{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:08:33Z","timestamp":1788988113169,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":79,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373557","type":"print"},{"value":"9783032373564","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\/978-3-032-37356-4_17","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:26:25Z","timestamp":1788985585000},"page":"297-316","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision-Language Memory for\u00a0Spatial Reasoning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1351-6847","authenticated-orcid":false,"given":"Zuntao","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4312-2170","authenticated-orcid":false,"given":"Yi","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4545-7736","authenticated-orcid":false,"given":"Taimeng","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-2327","authenticated-orcid":false,"given":"Shaoshu","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1886-1020","authenticated-orcid":false,"given":"Cherie","family":"Ho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4630-0805","authenticated-orcid":false,"given":"Chen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"17_CR1","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, pp. 19129\u201319139 (2022)","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"17_CR2","unstructured":"Bai, S., et al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"17_CR3","unstructured":"Bai, S., et al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"17_CR4","unstructured":"Baruch, G., et al.: Arkitscenes: a diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data. arXiv preprint arXiv:2111.08897 (2021)"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Cai, W., et al.: Spatialbot: precise spatial understanding with vision language models. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 9490\u20139498. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11128671"},{"key":"17_CR6","unstructured":"Cen, J., et al.: Tackling view-dependent semantics in 3D language gaussian splatting. In: Forty-Second International Conference on Machine Learning (2025)"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Spatialvlm: endowing vision-language models with spatial reasoning capabilities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14455\u201314465 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Ll3da: visual interactive instruction tuning for omni-3d understanding reasoning and planning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26428\u201326438 (2024)","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"17_CR9","unstructured":"Chen, Y., Qi, Z., Zhang, W., Jin, X., Zhang, L., Liu, P.: Reasoning in space via grounding in the world. arXiv preprint arXiv:2510.13800 (2025)"},{"key":"17_CR10","unstructured":"Chen, Z., et al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., Qin, M., Yuan, T., Liu, Z., Zhao, H.: Long3r: long sequence streaming 3D reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5273\u20135284 (2025)","DOI":"10.1109\/ICCV51701.2025.00501"},{"key":"17_CR12","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":"17_CR13","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":"17_CR14","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Deng, J., He, T., Jiang, L., Wang, T., Dayoub, F., Reid, I.: 3D-llava: towards generalist 3D LMMs with omni superpoint transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3772\u20133782 (2025)","DOI":"10.1109\/CVPR52734.2025.00357"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Diomataris, M., Gkanatsios, N., Pitsikalis, V., Maragos, P.: Grounding consistency: distilling spatial common sense for precise visual relationship detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15911\u201315920 (2021)","DOI":"10.1109\/ICCV48922.2021.01561"},{"key":"17_CR17","unstructured":"Fan, Z., et al.: VLM-3R: vision-language models augmented with instruction-aligned 3D reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 31054\u201331065 (2026)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Fu, C., et al.: Video-MME: the first-ever comprehensive evaluation benchmark of multi-modal LLMs in video analysis. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24108\u201324118 (2025)","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Blink: multimodal large language models can see but not perceive. In: European Conference on Computer Vision, pp. 148\u2013166. Springer (2024)","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"He, B., et al.: MA-LMM: memory-augmented large multimodal model for long-term video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13504\u201313514 (2024)","DOI":"10.1109\/CVPR52733.2024.01282"},{"key":"17_CR21","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)"},{"issue":"8","key":"17_CR22","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"17_CR23","doi-asserted-by":"publisher","first-page":"20482","DOI":"10.52202\/075280-0900","volume":"36","author":"Y Hong","year":"2023","unstructured":"Hong, Y., et al.: 3D-LLM: injecting the 3D world into large language models. Adv. Neural. Inf. Process. Syst. 36, 20482\u201320494 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"17_CR24","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"key":"17_CR25","first-page":"67856","volume":"38","author":"W Hu","year":"2026","unstructured":"Hu, W., et al.: 3DLLM-Mem: long-term spatial-temporal memory for embodied 3D large language model. Adv. Neural. Inf. Process. Syst. 38, 67856\u201367884 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR26","doi-asserted-by":"publisher","first-page":"113991","DOI":"10.52202\/079017-3620","volume":"37","author":"H Huang","year":"2024","unstructured":"Huang, H., et al.: Chat-scene: bridging 3D scene and large language models with object identifiers. Adv. Neural. Inf. Process. Syst. 37, 113991\u2013114017 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Chat-3d v2: bridging 3D scene and large language models with object identifiers. CoRR (2023)","DOI":"10.52202\/079017-3620"},{"key":"17_CR28","unstructured":"Huang, J., et al.: An embodied generalist agent in 3D world. arXiv preprint arXiv:2311.12871 (2023)"},{"key":"17_CR29","unstructured":"Huang, J., et al.: Memory forcing: spatio-temporal memory for consistent scene generation on minecraft. arXiv preprint arXiv:2510.03198 (2025)"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Huang, X., Wu, J., Xie, Q., Han, K.: 3DRS: MLLMs need 3D-aware representation supervision for scene understanding. In: Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-2282"},{"key":"17_CR31","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Khanna, M., et al.: Goat-bench: a benchmark for multi-modal lifelong navigation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16373\u201316383 (2024)","DOI":"10.1109\/CVPR52733.2024.01549"},{"key":"17_CR33","unstructured":"LeCun, Y.: A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27. Open Rev. 62(1), 1\u201362 (2022)"},{"key":"17_CR34","unstructured":"Li, B., et al.: LLaVA-onevision: easy visual task transfer. TMLR (2025)"},{"issue":"8","key":"17_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3746284","volume":"21","author":"G Liao","year":"2025","unstructured":"Liao, G., Li, J., Bao, Z., Ye, X., Li, Q., Liu, K.: CLIP-Gs: clip-informed gaussian splatting for view-consistent 3D indoor semantic understanding. ACM Trans. Multimed. Comput. Commun. Appl. 21(8), 1\u201324 (2025)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Liao, G., Zhou, K., Bao, Z., Liu, K., Li, Q.: OV-nerf: open-vocabulary neural radiance fields with vision and language foundation models for 3D semantic understanding. IEEE Trans. Circ. Syst. Video Technol. (2024)","DOI":"10.1109\/TCSVT.2024.3439737"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Lin, J., Yin, H., Ping, W., Molchanov, P., Shoeybi, M., Han, S.: Vila: on pre-training for visual language models. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"17_CR38","first-page":"123926","volume":"38","author":"Y Liu","year":"2026","unstructured":"Liu, Y., et al.: SSR: enhancing depth perception in vision-language models via rationale-guided spatial reasoning. Adv. Neural. Inf. Process. Syst. 38, 123926\u2013123958 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR39","unstructured":"Liu, Z., Dong, Y., Liu, Z., Hu, W., Lu, J., Rao, Y.: Oryx MLLM: on-demand spatial-temporal understanding at arbitrary resolution. In: International Conference on Learning Representations, vol.\u00a02025, pp. 85485\u201385507 (2025)"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Ma, W., et al.: 3dsrbench: a comprehensive 3D spatial reasoning benchmark. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6924\u20136934 (2025)","DOI":"10.1109\/ICCV51701.2025.00651"},{"key":"17_CR41","unstructured":"Ma, X., et al.: Sqa3d: situated question answering in 3D scenes. In: International Conference on Learning Representations (2023)"},{"key":"17_CR42","unstructured":"OpenAI: GPT-4o (2024). https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Shi, J.C., Wang, M., Duan, H.B., Guan, S.H.: Language embedded 3D gaussians for open-vocabulary scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5333\u20135343 (2024)","DOI":"10.1109\/CVPR52733.2024.00510"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Song, C.H., Blukis, V., Tremblay, J., Tyree, S., Su, Y., Birchfield, S.: 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":"17_CR45","doi-asserted-by":"crossref","unstructured":"Song, E., et al.: Moviechat: from dense token to sparse memory for long video understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18221\u201318232 (2024)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"17_CR46","unstructured":"Team, Q.: Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)"},{"key":"17_CR47","doi-asserted-by":"publisher","first-page":"87310","DOI":"10.52202\/079017-2771","volume":"37","author":"P Tong","year":"2024","unstructured":"Tong, P., et al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs. Adv. Neural. Inf. Process. Syst. 37, 87310\u201387356 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Imperative learning: a self-supervised neuro-symbolic learning framework for robot autonomy. Int. J. Robot. Res. 02783649251353181 (2024)","DOI":"10.1177\/02783649251353181"},{"issue":"4","key":"17_CR49","doi-asserted-by":"publisher","first-page":"2446","DOI":"10.1109\/TRO.2021.3129972","volume":"38","author":"C Wang","year":"2021","unstructured":"Wang, C., Qiu, Y., Wang, W., Hu, Y., Kim, S., Scherer, S.: Unsupervised online learning for robotic interestingness with visual memory. IEEE Trans. Rob. 38(4), 2446\u20132461 (2021)","journal-title":"IEEE Trans. Rob."},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Wang, C., Wang, W., Qiu, Y., Hu, Y., Scherer, S.: Visual memorability for robotic interestingness via unsupervised online learning. In: European Conference on Computer Vision, pp. 52\u201368. Springer (2020)","DOI":"10.1007\/978-3-030-58536-5_4"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhao, Y., Wang, T., Fan, H., Zhang, X., Zhang, Z.: Ross3d: reconstructive visual instruction tuning with 3D-awareness. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9275\u20139286 (2025)","DOI":"10.1109\/ICCV51701.2025.00866"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Wang, H., Agapito, L.: 3D reconstruction with spatial memory. arXiv preprint arXiv:2408.16061 (2024)","DOI":"10.1109\/3DV66043.2025.00013"},{"key":"17_CR53","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 Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"17_CR54","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 Computer Vision and Pattern Recognition Conference, pp. 10510\u201310522 (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"17_CR55","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: Dust3r: geometric 3D vision made easy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"17_CR56","unstructured":"Wang, Y., et al.: $$\\pi ^3$$: scalable permutation-equivariant visual geometry learning. arXiv preprint arXiv:2507.13347 (2025)"},{"key":"17_CR57","unstructured":"Wang, Z., Huang, H., Zhao, Y., Zhang, Z., Zhao, Z.: Chat-3d: data-efficiently tuning large language model for universal dialogue of 3D scenes. arXiv preprint arXiv:2308.08769 (2023)"},{"key":"17_CR58","first-page":"13569","volume":"38","author":"D Wu","year":"2026","unstructured":"Wu, D., Liu, F., Hung, Y.H., Duan, Y.: Spatial-MLLM: boosting MLLM capabilities in visual-based spatial intelligence. Adv. Neural. Inf. Process. Syst. 38, 13569\u201313597 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR59","first-page":"49371","volume":"38","author":"T Wu","year":"2026","unstructured":"Wu, T., et al.: Video world models with long-term spatial memory. Adv. Neural. Inf. Process. Syst. 38, 49371\u201349393 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR60","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zheng, W., Zhou, J., Lu, J.: Point3r: streaming 3D reconstruction with explicit spatial pointer memory. arXiv preprint arXiv:2507.02863 (2025)","DOI":"10.52202\/085713-2344"},{"key":"17_CR61","unstructured":"Xu, Z., He, Z., Wu, J., Song, S.: Learning 3D dynamic scene representations for robot manipulation. In: Conference on Robot Learning (CoRL) (2020)"},{"key":"17_CR62","doi-asserted-by":"crossref","unstructured":"Yang, F., Frivik, P., Hoeller, D., Wang, C., Cadena, C., Hutter, M.: Spatially-enhanced recurrent memory for long-range mapless navigation via end-to-end reinforcement learning. Int. J. Robot. Res. 02783649251401926 (2025)","DOI":"10.1177\/02783649251401926"},{"key":"17_CR63","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Magma: a foundation model for multimodal AI agents. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 14203\u201314214 (2025)","DOI":"10.1109\/CVPR52734.2025.01325"},{"key":"17_CR64","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 Computer Vision and Pattern Recognition Conference, pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"17_CR65","unstructured":"Yang, R., et al.: Embodiedbench: comprehensive benchmarking multi-modal large language models for vision-driven embodied agents. arXiv preprint arXiv:2502.09560 (2025)"},{"key":"17_CR66","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: 3D-Mem: 3D scene memory for embodied exploration and reasoning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17294\u201317303 (2025)","DOI":"10.1109\/CVPR52734.2025.01612"},{"key":"17_CR67","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: Scannet++: a high-fidelity dataset of 3D indoor scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12\u201322 (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"17_CR68","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Context as memory: scene-consistent interactive long video generation with memory retrieval. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201311 (2025)","DOI":"10.1145\/3757377.3763833"},{"key":"17_CR69","doi-asserted-by":"crossref","unstructured":"Yuan, Z., et al.: Empowering large language models with 3D situation awareness. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 19435\u201319445 (2025)","DOI":"10.1109\/CVPR52734.2025.01810"},{"key":"17_CR70","doi-asserted-by":"crossref","unstructured":"Yue, X., et al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"17_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Flash-vstream: memory-based real-time understanding for long video streams. arXiv preprint arXiv:2406.08085 (2024)","DOI":"10.1109\/ICCV51701.2025.01957"},{"key":"17_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: From flatland to space: teaching vision-language models to perceive and reason in 3D. arXiv preprint arXiv:2503.22976 (2025)","DOI":"10.52202\/085713-5180"},{"key":"17_CR73","unstructured":"Zhang, Y., et al.: Llava-next: a strong zero-shot video understanding model (2024)"},{"key":"17_CR74","unstructured":"Zhang, Y., et al.: Video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713 (2024)"},{"key":"17_CR75","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 Computer Vision and Pattern Recognition Conference, pp. 8995\u20139006 (2025)","DOI":"10.1109\/CVPR52734.2025.00841"},{"key":"17_CR76","first-page":"20560","volume":"38","author":"D Zheng","year":"2026","unstructured":"Zheng, D., Li, Y., Wang, L., et al.: Learning from videos for 3D world: enhancing MLLMs with 3D vision geometry priors. Adv. Neural. Inf. Process. Syst. 38, 20560\u201320586 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR77","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\/CVF International Conference on Computer Vision, pp. 4295\u20134305 (2025)","DOI":"10.1109\/ICCV51701.2025.00409"},{"key":"17_CR78","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Ma, X., Chen, Y., Deng, Z., Huang, S., Li, Q.: 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"},{"key":"17_CR79","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et al.: Move to understand a 3D scene: bridging visual grounding and exploration for efficient and versatile embodied navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8120\u20138132 (2025)","DOI":"10.1109\/ICCV51701.2025.00761"}],"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\/978-3-032-37356-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:26:38Z","timestamp":1788985598000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37356-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373557","9783032373564"],"references-count":79,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37356-4_17","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":"10 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"}}]}}