{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:08:18Z","timestamp":1789031298104,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":56,"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_8","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:28:05Z","timestamp":1789028885000},"page":"128-146","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MindBlock: Probing Spatial Assembly and\u00a0Structure in\u00a0Unified Multimodal Models"],"prefix":"10.1007","author":[{"given":"Baiqiao","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heyang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingxuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengzu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manling","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"8_CR1","unstructured":"Cai, J., et\u00a0al.: Internvla-a1: Unifying understanding, generation and action for robotic manipulation. arXiv preprint arXiv:2601.02456 (2026)"},{"key":"8_CR2","unstructured":"Cen, J., et\u00a0al.: Rynnvla-002: A unified vision-language-action and world model. arXiv preprint arXiv:2511.17502 (2025)"},{"key":"8_CR3","unstructured":"Chen, J., et al.: Blip3o-next: Next frontier of native image generation (2025). https:\/\/arxiv.org\/abs\/2510.15857"},{"key":"8_CR4","unstructured":"Chen, Y., Wang, C., Fei-Fei, L., Liu, C.K.: Sequential dexterity: chaining dexterous policies for long-horizon manipulation. In: Proceedings of Machine Learning Research (2023)"},{"key":"8_CR5","unstructured":"Cui, Y., et al.: Emu3.5: Native multimodal models are world learners (2025). https:\/\/arxiv.org\/abs\/2510.26583"},{"key":"8_CR6","unstructured":"Cui, Y., et\u00a0al.: Emu3. 5: Native multimodal models are world learners. arXiv preprint arXiv:2510.26583 (2025)"},{"key":"8_CR7","unstructured":"Deng, C., et\u00a0al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"key":"8_CR8","unstructured":"Dongfang, Z., et al.: Are multimodal large language models ready for omnidirectional spatial reasoning? arXiv preprint, (2025). arXiv:2505.11907"},{"issue":"2","key":"8_CR9","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s10339-012-0534-0","volume":"14","author":"A Frick","year":"2013","unstructured":"Frick, A., Ferrara, K., Newcombe, N.S.: Using a touch screen paradigm to assess the development of mental rotation between 3$$1\/2$$ and 5$$1\/2$$ years of age. Cogn. Process. 14(2), 117\u2013127 (2013)","journal-title":"Cogn. Process."},{"key":"8_CR10","unstructured":"Genesis Authors: Genesis: A universal and generative physics engine for robotics and beyond (2024). https:\/\/github.com\/Genesis-Embodied-AI\/Genesis"},{"key":"8_CR11","unstructured":"Gu, C., et\u00a0al.: Manualvla: A unified vla model for chain-of-thought manual generation and robotic manipulation. arXiv preprint arXiv:2512.02013 (2025)"},{"key":"8_CR12","unstructured":"Gu, J., et al.: Thinkmorph: Emergent properties in multimodal interleaved chain-of-thought reasoning (2026), https:\/\/arxiv.org\/abs\/2510.27492"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Han, W., Xiang, S., Liu, C., Wang, R., Feng, C.: Spare3d: a dataset for spatial reasoning on three-view line drawings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14690\u201314699 (2020)","DOI":"10.1109\/CVPR42600.2020.01470"},{"key":"8_CR14","unstructured":"Hu, J., et al.: Omni-view: unlocking how generation facilitates understanding in unified 3d model based on multiview images. arXiv preprint (2025)arXiv:2511.07222"},{"key":"8_CR15","unstructured":"Huang, R., et al.: Illume+: Illuminating unified mllm with dual visual tokenization and diffusion refinement (2025). https:\/\/arxiv.org\/abs\/2504.01934"},{"key":"8_CR16","unstructured":"Intelligence, P., et\u00a0al.: $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization. arXiv preprint arXiv:2504.16054 (2025)"},{"key":"8_CR17","unstructured":"Jia, M., et al.: Omnispatial: towards comprehensive spatial reasoning benchmark for vision language models. arXiv preprint arXiv:2506.03135 (2025)"},{"key":"8_CR18","unstructured":"Kim, J.W.: Survey on automated lego assembly construction. In: WSCG (2014)"},{"key":"8_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogdev.2024.101463","volume":"71","author":"B Landau","year":"2024","unstructured":"Landau, B., Davis, E.E., Cortesa, C.S., Wang, Z., Jones, J.D., Shelton, A.L.: Young children\u2019s copying of block constructions: significant constraints in a highly complex task. Cogn. Dev. 71, 101463 (2024)","journal-title":"Cogn. Dev."},{"key":"8_CR20","unstructured":"Li, L., et al.: Unfolding spatial cognition: Evaluating multimodal models on visual simulations. arXiv preprint arXiv:2506.04633 (2025)"},{"key":"8_CR21","unstructured":"Li, Y., et al.: Unieval: unified holistic evaluation for unified multimodal understanding and generation. arXiv preprint arXiv:2505.10483 (2025)"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Dual diffusion for unified image generation and understanding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2779\u20132790 (2025)","DOI":"10.1109\/CVPR52734.2025.00265"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C., et al.: On-the-fly vla adaptation via test-time reinforcement learning. arXiv preprint arXiv:2601.06748 (2026)","DOI":"10.18653\/v1\/2026.acl-long.1863"},{"key":"8_CR24","unstructured":"Liu, M., et al.: Holistic evaluation for interleaved text-and-image generation. arXiv preprint arXiv:2406.14643 (2024)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Liu, R., et\u00a0al.: Prompt-to-product: Generative assembly via bimanual manipulation. arXiv preprint arXiv:2508.21063 (2025)","DOI":"10.1109\/MRA.2026.3693138"},{"key":"8_CR26","unstructured":"Liu, S., et al.: Step1x-edit: A practical framework for general image editing (2025). https:\/\/arxiv.org\/abs\/2504.17761"},{"key":"8_CR27","unstructured":"Liu, Z., Gu, Y., Zheng, S., Xue, X., Fu, Y.: Trivla: a triple-system-based unified vision-language-action model for general robot control. arXiv e-prints pp. arXiv\u20132507 (2025)"},{"issue":"6","key":"8_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818091","volume":"34","author":"SJ Luo","year":"2015","unstructured":"Luo, S.J., et al.: Legolization: optimizing lego designs. ACM Trans. Graph. (ToG) 34(6), 1\u201312 (2015)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Ma, L., et al.: Phyblock: a progressive benchmark for physical understanding and planning via 3d block assembly (2025). https:\/\/arxiv.org\/abs\/2506.08708","DOI":"10.52202\/085713-3670"},{"key":"8_CR30","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":"8_CR31","doi-asserted-by":"crossref","unstructured":"Ma, W., et al.: Spatialreasoner: Towards explicit and generalizable 3d spatial reasoning. arXiv preprint arXiv:2504.20024 (2025)","DOI":"10.52202\/085713-4703"},{"issue":"4","key":"8_CR32","first-page":"354","volume":"1","author":"S Ono","year":"2013","unstructured":"Ono, S., Andr\u00e9, A., Chang, Y., Nakajima, M.: Lego builder: automatic generation of lego assembly manual from 3d polygon model. ITE Trans. Media Technol. Appl. 1(4), 354\u2013360 (2013)","journal-title":"ITE Trans. Media Technol. Appl."},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Pun, A., Deng, K., Liu, R., Ramanan, D., Liu, C., Zhu, J.Y.: Generating physically stable and buildable brick structures from text. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14798\u201314809 (2025)","DOI":"10.1109\/ICCV51701.2025.01373"},{"key":"8_CR34","unstructured":"Qin, L., et al.: Uni-cot: Towards unified chain-of-thought reasoning across text and vision (2026). https:\/\/arxiv.org\/abs\/2508.05606"},{"key":"8_CR35","unstructured":"Shi, Q., et\u00a0al.: Muddit: Liberating generation beyond text-to-image with a unified discrete diffusion model. arXiv preprint arXiv:2505.23606 (2025)"},{"key":"8_CR36","unstructured":"Tang, K., et al.: Lego-puzzles: how good are mllms at multi-step spatial reasoning? arXiv preprint, (2025). arXiv:2503.19990"},{"key":"8_CR37","unstructured":"Thompson, R., Ghalebi, E., DeVries, T., Taylor, G.W.: Building lego using deep generative models of graphs. arXiv preprint arXiv:2012.11543 (2020)"},{"key":"8_CR38","unstructured":"Wang, G.H., et al.: Ovis-u1 technical report (2025). https:\/\/arxiv.org\/abs\/2506.23044"},{"key":"8_CR39","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-031-19836-6_38","volume-title":"Computer Vision - ECCV 2022","author":"R Wang","year":"2022","unstructured":"Wang, R., Zhang, Y., Mao, J., Cheng, C.Y., Wu, J.: Translating a visual lego manual to a machine-executable plan. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, pp. 677\u2013694. Springer Nature Switzerland, Cham (2022)"},{"key":"8_CR40","unstructured":"Wang, S., et al.: Spatialviz-bench: An mllm benchmark for spatial visualization. arXiv preprint arXiv:2507.07610 (2025)"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Wang, X., Ma, W., Zhang, T., de\u00a0Melo, C.M., Chen, J., Yuille, A.: Spatial457: a diagnostic benchmark for 6d spatial reasoning of large mutimodal models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24669\u201324679 (2025)","DOI":"10.1109\/CVPR52734.2025.02297"},{"key":"8_CR42","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"8_CR43","unstructured":"Xiao, S., et al.: Omnigen: Unified image generation (2024). https:\/\/arxiv.org\/abs\/2409.11340"},{"key":"8_CR44","unstructured":"Xie, J., et al.: Show-o: one single transformer to unify multimodal understanding and generation. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Xie, J., Yang, Z., Shou, M.Z.: Show-o2: Improved native unified multimodal models. arXiv preprint arXiv:2506.15564 (2025)","DOI":"10.52202\/085713-1584"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Xie, X., Zou, C., Karumuri, M.G., Lenssen, J.E., Pons-Moll, G.: Mvgbench: Comprehensive benchmark for multi-view generation models (2025), https:\/\/arxiv.org\/abs\/2507.00006","DOI":"10.1109\/ICCV51701.2025.00769"},{"key":"8_CR47","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 (2025)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Mmada: Multimodal large diffusion language models. arXiv preprint arXiv:2505.15809 (2025)","DOI":"10.52202\/085713-4636"},{"key":"8_CR49","unstructured":"Yang, S., et\u00a0al.: Cambrian-s: Towards spatial supersensing in video. arXiv preprint arXiv:2511.04670 (2025)"},{"key":"8_CR50","unstructured":"Yang, S., et\u00a0al.: Mmsi-bench: a benchmark for multi-image spatial intelligence. arXiv preprint arXiv:2505.23764 (2025)"},{"key":"8_CR51","unstructured":"Yeh, C.H., et al.: Seeing from another perspective: evaluating multi-view understanding in mllms. arXiv preprint arXiv:2504.15280 (2025)"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, J., Cherian, A., Rodriguez, C., Deng, W., Gould, S.: Manual-pa: Learning 3d part assembly from instruction diagrams. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6304\u20136314 (2025)","DOI":"10.1109\/ICCV51701.2025.00595"},{"key":"8_CR53","unstructured":"Zhang, J., et al.: Ascending the infinite ladder: benchmarking spatial deformation reasoning in vision-language models. arXiv preprint arXiv:2507.02978 (2025)"},{"key":"8_CR54","unstructured":"Zhang, J., Guo, Y., Hu, Y., Chen, X., Zhu, X., Chen, J.: Up-vla: a unified understanding and prediction model for embodied agent. In: International Conference on Machine Learning. pp. 74911\u201374922. PMLR (2025)"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, P., et\u00a0al.: Opening: a comprehensive benchmark for judging open-ended interleaved image-text generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 56\u201366 (2025)","DOI":"10.1109\/CVPR52734.2025.00015"},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"Zhu, F., Wu, H., Guo, S., Liu, Y., Cheang, C., Kong, T.: Irasim: a fine-grained world model for robot manipulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9834\u20139844 (2025)","DOI":"10.1109\/ICCV51701.2025.00917"}],"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_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:28:26Z","timestamp":1789028906000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37432-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374318","9783032374325"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37432-5_8","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"}}]}}