{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:59:06Z","timestamp":1781294346904,"version":"3.54.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFF0905500"],"award-info":[{"award-number":["2023YFF0905500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of Heilong Jiang","award":["2022ZX01A11"],"award-info":[{"award-number":["2022ZX01A11"]}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","award":["LH2023F001"],"award-info":[{"award-number":["LH2023F001"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ZTE Industry-University-Institute Cooperation Funds","award":["2022H2ZTE02-01-P4"],"award-info":[{"award-number":["2022H2ZTE02-01-P4"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tsc.2025.3623300","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:50:04Z","timestamp":1760982604000},"page":"1816-1829","source":"Crossref","is-referenced-by-count":0,"title":["Joint Optimization of Fine-Grained Representation and Workflow Orchestration in Metaverse Articulated Manipulation Auto-Generation by VLA Method"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4189-1657","authenticated-orcid":false,"given":"Ruihan","family":"Hu","sequence":"first","affiliation":[{"name":"National Pilot School of Software, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2204-0536","authenticated-orcid":false,"given":"Xiangdong","family":"He","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0096-7974","authenticated-orcid":false,"given":"Feiyang","family":"Huang","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxing","family":"Zhao","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5550-1478","authenticated-orcid":false,"given":"Xinrui","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9084-7373","authenticated-orcid":false,"given":"Zhongjie","family":"Wang","sequence":"additional","affiliation":[{"name":"National Pilot School of Software, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS60048.2023.00037"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3341988"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3436705"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00684"},{"issue":"3","key":"ref5","first-page":"71","article-title":"Key techniques and challenges in NeRF-based dynamic 3D reconstruction","volume":"23","author":"Lu","year":"2025","journal-title":"ZTE Commun."},{"key":"ref6","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120495"},{"key":"ref8","volume-title":"Introduction to Robotics: Analysis, Systems, Applications","volume":"7","author":"Niku","year":"2001"},{"issue":"3","key":"ref9","first-page":"15","article-title":"VOTI: Jailbreaking vision-language models via visual obfuscation and task induction","volume":"23","author":"Zhu","year":"2025","journal-title":"ZTE Commun."},{"issue":"3","key":"ref10","first-page":"48","article-title":"StegoAgent: A generative steganography framework based on GUI agents","volume":"23","author":"Huang","year":"2025","journal-title":"ZTE Commun."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610744"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref13","article-title":"A3VLM: Actionable articulation-aware vision language model","author":"Huang","year":"2024"},{"key":"ref14","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","author":"O\u2019Neill","year":"2023"},{"key":"ref15","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref16","article-title":"OpenVLA: An open-source vision-language-action model","author":"Kim","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3524"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112125"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00674"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142397"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00358"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111177"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5954\/ICAROB.2024.OS15-4"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2025.3596891"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02214-4"},{"issue":"1090","key":"ref29","first-page":"25081","article-title":"EmbodiedGPT: Vision-language pre-training via embodied chain of thought","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mu","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3504271"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-71261-6_5"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref33","article-title":"SPHINX-X: Scaling data and parameters for a family of multi-modal large language models","author":"Liu","year":"2024"},{"key":"ref34","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref35","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"issue":"3","key":"ref36","first-page":"38","article-title":"Dataset copyright auditing for large models: Fundamentals, open problems, and future directions","volume":"23","author":"Du","year":"2025","journal-title":"ZTE-Commun."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103254"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref39","article-title":"RoboMamba: Multimodal state space model for efficient robot reasoning and manipulation","author":"Liu","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4629386\/11559165\/11207517.pdf?arnumber=11207517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:43:22Z","timestamp":1781293402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11207517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2025.3623300","relation":{},"ISSN":["1939-1374","2372-0204"],"issn-type":[{"value":"1939-1374","type":"electronic"},{"value":"2372-0204","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}