{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:13Z","timestamp":1786120813195,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":75,"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"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U22A2098"],"award-info":[{"award-number":["U22A2098"]}]},{"name":"National Natural Science Foundation of China","award":["62206105"],"award-info":[{"award-number":["62206105"]}]},{"name":"National Natural Science Foundation of China","award":["62202200"],"award-info":[{"award-number":["62202200"]}]},{"name":"Scientific and Technological Innovation Project of Changbaishan Laboratory","award":["CBS2026006-04"],"award-info":[{"award-number":["CBS2026006-04"]}]},{"name":"China Postdoctoral Science Foundation","award":["2025M780312"],"award-info":[{"award-number":["2025M780312"]}]},{"name":"Major Science and Technology Development Plan of Changchun","award":["2024WX05"],"award-info":[{"award-number":["2024WX05"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817467","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"8870-8881","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["OmniEarth: A Benchmark for Evaluating Vision\u2013Language Models in Geospatial Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0751-224X","authenticated-orcid":false,"given":"Ronghao","family":"Fu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5684-6468","authenticated-orcid":false,"given":"Haoran","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0700-7947","authenticated-orcid":false,"given":"Weijie","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5227-1156","authenticated-orcid":false,"given":"Zhiwen","family":"Lin","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5862-8646","authenticated-orcid":false,"given":"Xiao","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6915-8424","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chang Guang Satellite Technology, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1927-8419","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 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":"CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models. arXiv:2411.18145 [cs.CV] https:\/\/arxiv.org\/abs\/2411.18145","author":"An Xiao","year":"2025","unstructured":"Xiao An, Jiaxing Sun, Zihan Gui, and Wei He. 2025. CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models. arXiv:2411.18145 [cs.CV] https:\/\/arxiv.org\/abs\/2411.18145"},{"key":"e_1_3_2_1_2_1","unstructured":"Anthropic. 2025. Introducing Claude 4. Technical Report. Anthropic. https:\/\/www.anthropic.com\/news\/claude-4"},{"key":"e_1_3_2_1_3_1","volume-title":"arXiv preprint arXiv:2502.13923","author":"Bai Shuai","year":"2025","unstructured":"Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Haiyang Xu, and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)."},{"key":"e_1_3_2_1_4_1","unstructured":"Capella Space. n.d.. Capella Space: High-Resolution SAR Satellite Imagery. https:\/\/www.capellaspace.com\/. Accessed: 2026-02-08."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5194\/essd-17-6217-2025"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00646"},{"key":"e_1_3_2_1_8_1","unstructured":"Google Cloud. 2025. Gemini 2.0 Flash | Generative AI on Vertex AI. https:\/\/docs.cloud.google.com\/vertex-ai\/generative-ai\/docs\/models\/gemini\/2-0-flash?hl=zh-cn Accessed: 2025-11-14."},{"key":"e_1_3_2_1_9_1","volume-title":"A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs. arXiv preprint arXiv:2512.17319","author":"Dang Yunkai","year":"2025","unstructured":"Yunkai Dang, Meiyi Zhu, Donghao Wang, Yizhuo Zhang, Jiacheng Yang, Qi Fan, Yuekun Yang, Wenbin Li, Feng Miao, and Yang Gao. 2025. A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs. arXiv preprint arXiv:2512.17319 (2025)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00670"},{"key":"e_1_3_2_1_11_1","unstructured":"Esri. n.d.. ArcGIS Living Atlas of the World. https:\/\/livingatlas.arcgis.com\/. Accessed: 2026-02-08."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126285"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112534"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3378841"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3403260"},{"key":"e_1_3_2_1_16_1","unstructured":"Google LLC. n.d.. Google Earth Pro. https:\/\/earth.google.com\/. Accessed: 2026-02-08."},{"key":"e_1_3_2_1_17_1","volume-title":"xbd: A dataset for assessing building damage from satellite imagery. arXiv preprint arXiv:1911.09296","author":"Gupta Ritwik","year":"2019","unstructured":"Ritwik Gupta, Richard Hosfelt, Sandra Sajeev, Nirav Patel, Bryce Goodman, Jigar Doshi, Eric Heim, Howie Choset, and Matthew Gaston. 2019. xbd: A dataset for assessing building damage from satellite imagery. arXiv preprint arXiv:1911.09296 (2019)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"e_1_3_2_1_19_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2994349"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2858817"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3236380"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3764917.3771334"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 27831-27840","author":"Kuckreja Kartik","year":"2024","unstructured":"Kartik Kuckreja, Muhammad Sohail Danish, Muzammal Naseer, Abhijit Das, Salman Khan, and Fahad Shahbaz Khan. 2024. Geochat: Grounded large vision-language model for remote sensing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 27831-27840."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00986"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0106"},{"key":"e_1_3_2_1_28_1","volume-title":"Xiao Xiang Zhu, and Tianjin Huang","author":"Li Xiang","year":"2025","unstructured":"Xiang Li, Yong Tao, Siyuan Zhang, Siwei Liu, Zhitong Xiong, Chunbo Luo, Lu Liu, Mykola Pechenizkiy, Xiao Xiang Zhu, and Tianjin Huang. 2025c. REOBench: Benchmarking Robustness of Earth Observation Foundation Models. arXiv:2505.16793 [cs.CV] https:\/\/arxiv.org\/abs\/2505.16793"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.06.003"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3218921"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3478269"},{"key":"e_1_3_2_1_32_1","volume-title":"GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding. arXiv preprint arXiv:2512.02505","author":"Liu Jiaqi","year":"2025","unstructured":"Jiaqi Liu, Ronghao Fu, Haoran Liu, Lang Sun, and Bo Yang. 2025a. GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding. arXiv preprint arXiv:2512.02505 (2025)."},{"key":"e_1_3_2_1_33_1","volume-title":"SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts. arXiv preprint arXiv:2512.02517","author":"Liu Jiaqi","year":"2025","unstructured":"Jiaqi Liu, Ronghao Fu, Lang Sun, Haoran Liu, Xiao Yang, Weipeng Zhang, Xu Na, Zhuoran Duan, and Bo Yang. 2025b. SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts. arXiv preprint arXiv:2512.02517 (2025)."},{"key":"e_1_3_2_1_34_1","unstructured":"Jiaqi Liu Lang Sun Ronghao Fu and Bo Yang. 2026. Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models. arXiv:2509.22221 [cs.CV] https:\/\/arxiv.org\/abs\/2509.22221"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3388464"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"e_1_3_2_1_37_1","unstructured":"Siqi Lu Junlin Guo James R Zimmer-Dauphinee Jordan M Nieusma Xiao Wang Steven A Wernke Yuankai Huo et al. 2025. Vision foundation models in remote sensing: A survey. IEEE Geoscience and Remote Sensing Magazine (2025)."},{"key":"e_1_3_2_1_38_1","volume-title":"Skysensegpt: A fine-grained instruction tuning dataset and model for remote sensing vision-language understanding. arXiv preprint arXiv:2406.10100","author":"Luo Junwei","year":"2024","unstructured":"Junwei Luo, Zhen Pang, Yongjun Zhang, Tingzhu Wang, Linlin Wang, Bo Dang, Jiangwei Lao, Jian Wang, Jingdong Chen, Yihua Tan, et al., 2024. Skysensegpt: A fine-grained instruction tuning dataset and model for remote sensing vision-language understanding. arXiv preprint arXiv:2406.10100 (2024)."},{"key":"e_1_3_2_1_39_1","volume-title":"When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning. arXiv preprint arXiv:2503.07588","author":"Luo Junwei","year":"2025","unstructured":"Junwei Luo, Yingying Zhang, Xue Yang, Kang Wu, Qi Zhu, Lei Liang, Jingdong Chen, and Yansheng Li. 2025. When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning. arXiv preprint arXiv:2503.07588 (2025)."},{"key":"e_1_3_2_1_40_1","volume-title":"European Conference on Computer Vision. Springer, 440-457","author":"Muhtar Dilxat","year":"2024","unstructured":"Dilxat Muhtar, Zhenshi Li, Feng Gu, Xueliang Zhang, and Pengfeng Xiao. 2024. Lhrs-bot: Empowering remote sensing with vgi-enhanced large multimodal language model. In European Conference on Computer Vision. Springer, 440-457."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32683"},{"key":"e_1_3_2_1_42_1","volume-title":"IIR-VLM: In-Context Instance-level Recognition for Large Vision-Language Models. arXiv preprint arXiv:2601.14188","author":"Shi Liang","year":"2026","unstructured":"Liang Shi, Wei Li, Kevin M Beussman, Lin Chen, and Yun Fu. 2026. IIR-VLM: In-Context Instance-level Recognition for Large Vision-Language Models. arXiv preprint arXiv:2601.14188 (2026)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01334"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"e_1_3_2_1_45_1","unstructured":"V Team Wenyi Hong Wenmeng Yu Xiaotao Gu Guo Wang Guobing Gan et al. 2026. GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning. arXiv:2507.01006 [cs.CV] https:\/\/arxiv.org\/abs\/2507.01006"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Fengxiang Wang Mingshuo Chen Yueying Li Di Wang Haotian Wang Zonghao Guo Zefan Wang Boqi Shan Long Lan Yulin Wang et al. 2025a. GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution. arXiv preprint arXiv:2505.21375 (2025).","DOI":"10.52202\/085713-5317"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01336"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01935"},{"key":"e_1_3_2_1_49_1","volume-title":"Omnivl: One foundation model for image-language and video-language tasks. Advances in neural information processing systems","author":"Wang Junke","year":"2022","unstructured":"Junke Wang, Dongdong Chen, Zuxuan Wu, Chong Luo, Luowei Zhou, Yucheng Zhao, Yujia Xie, Ce Liu, Yu-Gang Jiang, and Lu Yuan. 2022. Omnivl: One foundation model for image-language and video-language tasks. Advances in neural information processing systems, Vol. 35 (2022), 5696-5710."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"crossref","unstructured":"Junjue Wang Weihao Xuan Heli Qi Zhihao Liu Kunyi Liu Yuhan Wu Hongruixuan Chen Jian Song Junshi Xia Zhuo Zheng and Naoto Yokoya. 2025 e. DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response. (2025).","DOI":"10.52202\/085713-5398"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28357"},{"key":"e_1_3_2_1_52_1","unstructured":"Weiyun Wang Zhangwei Gao Lixin Gu Hengjun Pu Long Cui Xingguang Wei Zhaoyang Liu Linglin Jing Shenglong Ye Jie Shao et al. 2025b. InternVL3.5: Advancing Open-Source Multimodal Models in Versatility Reasoning and Efficiency. arXiv preprint arXiv:2508.18265 (2025)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"e_1_3_2_1_54_1","volume-title":"European Conference on Computer Vision. Springer, 408-424","author":"Wei Haoran","year":"2024","unstructured":"Haoran Wei, Lingyu Kong, Jinyue Chen, Liang Zhao, Zheng Ge, Jinrong Yang, Jianjian Sun, Chunrui Han, and Xiangyu Zhang. 2024. Vary: Scaling up the vision vocabulary for large vision-language model. In European Conference on Computer Vision. Springer, 408-424."},{"key":"e_1_3_2_1_55_1","volume-title":"SARlang-1m: A benchmark for vision-language modeling in sar image understanding","author":"Wei Yimin","year":"2026","unstructured":"Yimin Wei, Aoran Xiao, Yexian Ren, Yuting Zhu, Hongruixuan Chen, Junshi Xia, and Naoto Yokoya. 2026. SARlang-1m: A benchmark for vision-language modeling in sar image understanding. IEEE Transactions on Geoscience and Remote Sensing (2026)."},{"key":"e_1_3_2_1_56_1","first-page":"2688","article-title":"MAR20: A benchmark for military aircraft recognition in remote sensing images","volume":"27","author":"Wenqi YU","year":"2024","unstructured":"YU Wenqi, Cheng Gong, WANG Meijun, Yao Yanqing, Xie Xingxing, Yao Xiwen, and Han Junwei. 2024. MAR20: A benchmark for military aircraft recognition in remote sensing images. National Remote Sensing Bulletin, Vol. 27, 12 (2024), 2688-2696.","journal-title":"National Remote Sensing Bulletin"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"crossref","unstructured":"Weihao Xuan Junjue Wang Heli Qi Zihang Chen Zhuo Zheng Yanfei Zhong Junshi Xia and Naoto Yokoya. 2025. DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding. arXiv:2505.21076 [cs.CV] https:\/\/arxiv.org\/abs\/2505.21076","DOI":"10.52202\/085713-1114"},{"key":"e_1_3_2_1_60_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_1_61_1","volume-title":"Falcon: A remote sensing vision-language foundation model. arXiv preprint arXiv:2503.11070","author":"Yao Kelu","year":"2025","unstructured":"Kelu Yao, Nuo Xu, Rong Yang, Yingying Xu, Zhuoyan Gao, Titinunt Kitrungrotsakul, Yi Ren, Pu Zhang, Jin Wang, Ning Wei, et al., 2025b. Falcon: A remote sensing vision-language foundation model. arXiv preprint arXiv:2503.11070 (2025)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754950"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33022"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.020"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00780"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3510781"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2981686"},{"key":"e_1_3_2_1_70_1","volume-title":"Rs5m and georsclip: A large scale vision-language dataset and a large vision-language model for remote sensing","author":"Zhang Zilun","year":"2024","unstructured":"Zilun Zhang, Tiancheng Zhao, Yulong Guo, and Jianwei Yin. 2024c. Rs5m and georsclip: A large scale vision-language dataset and a large vision-language model for remote sensing. IEEE Transactions on Geoscience and Remote Sensing (2024)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3392778"},{"key":"e_1_3_2_1_72_1","unstructured":"Baichuan Zhou Haote Yang Dairong Chen Junyan Ye Tianyi Bai Jinhua Yu Songyang Zhang Dahua Lin Conghui He and Weijia Li. 2025. UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios. arXiv:2408.17267 [cs.CV] https:\/\/arxiv.org\/abs\/2408.17267"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"crossref","unstructured":"He Zhu Junyou Su Minxin Chen Wen Wang Yijie Deng Guanhua Chen and Wenjia Zhang. 2025b. PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models. arXiv:2505.14481 [cs.CL] https:\/\/arxiv.org\/abs\/2505.14481","DOI":"10.18653\/v1\/2025.emnlp-industry.169"},{"key":"e_1_3_2_1_74_1","unstructured":"Jinguo Zhu Weiyun Wang Zhe Chen Zhaoyang Liu Shenglong Ye Lixin Gu Hao Tian Yuchen Duan Weijie Su Jie Shao et al. 2025c. Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01373"}],"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":"2026-08-07T01:28:51Z","timestamp":1786066131000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817467"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":75,"alternative-id":["10.1145\/3770855.3817467","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817467","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"}}]}}