{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T18:38:00Z","timestamp":1794854280214,"version":"4.9.1"},"publisher-location":"Cham","reference-count":82,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373717","type":"print"},{"value":"9783032373724","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\/978-3-032-37372-4_22","type":"book-chapter","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T15:07:47Z","timestamp":1790780867000},"page":"399-417","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MA-VLA: Multi-arm Vision-Language-Action Model for\u00a0Collaboration and\u00a0Compositional Generalization"],"prefix":"10.1007","author":[{"given":"Zaibin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junlan","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongbo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changxing","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Talas","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enshen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruimao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenfei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huchuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"22_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Akinola, I., Xu, J., Carius, J., Fox, D., Narang, Y.: TacSL: a library for visuotactile sensor simulation and learning. IEEE Trans. Rob. (2025)","DOI":"10.1109\/TRO.2025.3547267"},{"key":"22_CR3","unstructured":"Black, K., et\u00a0al.: pi_0: A vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164 (2024)"},{"key":"22_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Buamanee, T., Kobayashi, M., Uranishi, Y., Takemura, H.: Bi-ACT: bilateral control-based imitation learning via action chunking with transformer. In: 2024 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), pp. 410\u2013415. IEEE (2024)","DOI":"10.1109\/AIM55361.2024.10637173"},{"key":"22_CR6","unstructured":"Cadene, R., et al.: LeRobot: An open-source library for end-to-end robot learning. arXiv preprint arXiv:2602.22818 (2026)"},{"key":"22_CR7","unstructured":"Cheang, C., et\u00a0al.: GR-3 technical report. arXiv preprint arXiv:2507.15493 (2025)"},{"key":"22_CR8","unstructured":"Chebotar, Y., et al.: Q-Transformer: scalable offline reinforcement learning via autoregressive Q-functions. In: Conference on Robot Learning, pp. 3909\u20133928. PMLR (2023)"},{"key":"22_CR9","unstructured":"Chen, T., et\u00a0al.: RoboTwin 2.0: A scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation. arXiv preprint arXiv:2506.18088 (2025)"},{"issue":"10\u201311","key":"22_CR10","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1177\/02783649241273668","volume":"44","author":"C Chi","year":"2025","unstructured":"Chi, C., et al.: Diffusion policy: visuomotor policy learning via action diffusion. Int. J. Robot. Res. 44(10\u201311), 1684\u20131704 (2025)","journal-title":"Int. J. Robot. Res."},{"key":"22_CR11","unstructured":"Dalal, M., Mandlekar, A., Garrett, C., Handa, A., Salakhutdinov, R., Fox, D.: Imitating task and motion planning with visuomotor transformers. arXiv preprint arXiv:2305.16309 (2023)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Driess, D., et al.: Knowledge insulating vision-language-action models: Train fast, run fast, generalize better. arXiv preprint arXiv:2505.23705 (2025)","DOI":"10.52202\/085713-3439"},{"issue":"2","key":"22_CR13","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TETCI.2022.3141105","volume":"6","author":"J Duan","year":"2022","unstructured":"Duan, J., Yu, S., Tan, H.L., Zhu, H., Tan, C.: A survey of embodied AI: from simulators to research tasks. IEEE Trans. Emerg. Top. Comput. Intell. 6(2), 230\u2013244 (2022)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Garcia, R., Chen, S., Schmid, C.: Towards generalizable vision-language robotic manipulation: a benchmark and LLM-guided 3D policy. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 8996\u20139002. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127315"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Gong, R., et al.: ARNOLD: a benchmark for language-grounded task learning with continuous states in realistic 3D scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20483\u201320495 (2023)","DOI":"10.1109\/ICCV51070.2023.01873"},{"key":"22_CR16","unstructured":"Gupta, A., Kumar, V., Lynch, C., Levine, S., Hausman, K.: Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning. arXiv preprint arXiv:1910.11956 (2019)"},{"key":"22_CR17","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. Adv. Neural. Inf. Process. Syst. 29 (2016)"},{"key":"22_CR18","unstructured":"Hua, P., et al.: GenSim2: Scaling robot data generation with multi-modal and reasoning LLMs. arXiv preprint arXiv:2410.03645 (2024)"},{"key":"22_CR19","unstructured":"Huang, H., et al.: OTTER: A vision-language-action model with text-aware visual feature extraction. arXiv preprint arXiv:2503.03734 (2025)"},{"key":"22_CR20","unstructured":"Im, H., Jeong, E., Fu, J., Kolobov, A., Lee, Y.: TwinVLA: Data-efficient bimanual manipulation with twin single-arm vision-language-action models. arXiv preprint arXiv:2511.05275 (2025)"},{"key":"22_CR21","unstructured":"Intelligence, P., et al.: pi0.5: a vision-language-action model with open-world generalization. arXiv preprint arXiv:2504.16054 (2025)"},{"issue":"2","key":"22_CR22","doi-asserted-by":"publisher","first-page":"3019","DOI":"10.1109\/LRA.2020.2974707","volume":"5","author":"S James","year":"2020","unstructured":"James, S., Ma, Z., Arrojo, D.R., Davison, A.J.: RLBench: the robot learning benchmark & learning environment. IEEE Robot. Autom. Lett. 5(2), 3019\u20133026 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"22_CR23","unstructured":"Jang, E., et al.: BC-Z: zero-shot task generalization with robotic imitation learning. In: Conference on Robot Learning, pp. 991\u20131002. PMLR (2022)"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Jiang, J.J., et al.: Rethinking bimanual robotic manipulation: Learning with decoupled interaction framework. arXiv preprint arXiv:2503.09186 (2025)","DOI":"10.1109\/ICCV51701.2025.01155"},{"key":"22_CR25","unstructured":"Jiang, Y., et al.: VIMA: General robot manipulation with multimodal prompts. arXiv preprint arXiv:2210.030942(3), \u00a06 (2022)"},{"key":"22_CR26","unstructured":"Kalashnikov, D., et al.: MT-Opt: Continuous multi-task robotic reinforcement learning at scale. arXiv preprint arXiv:2104.08212 (2021)"},{"key":"22_CR27","unstructured":"Karamcheti, S., Nair, S., Balakrishna, A., Liang, P., Kollar, T., Sadigh, D.: Prismatic VLMs: investigating the design space of visually-conditioned language models. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"22_CR28","unstructured":"Kim, M.J., et al.: OpenVLA: An open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Kumar, A., et al.: Pre-training for robots: Offline RL enables learning new tasks from a handful of trials. arXiv preprint arXiv:2210.05178 (2022)","DOI":"10.15607\/RSS.2023.XIX.019"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Lai, M., et al.: RoboBallet: planning for multirobot reaching with graph neural networks and reinforcement learning. Sci. Robot. 10(106), eads1204 (2025)","DOI":"10.1126\/scirobotics.ads1204"},{"key":"22_CR31","unstructured":"Lee, A., Chuang, I., Chen, L.Y., Soltani, I.: InterACT: Inter-dependency aware action chunking with hierarchical attention transformers for bimanual manipulation. arXiv preprint arXiv:2409.07914 (2024)"},{"key":"22_CR32","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Li, P., et al.: BridgeVLA: Input-output alignment for efficient 3D manipulation learning with vision-language models. arXiv preprint arXiv:2506.07961 (2025)","DOI":"10.52202\/085713-2137"},{"key":"22_CR34","unstructured":"Li, X., et al.: Evaluating real-world robot manipulation policies in simulation. arXiv preprint arXiv:2405.05941 (2024)"},{"key":"22_CR35","unstructured":"Li, Y., et al.: HAMSTER: Hierarchical action models for open-world robot manipulation. arXiv preprint arXiv:2502.05485 (2025)"},{"key":"22_CR36","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"22_CR37","doi-asserted-by":"publisher","first-page":"44776","DOI":"10.52202\/075280-1939","volume":"36","author":"B Liu","year":"2023","unstructured":"Liu, B., et al.: LIBERO: benchmarking knowledge transfer for lifelong robot learning. Adv. Neural. Inf. Process. Syst. 36, 44776\u201344791 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR38","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."},{"key":"22_CR39","unstructured":"Liu, J., et\u00a0al.: HybridVLA: Collaborative diffusion and autoregression in a unified vision-language-action model. arXiv preprint arXiv:2503.10631 (2025)"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Lu, G., Yu, T., Deng, H., Chen, S.S., Tang, Y., Wang, Z.: AnyBimanual: transferring unimanual policy for general bimanual manipulation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13662\u201313672 (2025)","DOI":"10.1109\/ICCV51701.2025.01268"},{"key":"22_CR41","unstructured":"Ma, Y., Song, Z., Zhuang, Y., Hao, J., King, I.: A survey on vision-language-action models for embodied AI. arXiv preprint arXiv:2405.14093 (2024)"},{"key":"22_CR42","unstructured":"Mandlekar, A., Xu, D., Mart\u00edn-Mart\u00edn, R., Savarese, S., Fei-Fei, L.: Learning to generalize across long-horizon tasks from human demonstrations. arXiv preprint arXiv:2003.06085 (2024)"},{"issue":"3","key":"22_CR43","doi-asserted-by":"publisher","first-page":"7327","DOI":"10.1109\/LRA.2022.3180108","volume":"7","author":"O Mees","year":"2022","unstructured":"Mees, O., Hermann, L., Rosete-Beas, E., Burgard, W.: CALVIN: a benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks. IEEE Robot. Autom. Lett. 7(3), 7327\u20137334 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"22_CR44","unstructured":"Minsky, M.: Society of mind, Simon and Schuster (1986)"},{"key":"22_CR45","unstructured":"Mu, T., et al.: ManiSkill: Generalizable manipulation skill benchmark with large-scale demonstrations. arXiv preprint arXiv:2107.14483 (2021)"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Mu, Y., et al.: RoboTwin: dual-arm robot benchmark with generative digital twins (early version). In: European Conference on Computer Vision, pp. 264\u2013273. Springer (2024)","DOI":"10.1007\/978-3-031-91813-1_17"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Nasiriany, S., et al.: RoboCasa: Large-scale simulation of everyday tasks for generalist robots. arXiv preprint arXiv:2406.02523 (2024)","DOI":"10.15607\/RSS.2024.XX.050"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Osa, T., Pajarinen, J., Neumann, G., Bagnell, J.A., Abbeel, P., Peters, J., et\u00a0al.: An algorithmic perspective on imitation learning. Found. Trends\u00ae Robot. 7(1-2), 1\u2013179 (2018)","DOI":"10.1561\/2300000053"},{"key":"22_CR49","unstructured":"O\u2019Neill, A., et\u00a0al.: Open X-embodiment: robotic learning datasets and RT-X models: open x-embodiment collaboration 0. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 6892\u20136903. IEEE (2024)"},{"key":"22_CR50","doi-asserted-by":"crossref","unstructured":"Papagiannis, G., Li, Y.: Imitation learning with Sinkhorn distances. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 116\u2013131. Springer (2022)","DOI":"10.1007\/978-3-031-26412-2_8"},{"key":"22_CR51","doi-asserted-by":"crossref","unstructured":"Pertsch, K., et al.: FAST: Efficient action tokenization for vision-language-action models. arXiv preprint arXiv:2501.09747 (2025)","DOI":"10.15607\/RSS.2025.XXI.012"},{"key":"22_CR52","doi-asserted-by":"crossref","unstructured":"Pumacay, W., Singh, I., Duan, J., Krishna, R., Thomason, J., Fox, D.: The colosseum: A benchmark for evaluating generalization for robotic manipulation. arXiv preprint arXiv:2402.08191 (2024)","DOI":"10.15607\/RSS.2024.XX.133"},{"key":"22_CR53","doi-asserted-by":"crossref","unstructured":"Qi, Z., et\u00a0al.: SoFar: Language-grounded orientation bridges spatial reasoning and object manipulation. arXiv preprint arXiv:2502.13143 (2025)","DOI":"10.52202\/085713-2565"},{"key":"22_CR54","doi-asserted-by":"crossref","unstructured":"Qin, Y., et al.: RoboFactory: Exploring embodied agent collaboration with compositional constraints. arXiv preprint arXiv:2503.16408 (2025)","DOI":"10.1109\/ICCV51701.2025.00939"},{"key":"22_CR55","unstructured":"Qin, Y., et\u00a0al.: WorldSimBench: Towards video generation models as world simulators. arXiv preprint arXiv:2410.18072 (2024)"},{"key":"22_CR56","doi-asserted-by":"crossref","unstructured":"Qu, D., et\u00a0al.: SpatialVLA: Exploring spatial representations for visual-language-action model. arXiv preprint arXiv:2501.15830 (2025)","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"22_CR57","unstructured":"Shi, L.X., et al.: Hi Robot: Open-ended instruction following with hierarchical vision-language-action models. arXiv preprint arXiv:2502.19417 (2025)"},{"key":"22_CR58","unstructured":"Tan, H., et\u00a0al.: RoboBrain 2.5: Depth in sight, time in mind. arXiv preprint arXiv:2601.14352 (2026)"},{"key":"22_CR59","doi-asserted-by":"crossref","unstructured":"Tao, S., et\u00a0al.: ManiSkill3: GPU parallelized robotics simulation and rendering for generalizable embodied AI. arXiv preprint arXiv:2410.00425 (2024)","DOI":"10.15607\/RSS.2025.XXI.021"},{"key":"22_CR60","unstructured":"Team, B.R., et\u00a0al.: RoboBrain 2.0 technical report. arXiv preprint arXiv:2507.02029 (2025)"},{"key":"22_CR61","unstructured":"Team, G.R., et al.: Gemini robotics: Bringing AI into the physical world. arXiv preprint arXiv:2503.20020 (2025)"},{"key":"22_CR62","unstructured":"Team, O.M., et al.: Octo: An open-source generalist robot policy. arXiv preprint arXiv:2405.12213 (2024)"},{"key":"22_CR63","unstructured":"Touvron, H., et al.: LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"22_CR64","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"22_CR65","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhu, H., Liu, M., Yang, J., Fang, H.S., He, T.: VQ-VLA: Improving vision-language-action models via scaling vector-quantized action tokenizers. arXiv preprint arXiv:2507.01016 (2025)","DOI":"10.1109\/ICCV51701.2025.01032"},{"key":"22_CR66","unstructured":"Wang, Y.R., et al.: RoboEval: Where robotic manipulation meets structured and scalable evaluation. arXiv preprint arXiv:2507.00435 (2025)"},{"key":"22_CR67","unstructured":"Wen, J., Zhu, Y., Li, J., Tang, Z., Shen, C., Feng, F.: DexVLA: Vision-language model with plug-in diffusion expert for general robot control. arXiv preprint arXiv:2502.05855 (2025)"},{"key":"22_CR68","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, pp. 1714\u20131723 (2025)","DOI":"10.1109\/CVPR52734.2025.00167"},{"key":"22_CR69","unstructured":"Yang, R., et\u00a0al.: EmbodiedBench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents. arXiv preprint arXiv:2502.09560 (2025)"},{"key":"22_CR70","unstructured":"Yenamandra, S., et al.: HomeRobot: Open-vocabulary mobile manipulation. arXiv preprint arXiv:2306.11565 (2023)"},{"key":"22_CR71","unstructured":"Yu, S., et\u00a0al.: How far are VLMs from visual spatial intelligence? A benchmark-driven perspective. arXiv preprint arXiv:2509.18905 (2025)"},{"key":"22_CR72","unstructured":"Yu, T., et al.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Conference on Robot Learning, pp. 1094\u20131100. PMLR (2020)"},{"key":"22_CR73","doi-asserted-by":"crossref","unstructured":"Ze, Y., Zhang, G., Zhang, K., Hu, C., Wang, M., Xu, H.: 3D diffusion policy: Generalizable visuomotor policy learning via simple 3D representations. arXiv preprint arXiv:2403.03954 (2024)","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"22_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, J., et\u00a0al.: 4D-VLA: Spatiotemporal vision-language-action pretraining with cross-scene calibration. arXiv preprint arXiv:2506.22242 (2025)","DOI":"10.52202\/085713-1139"},{"key":"22_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, W., et\u00a0al.: DreamVLA: a vision-language-action model dreamed with comprehensive world knowledge. arXiv preprint arXiv:2507.04447 (2025)","DOI":"10.52202\/085713-0818"},{"key":"22_CR76","doi-asserted-by":"crossref","unstructured":"Zhao, Q., et al.: CoT-VLA: visual chain-of-thought reasoning for vision-language-action models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1702\u20131713 (2025)","DOI":"10.1109\/CVPR52734.2025.00166"},{"key":"22_CR77","doi-asserted-by":"crossref","unstructured":"Zhao, T.Z., Kumar, V., Levine, S., Finn, C.: Learning fine-grained bimanual manipulation with low-cost hardware. arXiv preprint arXiv:2304.13705 (2023)","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"22_CR78","first-page":"28404","volume":"38","author":"E Zhou","year":"2026","unstructured":"Zhou, E., et al.: RoboRefer: towards spatial referring with reasoning in vision-language models for robotics. Adv. Neural. Inf. Process. Syst. 38, 28404\u201328481 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR79","unstructured":"Zhou, E., et\u00a0al.: RoboTracer: Mastering spatial trace with reasoning in vision-language models for robotics. arXiv preprint arXiv:2512.13660 (2025)"},{"key":"22_CR80","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Zhu, Y., Wen, J., Shen, C., Xu, Y.: Vision-language-action model with open-world embodied reasoning from pretrained knowledge. arXiv preprint arXiv:2505.21906 (2025)","DOI":"10.52202\/085713-1518"},{"key":"22_CR81","unstructured":"Zhu, Y., et al.: robosuite: A modular simulation framework and benchmark for robot learning. arXiv preprint arXiv:2009.12293 (2020)"},{"key":"22_CR82","unstructured":"Zitkovich, B., et\u00a0al.: RT-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning, pp. 2165\u20132183. PMLR (2023)"}],"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\/978-3-032-37372-4_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T15:08:03Z","timestamp":1790780883000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37372-4_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373717","9783032373724"],"references-count":82,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37372-4_22","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-3-032-37372-4","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 October 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"}}]}}