{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:39:19Z","timestamp":1786120759960,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817501","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"10326-10337","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9653-3316","authenticated-orcid":false,"given":"Baining","family":"Zhao","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2297-1830","authenticated-orcid":false,"given":"Ziyou","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University, Qinhuangdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2599-9929","authenticated-orcid":false,"given":"Jianjie","family":"Fang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6979-4761","authenticated-orcid":false,"given":"Zile","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0009-3553","authenticated-orcid":false,"given":"Yanggang","family":"Xu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5256-0378","authenticated-orcid":false,"given":"Yatai","family":"Ji","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Digital Intelligent Modeling and Simulation, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8439-379X","authenticated-orcid":false,"given":"Jiacheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8111-4417","authenticated-orcid":false,"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8892-9389","authenticated-orcid":false,"given":"Weichen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7561-5646","authenticated-orcid":false,"given":"Chen","family":"Gao","sequence":"additional","affiliation":[{"name":"BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8271-5023","authenticated-orcid":false,"given":"Xinlei","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Alexey Dosovitskiy, Saurabh Gupta, Vladlen Koltun, Jana Kosecka, Jitendra Malik, Roozbeh Mottaghi, Manolis Savva, et al.","author":"Anderson Peter","year":"2018","unstructured":"Peter Anderson, Angel Chang, Devendra Singh Chaplot, Alexey Dosovitskiy, Saurabh Gupta, Vladlen Koltun, Jana Kosecka, Jitendra Malik, Roozbeh Mottaghi, Manolis Savva, et al., 2018. On evaluation of embodied navigation agents. arXiv preprint arXiv:1807.06757 (2018)."},{"key":"e_1_3_2_1_2_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_3_1","unstructured":"Alibaba Cloud. 2025. Qwen Documentation. https:\/\/tongyi.aliyun.com\/. Accessed: 2025-09-24."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jairtraman.2020.101862"},{"key":"e_1_3_2_1_5_1","volume-title":"Clip-nav: Using clip for zero-shot vision-and-language navigation. arXiv preprint arXiv:2211.16649","author":"Dorbala Vishnu Sashank","year":"2022","unstructured":"Vishnu Sashank Dorbala, Gunnar Sigurdsson, Robinson Piramuthu, Jesse Thomason, and Gaurav S Sukhatme. 2022. Clip-nav: Using clip for zero-shot vision-and-language navigation. arXiv preprint arXiv:2211.16649 (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al.","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al., 2023. Palm-e: An embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.190"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.190"},{"key":"e_1_3_2_1_9_1","unstructured":"Jie Feng Jinwei Zeng Qingyue Long Hongyi Chen Jie Zhao Yanxin Xi Zhilun Zhou Yuan Yuan Shengyuan Wang Qingbin Zeng et al. 2025. A survey of large language model-powered spatial intelligence across scales: Advances in embodied agents smart cities and earth science. arXiv preprint arXiv:2504.09848 (2025)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"e_1_3_2_1_11_1","volume-title":"EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment. arXiv preprint arXiv:2410.09604","author":"Gao Chen","year":"2024","unstructured":"Chen Gao, Baining Zhao, Weichen Zhang, Jun Zhang, Jinzhu Mao, Zhiheng Zheng, Fanhang Man, Jianjie Fang, Zile Zhou, Jinqiang Cui, Xinlei Chen, and Yong Li. 2024b. EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment. arXiv preprint arXiv:2410.09604 (2024)."},{"key":"e_1_3_2_1_12_1","unstructured":"Yunpeng Gao Chenhui Li Zhongrui You Junli Liu Zhen Li Pengan Chen Qizhi Chen Zhonghan Tang Liansheng Wang Penghui Yang et al. 2025. OpenFly: A Comprehensive Platform for Aerial Vision-Language Navigation. arXiv preprint arXiv:2502.18041 (2025)."},{"key":"e_1_3_2_1_13_1","volume-title":"Aerial Vision-and-Language Navigation via Semantic-Topo-Metric Representation Guided LLM Reasoning. arXiv preprint arXiv:2410.08500","author":"Gao Yunpeng","year":"2024","unstructured":"Yunpeng Gao, Zhigang Wang, Linglin Jing, Dong Wang, Xuelong Li, and Bin Zhao. 2024a. Aerial Vision-and-Language Navigation via Semantic-Topo-Metric Representation Guided LLM Reasoning. arXiv preprint arXiv:2410.08500 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793","author":"Aohan Zeng Team GLM","year":"2024","unstructured":"Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, et al., 2024. Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793 (2024)."},{"key":"e_1_3_2_1_15_1","unstructured":"Google. 2025. Gemini API. https:\/\/ai.google.dev\/gemini-api. Accessed: 2025-04-12."},{"key":"e_1_3_2_1_16_1","volume-title":"MR-COGraphs: Communication-efficient multi-robot open-vocabulary mapping system via 3D scene graphs","author":"Gu Qiuyi","year":"2025","unstructured":"Qiuyi Gu, Zhaocheng Ye, Jincheng Yu, Jiahao Tang, Tinghao Yi, Yuhan Dong, Jian Wang, Jinqiang Cui, Xinlei Chen, and Yu Wang. 2025. MR-COGraphs: Communication-efficient multi-robot open-vocabulary mapping system via 3D scene graphs. IEEE Robotics and Automation Letters (2025)."},{"key":"e_1_3_2_1_17_1","volume-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models. arXiv preprint arXiv:2307.05973","author":"Huang Wenlong","year":"2023","unstructured":"Wenlong Huang, Chen Wang, Ruohan Zhang, Yunzhu Li, Jiajun Wu, and Li Fei-Fei. 2023. Voxposer: Composable 3d value maps for robotic manipulation with language models. arXiv preprint arXiv:2307.05973 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology. arXiv preprint arXiv:2505.08765","author":"Ji Yatai","year":"2025","unstructured":"Yatai Ji, Zhengqiu Zhu, Yong Zhao, Beidan Liu, Chen Gao, Yihao Zhao, Sihang Qiu, Yue Hu, Quanjun Yin, and Yong Li. 2025. Towards Autonomous UAV Visual Object Search in City Space: Benchmark and Agentic Methodology. arXiv preprint arXiv:2505.08765 (2025)."},{"key":"e_1_3_2_1_19_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_20_1","volume-title":"CityNav: Language-Goal Aerial Navigation Dataset with Geographic Information. arXiv preprint arXiv:2406.14240","author":"Lee Jungdae","year":"2024","unstructured":"Jungdae Lee, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Yutaka Matsuo, and Nakamasa Inoue. 2024. CityNav: Language-Goal Aerial Navigation Dataset with Geographic Information. arXiv preprint arXiv:2406.14240 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29813"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.745"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.745"},{"key":"e_1_3_2_1_24_1","volume-title":"The development of llms for embodied navigation. arXiv preprint arXiv:2311.00530","author":"Lin Jinzhou","year":"2023","unstructured":"Jinzhou Lin, Han Gao, Rongtao Xu, Changwei Wang, Li Guo, and Shibiao Xu. 2023. The development of llms for embodied navigation. arXiv preprint arXiv:2311.00530 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"European conference on computer vision. Springer, 38-55","author":"Liu Shilong","year":"2024","unstructured":"Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, et al., 2024b. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In European conference on computer vision. Springer, 38-55."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01411"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.resuscitation.2022.12.007"},{"key":"e_1_3_2_1_28_1","volume-title":"NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation. arXiv preprint arXiv:2411.08579","author":"Liu Youzhi","year":"2024","unstructured":"Youzhi Liu, Fanglong Yao, Yuanchang Yue, Guangluan Xu, Xian Sun, and Kun Fu. 2024a. NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation. arXiv preprint arXiv:2411.08579 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2343"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0031"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1108\/IJPDLM-02-2019-0048"},{"key":"e_1_3_2_1_32_1","unstructured":"NVIDIA: Alisson Azzolini Junjie Bai Hannah Brandon Jiaxin Cao Prithvijit Chattopadhyay Huayu Chen Jinju Chu Yin Cui Jenna Diamond Yifan Ding Liang Feng Francesco Ferroni Rama Govindaraju Jinwei Gu Siddharth Gururani Imad El Hanafi Zekun Hao Jacob Huffman Jingyi Jin Brendan Johnson Rizwan Khan George Kurian Elena Lantz Nayeon Lee Zhaoshuo Li Xuan Li Maosheng Liao Tsung-Yi Lin Yen-Chen Lin Ming-Yu Liu Xiangyu Lu Alice Luo Andrew Mathau Yun Ni Lindsey Pavao Wei Ping David W. Romero Misha Smelyanskiy Shuran Song Lyne Tchapmi Andrew Z. Wang Boxin Wang Haoxiang Wang Fangyin Wei Jiashu Xu Yao Xu Dinghao Yang Xiaodong Yang Zhuolin Yang Jingxu Zhang Xiaohui Zeng and Zhe Zhang. 2025. Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning. arXiv:2503.15558 [cs.AI] https:\/\/arxiv.org\/abs\/2503.15558"},{"key":"e_1_3_2_1_33_1","unstructured":"OpenAI. 2025. GPT-4o API. https:\/\/openai.com\/api\/. Accessed: 2025-04-12."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"e_1_3_2_1_35_1","volume-title":"Saynav: Grounding large language models for dynamic planning to navigation in new environments. arXiv preprint arXiv:2309.04077","author":"Rajvanshi Abhinav","year":"2023","unstructured":"Abhinav Rajvanshi, Karan Sikka, Xiao Lin, Bhoram Lee, Han-Pang Chiu, and Alvaro Velasquez. 2023. Saynav: Grounding large language models for dynamic planning to navigation in new environments. arXiv preprint arXiv:2309.04077 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.resplu.2022.100347"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28694-0_27"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29858"},{"key":"e_1_3_2_1_39_1","volume-title":"Conference on robot learning. PMLR, 492-504","author":"Shah Dhruv","year":"2023","unstructured":"Dhruv Shah, B\u0142a\u017cej Osi'nski, Sergey Levine, et al., 2023a. Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action. In Conference on robot learning. PMLR, 492-504."},{"key":"e_1_3_2_1_40_1","volume-title":"ViNT: A foundation model for visual navigation. arXiv preprint arXiv:2306.14846","author":"Shah Dhruv","year":"2023","unstructured":"Dhruv Shah, Ajay Sridhar, Nitish Dashora, Kyle Stachowicz, Kevin Black, Noriaki Hirose, and Sergey Levine. 2023b. ViNT: A foundation model for visual navigation. arXiv preprint arXiv:2306.14846 (2023)."},{"key":"e_1_3_2_1_41_1","unstructured":"Shital Shah Debadeepta Dey Chris Lovett and Ashish Kapoor. 2017. AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles. In Field and Service Robotics. showeprintarXiv:1705.05065 https:\/\/arxiv.org\/abs\/1705.05065"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01128"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Sai Vemprala Rogerio Bonatti Arthur Bucker and Ashish Kapoor. 2023. ChatGPT for Robotics: Design Principles and Model Abilities. Technical Report MSR-TR-2023-8. Microsoft. https:\/\/www.microsoft.com\/en-us\/research\/publication\/chatgpt-for-robotics-design-principles-and-model-abilities\/","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621375"},{"key":"e_1_3_2_1_46_1","volume-title":"Towards realistic uav vision-language navigation: Platform, benchmark, and methodology. arXiv preprint arXiv:2410.07087","author":"Wang Xiangyu","year":"2024","unstructured":"Xiangyu Wang, Donglin Yang, Ziqin Wang, Hohin Kwan, Jinyu Chen, Wenjun Wu, Hongsheng Li, Yue Liao, and Si Liu. 2024b. Towards realistic uav vision-language navigation: Platform, benchmark, and methodology. arXiv preprint arXiv:2410.07087 (2024)."},{"key":"e_1_3_2_1_47_1","volume-title":"explain, plan and select: Interactive planning with large language models enables open-world multi-task agents. arXiv preprint arXiv:2302.01560","author":"Wang Zihao","year":"2023","unstructured":"Zihao Wang, Shaofei Cai, Guanzhou Chen, Anji Liu, Xiaojian Ma, and Yitao Liang. 2023. Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents. arXiv preprint arXiv:2302.01560 (2023)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09217-1"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758251"},{"key":"e_1_3_2_1_50_1","volume-title":"Urban generative intelligence (ugi): A foundational platform for agents in embodied city environment. arXiv preprint arXiv:2312.11813","author":"Xu Fengli","year":"2023","unstructured":"Fengli Xu, Jun Zhang, Chen Gao, Jie Feng, and Yong Li. 2023. Urban generative intelligence (ugi): A foundational platform for agents in embodied city environment. arXiv preprint arXiv:2312.11813 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2026.3669346"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"e_1_3_2_1_53_1","volume-title":"Aeroverse: Uav-agent benchmark suite for simulating, pre-training, finetuning, and evaluating aerospace embodied world models. arXiv preprint arXiv:2408.15511","author":"Yao Fanglong","year":"2024","unstructured":"Fanglong Yao, Yuanchang Yue, Youzhi Liu, Xian Sun, and Kun Fu. 2024. Aeroverse: Uav-agent benchmark suite for simulating, pre-training, finetuning, and evaluating aerospace embodied world models. arXiv preprint arXiv:2408.15511 (2024)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1200"},{"key":"e_1_3_2_1_56_1","volume-title":"Uni-navid: A video-based vision-language-action model for unifying embodied navigation tasks. arXiv preprint arXiv:2412.06224","author":"Zhang Jiazhao","year":"2024","unstructured":"Jiazhao Zhang, Kunyu Wang, Shaoan Wang, Minghan Li, Haoran Liu, Songlin Wei, Zhongyuan Wang, Zhizheng Zhang, and He Wang. 2024. Uni-navid: A video-based vision-language-action model for unifying embodied navigation tasks. arXiv preprint arXiv:2412.06224 (2024)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1511"},{"key":"e_1_3_2_1_58_1","unstructured":"Weichen Zhang Peizhi Tang Xin Zeng Fanhang Man Shiquan Yu Zichao Dai Baining Zhao Hongjin Chen Yu Shang Wei Wu Chen Gao Xinlei Chen Xin Wang Yong Li and Wenwu Zhu. 2026. Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space. arXiv:2512.21887 [cs.RO] https:\/\/arxiv.org\/abs\/2512.21887"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"crossref","unstructured":"Weichen Zhang Zile Zhou Xin Zeng Xuchen Liu Jianjie Fang Chen Gao Yong Li Jinqiang Cui Xinlei Chen and Xiao-Ping Zhang. 2025c. Open3D-VQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space. arXiv:2503.11094 [cs.CV] https:\/\/arxiv.org\/abs\/2503.11094","DOI":"10.1145\/3746027.3758219"},{"key":"e_1_3_2_1_60_1","volume-title":"Guo-Hua Wang, Qing-Guo Chen, Zhao Xu, et al.","author":"Zhang Xinjie","year":"2025","unstructured":"Xinjie Zhang, Jintao Guo, Shanshan Zhao, Minghao Fu, Lunhao Duan, Jiakui Hu, Yong Xien Chng, Guo-Hua Wang, Qing-Guo Chen, Zhao Xu, et al., 2025b. Unified multimodal understanding and generation models: Advances, challenges, and opportunities. arXiv preprint arXiv:2505.02567 (2025)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.737"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1558"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758180"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755703"},{"key":"e_1_3_2_1_65_1","volume-title":"Wee Sun Lee, and David Hsu","author":"Zhao Zirui","year":"2024","unstructured":"Zirui Zhao, Wee Sun Lee, and David Hsu. 2024. Large language models as commonsense knowledge for large-scale task planning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_66_1","volume-title":"Navgpt: Explicit reasoning in vision-and-language navigation with large language models. arXiv preprint arXiv:2305.16986","author":"Zhou Gengze","year":"2023","unstructured":"Gengze Zhou, Yicong Hong, and Qi Wu. 2023a. Navgpt: Explicit reasoning in vision-and-language navigation with large language models. arXiv preprint arXiv:2305.16986 (2023)."},{"key":"e_1_3_2_1_67_1","volume-title":"International Conference on Machine Learning. PMLR, 42829-42842","author":"Zhou Kaiwen","year":"2023","unstructured":"Kaiwen Zhou, Kaizhi Zheng, Connor Pryor, Yilin Shen, Hongxia Jin, Lise Getoor, and Xin Eric Wang. 2023b. Esc: Exploration with soft commonsense constraints for zero-shot object navigation. In International Conference on Machine Learning. PMLR, 42829-42842."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:18:45Z","timestamp":1786065525000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817501"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":68,"alternative-id":["10.1145\/3770855.3817501","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817501","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}