{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:30:16Z","timestamp":1756992616096,"version":"3.32.0"},"reference-count":42,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802219","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"9510-9517","source":"Crossref","is-referenced-by-count":1,"title":["KOSMOS-E : Learning to Follow Instruction for Robotic Grasping"],"prefix":"10.1109","author":[{"given":"Zhi","family":"Wang","sequence":"first","affiliation":[{"name":"Microsoft Research Asia,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaohan","family":"Huang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Dong","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuming","family":"Ma","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Furu","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref1"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref2"},{"key":"ref3","article-title":"Language is not all you need: Aligning perception with language models","volume":"abs\/2302.14045","author":"Huang","year":"2023"},{"article-title":"Kosmos-2: Grounding multimodal large language models to the world","year":"2023","author":"Peng","key":"ref4"},{"key":"ref5","first-page":"22 199","article-title":"Large language models are zero-shot reasoners","volume-title":"Advances in neural information processing systems","volume":"35","author":"Kojima"},{"key":"ref6","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Wei"},{"article-title":"Inner monologue: Embodied reasoning through planning with language models","year":"2022","author":"Huang","key":"ref7"},{"article-title":"React: Synergizing reasoning and acting in language models","year":"2022","author":"Yao","key":"ref8"},{"article-title":"Code llama: Open foundation models for code","year":"2023","author":"Roziere","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"ref11","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"author":"Minderer","key":"ref13","article-title":"Simple open-vocabulary object detection with vision transformers"},{"article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","year":"2023","author":"Huang","key":"ref14"},{"article-title":"Programmatically grounded, compositionally generalizable robotic manipulation","year":"2023","author":"Wang","key":"ref15"},{"article-title":"Open-world object manipulation using pre-trained vision-language models","year":"2023","author":"Stone","key":"ref16"},{"article-title":"Do as i can, not as i say: Grounding language in robotic affordances","year":"2022","author":"Ahn","key":"ref17"},{"article-title":"Palm-e: An embodied multimodal language model","year":"2023","author":"Driess","key":"ref18"},{"article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","year":"2023","author":"Brohan","key":"ref19"},{"article-title":"The flan collection: Designing data and methods for effective instruction tuning","year":"2023","author":"Longpre","key":"ref20"},{"key":"ref21","article-title":"Visual instruction tuning","volume-title":"Advances in neural information processing systems","volume":"36","author":"Liu"},{"article-title":"Reasoning tuning grasp: Adapting multi-modal large language models for robotic grasping","volume-title":"2nd Workshop on Language and Robot Learning: Language as Grounding","author":"Xu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref24","first-page":"3511","article-title":"Jacquard: A large scale dataset for robotic grasp detection","volume-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Depierre"},{"key":"ref25","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref26","article-title":"Foundation transformers","volume":"abs\/2210.06423","author":"Wang","year":"2022","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980145"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919859066"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907124"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9402-3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/027836499501400402"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1115\/IMECE2000-2439"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917735594"},{"article-title":"End-to-end learning of semantic grasping","year":"2017","author":"Jang","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191194"},{"key":"ref37","first-page":"618","article-title":"Learning generalizable dexterous manipulation from human grasp affordance","volume-title":"Conference on Robot Learning","author":"Wu"},{"article-title":"Autort: Embodied foundation models for large scale orchestration of robotic agents","year":"2024","author":"Ahn","key":"ref38"},{"article-title":"Llm+ p: Empowering large language models with optimal planning proficiency","year":"2023","author":"Liu","key":"ref39"},{"key":"ref40","first-page":"20","article-title":"Chatgpt for robotics: Design principles and model abilities","volume":"2","author":"Vemprala","year":"2023","journal-title":"Microsoft Auton. Syst. Robot. Res"},{"article-title":"Lan-grasp: Using large language models for semantic object grasping","year":"2023","author":"Mirjalili","key":"ref41"},{"article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","year":"2023","author":"Mu","key":"ref42"}],"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\/10802219.pdf?arnumber=10802219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:00:07Z","timestamp":1735196407000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802219","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}