{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:08:34Z","timestamp":1789031314279,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374318","type":"print"},{"value":"9783032374325","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37432-5_22","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:26:06Z","timestamp":1789028766000},"page":"381-397","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Stand Up and\u00a0Move: Benchmarking Interactive Spatial Intelligence in\u00a0WalkerBench"],"prefix":"10.1007","author":[{"given":"Zhiqi","family":"Ge","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyang","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingzhe","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuancheng","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qizhou","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"22_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report (2023). arXiv preprint arXiv:2303.08774"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3674\u20133683 (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"22_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Chen, H., Suhr, A., Misra, D., Snavely, N., Artzi, Y.: Touchdown: natural language navigation and spatial reasoning in visual street environments. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12538\u201312547 (2019)","DOI":"10.1109\/CVPR.2019.01282"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, A.C., et al.: Navila: legged robot vision-language-action model for navigation (2024). arXiv preprint arXiv:2412.04453","DOI":"10.15607\/RSS.2025.XXI.018"},{"key":"22_CR6","doi-asserted-by":"publisher","first-page":"135062","DOI":"10.52202\/079017-4293","volume":"37","author":"AC Cheng","year":"2024","unstructured":"Cheng, A.C., et al.: Spatialrgpt: grounded spatial reasoning in vision-language models. Adv. Neural. Inf. Process. Syst. 37, 135062\u2013135093 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR7","unstructured":"Fried, D., et al.: Speaker-follower models for vision-and-language navigation. In: Advances in Neural Information Processing Systems, p. 31 (2018)"},{"key":"22_CR8","unstructured":"Grauman, K., et\u00a0al.: Ego4d: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"22_CR9","unstructured":"Guo, D., et\u00a0al.: Seed1. 5-vl technical report. arXiv preprint arXiv:2505.07062 (2025)"},{"issue":"1","key":"22_CR10","doi-asserted-by":"publisher","first-page":"5721","DOI":"10.1038\/s41467-021-25874-z","volume":"12","author":"A Gupta","year":"2021","unstructured":"Gupta, A., Savarese, S., Ganguli, S., Fei-Fei, L.: Embodied intelligence via learning and evolution. Nat. Commun. 12(1), 5721 (2021)","journal-title":"Nat. Commun."},{"key":"22_CR11","unstructured":"Hong, W., et al.: GLM-4.1 v-thinking: towards versatile multimodal reasoning with scalable reinforcement learning (2025). arXiv preprint arXiv:2507.01006"},{"key":"22_CR12","unstructured":"Kim, M.J., et al.: Openvla: an open-source vision-language-action model (2024). arXiv preprint arXiv:2406.09246"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Krantz, J., Wijmans, E., Majumdar, A., Batra, D., Lee, S.: Beyond the nav-graph: vision-and-language navigation in continuous environments. In: European Conference on Computer Vision, pp. 104\u2013120. Springer (2020)","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Ku, A., Anderson, P., Patel, R., Ie, E., Baldridge, J.: Room-across-room: multilingual vision-and-language navigation with dense spatiotemporal grounding (2020). arXiv preprint arXiv:2010.07954","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Sti-bench: are MLLMs ready for precise spatial-temporal world understanding? arXiv preprint arXiv:2503.23765 (2025)","DOI":"10.1109\/ICCV51701.2025.00533"},{"key":"22_CR16","unstructured":"Lin, J., et\u00a0al.: MMSI-video-bench: a holistic benchmark for video-based spatial intelligence. arXiv preprint arXiv:2512.10863 (2025)"},{"key":"22_CR17","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1162\/tacl_a_00566","volume":"11","author":"F Liu","year":"2023","unstructured":"Liu, F., Emerson, G., Collier, N.: Visual spatial reasoning. Trans. Assoc. Comput. Linguist. 11, 635\u2013651 (2023)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Mehta, H., Artzi, Y., Baldridge, J., Ie, E., Mirowski, P.: Retouchdown: adding touchdown to streetlearn as a shareable resource for language grounding tasks in street view (2020). arXiv preprint arXiv:2001.03671","DOI":"10.18653\/v1\/2020.splu-1.7"},{"key":"22_CR19","unstructured":"Mirowski, P., et al.: The streetlearn environment and dataset (2019). arXiv preprint arXiv:1903.01292"},{"key":"22_CR20","unstructured":"NVIDIA: Isaac sim-robotics simulation and synthetic data generation (2023). https:\/\/developer.nvidia.com\/isaac\/sim"},{"key":"22_CR21","unstructured":"Roy, N., et al.: From machine learning to robotics: challenges and opportunities for embodied intelligence (2021). arXiv:2110.15245 arXiv preprint"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Savva, M., et al.: Habitat: a platform for embodied ai research. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9339\u20139347 (2019)","DOI":"10.1109\/ICCV.2019.00943"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Song, C.H., et al.: Robospatial: teaching spatial understanding to 2D and 3D vision-language models for robotics. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15768\u201315780 (2025)","DOI":"10.1109\/CVPR52734.2025.01470"},{"key":"22_CR24","unstructured":"Sumers, T., Yao, S., Narasimhan, K.R., Griffiths, T.L.: Cognitive architectures for language agents. Trans. Mach. Learn. Res. (2023)"},{"key":"22_CR25","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models (2023). arXiv preprint arXiv:2312.11805"},{"key":"22_CR26","unstructured":"Team, G.R., et al.: Gemini robotics 1.5: pushing the frontier of generalist robots with advanced embodied reasoning, thinking, and motion transfer (2025). arXiv preprint arXiv:2510.03342"},{"key":"22_CR27","unstructured":"Team, K., et\u00a0al.: Kimi k2: Open agentic intelligence. arXiv preprint arXiv:2507.20534 (2025)"},{"key":"22_CR28","unstructured":"Wei, M., et\u00a0al.: StreamVLN: streaming vision-and-language navigation via slowfast context modeling. arXiv preprint arXiv:2507.05240 (2025)"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Xia, F., et al.: Gibson env: real-world perception for embodied agents. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9068\u20139079 (2018)","DOI":"10.1109\/CVPR.2018.00945"},{"key":"22_CR30","unstructured":"Xu, P., Wang, S., Zhu, Y., Li, J., Zhang, Y.: Spatialbench: benchmarking multimodal large language models for spatial cognition (2025). arXiv preprint arXiv:2511.21471"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Thinking in space: How multimodal large language models see, remember, and recall spaces. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"22_CR32","doi-asserted-by":"publisher","first-page":"50528","DOI":"10.52202\/079017-1601","volume":"37","author":"J Yang","year":"2024","unstructured":"Yang, J., et al.: SWE-agent: agent-computer interfaces enable automated software engineering. Adv. Neural. Inf. Process. Syst. 37, 50528\u201350652 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR33","unstructured":"Yao, S., et al.: React: Synergizing reasoning and acting in language models. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"22_CR34","unstructured":"Yeh, C.H., et al.: Seeing from another perspective: evaluating multi-view understanding in MLLMs. arXiv preprint arXiv:2504.15280 (2025)"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Navid: video-based VLM plans the next step for vision-and-language navigation. arXiv preprint arXiv:2402.15852 (2024)","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, G., Hong, Y., Wu, Q.: NavGPT: explicit reasoning in vision-and-language navigation with large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 7641\u20137649 (2024)","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Vlm4d: towards spatiotemporal awareness in vision language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8600\u20138612 (2025)","DOI":"10.1109\/ICCV51701.2025.00805"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37432-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:26:22Z","timestamp":1789028782000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37432-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374318","9783032374325"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37432-5_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}