{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T17:15:46Z","timestamp":1789578946117,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":104,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372345","type":"print"},{"value":"9783032372352","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\/978-3-032-37235-2_15","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:01:33Z","timestamp":1789372893000},"page":"237-258","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Generation Models Know Space: Unleashing Implicit 3D Priors for\u00a0Scene Understanding"],"prefix":"10.1007","author":[{"given":"Xianjin","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingkang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianrui","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kui","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yumeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"15_CR1","unstructured":"Assran, M., et al.: V-JEPA 2: self-supervised video models enable understanding, prediction and planning. arXiv preprint arXiv:2506.09985 (2025)"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Azuma, D., Miyanishi, T., Kurita, S., Kawanabe, M.: ScanQA: 3d question answering for spatial scene understanding. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2022). License: Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"15_CR3","unstructured":"Ball, P.J., et al.: Genie 3: a new frontier for world models (2025). https:\/\/deepmind.google\/blog\/genie-3-a-new-frontier-for-world-models\/. Accessed 28 June 2026"},{"key":"15_CR4","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint. arXiv:2311.15127 (2023)"},{"key":"15_CR5","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators. Accessed 28 June 2026"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Bu, Q., et al.: UniVLA: learning to act anywhere with task-centric latent actions. Robot. Sci. Syst. (RSS) (2025)","DOI":"10.15607\/RSS.2025.XXI.014"},{"key":"15_CR7","unstructured":"Cao, M., et al.: Seeing through imagination: learning scene geometry via implicit spatial world modeling (2025). https:\/\/arxiv.org\/abs\/2512.01821. Accessed 28 June 2026"},{"key":"15_CR8","unstructured":"Cheang, C.L., et\u00a0al.: GR-2: a generative video-language-action model with web-scale knowledge for robot manipulation. arXiv preprint arXiv:2410.06158 (2024)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: SpatialVLM: endowing vision-language models with spatial reasoning capabilities. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit, pp. 14455\u201314465 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"15_CR10","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: ScanRefer: 3d object localization in RGB-D scans using natural language. In: Proc. Eur. Conf. Comput. Vis. (2020). License: Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License"},{"key":"15_CR11","unstructured":"Chen, D., et al.: VL-JEPA: joint embedding predictive architecture for vision-language. In: Proc. Int. Conf. Learn. Representations (2026)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Chen, S., Guhur, P., Tapaswi, M., Schmid, C., Laptev, I.: Language conditioned spatial relation reasoning for 3d object grounding. Proc. Adv. Neural Inf. Process. Syst. (2022)","DOI":"10.52202\/068431-1492"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: LL3DA: visual interactive instruction tuning for omni-3d understanding, reasoning, and planning. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2024)","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"15_CR14","unstructured":"Chen, Y., et al.: Grounded 3D-LLM with referent tokens. arXiv preprint arXiv:2405.10370 (2024)"},{"key":"15_CR15","unstructured":"Chen, Y., et\u00a0al.: LongVILA: scaling long-context visual language models for long videos. In: Proc. Int. Conf. Learn. Representations (2025)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, X., Xu, H., Xie, J., Tu, Z.: CVP: central-peripheral vision-inspired multimodal model for spatial reasoning. arXiv preprint arXiv:2512.08135 (2025)","DOI":"10.1109\/WACV61042.2026.00227"},{"key":"15_CR17","unstructured":"Chen, Z., et al.: Think with 3d: geometric imagination grounded spatial reasoning from limited views. arXiv preprint arXiv:2510.18632 (2025)"},{"issue":"12","key":"15_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5","volume":"67","author":"Z Chen","year":"2024","unstructured":"Chen, Z., et al.: How far are we to GPT-4V? Closing the gap to commercial multimodal models with open-source suites. SCIENCE CHINA Inf. Sci. 67(12), 220101 (2024)","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"15_CR19","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: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2021). License: Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Chi, C., et al.: Diffusion policy: visuomotor policy learning via action diffusion. Int. J. Robot. Res. (2023)","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"15_CR21","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: Proc. IEEE Conf. Comput. Vis. Pattern Recognit (2017). License: ScanNet Terms of Use","DOI":"10.1109\/CVPR.2017.261"},{"key":"15_CR22","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: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2025)","DOI":"10.1109\/CVPR52734.2025.00357"},{"key":"15_CR23","unstructured":"Deng, T., et al.: GaussianDWM: 3d gaussian driving world model for unified scene understanding and multi-modal generation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2026)"},{"key":"15_CR24","unstructured":"Deng, T., et al.: What is the best 3d scene representation for robotics? from geometric to foundation models. arXiv preprint arXiv:2512.03422 (2025)"},{"key":"15_CR25","unstructured":"Fan, Z., et\u00a0al.: VLM-3R: vision-language models augmented with instruction-aligned 3d reconstruction. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2026)"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Fang, H., Li, S., Wang, S., Xi, X., Liang, D., Bai, X.: Towards generalizable robotic manipulation in dynamic environments. arXiv preprint arXiv:2603.15620 (2026)","DOI":"10.1007\/978-3-032-37592-6_18"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Feng, K., et al.: Video-R1: reinforcing video reasoning in MLLMs. In: Proc. Adv. Neural Inf. Process. Syst. (2025)","DOI":"10.52202\/085713-3310"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: MindDrive: a vision-language-action model for autonomous driving via online reinforcement learning. arXiv preprint arXiv:2512.13636 (2025)","DOI":"10.1007\/978-3-032-37026-6_28"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Fu, R., Liu, J., Chen, X., Nie, Y., Xiong, W.: Scene-LLM: extending language model for 3d visual reasoning. In: Proceedings of the Winter Conference on Applications of Computer Vision (WACV), pp. 2195\u20132206 (2025)","DOI":"10.1109\/WACV61041.2025.00220"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Gao, J., et al.: Physically grounded vision-language models for robotic manipulation. In: Proc. IEEE Int. Conf. Robotics Automation, pp. 12462\u201312469. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610090"},{"key":"15_CR31","unstructured":"Gemini Team: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"15_CR32","unstructured":"Guan, Y., et al.: Video streaming thinking: videoLLMs can watch and think simultaneously. arXiv preprint arXiv:2603.12262 (2026)"},{"key":"15_CR33","unstructured":"Guo, Z., et\u00a0al.: Point-bind & point-LLM: aligning point cloud with multi-modality for 3d understanding, generation, and instruction following. arXiv preprint arXiv:2309.00615 (2023)"},{"key":"15_CR34","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: CogVideo: large-scale pretraining for text-to-video generation via transformers. In: Proc. Int. Conf. Learn. Representations (2023)"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Hou, Z., et al.: Dita: scaling diffusion transformer for generalist vision-language-action policy. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 7686\u20137697 (2025)","DOI":"10.1109\/ICCV51701.2025.00721"},{"key":"15_CR36","unstructured":"Hu, J., et al.: Omni-view: unlocking how generation facilitates understanding in unified 3d model based on multiview images. In: Proc. Int. Conf. Learn. Representations (2026)"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: Chat-3d V2: bridging 3d scene and large language models with object identifiers. In: Proc. Adv. Neural Inf. Process. Syst. (2024)","DOI":"10.52202\/079017-3620"},{"key":"15_CR38","unstructured":"Huang, J., et al.: An embodied generalist agent in 3d world. In: Proc. Int. Conf. Mach. Learn. (2024)"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Huang, S., Chen, Y., Jia, J., Wang, L.: Multi-view transformer for 3d visual grounding. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2022)","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"15_CR40","unstructured":"Huang, S., Wu, J., Zhou, Q., Miao, S., Long, M.: Vid2World: crafting video diffusion models to interactive world models. In: Proc. Int. Conf. Learn. Representations (2026)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Huang, X., Wu, J., Xie, Q., Han, K.: 3DRS: MLLMs need 3d-aware representation supervision for scene understanding. Proc. Adv. Neural Inf. Process. Syst. (2025)","DOI":"10.52202\/085713-2282"},{"key":"15_CR42","unstructured":"Hurst, A., et al.: GPT-4O system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"15_CR43","unstructured":"Jia, M., et al.: OmniSpatial: towards comprehensive spatial reasoning benchmark for vision language models. In: Proc. Int. Conf. Learn. Representations (2026)"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Han, Z., Mao, C., Zhang, J., Pan, Y., Liu, Y.: VACE: all-in-one video creation and editing. In: Proc. IEEE Int. Conf. Comput. Vis., pp. 17191\u201317202 (2025)","DOI":"10.1109\/ICCV51701.2025.01597"},{"key":"15_CR45","unstructured":"Kang, B., et al.: How far is video generation from world model: a physical law perspective. In: Proc. Int. Conf. Mach. Learn. (2025)"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Kim, G., Han, J., Cho, S.: Videofrom3d: 3d scene video generation via complementary image and video diffusion models. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201311 (2025)","DOI":"10.1145\/3757377.3763871"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Kim, M.J., Finn, C., Liang, P.: Fine-tuning vision-language-action models: optimizing speed and success. Robot. Sci. Syst. (RSS) (2025)","DOI":"10.15607\/RSS.2025.XXI.017"},{"key":"15_CR48","unstructured":"Kim, M.J., et al.: OpenVLA: an open-source vision-language-action model. In: Proceedings of the 8th Conference on Robot Learning, pp. 2679\u20132713. PMLR (2024)"},{"key":"15_CR49","unstructured":"Kondratyuk, D., et al.: VideoPoet: a large language model for zero-shot video generation. In: Proc. Int. Conf. Mach. Learn. (2024)"},{"key":"15_CR50","unstructured":"Li, B., et\u00a0al.: LLaVA-OneVision: easy visual task transfer. Trans. Mach. Learn. Res. (2025)"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Li, R., Torr, P., Vedaldi, A., Jakab, T.: VMem: consistent interactive video scene generation with surfel-indexed view memory. In: Proc. IEEE Int. Conf. Comput. Vis. (2025)","DOI":"10.1109\/ICCV51701.2025.02383"},{"key":"15_CR52","unstructured":"Liao, Z., et al.: Improved visual-spatial reasoning via R1-zero-like training. arXiv preprint arXiv:2504.00883 (2025)"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: OST-bench: evaluating the capabilities of MLLMs in online spatio-temporal scene understanding. Proc. Adv. Neural Inf. Process. Syst. (2025)","DOI":"10.52202\/085713-0385"},{"key":"15_CR54","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: Proc. Int. Conf. Learn. Representations (2023)"},{"key":"15_CR55","doi-asserted-by":"crossref","unstructured":"Liu, B., et al.: LIBERO: benchmarking knowledge transfer for lifelong robot learning. Adv. Neural Inf. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-1939"},{"key":"15_CR56","unstructured":"Liu, H., et al.: LLaVA-next: improved reasoning, OCR, and world knowledge (2024). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/. Accessed 28 June 2026"},{"key":"15_CR57","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"15_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-024-4303-8","volume":"68","author":"Y Liu","year":"2025","unstructured":"Liu, Y., et al.: Embodied navigation. SCIENCE CHINA Inf. Sci. 68(4), 1\u201339 (2025)","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: NVILA: efficient frontier visual language models. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 4122\u20134134 (2025)","DOI":"10.1109\/CVPR52734.2025.00390"},{"key":"15_CR60","unstructured":"Ma, X., et al.: SQA3D: situated question answering in 3d scenes. In: Proc. Int. Conf. Learn. Representations (2023). License: CC-BY-4.0"},{"key":"15_CR61","unstructured":"Mei, G., Lin, W., Riz, L., Wu, Y., Wang, Y., Poiesi, F.: Efficient encoder-free Fourier-based 3d large multimodal model. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2026)"},{"key":"15_CR62","unstructured":"Miao, S., et al.: JEPA-VLA: video predictive embedding is needed for VLA models. arXiv preprint arXiv:2602.11832 (2026)"},{"key":"15_CR63","doi-asserted-by":"crossref","unstructured":"Mu, Y., Chen, T.: RoboTwin: dual-arm robot benchmark with generative digital twins. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2025)","DOI":"10.1007\/978-3-031-91813-1_17"},{"key":"15_CR64","unstructured":"Ouyang, K., et al.: Spacer: reinforcing MLLMs in video spatial reasoning. arXiv preprint arXiv:2504.01805 (2025)"},{"key":"15_CR65","doi-asserted-by":"crossref","unstructured":"Qi, Z., et al.: GPT4Point: a unified framework for point-language understanding and generation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2024)","DOI":"10.1109\/CVPR52733.2024.02495"},{"key":"15_CR66","unstructured":"Qi, Z., Zhang, Z., Fang, Y., Wang, J., Zhao, H.: GPT4Scene: understand 3d scenes from videos with vision-language models. In: Proc. Int. Conf. Learn. Representations (2026)"},{"key":"15_CR67","unstructured":"Qwen Team: Qwen2.5-VL technical report. arXiv preprint. arXiv:2502.13923"},{"key":"15_CR68","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proc. Int. Conf. Mach. Learn, pp. 8748\u20138763. PMLR (2021)"},{"key":"15_CR69","doi-asserted-by":"crossref","unstructured":"Ren, X., et al.: GEN3C: 3D-informed world-consistent video generation with precise camera control. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6121\u20136132 (2025)","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"15_CR70","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"15_CR71","unstructured":"Sim\u00e9oni, O., et\u00a0al.: DinoV3. arXiv preprint arXiv:2508.10104 (2025)"},{"key":"15_CR72","unstructured":"Team, O.M., et\u00a0al.: Octo: an open-source generalist robot policy. Robot. Sci. Syst. (RSS) (2024)"},{"key":"15_CR73","unstructured":"Tschannen, M., et al.: SigLIP 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"15_CR74","unstructured":"Valevski, D., Leviathan, Y., Arar, M., Fruchter, S.: Diffusion models are real-time game engines. In: Proc. Int. Conf. Learn. Representations (2025)"},{"key":"15_CR75","unstructured":"Wan, T., et\u00a0al.: WAN: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"15_CR76","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: Proc. IEEE Int. Conf. Comput. Vis. (2025)","DOI":"10.1109\/ICCV51701.2025.00866"},{"key":"15_CR77","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"15_CR78","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":"15_CR79","doi-asserted-by":"crossref","unstructured":"Xiao, Z., et al.: WorldMem: long-term consistent world simulation with memory. In: Proc. Adv. Neural Inf. Process. Syst. (2025)","DOI":"10.52202\/085713-1659"},{"key":"15_CR80","unstructured":"Xu, G., et al.: Next forcing: causal world modeling with multi-chunk prediction. arXiv preprint arXiv:2606.11187 (2026)"},{"key":"15_CR81","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: Proc. Eur. Conf. Comput. Vis. (2024)","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"15_CR82","doi-asserted-by":"publisher","first-page":"59468","DOI":"10.52202\/079017-1899","volume":"37","author":"W Xu","year":"2024","unstructured":"Xu, W., Shi, C., Tu, S., Zhou, X., Liang, D., Bai, X.: A unified framework for 3d scene understanding. Adv. Neural. Inf. Process. Syst. 37, 59468\u201359490 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR83","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: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 10632\u201310643 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"15_CR84","unstructured":"Yang, S., et\u00a0al.: MMSI-Bench: a benchmark for multi-image spatial intelligence. In: Proc. Int. Conf. Learn. Representations (2026)"},{"key":"15_CR85","unstructured":"Yang, Z., et\u00a0al.: CogVideoX: text-to-video diffusion models with an expert transformer. In: Proc. Int. Conf. Learn. Representations (2025)"},{"key":"15_CR86","unstructured":"Yin, B., et\u00a0al.: Spatial mental modeling from limited views. In: Structural Priors for Vision Workshop at ICCV 2025 (2025)"},{"key":"15_CR87","doi-asserted-by":"crossref","unstructured":"Yu, H., Li, W., Wang, S., Chen, J., Zhu, J.: Inst3D-LMM: instance-aware 3d scene understanding with multi-modal instruction tuning. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2025)","DOI":"10.1109\/CVPR52734.2025.01320"},{"key":"15_CR88","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"15_CR89","doi-asserted-by":"crossref","unstructured":"Zhang, J., et\u00a0al.: From flatland to space: teaching vision-language models to perceive and reason in 3d. In: Proc. IEEE Int. Conf. Comput. Vis. (2025)","DOI":"10.52202\/085713-5180"},{"key":"15_CR90","unstructured":"Zhang, K., et al.: Can world models benefit VLMs for world dynamics? arXiv preprint arXiv:2510.00855 (2025)"},{"key":"15_CR91","unstructured":"Zhang, P., et al.: Long context transfer from language to vision. arXiv preprint arXiv:2406.16852 (2024)"},{"key":"15_CR92","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Sphere: unveiling spatial blind spots in vision-language models through hierarchical evaluation. In: Proc. Annual Meeting of the Association for Computational Linguistics, pp. 11591\u201311609 (2025)","DOI":"10.18653\/v1\/2025.acl-long.568"},{"key":"15_CR93","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Gong, Z., Chang, A.X.: Multi3DRefer: grounding text description to multiple 3d objects. In: Proc. IEEE Int. Conf. Comput. Vis. (2023)","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"15_CR94","unstructured":"Zhang, Z., et al.: OmniDrive-R1: reinforcement-driven interleaved multi-modal chain-of-thought for trustworthy vision-language autonomous driving. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2026)"},{"key":"15_CR95","doi-asserted-by":"crossref","unstructured":"Zhao, L., Cai, D., Sheng, L., Xu, D.: 3DVG-transformer: relation modeling for visual grounding on point clouds. In: Proc. IEEE Int. Conf. Comput. Vis. (2021)","DOI":"10.1109\/ICCV48922.2021.00292"},{"key":"15_CR96","doi-asserted-by":"crossref","unstructured":"Zhao, Q., et al.: CoT-VLA: visual chain-of-thought reasoning for vision-language-action models. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 1702\u20131713 (2025)","DOI":"10.1109\/CVPR52734.2025.00166"},{"key":"15_CR97","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. Proc. Adv. Neural Inf. Process. Syst. (2025)","DOI":"10.52202\/085713-0693"},{"key":"15_CR98","doi-asserted-by":"crossref","unstructured":"Zheng, D., Huang, S., Wang, L.: Video-3D LLM: learning position-aware video representation for 3d scene understanding. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2025)","DOI":"10.1109\/CVPR52734.2025.00841"},{"key":"15_CR99","doi-asserted-by":"crossref","unstructured":"Zheng, D., Huang, S., Zhao, L., Zhong, Y., Wang, L.: Towards learning a generalist model for embodied navigation. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 13624\u201313634 (2024)","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"15_CR100","unstructured":"Zhou, H., Lee, G.H.: LLaVA-4D: embedding spatiotemporal prompt into LMMs for 4d scene understanding. In: Proc. Int. Conf. Learn. Representations (2026)"},{"key":"15_CR101","doi-asserted-by":"crossref","unstructured":"Zhou, J., et al.: Stable virtual camera: generative view synthesis with diffusion models. In: Proc. IEEE Int. Conf. Comput. Vis. (2025)","DOI":"10.1109\/ICCV51701.2025.01153"},{"key":"15_CR102","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. In: Proc. IEEE Int. Conf. Comput. Vis. (2024)","DOI":"10.1109\/ICCV51701.2025.00409"},{"key":"15_CR103","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: Proc. IEEE Int. Conf. Comput. Vis. (2023)","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"15_CR104","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et al.: Unifying 3d vision-language understanding via promptable queries. In: Proc. Eur. Conf. Comput. Vis. (2024)","DOI":"10.1007\/978-3-031-72784-9_11"}],"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\/978-3-032-37235-2_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:02:32Z","timestamp":1789372952000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37235-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372345","9783032372352"],"references-count":104,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37235-2_15","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":"15 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"}}]}}