{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T20:30:00Z","timestamp":1785357000525,"version":"3.55.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225308"],"award-info":[{"award-number":["62225308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12471501"],"award-info":[{"award-number":["12471501"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sci-Tech Innovation Initiative by the Science and Technology Commission of Shanghai Municipality","award":["24ZR1419000"],"award-info":[{"award-number":["24ZR1419000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/lra.2026.3653303","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T23:58:44Z","timestamp":1768262324000},"page":"2506-2513","source":"Crossref","is-referenced-by-count":9,"title":["PointVLA: Injecting the 3D World Into Vision-Language-Action Models"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3549-1055","authenticated-orcid":false,"given":"Chengmeng","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1660-3268","authenticated-orcid":false,"given":"Junjie","family":"Wen","sequence":"additional","affiliation":[{"name":"Midea Group, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2983-555X","authenticated-orcid":false,"given":"Yaxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1312-9527","authenticated-orcid":false,"given":"Yan","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5126-838X","authenticated-orcid":false,"given":"Yichen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Midea Group, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref2","article-title":"Prismatic VLMs: Investigating the design space of visually-conditioned language models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Karamcheti","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref4","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Kim","year":"2025"},{"key":"ref5","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3544909"},{"key":"ref7","first-page":"3094","article-title":"DexVLA: Vision-language model with plug-in diffusion expert for general robot control","volume-title":"Proc. 9th Conf. Robot Learn.","author":"Wen","year":"2025"},{"key":"ref8","article-title":"CoA-VLA: Improving vision-language-action models via visual-textual chain-of-affordance","author":"Li","year":"2025"},{"key":"ref9","article-title":"Qwen2-VL: Enhancing vision-language models perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref10","article-title":"Deepseek-Vl: Towards real-world vision-language understanding","author":"Lu","year":"2024"},{"key":"ref11","article-title":"PaliGemma: A versatile 3B VLM for transfer","author":"Beyer","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i10.33194"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247088"},{"key":"ref14","article-title":"HybridVLA: Collaborative diffusion and autoregression in a unified vision-language-action model","author":"Liu","year":"2025"},{"key":"ref15","first-page":"1004","article-title":"GraspVLA: A grasping foundation model pre-trained on billion-scale synthetic action data","volume-title":"Proc. 9th Conf. Robot Learn.","author":"Deng","year":"2025"},{"key":"ref16","first-page":"6892","article-title":"Open X-Embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. IEEE Int. Conf. Robot. Autom. (ICRA)","author":"ONeill","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.120"},{"key":"ref18","first-page":"19542","article-title":"Video prediction policy: A generalist robot policy with predictive visual representations","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Hu","year":"2025"},{"key":"ref19","article-title":"Towards synergistic, generalized, and efficient dual-system for robotic manipulation","author":"Bu","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02575"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611615"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127493"},{"key":"ref24","article-title":"Data scaling laws in imitation learning for robotic manipulation","volume-title":"Proc. 13th Int. Conf. Learn. Representations (ICLR)","author":"Lin","year":"2025"},{"key":"ref25","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Kim","year":"2025"},{"key":"ref26","first-page":"3157","article-title":"Robotic control via embodied chain-of-thought reasoning","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Zawalski","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.014"},{"key":"ref28","article-title":"DistRL: An asynchronous distributed reinforcement learning framework for on-device control agents","volume-title":"Proc. 13th Int. Conf. Learn. Representations (ICLR)","author":"Wang","year":"2025"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"ref30","first-page":"20413","article-title":"An embodied generalist agent in 3D world","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Huang","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11246340"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128074"},{"key":"ref33","first-page":"4295","article-title":"LLaVA-3D: A simple yet effective pathway to empowering LMMs with 3D-awareness","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Zhu","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.941"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_42"},{"key":"ref36","article-title":"FLUX.1 Kontext: Flow matching for in-context image generation and editing in latent space","year":"2025"},{"key":"ref37","article-title":"Flux.1 Lite: Distilling flux1.dev for efficient text-to-image generation","author":"Verd","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.090"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127630"},{"key":"ref42","article-title":"FP3: A 3D foundation policy for robotic manipulation","volume-title":"Proc. 13th Int. Conf. Learn. Representations (ICLR)","author":"Yang","year":"2025"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11359420\/11346992.pdf?arnumber=11346992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:11:59Z","timestamp":1769029919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11346992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":42,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3653303","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}