{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:02:39Z","timestamp":1790276559192,"version":"4.1.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369833","type":"print"},{"value":"9783032369840","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\/978-3-032-36984-0_35","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:56:51Z","timestamp":1790276211000},"page":"638-655","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RL from\u00a0Physical Feedback: Aligning Large Motion Models with\u00a0Humanoid Control"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6822-3366","authenticated-orcid":false,"given":"Junpeng","family":"Yue","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zepeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinrun","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziluo","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sipeng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangxing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3967-2704","authenticated-orcid":false,"given":"Zongqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Fan, K., et al.: Go to zero: towards zero-shot motion generation with million-scale data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 13336\u201313348 (2025)","DOI":"10.1109\/ICCV51701.2025.01239"},{"key":"35_CR2","unstructured":"Fu, Z., Zhao, Q., Wu, Q., Wetzstein, G., Finn, C.: Humanplus: humanoid shadowing and imitation from humans. arXiv preprint arXiv:2406.10454 (2024)"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3d human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"35_CR4","unstructured":"Guo, D., et\u00a0al.: Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Han, G., Liang, M., Tang, J., Cheng, Y., Liu, W., Huang, S.: Reindiffuse: crafting physically plausible motions with reinforced diffusion model. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2218\u20132227. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00222"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"He, T., et\u00a0al.: Asap: Aligning simulation and real-world physics for learning agile humanoid whole-body skills. arXiv preprint arXiv:2502.01143 (2025)","DOI":"10.15607\/RSS.2025.XXI.066"},{"key":"35_CR7","unstructured":"He, T., et al.: Omnih2o: universal and dexterous human-to-humanoid whole-body teleoperation and learning. In: Conference on Robot Learning, pp. 1516\u20131540. PMLR (2025)"},{"key":"35_CR8","unstructured":"Ji, M., et al.: Exbody2: Advanced expressive humanoid whole-body control. arXiv preprint arXiv:2412.13196 (2024)"},{"key":"35_CR9","doi-asserted-by":"publisher","first-page":"20067","DOI":"10.52202\/075280-0880","volume":"36","author":"B Jiang","year":"2023","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: Motiongpt: human motion as a foreign language. Adv. Neural. Inf. Process. Syst. 36, 20067\u201320079 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.S.: Autoregressive image generation using residual quantization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11523\u201311532 (2022)","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"35_CR11","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":"35_CR12","unstructured":"Li, Z., et al.: From language to locomotion: Retargeting-free humanoid control via motion latent guidance. arXiv preprint arXiv:2510.14952 (2025)"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Liao, Q., et al.: Beyondmimic: From motion tracking to versatile humanoid control via guided diffusion. arXiv preprint arXiv:2508.08241 (2025)","DOI":"10.1126\/scirobotics.adx8924"},{"key":"35_CR14","doi-asserted-by":"publisher","first-page":"25268","DOI":"10.52202\/075280-1099","volume":"36","author":"J Lin","year":"2023","unstructured":"Lin, J., et al.: Motion-x: a large-scale 3d expressive whole-body human motion dataset. Adv. Neural. Inf. Process. Syst. 36, 25268\u201325280 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Luo, Z., Cao, J., Kitani, K., Xu, W.: Perpetual humanoid control for real-time simulated avatars. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10895\u201310904. (2023)","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: Amass: archive of motion capture as surface shapes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5442\u20135451 (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"35_CR17","unstructured":"Makoviychuk, V., et al.: Isaac gym: High performance gpu-based physics simulation for robot learning. arXiv preprint arXiv:2108.10470 (2021)"},{"key":"35_CR18","unstructured":"Mao, J., et al.: Learning from massive human videos for universal humanoid pose control. arXiv preprint arXiv:2412.14172 (2024)"},{"key":"35_CR19","unstructured":"Mao, Y., Liu, X., Zhou, W., Lu, Z., Li, H.: Learning generalizable human motion generator with reinforcement learning. arXiv preprint arXiv:2405.15541 (2024)"},{"key":"35_CR20","doi-asserted-by":"publisher","first-page":"27730","DOI":"10.52202\/068431-2011","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"4","key":"35_CR21","first-page":"1","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng, X.B., Abbeel, P., Levine, S., Van de Panne, M.: Deepmimic: example-guided deep reinforcement learning of physics-based character skills. ACM Trans. Graph. (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"35_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459670","volume":"40","author":"XB Peng","year":"2021","unstructured":"Peng, X.B., Ma, Z., Abbeel, P., Levine, S., Kanazawa, A.: AMP: adversarial motion priors for stylized physics-based character control. ACM Trans. Graph. (ToG) 40(4), 1\u201320 (2021)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"35_CR23","unstructured":"Ross, S., Gordon, G., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 627\u2013635. JMLR Workshop and Conference Proceedings (2011)"},{"key":"35_CR24","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"35_CR25","doi-asserted-by":"crossref","unstructured":"Serifi, A., Grandia, R., Knoop, E., Gross, M., B\u00e4cher, M.: Robot motion diffusion model: motion generation for robotic characters. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u20139 (2024)","DOI":"10.1145\/3680528.3687626"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Shao, Y., et al.: Langwbc: Language-directed humanoid whole-body control via end-to-end learning. arXiv preprint arXiv:2504.21738 (2025)","DOI":"10.15607\/RSS.2025.XXI.065"},{"key":"35_CR27","unstructured":"Shao, Z., et\u00a0al.: Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"35_CR28","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: Advances in Neural Information Processing Systems, p. 28 (2015)"},{"key":"35_CR29","first-page":"3008","volume":"33","author":"N Stiennon","year":"2020","unstructured":"Stiennon, N., et al.: Learning to summarize with human feedback. Adv. Neural. Inf. Process. Syst. 33, 3008\u20133021 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"6","key":"35_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3687951","volume":"43","author":"C Tessler","year":"2024","unstructured":"Tessler, C., Guo, Y., Nabati, O., Chechik, G., Peng, X.B.: Maskedmimic: unified physics-based character control through masked motion inpainting. ACM Trans. Graph. (TOG) 43(6), 1\u201321 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"35_CR31","doi-asserted-by":"crossref","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A.H., Cohen-Or, D.: Motionclip: exposing human motion generation to clip space. In: European Conference on Computer Vision, pp. 358\u2013374. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"35_CR32","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)"},{"key":"35_CR33","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":"35_CR34","unstructured":"Touvron, H., et al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"35_CR35","doi-asserted-by":"crossref","unstructured":"Tseng, J., Castellon, R., Liu, K.: Edge: editable dance generation from music. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 448\u2013458 (2023)","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"35_CR36","unstructured":"Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"35_CR37","unstructured":"Wang, Y., et al.: Scaling large motion models with million-level human motions. arXiv preprint arXiv:2410.03311 (2024)"},{"key":"35_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Motiongpt-2: a general-purpose motion-language model for motion generation and understanding. In: IEEE Trans. Circ. Syst. Video Technol. (2026)","DOI":"10.1109\/TCSVT.2026.3694713"},{"key":"35_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: From experts to a generalist: Toward general whole-body control for humanoid robots. arXiv preprint arXiv:2506.12779 (2025)","DOI":"10.52202\/085713-4941"},{"key":"35_CR40","unstructured":"Xue, H., et al.: Leverb: Humanoid whole-body control with latent vision-language instruction. arXiv preprint arXiv:2506.13751 (2025)"},{"key":"35_CR41","doi-asserted-by":"crossref","unstructured":"Yin, K., et al.: Unitracker: learning universal whole-body motion tracker for humanoid robots. IEEE Robot. Autom. Lett. (2026)","DOI":"10.1109\/LRA.2026.3692091"},{"key":"35_CR42","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Song, J., Iqbal, U., Vahdat, A., Kautz, J.: Physdiff: physics-guided human motion diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16010\u201316021 (2023)","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"35_CR43","unstructured":"Ze, Y., et al.: Twist: Teleoperated whole-body imitation system. arXiv preprint arXiv:2505.02833 (2025)"},{"key":"35_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Generating human motion from textual descriptions with discrete representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14730\u201314740 (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"issue":"6","key":"35_CR45","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.1109\/TPAMI.2024.3355414","volume":"46","author":"M Zhang","year":"2024","unstructured":"Zhang, M., et al.: Motiondiffuse: text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. 46(6), 4115\u20134128 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"35_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, M., et\u00a0al.: Large motion model for unified multi-modal motion generation. In: European Conference on Computer Vision, pp. 397\u2013421. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72624-8_23"}],"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\/978-3-032-36984-0_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:57:04Z","timestamp":1790276224000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36984-0_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369833","9783032369840"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36984-0_35","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":"25 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"}}]}}