"36","author":"Liu Bo","year":"2023","unstructured":"Bo Liu, Yifeng Zhu, Chongkai Gao, Yihao Feng, Qiang Liu, Yuke Zhu, and Peter Stone. 2023. Libero: Benchmarking knowledge transfer for lifelong robot learning. Advances in Neural Information Processing Systems (NeurIPS) 36 (2023), 44776-44791.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_16_1","first-page":"40085","article-title":"Robomamba: Efficient vision-language-action model for robotic reasoning and manipulation","volume":"37","author":"Liu Jiaming","year":"2024","unstructured":"Jiaming Liu, Mengzhen Liu, Zhenyu Wang, Pengju An, Xiaoqi Li, Kaichen Zhou, Senqiao Yang, Renrui Zhang, Yandong Guo, and Shanghang Zhang. 2024. Robomamba: Efficient vision-language-action model for robotic reasoning and manipulation. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 40085-40110.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_17_1","volume-title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation. arXiv preprint arXiv:2410.07864","author":"Liu Songming","year":"2024","unstructured":"Songming Liu, Lingxuan Wu, Bangguo Li, Hengkai Tan, Huayu Chen, Zhengyi Wang, Ke Xu, Hang Su, and Jun Zhu. 2024. RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation. arXiv preprint arXiv:2410.07864 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30552"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Machine Learning (ICML). PMLR, 23301-23320","author":"Ma Yecheng Jason","year":"2023","unstructured":"Yecheng Jason Ma, Vikash Kumar, Amy Zhang, Osbert Bastani, and Dinesh Jayaraman. 2023. Liv: Language-image representations and rewards for robotic control. In International Conference on Machine Learning (ICML). PMLR, 23301-23320."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00272"},{"key":"e_1_3_2_1_22_1","first-page":"25081","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","volume":"36","author":"Mu Yao","year":"2023","unstructured":"Yao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang, Mingyu Ding, Jun Jin, BinWang, Jifeng Dai, Yu Qiao, and Ping Luo. 2023. Embodiedgpt: Vision-language pre-training via embodied chain of thought. Advances in Neural Information Processing Systems (NeurIPS) 36 (2023), 25081-25094.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_23_1","volume-title":"R3m: A universal visual representation for robot manipulation. arXiv preprint arXiv:2203.12601","author":"Nair Suraj","year":"2022","unstructured":"Suraj Nair, Aravind Rajeswaran, Vikash Kumar, Chelsea Finn, and Abhinav Gupta. 2022. R3m: A universal visual representation for robot manipulation. arXiv preprint arXiv:2203.12601 (2022)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01281"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01327"},{"key":"e_1_3_2_1_26_1","first-page":"17541","article-title":"PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for Manipulation","volume":"37","author":"Ni Fei","year":"2024","unstructured":"Fei Ni, Jianye Hao, Shiguang Wu, Longxin Kou, Yifu Yuan, Zibin Dong, Jinyi Liu, MingZhi Li, Yuzheng Zhuang, and Yan Zheng. 2024. PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for Manipulation. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 17541-17571.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_28_1","first-page":"55681","article-title":"Roboclip: One demonstration is enough to learn robot policies","volume":"36","author":"Sontakke Sumedh","year":"2023","unstructured":"Sumedh Sontakke, Jesse Zhang, S\u00e9b Arnold, Karl Pertsc, Dorsa Sadigh, Chelsea Finn, and Laurent Itti. 2023. Roboclip: One demonstration is enough to learn robot policies. Advances in Neural Information Processing Systems (NeurIPS) 36 (2023), 55681-55693.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_29_1","first-page":"13139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume":"33","author":"Stepputtis Simon","year":"2020","unstructured":"Simon Stepputtis, Joseph Campbell, Mariano Phielipp, Stefan Lee, Chitta Baral, and Heni Ben Amor. 2020. Language-conditioned imitation learning for robot manipulation tasks. Advances in Neural Information Processing Systems (NeurIPS) 33 (2020), 13139-13150.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_30_1","first-page":"20198","article-title":"Grounding multimodal large language models in actions","volume":"37","author":"Szot Andrew","year":"2024","unstructured":"Andrew Szot, Bogdan Mazoure, Harsh Agrawal, R Devon Hjelm, Zsolt Kira, and Alexander Toshev. 2024. Grounding multimodal large language models in actions. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 20198-20224.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_31_1","first-page":"1363","article-title":"Emergent correspondence from image diffusion","volume":"36","author":"Tang Luming","year":"2023","unstructured":"Luming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo, and Bharath Hariharan. 2023. Emergent correspondence from image diffusion. Advances in Neural Information Processing Systems (NeurIPS) 36 (2023), 1363-1389.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00321"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"e_1_3_2_1_34_1","first-page":"124420","article-title":"Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers","volume":"37","author":"Wang Lirui","year":"2024","unstructured":"Lirui Wang, Xinlei Chen, Jialiang Zhao, and Kaiming He. 2024. Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 124420-124450.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision (ICCV). 568-578","author":"Xie Enze","year":"2021","unstructured":"WenhaiWang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, and Ling Shao. 2021. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV). 568-578."},{"key":"e_1_3_2_1_36_1","first-page":"73278","article-title":"Omnijarvis: Unified vision-language-action tokenization enables open-world instruction following agents","volume":"37","author":"Wang Zihao","year":"2024","unstructured":"Zihao Wang, Shaofei Cai, Zhancun Mu, Haowei Lin, Ceyao Zhang, Xuejie Liu, Qing Li, Anji Liu, Xiaojian Shawn Ma, and Yitao Liang. 2024. Omnijarvis: Unified vision-language-action tokenization enables open-world instruction following agents. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 73278-73308.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_37_1","first-page":"41051","article-title":"Vidman: Exploiting implicit dynamics from video diffusion model for effective robot manipulation","volume":"37","author":"Lin Junfan","year":"2024","unstructured":"YoupengWen, Junfan Lin, Yi Zhu, Jianhua Han, Hang Xu, Shen Zhao, and Xiaodan Liang. 2024. Vidman: Exploiting implicit dynamics from video diffusion model for effective robot manipulation. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 41051-41075.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_38_1","volume-title":"2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2766-2773","author":"Chen Guilian","year":"2023","unstructured":"ZizhangWu, Guilian Chen, Yuanzhu Gan, LeiWang, and Jian Pu. 2023. Mvfusion: Multi-view 3d object detection with semantic-aligned radar and camera fusion. In 2023 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2766-2773."},{"key":"e_1_3_2_1_39_1","unstructured":"Zhiyu Wu Xiaokang Chen Zizheng Pan Xingchao Liu Wen Liu Damai Dai Huazuo Gao Yiyang Ma Chengyue Wu Bingxuan Wang et al. 2024. Deepseekvl2: Mixture-of-experts vision-language models for advanced multimodal understanding. arXiv preprint arXiv:2412.10302 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612151"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28501"},{"key":"e_1_3_2_1_43_1","first-page":"56619","article-title":"Deer-vla: Dynamic inference of multimodal large language models for efficient robot execution","volume":"37","author":"Yue Yang","year":"2024","unstructured":"Yang Yue, YulinWang, Bingyi Kang, Yizeng Han, ShenzhiWang, Shiji Song, Jiashi Feng, and Gao Huang. 2024. Deer-vla: Dynamic inference of multimodal large language models for efficient robot execution. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 56619-56643.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_44_1","volume-title":"Xue Bin Peng, and Jiajun Wu","author":"Ze Yanjie","year":"2024","unstructured":"Yanjie Ze, Zixuan Chen, Wenhao Wang, Tianyi Chen, Xialin He, Ying Yuan, Xue Bin Peng, and Jiajun Wu. 2024. Generalizable humanoid manipulation with improved 3d diffusion policies. arXiv preprint arXiv:2410.10803 (2024)."},{"key":"e_1_3_2_1_45_1","first-page":"110935","article-title":"Fine-tuning large vision-language models as decision-making agents via reinforcement learning","volume":"37","author":"Zhai Simon","year":"2024","unstructured":"Simon Zhai, Hao Bai, Zipeng Lin, Jiayi Pan, Peter Tong, Yifei Zhou, Alane Suhr, Saining Xie, Yann LeCun, Yi Ma, et al. 2024. Fine-tuning large vision-language models as decision-making agents via reinforcement learning. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 110935-110971.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_46_1","first-page":"52296","article-title":"E2e-mfd: Towards end-to-end synchronous multimodal fusion detection","volume":"37","author":"Zhang Jiaqing","year":"2024","unstructured":"Jiaqing Zhang, Mingxiang Cao, Weiying Xie, Jie Lei, Daixun Li, Wenbo Huang, Yunsong Li, and Xue Yang. 2024. E2e-mfd: Towards end-to-end synchronous multimodal fusion detection. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 52296-52322.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_48_1","first-page":"665","article-title":"Vlmbench: A compositional benchmark for vision-and-language manipulation","volume":"35","author":"Zheng Kaizhi","year":"2022","unstructured":"Kaizhi Zheng, Xiaotong Chen, Odest Chadwicke Jenkins, and Xin Wang. 2022. Vlmbench: A compositional benchmark for vision-and-language manipulation. Advances in Neural Information Processing Systems (NeurIPS) 35 (2022), 665-678.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"}],"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\/3746027.3754495","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:01:27Z","timestamp":1765339287000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754495"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3754495","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754495","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"}}]}}