{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T08:40:18Z","timestamp":1735202418084,"version":"3.32.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802579","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"9604-9611","source":"Crossref","is-referenced-by-count":0,"title":["LLaKey: Follow My Basic Action Instructions to Your Next Key State"],"prefix":"10.1109","author":[{"given":"Zheyi","family":"Zhao","sequence":"first","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,P.R. China,518060"}]},{"given":"Ying","family":"He","sequence":"additional","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,P.R. China,518060"}]},{"given":"Fei","family":"Yu","sequence":"additional","affiliation":[{"name":"Shenzhen University,College of Computer Science and Software Engineering,P.R. China"}]},{"given":"Pengteng","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,P.R. China,518060"}]},{"given":"Fan","family":"Zhuo","sequence":"additional","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,P.R. China,518060"}]},{"given":"Xilong","family":"Sun","sequence":"additional","affiliation":[{"name":"Shenzhen University,Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,P.R. China,518060"}]}],"member":"263","reference":[{"article-title":"Act3d: Infinite resolution action detection transformer for robotic manipulation","year":"2023","author":"Gervet","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611293"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"article-title":"A generalist agent","year":"2022","author":"Reed","key":"ref4"},{"key":"ref5","first-page":"991","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proceedings of the Conference on Robot Learning","author":"Jang"},{"key":"ref6","first-page":"175","article-title":"Instruction-driven history-aware policies for robotic manipulations","volume-title":"Proceedings of the Conference on Robot Learning","author":"Guhur"},{"article-title":"Open-world object manipulation using pre-trained vision-language models","year":"2023","author":"Stone","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref10","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Proceedings of the Conference on Robot Learning","author":"Shridhar"},{"article-title":"RVT: Robotic view transformer for 3d object manipulation","year":"2023","author":"Goyal","key":"ref11"},{"key":"ref12","first-page":"33330","article-title":"Point transformer v2: Grouped vector attention and partition-based pooling","volume":"35","author":"Wu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Emergent abilities of large language models","year":"2022","author":"Wei","key":"ref14"},{"article-title":"GPT-4 Technical Report","year":"2023","author":"Achiam","key":"ref15"},{"article-title":"Training socially aligned language models in simulated human society","year":"2023","author":"Liu","key":"ref16"},{"key":"ref17","article-title":"LLM-powered Autonomous Agents","author":"Weng","year":"2023","journal-title":"lilian-weng.github.io"},{"article-title":"Cognitive architectures for language agents","year":"2023","author":"Sumers","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"volume-title":"Large language models are zero-shot reasoners, 2022","year":"2022","author":"Kojima","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"article-title":"Instruct2act: Mapping multi-modality instructions to robotic actions with large language model","year":"2023","author":"Huang","key":"ref23"},{"article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","year":"2022","author":"Zeng","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","year":"2023","author":"Huang","key":"ref26"},{"key":"ref27","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Huang"},{"article-title":"Do as I can, not as I say: Grounding language in robotic affordances","year":"2022","author":"Ahn","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341577"},{"article-title":"Vision-language models as success detectors","year":"2023","author":"Du","key":"ref30"},{"key":"ref31","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proceedings of the Conference on Robot Learning","author":"Zitkovich"},{"article-title":"PaLM-E: An embodied multimodal language model","year":"2023","author":"Driess","key":"ref33"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref34"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"article-title":"Pyrep: Bringing v-rep to deep robot learning","year":"2019","author":"James","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802579.pdf?arnumber=10802579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:33:50Z","timestamp":1735198430000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802579","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}