{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:51:26Z","timestamp":1777654286166,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"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":[[2025,6,10]]},"DOI":"10.1109\/cvpr52734.2025.01139","type":"proceedings-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:26:42Z","timestamp":1755106002000},"page":"12199-12208","source":"Crossref","is-referenced-by-count":4,"title":["UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping"],"prefix":"10.1109","author":[{"given":"Wenbo","family":"Wang","sequence":"first","affiliation":[{"name":"University of Sydney"}]},{"given":"Fangyun","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Lei","family":"Zhou","sequence":"additional","affiliation":[{"name":"National University of Singapore"}]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Lin","family":"Luo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Xiaohan","family":"Yi","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Yizhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Yaobo","family":"Liang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Chang","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Sydney"}]},{"given":"Yan","family":"Lu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Jiaolong","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Baining","family":"Guo","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907059"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967960"},{"key":"ref3","article-title":"Volumetric grasping network: Real-time 6 dof grasp detection in clutter","author":"Breyer","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01992"},{"key":"ref5","article-title":"Distilling policy distillation","author":"Czarnecki","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2025.102054"},{"key":"ref9","article-title":"Divide-and-conquer reinforcement learning","author":"Ghosh","year":"2018"},{"key":"ref10","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref11","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","author":"Huang","year":"2024"},{"key":"ref12","article-title":"InspireRobots","year":"2016"},{"key":"ref13","article-title":"Improving policy optimization with generalist-specialist learning","author":"Jia","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01092"},{"key":"ref15","article-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139793"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref18","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","author":"Kroemer","year":"2020"},{"key":"ref19","article-title":"Learning dexterous manipulation policies from experience and imitation","author":"Kumar","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.066"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3129138"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28619-4_35"},{"key":"ref23","article-title":"Dextrah-g: Pixels-to-action dexterous arm-hand grasping with geometric fabrics","author":"Lum","year":"2024"},{"key":"ref24","first-page":"515","article-title":"Learning deep policies for robot bin picking by simulating robust grasping sequences","volume-title":"Proceedings of the 1st Annual Conference on Robot Learning","author":"Mahler"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau4984"},{"key":"ref27","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561802"},{"key":"ref29","article-title":"Dexvip: Learning dexterous grasping with human hand pose priors from video","author":"Mandikal","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610700"},{"key":"ref31","article-title":"Refactoring policy for compositional generalizability using self-supervised object proposals","author":"Mu","year":"2020"},{"key":"ref32","article-title":"Deep dynamics models for learning dexterous manipulation","author":"Nagabandi","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref34","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","author":"Parisotto","year":"2016"},{"key":"ref35","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","author":"Qi","year":"2017"},{"key":"ref36","article-title":"Dexpoint: Generalizable point cloud reinforcement learning for sim-to-real dexterous manipulation","author":"Qin","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_33"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636557"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref40","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"Ross","year":"2011"},{"key":"ref41","article-title":"Policy distillation","author":"Rusu","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref45","article-title":"Distral: Robust multitask reinforcement learning","author":"Teh","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769866"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad467"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00360"},{"key":"ref50","article-title":"Lessons from learning to spin \u201cpens\u201d","author":"Wang","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160982"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10609868"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1455431"},{"key":"ref54","article-title":"Mat: Multi-fingered adaptive tactile grasping via deep reinforcement learning","author":"Wu","year":"2019"},{"key":"ref55","article-title":"Learning generalizable dexterous manipulation from human grasp affordance","author":"Wu","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00459"},{"key":"ref57","article-title":"Robotic grasping from classical to modern: A survey","author":"Zhang","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00016"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_22"},{"key":"ref60","article-title":"Dexgrasp-diffusion: Diffusion-based unified functional grasp synthesis method for multi-dexterous robotic hands","author":"Zhang","year":"2024"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611371"}],"event":{"name":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Nashville, TN, USA","start":{"date-parts":[[2025,6,10]]},"end":{"date-parts":[[2025,6,17]]}},"container-title":["2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11091818\/11091608\/11094643.pdf?arnumber=11094643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T08:28:02Z","timestamp":1755160082000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11094643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,10]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/cvpr52734.2025.01139","relation":{},"subject":[],"published":{"date-parts":[[2025,6,10]]}}}