{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:52:03Z","timestamp":1765309923167,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","funder":[{"name":"NSFC","award":["62176061"],"award-info":[{"award-number":["62176061"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755232","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"3913-3922","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Ali-UI: Enhancing Complex Vision-Language Navigation with Alignment of Unified Map and Instruction Parsing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8003-5977","authenticated-orcid":false,"given":"Shanshan","family":"Li","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5830-6510","authenticated-orcid":false,"given":"Jiawei","family":"Hou","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5139-1191","authenticated-orcid":false,"given":"Da","family":"Huang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Shanghai Innovation Institution, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6595-6893","authenticated-orcid":false,"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China and Shanghai Innovation Institution, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4897-9209","authenticated-orcid":false,"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Bevbert: Multimodal map pre-training for language-guided navigation. arXiv preprint arXiv:2212.04385","author":"An Dong","year":"2022","unstructured":"Dong An, Yuankai Qi, Yangguang Li, et al., 2022. Bevbert: Multimodal map pre-training for language-guided navigation. arXiv preprint arXiv:2212.04385 (2022)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang et al. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610499"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2019.8914278"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"e_1_3_2_1_8_1","volume-title":"Goat: Go to any thing. arXiv preprint arXiv:2311.06430","author":"Chang Matthew","year":"2023","unstructured":"Matthew Chang, Theophile Gervet, Mukul Khanna, et al., 2023. Goat: Go to any thing. arXiv preprint arXiv:2311.06430 (2023)."},{"key":"e_1_3_2_1_9_1","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Chaplot Devendra Singh","year":"2020","unstructured":"Devendra Singh Chaplot, Dhiraj Prakashchand Gandhi, Abhinav Gupta, et al., 2020a. Object goal navigation using goal-oriented semantic exploration. Advances in Neural Information Processing Systems, Vol. 33 (2020), 4247-4258.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 12875-12884","author":"Chaplot Devendra Singh","year":"2020","unstructured":"Devendra Singh Chaplot, Ruslan Salakhutdinov, Abhinav Gupta, et al., 2020b. Neural topological slam for visual navigation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 12875-12884."},{"key":"e_1_3_2_1_11_1","volume-title":"Mapgpt: Map-guided prompting with adaptive path planning for vision-and-language navigation. arXiv preprint arXiv:2401.07314","author":"Chen Jiaqi","year":"2024","unstructured":"Jiaqi Chen, Bingqian Lin, Ran Xu, et al., 2024. Mapgpt: Map-guided prompting with adaptive path planning for vision-and-language navigation. arXiv preprint arXiv:2401.07314 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"e_1_3_2_1_13_1","volume-title":"Conference on robot learning. PMLR, 64-79","author":"Chitnis Rohan","year":"2021","unstructured":"Rohan Chitnis, Tom Silver, Beomjoon Kim, et al., 2021. Camps: Learning context-specific abstractions for efficient planning in factored mdps. In Conference on robot learning. PMLR, 64-79."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610178"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_16_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, et al., 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3346800"},{"key":"e_1_3_2_1_18_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, et al., 2022. Clip-nav: Using clip for zero-shot vision-and-language navigation. arXiv preprint arXiv:2211.16649 (2022)."},{"key":"e_1_3_2_1_19_1","volume-title":"9th International Conference on Learning Representations, ICLR","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, et al., 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_1_20_1","volume-title":"European Conference on Computer Vision. Springer, 247-264","author":"Fu Yuqian","year":"2024","unstructured":"Yuqian Fu, Yu Wang, Yixuan Pan, et al., 2024. Cross-domain few-shot object detection via enhanced open-set object detector. In European Conference on Computer Vision. Springer, 247-264."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01432"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193254"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adf6991"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49997.2022.9926452"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00884"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Yicong Hong Cristian Rodriguez-Opazo Qi Wu et al. 2020. Sub-instruction aware vision-and-language navigation. arXiv preprint arXiv:2004.02707 (2020).","DOI":"10.18653\/v1\/2020.emnlp-main.271"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2893432"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3429280"},{"key":"e_1_3_2_1_35_1","first-page":"773","article-title":"Visual memory for robust path following (NIPS'18). Curran Associates Inc., Red Hook","author":"Kumar Ashish","year":"2018","unstructured":"Ashish Kumar, Saurabh Gupta, David Fouhey, et al., 2018. Visual memory for robust path following (NIPS'18). Curran Associates Inc., Red Hook, NY, USA, 773-782.","journal-title":"NY, USA"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3554559"},{"key":"e_1_3_2_1_37_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu et al. 2023. Visual instruction tuning. Advances in neural information processing systems Vol. 36 (2023) 34892-34916."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"e_1_3_2_1_39_1","first-page":"32340","article-title":"Zson: Zero-shot object-goal navigation using multimodal goal embeddings","volume":"35","author":"Majumdar Arjun","year":"2022","unstructured":"Arjun Majumdar, Gunjan Aggarwal, Bhavika Devnani, et al., 2022. Zson: Zero-shot object-goal navigation using multimodal goal embeddings. Advances in Neural Information Processing Systems, Vol. 35 (2022), 32340-32352.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32672"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"e_1_3_2_1_43_1","volume-title":"Open-nav: Exploring zero-shot vision-and-language navigation in continuous environment with open-source llms. arXiv preprint arXiv:2409.18794","author":"Qiao Yanyuan","year":"2024","unstructured":"Yanyuan Qiao, Wenqi Lyu, Hui Wang, et al., 2024. Open-nav: Exploring zero-shot vision-and-language navigation in continuous environment with open-source llms. arXiv preprint arXiv:2409.18794 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of The 7th Conference on Robot Learning (Proceedings of Machine Learning Research","volume":"72","author":"Rana Krishan","year":"2023","unstructured":"Krishan Rana, Jesse Haviland, Sourav Garg, et al., 2023. SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning. In Proceedings of The 7th Conference on Robot Learning (Proceedings of Machine Learning Research, Vol. 229). PMLR, 23-72."},{"key":"e_1_3_2_1_46_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., 2023. 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_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17421"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01128"},{"key":"e_1_3_2_1_49_1","unstructured":"Qwen Team. 2025. Qwen2.5-VL. https:\/\/qwenlm.github.io\/blog\/qwen2.5-vl\/"},{"key":"e_1_3_2_1_50_1","volume-title":"Vision-and-Dialog Navigation. In Proceedings of the Conference on Robot Learning (CoRL). PMLR, 394-406","author":"Thomason Jesse","year":"2020","unstructured":"Jesse Thomason, Michael Murray, Maya Cakmak, et al., 2020. Vision-and-Dialog Navigation. In Proceedings of the Conference on Robot Learning (CoRL). PMLR, 394-406."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794287"},{"key":"e_1_3_2_1_52_1","first-page":"16353","article-title":"Find what you want: Learning demand-conditioned object attribute space for demand-driven navigation","volume":"36","author":"Wang Hongcheng","year":"2023","unstructured":"Hongcheng Wang, Andy Guan Hong Chen, Xiaoqi Li, et al., 2023a. Find what you want: Learning demand-conditioned object attribute space for demand-driven navigation. Advances in Neural Information Processing Systems, Vol. 36 (2023), 16353-16366.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"e_1_3_2_1_54_1","unstructured":"Peng Wang Shuai Bai Sinan Tan et al. 2024a. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01305"},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of The 8th Conference on Robot Learning. 3866-3887","author":"Xu Zhuo","year":"2025","unstructured":"Zhuo Xu, Hao-Tien Lewis Chiang, Zipeng Fu, et al., 2025. Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMS and Topological Graphs. In Proceedings of The 8th Conference on Robot Learning. 3866-3887."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01581"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"e_1_3_2_1_63_1","volume-title":"Navid: Video-based vlm plans the next step for vision-and-language navigation. arXiv preprint arXiv:2402.15852","author":"Zhang Jiazhao","year":"2024","unstructured":"Jiazhao Zhang, Kunyu Wang, Rongtao Xu, et al., 2024b. Navid: Video-based vlm plans the next step for vision-and-language navigation. arXiv preprint arXiv:2402.15852 (2024)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610751"},{"key":"e_1_3_2_1_65_1","volume-title":"European Conference on Computer Vision. Springer, 260-278","author":"Zhou Gengze","year":"2024","unstructured":"Gengze Zhou, Yicong Hong, Zun Wang, et al., 2024b. Navgpt-2: Unleashing navigational reasoning capability for large vision-language models. In European Conference on Computer Vision. Springer, 260-278."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"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, et al., 2023. 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":"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\/3746027.3755232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:49:54Z","timestamp":1765309794000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":68,"alternative-id":["10.1145\/3746027.3755232","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755232","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"}}]}}