{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:06:23Z","timestamp":1788937583720,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373588","type":"print"},{"value":"9783032373595","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\/978-3-032-37359-5_14","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:10:19Z","timestamp":1788934219000},"page":"242-259","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MobileManiBench: Simplifying Model Verification for\u00a0Mobile Manipulation"],"prefix":"10.1007","author":[{"given":"Wenbo","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangyun","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qixiu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaobo","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaolong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baining","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"14_CR1","unstructured":"AgiBot-World-Contributors, Bu, Q., et al.: AgiBot world colosseo: a large-scale manipulation platform for scalable and intelligent embodied systems (2025). https:\/\/arxiv.org\/abs\/2503.06669"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Bao, C., Xu, H., Qin, Y., Wang, X.: DexArt: benchmarking generalizable dexterous manipulation with articulated objects (2023). https:\/\/arxiv.org\/abs\/2305.05706","DOI":"10.1109\/CVPR52729.2023.02030"},{"key":"14_CR3","unstructured":"Beyer, L., et al.: PaliGemma: a versatile 3B VLM for transfer. arXiv preprint: arXiv:2407.07726 (2024)"},{"key":"14_CR4","unstructured":"Bjorck, J., et\u00a0al.: GR00t N1: an open foundation model for generalist humanoid robots. arXiv preprint: arXiv:2503.14734 (2025)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Black, K., et\u00a0al.: $$\\pi _0$$: a vision-language-action flow model for general robot control (2024). arXiv:2410.24164","DOI":"10.15607\/RSS.2025.XXI.010"},{"key":"14_CR6","unstructured":"Brohan, A., et al.: RT-1: robotics transformer for real-world control at scale. arXiv:2212.06817 (2022)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Calli, B., Singh, A., Walsman, A., Srinivasa, S.S., Abbeel, P., Dollar, A.M.: The YCB object and model set: towards common benchmarks for manipulation research. In: Proceedings of the IEEE International Conference on Advanced Robotics (ICAR), pp. 510\u2013517 (2015)","DOI":"10.1109\/ICAR.2015.7251504"},{"key":"14_CR8","unstructured":"Cheang, C., et\u00a0al.: GR-3 technical report. arXiv preprint: arXiv:2507.15493 (2025)"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: OWMM-agent: open world mobile manipulation with multi-modal agentic data synthesis. https:\/\/arxiv.org\/abs\/2506.04217 (2025)","DOI":"10.52202\/085713-4330"},{"key":"14_CR10","unstructured":"Chen, T., et al.: RoboTwin 2.0: a scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation (2025). https:\/\/arxiv.org\/abs\/2506.18088"},{"key":"14_CR11","unstructured":"Chen, X., et al.: PaLI-X: on scaling up a multilingual vision and language model. arXiv preprint: arXiv:2305.18565 (2023)"},{"key":"14_CR12","unstructured":"Driess, D., et al.: PaLM-E: an embodied multimodal language model (2023)"},{"key":"14_CR13","unstructured":"Fu, Z., Zhao, T.Z., Finn, C.: Mobile ALOHA: learning bimanual mobile manipulation with low-cost whole-body teleoperation (2024). https:\/\/arxiv.org\/abs\/2401.02117"},{"key":"14_CR14","unstructured":"Gu, J., et al.: ManiSkill2: a unified benchmark for generalizable manipulation skills (2023). https:\/\/arxiv.org\/abs\/2302.04659"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Han, S., et al.: RoboCerebra: a large-scale benchmark for long-horizon robotic manipulation evaluation (2025). https:\/\/arxiv.org\/abs\/2506.06677","DOI":"10.52202\/085713-4031"},{"key":"14_CR16","unstructured":"Huang, W., Wang, C., Li, Y., Zhang, R., Fei-Fei, L.: ReKep: spatio-temporal reasoning of relational keypoint constraints for robotic manipulation (2024). https:\/\/arxiv.org\/abs\/2409.01652"},{"key":"14_CR17","unstructured":"Intelligence, P., et\u00a0al.: $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization (2025). arXiv:2504.16054"},{"key":"14_CR18","unstructured":"James, S., Ma, Z., Arrojo, D.R., Davison, A.J.: RLBench: the robot learning benchmark & learning environment (2019). https:\/\/arxiv.org\/abs\/1909.12271"},{"key":"14_CR19","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":"14_CR20","unstructured":"Khazatsky, A., et al.: DROID: a large-scale in-the-wild robot manipulation dataset (2025). https:\/\/arxiv.org\/abs\/2403.12945"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Kim, M.J., Finn, C., Liang, P.: Fine-tuning vision-language-action models: optimizing speed and success (2025). arXiv:2502.19645","DOI":"10.15607\/RSS.2025.XXI.017"},{"key":"14_CR22","unstructured":"Kim, M.J., et al.: OpenVLA: an open-source vision-language-action model (2024). arXiv:2406.09246"},{"key":"14_CR23","unstructured":"Li, C., et al.: BEHAVIOR-1K: a human-centered, embodied ai benchmark with 1,000 everyday activities and realistic simulation (2024). https:\/\/arxiv.org\/abs\/2403.09227"},{"key":"14_CR24","unstructured":"Li, Q., et\u00a0al.: Scalable vision-language-action model pretraining for robotic manipulation with real-life human activity videos. arXiv preprint: arXiv:2510.21571 (2025)"},{"key":"14_CR25","unstructured":"Li, Q., et\u00a0al.: CogACT: a foundational vision-language-action model for synergizing cognition and action in robotic manipulation (2024). arXiv:2411.19650"},{"key":"14_CR26","unstructured":"Li, X., et\u00a0al.: Vision-language foundation models as effective robot imitators. In: ICLR (2022)"},{"key":"14_CR27","unstructured":"Li, X., et al.: Evaluating real-world robot manipulation policies in simulation. arXiv preprint: arXiv:2405.05941 (2024)"},{"key":"14_CR28","unstructured":"Li, Y., et al.: UniDoorManip: learning universal door manipulation policy over large-scale and diverse door manipulation environments (2024). https:\/\/arxiv.org\/abs\/2403.02604"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Liu, B., et al.: LIBERO: benchmarking knowledge transfer for lifelong robot learning (2023). https:\/\/arxiv.org\/abs\/2306.03310","DOI":"10.52202\/075280-1939"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"14_CR31","unstructured":"Liu, S., et al.: RDT-1B: a diffusion foundation model for bimanual manipulation. ICLR (2025)"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Mees, O., Hermann, L., Rosete-Beas, E., Burgard, W.: CALVIN: a benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks (2022). https:\/\/arxiv.org\/abs\/2112.03227","DOI":"10.1109\/LRA.2022.3180108"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Nasiriany, S., et al.: RoboCasa: large-scale simulation of everyday tasks for generalist robots (2024). https:\/\/arxiv.org\/abs\/2406.02523","DOI":"10.15607\/RSS.2024.XX.050"},{"key":"14_CR34","unstructured":"NVIDIA: Isaac Sim. https:\/\/github.com\/isaac-sim\/IsaacSim"},{"key":"14_CR35","unstructured":"O\u2019Neill, A., et\u00a0al.: Open X-Embodiment: Robotic learning datasets and RT-X models. In: ICRA (2024)"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Qu, D., et al.: SpatialVLA: exploring spatial representations for visual-language-action model (2025). arXiv:2501.15830","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"14_CR37","unstructured":"ROBOTERA: XHAND (2025). https:\/\/www.robotera.com\/en\/"},{"key":"14_CR38","unstructured":"Robotics, A.: AGIBOT G1 mobile manipulator (2025). https:\/\/www.agibot.com\/products\/G1"},{"key":"14_CR39","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017). https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"14_CR40","unstructured":"Shi, H., et al.: MemoryVLA: perceptual-cognitive memory in vision-language-action models for robotic manipulation. arXiv preprint: arXiv:2508.19236 (2025)"},{"key":"14_CR41","unstructured":"Steiner, A., et al.: PaliGemma 2: a family of versatile VLMs for transfer. arXiv preprint: arXiv:2412.03555 (2024)"},{"key":"14_CR42","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models (2023). arXiv:2312.11805"},{"key":"14_CR43","unstructured":"Team, G.R., et al.: Gemini robotics: bringing ai into the physical world. arXiv preprint: arXiv:2503.20020 (2025)"},{"key":"14_CR44","unstructured":"Team, G., et al.: Gemma 2: improving open language models at a practical size. arXiv preprint: arXiv:2408.00118 (2024)"},{"key":"14_CR45","unstructured":"Team, G.S.: Genie sim assets (2025). https:\/\/github.com\/AgibotTech\/genie_sim"},{"key":"14_CR46","unstructured":"Team, O.M., et al.: Octo: an open-source generalist robot policy (2024). arXiv:2405.12213"},{"key":"14_CR47","unstructured":"Wang, H., et al.: GRUtopia: dream general robots in a city at scale (2024). https:\/\/arxiv.org\/abs\/2407.10943"},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Wang, W., Li, G., Zamora, M., Coros, S.: TRTM: template-based reconstruction and target-oriented manipulation of crumpled cloths (2024). https:\/\/arxiv.org\/abs\/2308.04670","DOI":"10.1109\/ICRA57147.2024.10609868"},{"key":"14_CR49","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: UniGraspTransformer: simplified policy distillation for scalable dexterous robotic grasping (2025). https:\/\/arxiv.org\/abs\/2412.02699","DOI":"10.1109\/CVPR52734.2025.01139"},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Unified vision-language-action model (2025). arXiv:2506.19850","DOI":"10.5772\/intechopen.1014640"},{"key":"14_CR51","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. In: CoRL (2025)"},{"key":"14_CR52","unstructured":"Xiang, F., et\u00a0al.: PartNet-Mobility: a large-scale database for articulated objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11359\u201311368 (2020)"},{"key":"14_CR53","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Magma: a foundation model for multimodal ai agents. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 14203\u201314214 (2025)","DOI":"10.1109\/CVPR52734.2025.01325"},{"key":"14_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, H., Christen, S., Fan, Z., Hilliges, O., Song, J.: GraspXL: generating grasping motions for diverse objects at scale. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-73347-5_22"},{"key":"14_CR55","unstructured":"Zhang, S., et al.: VLABench: a large-scale benchmark for language-conditioned robotics manipulation with long-horizon reasoning tasks (2024). https:\/\/arxiv.org\/abs\/2412.18194"},{"key":"14_CR56","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":"14_CR57","unstructured":"Zhao, Z., et al.: Humanoid everyday: a comprehensive robotic dataset for open-world humanoid manipulation (2025). https:\/\/arxiv.org\/abs\/2510.08807"},{"key":"14_CR58","unstructured":"Zhong, Y., et al.: DexGraspVLA: a vision-language-action framework towards general dexterous grasping (2025). arXiv:2502.20900"},{"key":"14_CR59","unstructured":"Zhu, Y., et al.: robosuite: a modular simulation framework and benchmark for robot learning. arXiv preprint: arXiv:2009.12293 (2020)"},{"key":"14_CR60","unstructured":"Zitkovich, B., et\u00a0al.: RT-2: vision-language-action models transfer web knowledge to robotic control. In: CoRL (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\/978-3-032-37359-5_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:10:31Z","timestamp":1788934231000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37359-5_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373588","9783032373595"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37359-5_14","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":"10 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"}}]}}