{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T22:06:48Z","timestamp":1771625208328,"version":"3.50.1"},"reference-count":46,"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\/iros60139.2025.11247288","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"19629-19636","source":"Crossref","is-referenced-by-count":0,"title":["HeStIa: Asynchronous Embodied Dynamic Locomotion Learning for Walking Robots through Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Xiaoyu","family":"Tan","sequence":"first","affiliation":[{"name":"Shanghai University of Engineering Science,School of Electronic and Electrical Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai University of Engineering Science,School of Electronic and Electrical Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sijia","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University of Engineering Science,School of Electronic and Electrical Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghui","family":"Xu","sequence":"additional","affiliation":[{"name":"Fudan University,AI3 Institute,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xihe","family":"Qiu","sequence":"additional","affiliation":[{"name":"Shanghai University of Engineering Science,School of Electronic and Electrical Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/JSEE.2023.000051"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10335-w"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679942"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102517"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00779-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.061"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi2243"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.plrev.2023.10.037"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2023.103960"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108531"},{"key":"ref12","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"ref14","article-title":"Robomamba: Multimodal state space model for efficient robot reasoning and manipulation","author":"Liu","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2022.102510"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.049"},{"key":"ref17","article-title":"Event-based vision for early prediction of manipulation actions","author":"Deniz","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-71152-7_4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CSCAIoT62585.2024.00009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3743127"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3272661"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03510-7"},{"key":"ref24","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","article-title":"A theoretical analysis of optimistic proximal policy optimization in linear markov decision processes","volume":"36","author":"Zhong","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.895"},{"key":"ref27","article-title":"Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness","author":"Yu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3292066"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610948"},{"key":"ref30","article-title":"Deep reinforcement learning for bipedal locomotion: A brief survey","author":"Bao","year":"2024"},{"key":"ref31","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Conference on Robot Learning","author":"Agarwal"},{"key":"ref32","article-title":"Visual-locomotion: Learning to walk on complex terrains with vision","volume-title":"5th Annual Conference on Robot Learning","author":"Yu"},{"key":"ref33","article-title":"A survey on vision-language-action models for embodied ai","author":"Ma","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3729343"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15960"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812166"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3151396"},{"key":"ref39","article-title":"Llara: Supercharging robot learning data for vision-language policy","author":"Li","year":"2024"},{"key":"ref40","article-title":"Robopoint: A vision-language model for spatial affordance prediction for robotics","author":"Yuan","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11246632"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3233383"},{"key":"ref43","first-page":"70 247","article-title":"Direct preference-based policy optimization without reward modeling","volume":"36","author":"An","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3329530"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3335416"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00713"}],"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\/11247288.pdf?arnumber=11247288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T21:12:06Z","timestamp":1771621926000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247288","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}