{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:37:31Z","timestamp":1757608651368,"version":"3.44.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2143730"],"award-info":[{"award-number":["2143730"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128679","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"14353-14360","source":"Crossref","is-referenced-by-count":0,"title":["A Parameter-Efficient Tuning Framework for Language-Guided Object Grounding and Robot Grasping"],"prefix":"10.1109","author":[{"given":"Houjian","family":"Yu","sequence":"first","affiliation":[{"name":"Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA"}]},{"given":"Mingen","family":"Li","sequence":"additional","affiliation":[{"name":"Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA"}]},{"given":"Alireza","family":"Rezazadeh","sequence":"additional","affiliation":[{"name":"Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Univ. of Minnesota,Department of Computer Science and Engineering,Minneapolis,USA"}]},{"given":"Changhyun","family":"Choi","sequence":"additional","affiliation":[{"name":"Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092640"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561473"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342412"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794143"},{"key":"ref7","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_36"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3060341"},{"key":"ref11","article-title":"Language-guided robot grasping: Clip-based referring grasp synthesis in clutter","volume-title":"7th Annual Conference on Robot Learning","author":"Tziafas","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3353484"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812279"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161041"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561139"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01695"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_21"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801993"},{"key":"ref19","article-title":"Thinkgrasp: A vision-language system for strategic part grasping in clutter","author":"Qian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Reasoning grasping via multimodal large language model","author":"Jin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref22","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":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342331"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref27","article-title":"Eavl: Explicitly align vision and language for referring image segmentation","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341379"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342268"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811367"},{"key":"ref31","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on robot learning","author":"Shridhar","year":"2022"},{"key":"ref32","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International conference on machine learning","author":"Houlsby","year":"2019"},{"key":"ref33","first-page":"16664","article-title":"Adaptformer: Adapting vision transformers for scalable visual recognition","volume":"35","author":"Chen","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3233\/faia240489"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref36","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","article-title":"Position-aware contrastive alignment for referring image segmentation","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414006"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00376"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01761"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251504"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128679.pdf?arnumber=11128679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:08:31Z","timestamp":1756879711000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128679","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}