{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:47:10Z","timestamp":1785829630013,"version":"3.56.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032313966","type":"print"},{"value":"9783032313973","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31397-3_29","type":"book-chapter","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:07:20Z","timestamp":1785827240000},"page":"437-451","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Demystifying 3D Spatial Awareness via\u00a0LLM Router"],"prefix":"10.1007","author":[{"given":"He","family":"Tao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lidong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luyuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tesi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinjian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"29_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report (2023). arXiv preprint arXiv:2303.08774"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Azuma, D., Miyanishi, T., Kurita, S., Kawanabe, M.: Scanqa: 3D question answering for spatial scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"29_CR3","unstructured":"Brohan, A., et al.: Rt-2: Vision-language-action models transfer web knowledge to robotic control (2023). arXiv preprint arXiv:2307.15818"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Cai, W., et al.: Spatialbot: precise spatial understanding with vision language models (2024). arXiv preprint arXiv:2406.13642","DOI":"10.1109\/ICRA55743.2025.11128671"},{"key":"29_CR5","doi-asserted-by":"publisher","first-page":"53168","DOI":"10.52202\/079017-1684","volume":"37","author":"K Chandrasegaran","year":"2024","unstructured":"Chandrasegaran, K., et al.: Hourvideo: 1-hour video-language understanding. Adv. Neural. Inf. Process. Syst. 37, 53168\u201353197 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: Scanrefer: 3D object localization in RGB-d scans using natural language. In: European Conference on Computer Vision, pp. 202\u2013221. Springer (2020)","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"29_CR7","unstructured":"Chen, G., et\u00a0al.: VideoLLM: modeling video sequence with large language models. arXiv preprint arXiv:2305.13292 (2023)"},{"key":"29_CR8","doi-asserted-by":"publisher","first-page":"20522","DOI":"10.52202\/068431-1492","volume":"35","author":"S Chen","year":"2022","unstructured":"Chen, S., Guhur, P.L., Tapaswi, M., Schmid, C., Laptev, I.: Language conditioned spatial relation reasoning for 3D object grounding. Adv. Neural. Inf. Process. Syst. 35, 20522\u201320535 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR9","doi-asserted-by":"publisher","first-page":"66305","DOI":"10.52202\/079017-2120","volume":"37","author":"S Chen","year":"2024","unstructured":"Chen, S., Jiang, W., Lin, B., Kwok, J., Zhang, Y.: Routerdc: query-based router by dual contrastive learning for assembling large language models. Adv. Neural. Inf. Process. Syst. 37, 66305\u201366328 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Ll3da: visual interactive instruction tuning for omni-3D understanding, reasoning, and planning (2023)","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: End-to-End 3D dense captioning with vote2cap-detr. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11124\u201311133 (2023)","DOI":"10.1109\/CVPR52729.2023.01070"},{"key":"29_CR12","unstructured":"Chen, Y., et al.: Grounded 3D-LLM with referent tokens (2024). arXiv preprint arXiv:2405.10370"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gholami, A., Nie\u00dfner, M., Chang, A.X.: Scan2cap: context-aware dense captioning in RGB-d scans. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3193\u20133203 (2021)","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"29_CR14","unstructured":"Driess, D., et al.: Palm-e: an embodied multimodal language model (2023)"},{"key":"29_CR15","unstructured":"Gupta, N., et al.: Language model cascades: token-level uncertainty and beyond, (2024). arXiv preprint arXiv:2404.10136"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Huang, H., et\u00a0al.: Chat-scene: bridging 3D scene and large language models with object identifiers. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada (2024)","DOI":"10.52202\/079017-3620"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Chat-3d v2: bridging 3D scene and large language models with object identifiers. arXiv preprint arXiv:2312.08168 (2023)","DOI":"10.52202\/079017-3620"},{"key":"29_CR18","unstructured":"Huang, J., et al.: An embodied generalist agent in 3D world. In: Proceedings of the International Conference on Machine Learning (ICML) (2024)"},{"key":"29_CR19","unstructured":"Li, B., et\u00a0al.: Llava-onevision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"29_CR20","unstructured":"Li, F., et al.: Llava-next-interleave: tackling multi-image, video, and 3d in large multimodal models (2024). https:\/\/arxiv.org\/abs\/2407.07895"},{"key":"29_CR21","unstructured":"Li, J., Zhang, Q., Yu, Y., Fu, Q., Ye, D.: More agents is all you need (2024). arXiv preprint arXiv:2402.05120"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: Vila: on pre-training for visual language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26689\u201326699 (2024)","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"29_CR23","unstructured":"Liu, B., et al.: Coarse correspondence elicit 3D spacetime understanding in multimodal language model (2024). arXiv:2408.00754 arXiv preprint"},{"key":"29_CR24","unstructured":"Liu, Z., et al.: Oryx MLLM: on-demand spatial-temporal understanding at arbitrary resolution. arXiv preprint arXiv:2409.12961 (2024)"},{"key":"29_CR25","unstructured":"Lu, K., et al.: Routing to the expert: efficient reward-guided ensemble of large language models. arXiv preprint arXiv:2311.08692 (2023)"},{"key":"29_CR26","unstructured":"Ma, X., et al.: Sqa3D: Situated question answering in 3d scenes (2023). https:\/\/arxiv.org\/abs\/2210.07474"},{"key":"29_CR27","doi-asserted-by":"publisher","first-page":"46212","DOI":"10.52202\/075280-2004","volume":"36","author":"K Mangalam","year":"2023","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: Egoschema: a diagnostic benchmark for very long-form video language understanding. Adv. Neural. Inf. Process. Syst. 36, 46212\u201346244 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR28","unstructured":"Shnitzer, T., et al.: Large language model routing with benchmark datasets (2023). arXiv preprint arXiv:2309.15789"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Srivatsa, K., Maurya, K.K., Kochmar, E.: Harnessing the power of multiple minds: Lessons learned from LLM routing (2024). arXiv preprint arXiv:2405.00467","DOI":"10.18653\/v1\/2024.insights-1.15"},{"key":"29_CR30","unstructured":"Team, G., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context (2024). arXiv preprint arXiv:2403.05530"},{"key":"29_CR31","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models, (2022). arXiv preprint arXiv:2203.11171"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Thinking in Space: How Multimodal Large Language Models See, Remember and Recall Spaces. arXiv preprint arXiv:2412.14171 (2024)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"29_CR33","unstructured":"Yue, M., Zhao, J., Zhang, M., Du, L., Yao, Z.: Large language model cascades with mixture of thoughts representations for cost-efficient reasoning (2023). arXiv preprint arXiv:2310.03094"},{"key":"29_CR34","unstructured":"Zhang, P., et al.: Long context transfer from language to vision. arXiv preprint arXiv:2406.16852 (2024). https:\/\/arxiv.org\/abs\/2406.16852"},{"key":"29_CR35","unstructured":"Zhang, Y., et al.: Llava-next: a strong zero-shot video understanding model (2024). https:\/\/llava-vl.github.io\/blog\/2024-04-30-llava-next-video\/"},{"key":"29_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Loraretriever: input-aware lora retrieval and composition for mixed tasks in the wild (2024). arXiv preprint arXiv:2402.09997","DOI":"10.18653\/v1\/2024.findings-acl.263"},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, D., Huang, S., Wang, L.: Video-3d LLM: learning position-aware video representation for 3d scene understanding (2024). https:\/\/arxiv.org\/abs\/2412.00493","DOI":"10.1109\/CVPR52734.2025.00841"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Zhu, C., Wang, T., Zhang, W., Pang, J., Liu, X.: Llava-3D: A simple yet effective pathway to empowering LMMs with 3d-awareness (2024). arXiv preprint arXiv:2409.18125","DOI":"10.1109\/ICCV51701.2025.00409"},{"key":"29_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et al.: 3D-vista: pre-trained transformer for 3D vision and text alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2911\u20132921 (2023)","DOI":"10.1109\/ICCV51070.2023.00272"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31397-3_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:07:25Z","timestamp":1785827245000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31397-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"ISBN":["9783032313966","9783032313973"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31397-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"5 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}