{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T01:47:52Z","timestamp":1775785672012,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800613","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"358-362","source":"Crossref","is-referenced-by-count":1,"title":["Empowering Robots with Multimodal Language Models for Task Planning with Interaction"],"prefix":"10.1109","author":[{"given":"Tong Lee","family":"Chung","sequence":"first","affiliation":[{"name":"Research Institute of UBTech Robotics"}]},{"given":"Jianxin","family":"Pang","sequence":"additional","affiliation":[{"name":"Research Institute of UBTech Robotics"}]},{"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2023.1084000"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.birob.2023.100131"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"ref4","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/9781108676649"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1455375"},{"key":"ref7","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2492999"},{"key":"ref9","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref10","article-title":"Visual instruction tuning","volume-title":"Advances in Neural Information Processing Systems","author":"Liu","year":"2023"},{"key":"ref11","article-title":"Textually pretrained speech language models","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Hassid","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00637"},{"key":"ref13","article-title":"Copal: corrective planning of robot actions with large language models","author":"Joublin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341488"},{"key":"ref15","article-title":"Lamda: Language models for dialog applications","volume":"abs\/2201.08239","author":"Thoppilan","year":"2022","journal-title":"ArXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.224"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.24"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","article-title":"BC-z: Zero-shot task generalization with robotic imitation learning","volume-title":"5th Annual Conference on Robot Learning","author":"Jang","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref24","article-title":"A neural conversational model","volume-title":"ICML Deep Learning Workshop, 2015","author":"Vinyals","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/521"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.621"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00545"},{"key":"ref28","article-title":"On generative spoken language modeling from raw audio","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Lin-guistics"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3651029"},{"key":"ref30","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800613.pdf?arnumber=10800613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:34Z","timestamp":1735021594000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800613","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}