{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T16:16:56Z","timestamp":1771258616769,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100009002","name":"Shanghai University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10611525","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"4333-4339","source":"Crossref","is-referenced-by-count":9,"title":["Language-Conditioned Robotic Manipulation with Fast and Slow Thinking"],"prefix":"10.1109","author":[{"given":"Minjie","family":"Zhu","sequence":"first","affiliation":[{"name":"East China Normal University,School of Computer Science,China"}]},{"given":"Yichen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Midea Group,China"}]},{"given":"Jinming","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Science,Department of Mathematics,China"}]},{"given":"Junjie","family":"Wen","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science,China"}]},{"given":"Zhiyuan","family":"Xu","sequence":"additional","affiliation":[{"name":"Midea Group,China"}]},{"given":"Zhengping","family":"Che","sequence":"additional","affiliation":[{"name":"Midea Group,China"}]},{"given":"Chaomin","family":"Shen","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science,China"}]},{"given":"Yaxin","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Science,Department of Mathematics,China"}]},{"given":"Dong","family":"Liu","sequence":"additional","affiliation":[{"name":"Midea Group,China"}]},{"given":"Feifei","family":"Feng","sequence":"additional","affiliation":[{"name":"Midea Group,China"}]},{"given":"Jian","family":"Tang","sequence":"additional","affiliation":[{"name":"Midea Group,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref2","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Conference on Robot Learning","author":"Jang"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.4324\/9781410603432","volume-title":"Who is Rational? Studies of Individual Differences in Reasoning","author":"Stanovich","year":"1999"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511808098.004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.119.1.3"},{"key":"ref7","volume-title":"Thinking, Fast and Slow","author":"Kahneman","year":"2011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"ref9","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref11","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022"},{"key":"ref13","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023"},{"key":"ref14","article-title":"Least-to-most prompting enables complex reasoning in large language models","author":"Zhou","year":"2022"},{"key":"ref15","article-title":"Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks","author":"Chen","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_9081"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref19","first-page":"894","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1145\/3688863.3689575","article-title":"Llava-phi: Efficient multi-modal assistant with small language model","author":"Zhu","year":"2024"},{"key":"ref21","article-title":"Query-relevant images jailbreak large multi-modal models","author":"Liu","year":"2023"},{"key":"ref22","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref23","first-page":"18343","article-title":"MineDojo: Building open-ended embodied agents with internet-scale knowledge","volume":"35","author":"Fan","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref25","article-title":"RoCo: Dialectic multi-robot collaboration with large language models","author":"Mandi","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10609992"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3568162.3578623"},{"key":"ref29","article-title":"PaLI-x: On scaling up a multilingual vision and language model","author":"Chen","year":"2023"},{"key":"ref30","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref31","article-title":"GPT-4 Technical Report","year":"2023"},{"key":"ref32","article-title":"A generalist agent","author":"Reed","year":"2022"},{"key":"ref33","article-title":"VIMA: General robot manipulation with multimodal prompts","author":"Jiang","year":"2022"},{"key":"ref34","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref35","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref37","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref38","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref39","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref42","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Zeng"},{"key":"ref43","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"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10611525.pdf?arnumber=10611525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T13:31:34Z","timestamp":1732627894000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10611525\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10611525","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}