{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:22:54Z","timestamp":1774419774351,"version":"3.50.1"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"GP-Mech International Joint Graduate Program, Tohoku University"},{"name":"Innovation and Technology Commission of the HKSAR Government"},{"name":"JSPS KAKENHI","award":["JP24K00841"],"award-info":[{"award-number":["JP24K00841"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/lra.2026.3674003","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T19:55:25Z","timestamp":1773431725000},"page":"5550-5557","source":"Crossref","is-referenced-by-count":0,"title":["Language-Driven Multi-Task Manipulation With Action-Mask-Enhanced Multimodal Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7032-900X","authenticated-orcid":false,"given":"Ningquan","family":"Gu","sequence":"first","affiliation":[{"name":"Neuro-Robotics Laboratory, Department of Robotics, Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7676-2656","authenticated-orcid":false,"given":"Yuquan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2060-2936","authenticated-orcid":false,"given":"Kazuhiro","family":"Kosuge","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Faculty of Engineering, The University of Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6179-5706","authenticated-orcid":false,"given":"Mitsuhiro","family":"Hayashibe","sequence":"additional","affiliation":[{"name":"Neuro-Robotics Laboratory, Department of Robotics, Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3585396"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980391"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00880"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.960"},{"key":"ref7","first-page":"3766","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","volume-title":"Proc. Conf. Robot Learn.","author":"Ha","year":"2023"},{"key":"ref8","first-page":"14590","article-title":"RoBridge: A hierarchical architecture bridging cognition and execution for general robotic manipulation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vision","author":"Zhang","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611112"},{"key":"ref10","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref11","article-title":"Language-guided long horizon manipulation with LLM-based planning and visual perception","author":"Zhou","year":"2025"},{"key":"ref12","article-title":"SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025"},{"key":"ref13","first-page":"32100","article-title":"DoRA: Weight-decomposed low-rank adaptation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Liu","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref15","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Ahn","year":"2023"},{"key":"ref16","article-title":"Look before you leap: Unveiling the power of GPT-4V in robotic vision-language planning","author":"Hu","year":"2023"},{"key":"ref17","article-title":"Hierarchical vision-language planning for multi-step humanoid manipulation","author":"Schakkal","year":"2025"},{"key":"ref18","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref19","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref20","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35509"},{"key":"ref22","article-title":"Gemini robotics: Bringing ai into the physical world","author":"Team","year":"2025"},{"key":"ref23","first-page":"17","article-title":"$\\pi _{0.5}$: A vision-language-action model with open-world generalization","volume-title":"Proc. 9th Conf. Robot Learn.","volume":"305","author":"Black","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11435997\/11434491.pdf?arnumber=11434491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:37Z","timestamp":1774416277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":24,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3674003","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}