{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T09:01:52Z","timestamp":1789722112691,"version":"4.0.1"},"publisher-location":"Cham","reference-count":70,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374219","type":"print"},{"value":"9783032374226","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\/978-3-032-37422-6_8","type":"book-chapter","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:07:10Z","timestamp":1789718830000},"page":"135-153","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Humanoid Whole-Body Manipulation via\u00a0Active Spatial Brain and\u00a0Generalizable Action Cerebellum"],"prefix":"10.1007","author":[{"given":"Zhizhao","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Lin","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Xiang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhexi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun-Hui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun-Yu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,19]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Ben, Q., Jia, F., Zeng, J., Dong, J., Lin, D., Pang, J.: Homie: Humanoid loco-manipulation with isomorphic exoskeleton cockpit. arXiv preprint arXiv:2502.13013 (2025)","DOI":"10.15607\/RSS.2025.XXI.070"},{"key":"8_CR2","unstructured":"Bjorck, J., et\u00a0al.: Gr00t n1: An open foundation model for generalist humanoid robots. arXiv preprint arXiv:2503.14734 (2025)"},{"key":"8_CR3","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems (2020)"},{"key":"8_CR4","unstructured":"Bu, Q., et\u00a0al.: Agibot world colosseo: A large-scale manipulation platform for scalable and intelligent embodied systems. arXiv preprint arXiv:2503.06669 (2025)"},{"key":"8_CR5","unstructured":"Contributors, I.M.: Internvla-m1: A spatially guided vision-language-action framework for generalist robot policy. arXiv preprint arXiv:2510.13778 (2025)"},{"key":"8_CR6","unstructured":"Dai, Y., et al.: Aimbot: a simple auxiliary visual cue to enhance spatial awareness of visuomotor policies. In: Conference on Robot Learning (2025)"},{"key":"8_CR7","unstructured":"Ding, P., et al.: Humanoid-vla: Towards universal humanoid control with visual integration. arXiv preprint arXiv:2502.14795 (2025)"},{"key":"8_CR8","unstructured":"Dong, Y., et al.: A survey on code generation with LLM-based agents. arXiv preprint arXiv:2508.00083 (2025)"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Wang, C., Gou, M., Lu, C.: Graspnet-1billion: a large-scale benchmark for general object grasping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11444\u201311453 (2020)","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Fang, K., Liu, F., Abbeel, P., Levine, S.: Moka: open-world robotic manipulation through mark-based visual prompting. Robot. Sci. Syst. (2024)","DOI":"10.15607\/RSS.2024.XX.062"},{"key":"8_CR11","unstructured":"Fu, Z., Zhao, T.Z., Finn, C.: Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation. arXiv preprint arXiv:2401.02117 (2024)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"He, T., et al.: Omnih2o: universal and dexterous human-to-humanoid whole-body teleoperation and learning. In: Conference on Robot Learning (2024)","DOI":"10.1109\/IROS58592.2024.10801984"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"He, T., et al.: Learning human-to-humanoid real-time whole-body teleoperation. In: IEEE International Conference on Intelligent Robots and Systems (2024)","DOI":"10.1109\/IROS58592.2024.10801984"},{"key":"8_CR14","unstructured":"He, T., et al.: Viral: visual sim-to-real at scale for humanoid loco-manipulation. arXiv preprint arXiv:2511.15200 (2025)"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Huang, H., Lin, F., Hu, Y., Wang, S., Gao, Y.: Copa: general robotic manipulation through spatial constraints of parts with foundation models. In: IEEE International Conference on Intelligent Robots and Systems (2024)","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"8_CR16","unstructured":"Huang, W.J., et al.: Beyond mimicry: learning whole-body human-humanoid interaction from human-human demonstrations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 30740\u201330749 (2026)"},{"key":"8_CR17","unstructured":"Huang, W., Wang, C., Li, Y., Zhang, R., Fei-Fei, L.: Rekep: spatio-temporal reasoning of relational keypoint constraints for robotic manipulation. In: Conference on Robot Learning (2024)"},{"key":"8_CR18","unstructured":"Huang, W., Wang, C., Zhang, R., Li, Y., Wu, J., Fei-Fei, L.: Voxposer: composable 3d value maps for robotic manipulation with language models. In: Conference on Robot Learning (2023)"},{"key":"8_CR19","unstructured":"Huang, W., et al.: Inner monologue: embodied reasoning through planning with language models. In: Conference on Robot Learning (2022)"},{"key":"8_CR20","unstructured":"Hyper3D: Hyper3d: Ai-powered 3d model generator (2024). https:\/\/hyper3d.ai\/. Accessed 28 Feb 2026"},{"key":"8_CR21","unstructured":"Ichter, B., et al.: Do as I can, not as I say: grounding language in robotic affordances. In: Conference on Robot Learning (2022)"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Jeon, S., Jung, M., Choi, S., Kim, B., Hwangbo, J.: Learning whole-body manipulation for quadrupedal robot. IEEE Robot. Autom. Lett. (2023)","DOI":"10.1109\/LRA.2023.3335777"},{"key":"8_CR23","unstructured":"Jiang, H., et\u00a0al.: Wholebodyvla: Towards unified latent vla for whole-body loco-manipulation control. arXiv preprint arXiv:2512.11047 (2025)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Jiang, J.J., et al.: Rethinking bimanual robotic manipulation: learning with decoupled interaction framework. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12427\u201312437 (2025)","DOI":"10.1109\/ICCV51701.2025.01155"},{"key":"8_CR25","unstructured":"Jiang, J.J., et al.: Task editing for generalizable 3d visuomotor policy learning. arXiv preprint arXiv:2606.07012 (2026)"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. In: Advances in Neural Information Processing Systems (2022)","DOI":"10.52202\/068431-1613"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Li, J., Cheng, X., Huang, T., Yang, S., Qiu, R.Z., Wang, X.: Amo: adaptive motion optimization for hyper-dexterous humanoid whole-body control. arXiv preprint arXiv:2505.03738 (2025)","DOI":"10.15607\/RSS.2025.XXI.061"},{"key":"8_CR28","unstructured":"Li, J., et al.: Okami: teaching humanoid robots manipulation skills through single video imitation. In: Conference on Robot Learning (2024)"},{"key":"8_CR29","unstructured":"Li, Y., et al.: Clone: closed-loop whole-body humanoid teleoperation for long-horizon tasks. In: Conference on Robot Learning (2025)"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Liang, J., et al.: Code as policies: language model programs for embodied control. In: IEEE International Conference on Robotics and Automation (2023)","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"8_CR31","unstructured":"Lin, M., et al.: Bidexgrasp: Coordinated bimanual dexterous grasps across object geometries and sizes. arXiv preprint arXiv:2604.06589 (2026)"},{"key":"8_CR32","unstructured":"Liu, J., et al.: Trajbooster: boosting humanoid whole-body manipulation via trajectory-centric learning. arXiv preprintarXiv:2509.11839 (2025)"},{"key":"8_CR33","unstructured":"Liu, Y., et\u00a0al.: Spatial policy: guiding visuomotor robotic manipulation with spatial-aware modeling and reasoning. arXiv preprint arXiv:2508.15874 (2025)"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Easyhoi: unleashing the power of large models for reconstructing hand-object interactions in the wild. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 7037\u20137047 (2025)","DOI":"10.1109\/CVPR52734.2025.00660"},{"key":"8_CR35","unstructured":"Liu, Z., Gu, Y., Wang, Y., Xue, X., Fu, Y.: Activevla: injecting active perception into vision-language-action models for precise 3d robotic manipulation. arXiv preprint arXiv:2601.08325 (2026)"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Madaan, A., Zhou, S., Alon, U., Yang, Y., Neubig, G.: Language models of code are few-shot commonsense learners. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.90"},{"key":"8_CR37","unstructured":"Nai, R., et\u00a0al.: Humanoid manipulation interface: Humanoid whole-body manipulation from robot-free demonstrations. arXiv preprint arXiv:2602.06643 (2026)"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Niu, Y., et\u00a0al.: Human2locoman: Learning versatile quadrupedal manipulation with human pretraining. arXiv preprint arXiv:2506.16475 (2025)","DOI":"10.15607\/RSS.2025.XXI.122"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Pan, M., Zhang, J., Wu, T., Zhao, Y., Gao, W., Dong, H.: Omnimanip: towards general robotic manipulation via object-centric interaction primitives as spatial constraints. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.01618"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Qi, Z., et\u00a0al.: Sofar: language-grounded orientation bridges spatial reasoning and object manipulation. In: Advances in Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-2565"},{"key":"8_CR41","unstructured":"Qiu, R.Z., et al.: Humanoid policy human policy. In: Conference on Robot Learning (2025)"},{"key":"8_CR42","unstructured":"Shi, H., et al.: Spatialactor: exploring disentangled spatial representations for robust robotic manipulation. arXiv preprint arXiv:2511.09555 (2025)"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Singh, I., et al.: Progprompt: generating situated robot task plans using large language models. IEEE International Conference on Robotics and Automation (2023)","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"8_CR44","unstructured":"Su, C., Shang, W., Qian, C., Zhang, F., Cong, S.: Resemact: advancing fine-grained robotic manipulation via semantic structuring and affordance refinement. arXiv preprint arXiv:2507.18262 (2025)"},{"key":"8_CR45","unstructured":"Sun, W., Feng, L., Cao, B., Liu, Y., Jin, Y., Xie, Z.: ULC: a unified and fine-grained controller for humanoid loco-manipulation. arXiv preprint arXiv:2507.06905 (2025)"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: Mujoco: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 5026\u20135033. IEEE (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Wang, A.L., Chen, N., Lin, K.Y., Li, Y.M., Zheng, W.S.: Task-oriented 6-DoF grasp pose detection in clutters. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 5692\u20135698 IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11128749"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Wang, J., Rajabov, J., Xu, C., Zheng, Y., Wang, H.: Quadwbg: generalizable quadrupedal whole-body grasping. In: IEEE International Conference on Robotics and Automation (2025)","DOI":"10.1109\/ICRA55743.2025.11128027"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Wei, S., et al.: $$\\psi _0$$: an open foundation model towards universal humanoid loco-manipulation. In: Robotics: Science and Systems (2026)","DOI":"10.15607\/RSS.2026.XXII.021"},{"key":"8_CR50","doi-asserted-by":"publisher","first-page":"46881","DOI":"10.52202\/079017-1487","volume":"37","author":"YL Wei","year":"2024","unstructured":"Wei, Y.L., et al.: Grasp as you say: language-guided dexterous grasp generation. Adv. Neural. Inf. Process. Syst. 37, 46881\u201346907 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Wei, Y.L., et al.: Afforddexgrasp: open-set language-guided dexterous grasp with generalizable-instructive affordance. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11818\u201311828 (2025)","DOI":"10.1109\/ICCV51701.2025.01099"},{"key":"8_CR52","unstructured":"Wei, Y.L., et al.: Omnidexgrasp: generalizable dexterous grasping via foundation model and force feedback. In: IEEE International Conference on Robotics and Automation (ICRA) (2026)"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Wu, X.M., Cai, J.F., Jiang, J.J., Zheng, D., Wei, Y.L., Zheng, W.S.: An economic framework for 6-DoF grasp detection. In: European Conference on Computer Vision, pp. 357\u2013375. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-73383-3_21"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Wu, Z., Zhou, Y., Xu, X., Wang, Z., Yan, H.: Momanipvla: transferring vision-language-action models for general mobile manipulation. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.00167"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Xu, G.H., Wei, Y.L., Zheng, D., Wu, X.M., Zheng, W.S.: Dexterous grasp transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17933\u201317942 (2024)","DOI":"10.1109\/CVPR52733.2024.01698"},{"key":"8_CR56","unstructured":"Xue, H., et al.: Leverb: humanoid whole-body control with latent vision-language instruction. arXiv preprint arXiv:2506.13751 (2025)"},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"Xue, Z., Deng, S., Chen, Z., Wang, Y., Yuan, Z., Xu, H.: Demogen: synthetic demonstration generation for data-efficient visuomotor policy learning. arXiv preprint arXiv:2502.16932 (2025)","DOI":"10.15607\/RSS.2025.XXI.157"},{"key":"8_CR58","unstructured":"Yang, L., et al.: Omniretarget: interaction-preserving data generation for humanoid whole-body loco-manipulation and scene interaction. arXiv preprint arXiv:2509.26633 (2025)"},{"key":"8_CR59","unstructured":"Yang, R., et\u00a0al.: Egovla: learning vision-language-action models from egocentric human videos. arXiv preprint arXiv:2507.12440 (2025)"},{"key":"8_CR60","unstructured":"Yenamandra, S., et al.: Homerobot: open-vocabulary mobile manipulation. In: Annual Conference on Robot Learning (2023)"},{"key":"8_CR61","unstructured":"Yuan, H., et al.: Being-0: a humanoid robotic agent with vision-language models and modular skills. arXiv preprint arXiv:2503.12533 (2025)"},{"key":"8_CR62","unstructured":"Yuan, W., et al.: Robopoint: a vision-language model for spatial affordance prediction for robotics. arXiv preprint arXiv:2406.10721 (2024)"},{"key":"8_CR63","unstructured":"Ze, Y., et al.: Twist: teleoperated whole-body imitation system. In: Conference on Robot Learning (2025)"},{"key":"8_CR64","doi-asserted-by":"crossref","unstructured":"Ze, Y., et al.: Generalizable humanoid manipulation with 3d diffusion policies. In: IEEE International Conference on Intelligent Robots and Systems (2025)","DOI":"10.1109\/IROS60139.2025.11246340"},{"key":"8_CR65","unstructured":"Zhang, Y., et al.: Falcon: Learning force-adaptive humanoid loco-manipulation. arXiv preprint arXiv:2505.06776 (2025)"},{"key":"8_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Unleashing humanoid reaching potential via real-world-ready skill space. IEEE Robot. Autom. Lett. (2025)","DOI":"10.1109\/LRA.2025.3645662"},{"key":"8_CR67","unstructured":"Zhao, S., et al.: Resmimic: From general motion tracking to humanoid whole-body loco-manipulation via residual learning. arXiv preprint arXiv:2510.05070 (2025)"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Zhou, J., Ma, T., Lin, K.Y., Wang, Z., Qiu, R., Liang, J.: Mitigating the human-robot domain discrepancy in visual pre-training for robotic manipulation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 22551\u201322561 (2025)","DOI":"10.1109\/CVPR52734.2025.02100"},{"key":"8_CR69","first-page":"139899","volume":"38","author":"J Zhou","year":"2026","unstructured":"Zhou, J., et al.: Exploring the limits of vision-language-action manipulation in cross-task generalization. Adv. Neural. Inf. Process. Syst. 38, 139899\u2013139927 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR70","unstructured":"Zhu, T., et\u00a0al.: Clot: closed-loop global motion tracking for whole-body humanoid teleoperation. arXiv preprint arXiv:2602.15060 (2026)"}],"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\/978-3-032-37422-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:07:40Z","timestamp":1789718860000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37422-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374219","9783032374226"],"references-count":70,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37422-6_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":"19 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"}}]}}