{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:31:07Z","timestamp":1791567067414,"version":"4.3.4"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373823","type":"print"},{"value":"9783032373830","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\/978-3-032-37383-0_20","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:20:00Z","timestamp":1789374000000},"page":"336-353","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["VLA-R1: Enhancing Reasoning in\u00a0Vision-Language-Action Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7999-2474","authenticated-orcid":false,"given":"Angen","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dapeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"20_CR1","unstructured":"Abdin, M., et al.: Phi-4 technical report (2024). arXiv:2412.08905 arXiv preprint"},{"issue":"1","key":"20_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/0278364919887447","volume":"39","author":"M Andrychowicz","year":"2020","unstructured":"Andrychowicz, M., Baker, B., Chociej, M., et al.: Learning dexterous in-hand manipulation. Int. J. Robot. Res. 39(1), 3\u201320 (2020)","journal-title":"Int. J. Robot. Res."},{"key":"20_CR3","unstructured":"Azzolini, A., Brandon, H., Chattopadhyay, P., et al.: Cosmos-reason1: from physical common sense to embodied reasoning. arXiv preprint arXiv:2503.15558 (2025)"},{"key":"20_CR4","unstructured":"Bai, J., Bai, S., Chu, Y., et al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"20_CR5","unstructured":"Bai, S., Chen, K., Liu, X., Wang, J., et al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"20_CR6","unstructured":"Bai, S., Chen, K., Liu, X., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"20_CR7","unstructured":"Brohan, A., Brown, N., Carbajal, J., Chebotar, Y., et al.: Rt-2: Visionlanguage-action models transfer web knowledge to robotic control. arXiv preprint arXiv:2307.15818 (2023)"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"issue":"1","key":"20_CR9","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1146\/annurev-control-091420-084139","volume":"4","author":"CR Garrett","year":"2021","unstructured":"Garrett, C.R., Chitnis, R., Holladay, R., Kim, B., Silver, T., Kaelbling, L.P., Lozano-P\u00e9rez, T.: Integrated task and motion planning. Annu. Rev. Cont. Robot. Autonomous Syst. 4(1), 265\u2013293 (2021)","journal-title":"Annu. Rev. Cont. Robot. Autonomous Syst."},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Geng, Y., An, B., Geng, H., et al.: Rlafford: End-to-end affordance learning for robotic manipulation. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 5880\u20135886 (2023)","DOI":"10.1109\/ICRA48891.2023.10161571"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for roboticmanipulation with asynchronous off-policy updates. In: 2017 IEEE international conference on robotics and automation (ICRA), pp. 3389\u20133396. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"20_CR12","unstructured":"Guo, D., Yang, D., Zhang, H., et al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"20_CR13","unstructured":"Huang, T., Zhang, Z., Zhang, R., Zhao, Y.: Dc-scene: data-centric learning for 3d scene understanding. arXiv preprint arXiv:2505.15232 (2025)"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Huang, T., Zhang, Z., et al.: 3d coca: contrastive learners are 3d captioners. arXiv preprint arXiv:2504.09518 (2025)","DOI":"10.1109\/3DV69130.2026.00168"},{"key":"20_CR15","unstructured":"Huang, W., Wang, C., Zhang, R., Li, Y., et al.: Voxposer: composable 3d value maps for robotic manipulation with language models. In: Proceedings of the Conference on Robot Learning (CoRL). Proceedings of Machine Learning Research, vol. 229, pp. 540\u2013562 (2023)"},{"key":"20_CR16","unstructured":"Huang, W., Jia, B., Zhai, Z., Cao, S., et al.: Vision-r1: incentivizing reasoning capability in multimodal large language models. arXiv preprint arXiv:2503.06749 (2025)"},{"key":"20_CR17","unstructured":"Hung, C.Y., et al.: Nora: a small open-sourced generalist vision language action model for embodied tasks. arXiv preprint arXiv:2504.19854 (2025)"},{"key":"20_CR18","unstructured":"Intelligence, P., et al.: $$pi$$0. 5: a vision-language-action model with open-world generalization (2025). arXiv preprint arXiv:2504.16054 (2025)"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Ji, Y., Tan, H., Shi, J., Hao, X., et al.: Robobrain: a unified brain model for robotic manipulation from abstract to concrete. arXiv preprint arXiv:2502.21257 (2025)","DOI":"10.1109\/CVPR52734.2025.00168"},{"key":"20_CR20","unstructured":"Kim, M.J., et al.: Openvla: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"20_CR21","unstructured":"Kim, M.J., et al.: Openvla: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"20_CR22","unstructured":"Li, B., Zhang, Y., Guo, D., et al.: Llava-onevision: easy visual task transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, M., Geng, Y., et al.: Manipllm: Embodied multimodal large language model for object-centric robotic manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 18061\u201318070 (2024)","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"20_CR24","unstructured":"Li, X., Liu, M., Zhang, H., Yu, et al.: Vision-language foundation models as effective robot imitators. arXiv preprint arXiv:2311.01378 (2023)"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 36 (2024)","DOI":"10.52202\/075280-1516"},{"key":"20_CR27","unstructured":"Liu, J., Liu, M., Wang, Z., Lee, et al.: Robomamba: multimodal state space model for efficient robot reasoning and manipulation. arXiv preprint arXiv:2406.04339 (2024)"},{"key":"20_CR28","unstructured":"Liu, S., Wu, L., Li, B., et al.: RDT-1b: a diffusion foundation model for bimanual manipulation. arXiv preprint arXiv:2410.07864 (2024)"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Myers, A., Teo, C.L., Ferm\u00fcller, C., Aloimonos, Y.: Affordance detection of tool parts from geometric features. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 1374\u20131381. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"20_CR30","unstructured":"Niu, D., Sharma, Y., Biamby, G., Quenum, J., et al.: LLARVA: vision-action instruction tuning enhances robot learning. arXiv preprint arXiv:2406.11815 (2024)"},{"key":"20_CR31","unstructured":"O\u2019Neill, A., Rehman, A., Maddukuri, A., et al.: Open X-Embodiment: Robotic learning datasets and RT-X models. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 6892\u20136903. IEEE (2024)"},{"key":"20_CR32","unstructured":"Peng, Y., Zhang, G., Zhang, M., et al.: LMM-r1: empowering 3b LMMs ITH strong reasoning abilities through two-stage rule-based rl. arXiv preprintarXiv:2503.07536 (2025)"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: roceedings of the IEEE\/CVF conference on computer vision and pattern recognition,pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"20_CR34","unstructured":"Shao, Z., et al.: Deepseekmath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"20_CR35","unstructured":"Shen, H., Liu, P., Li, J., et al.: VLM-r1: a stable and generalizable r1-style large vision-language model. arXiv preprint arXiv:2504.07615 (2025)"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Song, Z., Ouyang, G., Li, M., et al.: Maniplvm-r1: reinforcement learning for reasoning in embodied manipulation with large vision-language models. arXiv preprint arXiv:2505.16517 (2025)","DOI":"10.1609\/aaai.v40i22.38922"},{"key":"20_CR37","unstructured":"Team, G., et\u00a0al.: Gemma 3 technical report (2025)"},{"key":"20_CR38","unstructured":"Vuong, Q., et al.: Open x-emdiment: robobotic learning datasets and rt-x models. In: Towards Generalist Robots: learning Paradigms for Scalable Skill Acquisition@ CoRL2023 (2023)"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Wan, W., Geng, H., Liu, et al.: Unidexgrasp++: improving dexterous grasping policy learning via geometry-aware curriculum and iterative generalist-specialist learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3891\u20133902 (2023)","DOI":"10.1109\/ICCV51070.2023.00360"},{"key":"20_CR40","unstructured":"Wang, B., et al.: Embodiedreamer: advancing real2sim2real transfer for policy training via embodied world modeling. arXiv preprint arXiv:2507.05198 (2025)"},{"key":"20_CR41","unstructured":"Wang, P., Bai, S., Tan, S.: Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution (2024). arXiv:2409.12191 arXiv preprint"},{"key":"20_CR42","unstructured":"Wang, Q., Zhang, H., Deng, C., You, Y.: Sparsedff: sparse-view feature distillation for one-shot dexterous manipulation (2023). arXiv:2310.16838 arXiv preprint"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Yan, H., et\u00a0al.: S-VAM: shortcut video-action model by self-distilling geometric and semantic foresight. arXiv preprint arXiv:2603.16195 (2026)","DOI":"10.1007\/978-3-032-37035-8_36"},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Ye, A., Song, Y., Su, J., Zhang, D.: Non-invasive spatial registration using customized dental bracket and improved genetic algorithms. In: 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE), pp. 3250\u20133255. IEEE (2024)","DOI":"10.1109\/CASE59546.2024.10711377"},{"key":"20_CR45","unstructured":"Yuan, Y., et al.: Embodied-r1: reinforced embodied reasoning for general robotic manipulation (2025). arXiv:2508.13998 arXiv preprint"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, W., Wang, M., Liu, G.: Embodied-reasoner: synergizing visual search, reasoning, and action for embodied interactive tasks (2025). arXiv:2503.21696 arXiv preprint","DOI":"10.18653\/v1\/2026.acl-long.1910"}],"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\/978-3-032-37383-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:20:33Z","timestamp":1789374033000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37383-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373823","9783032373830"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37383-0_20","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"}}]}}