{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:53:11Z","timestamp":1776783191436,"version":"3.51.2"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127931","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"15626-15633","source":"Crossref","is-referenced-by-count":4,"title":["Inference-Time Policy Steering Through Human Interactions"],"prefix":"10.1109","author":[{"given":"Yanwei","family":"Wang","sequence":"first","affiliation":[{"name":"MIT CSAIL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lirui","family":"Wang","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilun","family":"Du","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Balakumar","family":"Sundaralingam","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuning","family":"Yang","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Wei","family":"Chao","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudia","family":"P\u00e9rez-D\u2019Arpino","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter","family":"Fox","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julie","family":"Shah","sequence":"additional","affiliation":[{"name":"MIT CSAIL"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref2","article-title":"Open x-embodiment: Robotic learning datasets and $\\text{rt}-\\mathrm{x}$ models","author":"O\u2019Neill","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Octo: An open-source generalist robot policy","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Deep generative models in robotics: A survey on learning from multimodal demonstrations","author":"Urain","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref8","article-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.025"},{"key":"ref10","article-title":"Rt-trajectory: Robotic task generalization via hindsight trajectory sketches","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1349822.1349854"},{"key":"ref12","article-title":"Grounding language plans in demonstrations through counterfactual perturbations","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Ross"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1115\/1.4039145"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211050958"},{"key":"ref16","volume-title":"Learning for adaptive and reactive robot control: a dynamical systems approach","author":"Billard","year":"2022"},{"key":"ref17","article-title":"Temporal logic imitation: Learning plan-satisficing motion policies from demonstrations","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"arXiv preprint","author":"Janner","year":"2022"},{"key":"ref19","article-title":"Is conditional generative modeling all you need for decisionmaking?","author":"Ajay","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802208"},{"key":"ref21","first-page":"8489","article-title":"Reduce, reuse, recycle: Compositional generation with energy-based diffusion models and mcmc","volume-title":"International conference on machine learning","author":"Du"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"issue":"60","key":"ref23","doi-asserted-by":"crossref","first-page":"3021","DOI":"10.21105\/joss.03021","article-title":"seaborn: statistical data visualization","volume":"6","author":"Waskom","year":"2021","journal-title":"Journal of Open Source Software"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.014"},{"key":"ref25","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160765"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2001.1183338"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-020-00005-6"},{"key":"ref31","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on robot learning","author":"Brohan"},{"key":"ref32","article-title":"Rt-sketch: Goalconditioned imitation learning from hand-drawn sketches","author":"Sundaresan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Goal-conditioned imitation learning","volume":"32","author":"Ding","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196123"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3330663"},{"key":"ref36","article-title":"Behavior generation with latent actions","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3143198"},{"key":"ref39","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Conference on robot learning","author":"Lynch"},{"key":"ref40","article-title":"Model based planning with energy based models","volume-title":"Conference on Robot Learning","author":"Du"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.030"},{"key":"ref42","article-title":"Compositional diffusion-based continuous constraint solvers","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.028"},{"key":"ref44","first-page":"2905","article-title":"Generative skill chaining: Long-horizon skill planning with diffusion models","volume-title":"Conference on Robot Learning","author":"Mishra"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161569"},{"key":"ref46","article-title":"Steering your generalists: Improving robotic foundation models via value guidance","author":"Nakamoto","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.127"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127931.pdf?arnumber=11127931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:17:36Z","timestamp":1756880256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127931","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}