{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T03:11:09Z","timestamp":1790910669940,"version":"4.1.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370198","type":"print"},{"value":"9783032370204","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\/978-3-032-37020-4_13","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:06:04Z","timestamp":1789038364000},"page":"231-249","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Make Geometry Matter for\u00a0Spatial Reasoning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4244-2360","authenticated-orcid":false,"given":"Shihua","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuhong","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8179-0902","authenticated-orcid":false,"given":"Shizun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3168-3508","authenticated-orcid":false,"given":"Tianbo","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0057-1404","authenticated-orcid":false,"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"13_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1\u201314 (2016)"},{"key":"13_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"13_CR3","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"13_CR4","unstructured":"Chen, Y., et al.: Scaling RL to long videos. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1\u201329 (2025)"},{"key":"13_CR5","unstructured":"Cheng, A.C., et al.: 3D aware region prompted vision language model. In: Proceedings of the International Conference on Learning Representations, pp. 1\u201323 (2026)"},{"key":"13_CR6","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"13_CR7","unstructured":"Fan, Z., et\u00a0al.: VLM-3R: vision-language models augmented with instruction-aligned 3D reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u201321 (2026)"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Gao, M., et al.: TC-LLaVA: rethinking the transfer of LLaVA from image to video understanding with temporal considerations. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3086\u20133094 (2025)","DOI":"10.1609\/aaai.v39i3.32317"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Hong, Y., et al.: 3D-LLM: Injecting the 3D world into large language models. In: Proceedings of the Advances in Neural Information Processing Systems, vol.\u00a036, pp. 20482\u201320494 (2023)","DOI":"10.52202\/075280-0900"},{"key":"13_CR11","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"13_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representation, pp. 1\u201315 (2015)"},{"key":"13_CR13","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4015\u20134026. (2023)"},{"key":"13_CR14","unstructured":"Li, Q., et al.: Vision-language-action safety: threats, challenges, evaluations, and mechanisms. arXiv preprint arXiv:2604.23775 (2026)"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: STI-bench: are MLLMs ready for precise spatial-temporal world understanding? In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5622\u20135632 (2025)","DOI":"10.1109\/ICCV51701.2025.00533"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Ma, W., et al.: 3DSRBench: a comprehensive 3D spatial reasoning benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6924\u20136934 (2025)","DOI":"10.1109\/ICCV51701.2025.00651"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Maaz, M., Raasheed, H., Khan, S., Khan, F.: Video-chatGPT: towards detailed video understanding via large vision and language models. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 12585\u201312602 (2024)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"13_CR18","unstructured":"Pan, T., Yang, X., Wang, X.: Merge3D: efficient 3D multimodal LLMs via joint 2D-3D token merging. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 31066\u201331077 (2026)"},{"key":"13_CR19","unstructured":"Qi, Z., Zhang, Z., Fang, Y., Wang, J., Zhao, H.: GPT4Scene: understand 3D scenes from videos with vision-language models. arXiv preprint arXiv:2501.01428 (2025)"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: DeepSpeed: system optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the International Conference on Knowledge Discovery and Data Mining, pp. 3505\u20133506 (2020)","DOI":"10.1145\/3394486.3406703"},{"key":"13_CR21","unstructured":"Ray, A., et al.: SAT: dynamic spatial aptitude training for multimodal language models. In: Proceedings of the Conference on Language Modeling, pp. 1\u201327 (2025)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"13_CR23","unstructured":"Shen, Q., et al.: World action models: a survey. arXiv preprint arXiv:2606.20781 (2026)"},{"key":"13_CR24","unstructured":"Singh, A., et\u00a0al.: OpenAI GPT-5 system card. arXiv preprint arXiv:2601.03267 (2025)"},{"key":"13_CR25","doi-asserted-by":"publisher","first-page":"127063","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Video understanding with large language models: a survey. IEEE Trans. Circuits Syst. Video Technol. 36(2), 1355\u20131376 (2026)","DOI":"10.1109\/TCSVT.2025.3566695"},{"key":"13_CR27","unstructured":"Team, G., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"13_CR28","unstructured":"Team, O.: InternVL2: Better than the best\u2014expanding performance boundaries of open-source multimodal models with the progressive scaling strategy (2024)"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Tong, P., et\u00a0al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs. In: Proceedings of the Advances in Neural Information Processing Systems, vol.\u00a037, pp. 87310\u201387356 (2024)","DOI":"10.52202\/079017-2771"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Proceedings of the Advances in Neural Information Processing Systems, vol.\u00a035, pp. 10078\u201310093 (2022)","DOI":"10.52202\/068431-0732"},{"key":"13_CR31","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the Advances in Neural Information Processing Systems, vol.\u00a030, pp. 1\u201311 (2017)"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"13_CR33","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D perception model with persistent state. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10510\u201310522 (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"13_CR35","unstructured":"Wang, W., et al.: InternVL3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"13_CR36","unstructured":"Wang, Y., et al.: $$\\pi ^3$$: permutation-equivariant visual geometry learning. In: Proceedings of the International Conference on Learning Representations, pp. 1\u201314 (2026)"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Weinzaepfel, P., et al.: Croco v2: improved cross-view completion pre-training for stereo matching and optical flow. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 17969\u201317980 (2023)","DOI":"10.1109\/ICCV51070.2023.01647"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Wu, D., Liu, F., Hung, Y.H., Duan, Y.: Spatial-MLLM: boosting MLLM capabilities in visual-based spatial intelligence. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1\u201321 (2025)","DOI":"10.52202\/085713-0457"},{"key":"13_CR39","unstructured":"Xu, Q., Chen, S., Chen, G., Wang, Y., Zhang, Y.: ChatBEV: a visual language model that understands BEV maps. arXiv preprint arXiv:2503.13938 (2025)"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, X., Wang, T., Chen, Y., Pang, J., Lin, D.: PointLLM: empowering large language models to understand point clouds. In: European Conference on Computer Vision, pp. 131\u2013147 (2024)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A.W., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: how multimodal large language models see, remember, and recall spaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"Yin, S., et al.: A survey on multimodal large language models. Natl. Sci. Rev. 11(12), nwae403 (2024)","DOI":"10.1093\/nsr\/nwae403"},{"key":"13_CR43","unstructured":"Yu, R., Li, Q., Wang, X.: Discrete diffusion in large language and multimodal models: a survey. arXiv preprint arXiv:2506.13759 (2025)"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Yuan, Y., et\u00a0al.: VideoRefer suite: advancing spatial-temporal object understanding with video LLM. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 18970\u201318980 (2025)","DOI":"10.1109\/CVPR52734.2025.01767"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-LLaMA: an instruction-tuned audio-visual language model for video understanding. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 543\u2013553 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, J., et\u00a0al.: From flatland to space: teaching vision-language models to perceive and reason in 3D. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1\u201333 (2025)","DOI":"10.52202\/085713-5180"},{"issue":"8","key":"13_CR47","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625\u20135644 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR48","unstructured":"Zhang, S., et al.: Deep learning reforms image matching: a survey and outlook. arXiv preprint arXiv:2506.04619 (2025)"},{"key":"13_CR49","unstructured":"Zhang, Y., et al.: LLaVA-video: video instruction tuning with synthetic data. Trans. Mach. Learn. Res. 1\u201324 (2025)"},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Zheng, D., Huang, S., Li, Y., Wang, L.: Learning from videos for 3D world: enhancing MLLMs with 3D vision geometry priors. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 1\u201320 (2025)","DOI":"10.52202\/085713-0693"},{"key":"13_CR51","doi-asserted-by":"crossref","unstructured":"Zheng, D., Huang, S., Wang, L.: Video-3D LLM: learning position-aware video representation for 3d scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8995\u20139006 (2025)","DOI":"10.1109\/CVPR52734.2025.00841"},{"key":"13_CR52","unstructured":"Zhou, H., Lee, G.H.: LLaVA-4D: embedding spatiotemporal prompt into LMMs for 4D scene understanding. arXiv preprint arXiv:2505.12253 (2025)"},{"key":"13_CR53","unstructured":"Zhou, S., et al.: Learning to reason in 4D: dynamic spatial understanding for vision language models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u201318 (2026)"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: VLM4D: towards spatiotemporal awareness in vision language models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8600\u20138612 (2025)","DOI":"10.1109\/ICCV51701.2025.00805"},{"key":"13_CR55","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 capabilities. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4295\u20134305 (2025)","DOI":"10.1109\/ICCV51701.2025.00409"},{"key":"13_CR56","unstructured":"Zhu, J., et al.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"13_CR57","doi-asserted-by":"crossref","unstructured":"Zhu, W., et\u00a0al.: 4D-bench: benchmarking multi-modal large language models for 4D object understanding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 21129\u201321143 (2025)","DOI":"10.1109\/ICCV51701.2025.01963"}],"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\/978-3-032-37020-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:06:25Z","timestamp":1789038385000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37020-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370198","9783032370204"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37020-4_13","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"}}]}}