{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:54:09Z","timestamp":1777654449789,"version":"3.51.4"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802264","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"8465-8472","source":"Crossref","is-referenced-by-count":3,"title":["ARDuP: Active Region Video Diffusion for Universal Policies"],"prefix":"10.1109","author":[{"given":"Shuaiyi","family":"Huang","sequence":"first","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mara","family":"Levy","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anima","family":"Anandkumar","sequence":"additional","affiliation":[{"name":"California Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuke","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linxi","family":"Fan","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"De-An","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Shrivastava","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Video language planning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Du"},{"key":"ref2","article-title":"Learning universal policies via text-guided video generation","volume":"36","author":"Du","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","article-title":"Compositional foundation models for hierarchical planning","volume":"36","author":"Ajay","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"PRISE: LLM-style sequence compression for learning temporal action abstractions in control","volume-title":"Forty-first International Conference on Machine Learning","author":"Zheng"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref7","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref8","first-page":"1723","article-title":"Bridgedata v2: A dataset for robot learning at scale","volume-title":"Conference on Robot Learning","author":"Walke"},{"key":"ref9","article-title":"Is conditional generative modeling all you need for decision-making?","author":"Ajay","year":"2022"},{"key":"ref10","article-title":"Video as the new language for real-world decision making","author":"Yang","year":"2024"},{"key":"ref11","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022"},{"key":"ref12","article-title":"Learning to act from actionless videos through dense correspondences","author":"Ko","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.02.016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00846"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00210"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00594"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00273"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00274"},{"key":"ref22","volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"Puterman","year":"2014"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref25","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"issue":"1","key":"ref26","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"key":"ref27","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1055\/a-1858-6495"},{"key":"ref29","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref30","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Zeng"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802264.pdf?arnumber=10802264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:00:25Z","timestamp":1735196425000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802264","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}