{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:12:46Z","timestamp":1777889566495,"version":"3.51.4"},"reference-count":53,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62202431"],"award-info":[{"award-number":["62202431"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01306","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14073-14083","source":"Crossref","is-referenced-by-count":0,"title":["On-Device Diffusion Transformer Policy for Efficient Robot Manipulation"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computing and Data Science, The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenghao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information and Physical Sciences, The University of Newcastle"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxin","family":"Pang","sequence":"additional","affiliation":[{"name":"UBTech Robotics Corp"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computing and Data Science, The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref2","article-title":"Realtime execution of action chunking flow policies","author":"Black","year":"2025","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00041-008-9035-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","article-title":"Edgefusion: On-device text-to-image generation","author":"Castells","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611960"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680943"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01691"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0248"},{"key":"ref12","first-page":"158","article-title":"Implicit behavioral cloning","volume-title":"Conference on robot learning","author":"Florence"},{"key":"ref13","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"Frankle","year":"2019","journal-title":"ICLR"},{"key":"ref14","first-page":"1032310337","article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","volume-title":"International Conference on Machine Learning","author":"Frantar"},{"key":"ref15","article-title":"Mobile aloha: Learning bimanual mobile manipulation with lowcost whole-body teleoperation","volume-title":"Conference on Robot Learning","author":"Fu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01193"},{"key":"ref17","article-title":"Learning both weights and connections for efficient neural network","author":"Han","year":"2015","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2014","journal-title":"NIPS Workshop"},{"key":"ref19","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2021","journal-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications"},{"key":"ref20","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.032"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_22"},{"key":"ref24","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Conference on Robot Learning","author":"Jin Kim"},{"key":"ref25","article-title":"Pruning filters for efficient convnets","author":"Li","year":"2017","journal-title":"ICLR"},{"key":"ref26","article-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2024","journal-title":"ICLR"},{"key":"ref27","article-title":"Snapfusion: Text-to-image diffusion model on mobile devices within two seconds","author":"Li","year":"2023","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref29","article-title":"Latent consistency models: Synthesizing highresolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3180108"},{"key":"ref31","article-title":"Shortgpt: Layers in large language models are more redundant than you expect","author":"Men","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref33","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov","year":"2017","journal-title":"ICLR"},{"key":"ref34","article-title":"Skeletonization: A technique for trimming the fat from a network via relevance assessment","author":"Mozer","year":"1988","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.028"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.121"},{"key":"ref37","article-title":"Efficient diffusion transformer policies with mixture of expert denoisers for multitask learning","author":"Reuss","year":"2025","journal-title":"ICLR"},{"key":"ref38","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"ICLR"},{"key":"ref39","article-title":"Smolvla: A vision-language-action model for affordable and efficient robotics","author":"Shukor","year":"2025","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Improved techniques for training consistency models","author":"Song","year":"2024","journal-title":"ICLR"},{"key":"ref42","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref43","first-page":"32211","article-title":"Consistency models","volume-title":"Int. Conf. Mach. Learn.","author":"Song","year":"2023"},{"key":"ref44","author":"Model Team","year":"2024","journal-title":"Octo: An open-source generalist robot policy"},{"key":"ref45","article-title":"Neural pruning via growing regularization","author":"Wang","year":"2021","journal-title":"ICLR"},{"key":"ref46","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","author":"Wu","year":"2024","journal-title":"ICLR"},{"key":"ref47","article-title":"SANA 1.5: Efficient scaling of training-time and inferencetime compute in linear diffusion transformer","author":"Xie","year":"2025","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"ref49","article-title":"Deer-VLA: Dynamic inference of multimodal large language models for efficient robot execution","author":"Yue","year":"2024","journal-title":"NeurIPS"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.016"},{"key":"ref52","article-title":"Mobilediffusion: Subsecond text-to-image generation on mobile devices","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning","author":"Zitkovich"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444627.pdf?arnumber=11444627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:51Z","timestamp":1777612371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444627\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01306","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}