{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T14:50:06Z","timestamp":1769179806603,"version":"3.49.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,2]]},"DOI":"10.1109\/icar65334.2025.11338657","type":"proceedings-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:06:47Z","timestamp":1769029607000},"page":"869-875","source":"Crossref","is-referenced-by-count":0,"title":["MMVLA-EXT: Multi-Modal Vision-Language-Action Model with Efficient Cross-Platform Task Transfer"],"prefix":"10.1109","author":[{"given":"Sheng","family":"Guo","sequence":"first","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Ruiteng","family":"Zhao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Jinxian","family":"Zhou","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Chenchen","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Zhiyang","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Lei","family":"Zhou","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Jiawei","family":"Sun","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Chengran","family":"Yuan","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Zhengshen","family":"Zhang","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Francis","family":"Tay","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]},{"given":"Marcelo H","family":"Ang","sequence":"additional","affiliation":[{"name":"National University of Singapore,Advanced Robotics Centre,Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icrae59816.2023.10458574"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/drones8120728"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.112"},{"key":"ref5","article-title":"Do as i can, not as i say: Grounding language in robotic affordances[J]","author":"Ahn","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34526"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref8","article-title":"Ros-llm: A ros framework for embodied ai with task feedback and structured reasoning[J]","author":"Mower","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cdc56724.2024.10885862"},{"key":"ref10","article-title":"Openvla: An open-source vision-language-action model[J]","author":"Kim","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IRC63610.2024.00039"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CASE59546.2024.10711845"},{"key":"ref13","article-title":"ROSGPT Vision: Commanding Robots Using Only Language Models\u2019 Prompts[J]","author":"Benjdira","year":"2023"},{"key":"ref14","article-title":"Minivla: A better vla with a smaller footprint","author":"Belkhale","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128823"},{"key":"ref16","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision[C]","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref17","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning[J]","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref19","first-page":"17043","article-title":"Two-stream network for sign language recognition and translation[J]","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01430"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.722"},{"key":"ref22","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control[J]","author":"Brohan","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3005886"},{"key":"ref24","article-title":"Deepseek-v3 technical report[J]","author":"Liu","year":"2024"},{"key":"ref25","article-title":"DeepSeek-Coder: When the Large Language Model Meets Programming\u2013The Rise of Code Intelligence[J]","author":"Guo","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26054-9_1"},{"key":"ref27","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction[J]","author":"Shi","year":"2022"},{"key":"ref28","article-title":"Palm-e: An embodied multimodal language model[J]","author":"Driess","year":"2023"}],"event":{"name":"2025 IEEE International Conference on Advanced Robotics (ICAR)","location":"San Juan, Argentina","start":{"date-parts":[[2025,12,2]]},"end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 IEEE International Conference on Advanced Robotics (ICAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11338521\/11338600\/11338657.pdf?arnumber=11338657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T20:58:13Z","timestamp":1769115493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11338657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icar65334.2025.11338657","relation":{},"subject":[],"published":{"date-parts":[[2025,12,2]]}}}