{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:46:20Z","timestamp":1784389580254,"version":"3.55.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246340","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"2873-2880","source":"Crossref","is-referenced-by-count":14,"title":["Generalizable Humanoid Manipulation with 3D Diffusion Policies"],"prefix":"10.1109","author":[{"given":"Yanjie","family":"Ze","sequence":"first","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Wang","sequence":"additional","affiliation":[{"name":"UPenn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Chen","sequence":"additional","affiliation":[{"name":"UPenn"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xialin","family":"He","sequence":"additional","affiliation":[{"name":"UIUC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Yuan","sequence":"additional","affiliation":[{"name":"CMU"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue Bin","family":"Peng","sequence":"additional","affiliation":[{"name":"Simon Fraser University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247017"},{"key":"ref4","article-title":"Ace: A cross-platform visual-exoskeletons system for low-cost dexterous teleoperation","author":"Yang","year":"2024"},{"key":"ref5","article-title":"Bimanual dexterity for complex tasks","volume-title":"8th Annual Conference on Robot Learning","author":"Shaw"},{"key":"ref6","article-title":"Omnih2o: Universal and dexterous human-to-humanoid whole-body teleoperation and learning","author":"He","year":"2024"},{"key":"ref7","article-title":"Humanplus: Humanoid shadowing and imitation from humans","author":"Fu","year":"2024"},{"key":"ref8","article-title":"Twisting lids off with two hands","author":"Lin","year":"2024"},{"key":"ref9","article-title":"Learning to manipulate anywhere: A visual generalizable framework for reinforcement learning","author":"Yuan","year":"2024"},{"key":"ref10","article-title":"Open-television: Teleoperation with immersive active visual feedback","author":"Cheng","year":"2024"},{"key":"ref11","article-title":"Atlas","author":"Dynamics","year":"2024"},{"key":"ref12","article-title":"Optimus","year":"2024"},{"key":"ref13","article-title":"01","year":"2024"},{"key":"ref14","article-title":"H1","year":"2024"},{"key":"ref15","article-title":"Gr1","author":"Intelligence","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801984"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref19","article-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Fu","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref21","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128180"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.058"},{"key":"ref24","article-title":"Humanoid locomotion as next token prediction","author":"Radosavovic","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi9579"},{"key":"ref26","article-title":"Humanoid parkour learning","author":"Zhuang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.107"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.043"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375203"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127857"},{"key":"ref31","article-title":"Dexterous hands","author":"Robots","year":"2024"},{"key":"ref32","article-title":"Lidar camera l515","author":"RealSense","year":"2024"},{"key":"ref33","article-title":"Depth camera d435","author":"RealSense","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801678"},{"key":"ref35","article-title":"Apple vision pro","year":"2024"},{"key":"ref36","article-title":"Using apple vision pro to train and control robots","author":"Park","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.043"},{"key":"ref38","article-title":"Equibot: Sim(3)-equivariant diffusion policy for generalizable and data efficient learning","author":"Yang","year":"2024"},{"key":"ref39","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref40","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref41","article-title":"R3m: A universal visual representation for robot manipulation","author":"Nair","year":"2022"},{"key":"ref42","article-title":"On pre-training for visuo-motor control: Revisiting a learning-from-scratch baseline","author":"Hansen","year":"2022"},{"key":"ref43","article-title":"View-invariant policy learning via zero-shot novel view synthesis","author":"Tian","year":"2024"},{"key":"ref44","article-title":"Equivariant diffusion policy","author":"Wang","year":"2024"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246340.pdf?arnumber=11246340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:36:14Z","timestamp":1766061374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246340","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}