{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:04:05Z","timestamp":1777889045696,"version":"3.51.4"},"reference-count":54,"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\/501100003399","name":"STCSM","doi-asserted-by":"publisher","award":["24511103202,23511103104"],"award-info":[{"award-number":["24511103202,23511103104"]}],"id":[{"id":"10.13039\/501100003399","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\/iccv51701.2025.01344","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14486-14495","source":"Crossref","is-referenced-by-count":0,"title":["Dense Policy: Bidirectional Autoregressive Learning of Actions"],"prefix":"10.1109","author":[{"given":"Yue","family":"Su","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Zhan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongjie","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Xue","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao-Shu","family":"Fang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong-Lu","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lixin","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02030"},{"key":"ref2","author":"Black","year":"2024","journal-title":"\u03c00: A vision-language-action flow model for general robot control"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2008.02.009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref7","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"O\u2019Neill","year":"2024","journal-title":"ICRA"},{"key":"ref8","author":"Devlin","year":"2019","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611615"},{"key":"ref10","article-title":"Implicit behavioral cloning","author":"Florence","year":"2022","journal-title":"CoRL"},{"key":"ref11","article-title":"In-context imitation learning via nexttoken prediction","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Carp: Visuomotor policy learning via coarse-to-fine autore-gressive prediction","author":"Gong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","author":"Harvey","year":"2022","journal-title":"Conditional image generation by conditioning variational autoencoders"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Bc-z: Zero-shot task generalization with robotic imitation learning","author":"Jang","year":"2021","journal-title":"CoRL"},{"key":"ref17","article-title":"Vima: General robot manipulation with multimodal prompts","volume-title":"Fortieth International Conference on Machine Learning","author":"Jiang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref19","author":"Kaplan","year":"2020","journal-title":"Scaling laws for neural language models"},{"key":"ref20","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.1088545"},{"key":"ref23","article-title":"Convolutional networks for images, speech, and time series","author":"LeCun","year":"1995","journal-title":"The handbook of brain theory and neural networks"},{"key":"ref24","author":"Li","year":"2024","journal-title":"Autoregressive image generation without vector quantization"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01710"},{"key":"ref26","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref27","author":"Liu","year":"2024","journal-title":"Customize your visual autoregressive recipe with set autoregressive modeling"},{"key":"ref28","author":"Liu","year":"2019","journal-title":"Roberta: A robustly optimized bert pretraining approach"},{"key":"ref29","article-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024","journal-title":"RSS"},{"key":"ref30","article-title":"ALVINN: an autonomous land vehicle in a neural network","author":"Pomerleau","year":"1988","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25300"},{"key":"ref32","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2018.xiv.049"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Waypoint-based imitation learning for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shi"},{"key":"ref36","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref37","article-title":"Motion before action: Diffusing object motion as manipulation condition","author":"Su","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref41","article-title":"Neural discrete representation learning","author":"Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","article-title":"Vrl3: A data-driven framework for visual deep reinforcement learning","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10801678"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/81497"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref47","article-title":"Cage: Causal attention enables data-efficient generalizable robotic manipulation","author":"Xia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.052"},{"key":"ref50","article-title":"Metaworld: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"Yu","year":"2020","journal-title":"CoRL"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.067"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3550849"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref54","article-title":"RT-2: vision-language-action models transfer web knowledge to robotic control","author":"Zitkovich","year":"2023","journal-title":"CoRL"}],"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\/11449038.pdf?arnumber=11449038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:05:55Z","timestamp":1777611955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449038\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01344","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}