{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:52:04Z","timestamp":1761367924675,"version":"build-2065373602"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016443","name":"Amazon","doi-asserted-by":"publisher","award":["Lab126"],"award-info":[{"award-number":["Lab126"]}],"id":[{"id":"10.13039\/100016443","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9,30]]},"DOI":"10.1109\/humanoids65713.2025.11203093","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:50Z","timestamp":1761326150000},"page":"1123-1130","source":"Crossref","is-referenced-by-count":0,"title":["Attribute-Based Object Grounding and Robot Grasp Detection with Spatial Reasoning"],"prefix":"10.1109","author":[{"given":"Houjian","family":"Yu","sequence":"first","affiliation":[{"name":"Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omid","family":"Ghasemalizadeh","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyin","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Hao","family":"Kuo","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arnie","family":"Sen","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Sunnyvale,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhyun","family":"Choi","sequence":"additional","affiliation":[{"name":"Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342412"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_36"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340777"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01695"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3353484"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812279"},{"key":"ref9","article-title":"Reasoning grasping via multimodal large language model","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Glover: Generalizable open-vocabulary affordance reasoning for task-oriented grasping","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Robotic control via embodied chain-of-thought reasoning","author":"Zawalski","year":"2024","journal-title":"arXiv preprint"},{"article-title":"Towards open-world grasping with large vision-language models","volume-title":"8th Conference on Robot Learning (CoRL 2024)","author":"Tziafas","key":"ref13"},{"key":"ref14","article-title":"Thinkgrasp: A vision-language system for strategic part grasping in clutter","author":"Qian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford"},{"key":"ref16","first-page":"12888","article-title":"Blip: Bootstrapping languageimage pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning. PMLR","author":"Li"},{"key":"ref17","article-title":"A parameterefficient tuning framework for language-guided object grounding and robot grasping","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"article-title":"Language-guided robot grasping: Clip-based referring grasp synthesis in clutter","volume-title":"7th Annual Conference on Robot Learning","author":"Tziafas","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00602"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.143"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01605"},{"article-title":"Barleria: An efficient tuning framework for referring image segmentation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wang","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02257"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on robot learning. PMLR","author":"Shridhar"},{"key":"ref33","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251504"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341379"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"article-title":"Vima: General robot manipulation with multimodal prompts","volume-title":"Fortieth International Conference on Machine Learning","author":"Jiang","key":"ref39"}],"event":{"name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2025,9,30]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2025,10,2]]}},"container-title":["2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11202977\/11203009\/11203093.pdf?arnumber=11203093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:46:25Z","timestamp":1761367585000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11203093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/humanoids65713.2025.11203093","relation":{},"subject":[],"published":{"date-parts":[[2025,9,30]]}}}