{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:03:27Z","timestamp":1781535807981,"version":"3.54.5"},"reference-count":65,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["624B2105,62473295,62233013,62333017"],"award-info":[{"award-number":["624B2105,62473295,62233013,62333017"]}],"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\/iccv51701.2025.00882","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"9455-9465","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities"],"prefix":"10.1109","author":[{"given":"Liuyi","family":"Wang","sequence":"first","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyuan","family":"Xia","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilun","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengju","family":"Liu","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qijun","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3386695"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","first-page":"671","article-title":"Sim-to-real transfer for vision-and-language navigation","volume-title":"Conference on Robot Learning","author":"Anderson","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01472"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.070"},{"key":"ref6","article-title":"Navdp: Learning sim-to-real navigation diffusion policy with privileged information guidance","author":"Cai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref8","article-title":"Partnr: A benchmark for planning and reasoning in embodied multi-agent tasks","author":"Chang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01106"},{"key":"ref12","article-title":"Multiple thinking achieving metaability decoupling for object navigation","volume-title":"International Conference on Machine Learning (ICML)","author":"Dang","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0433"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3326373"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802484"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3596386"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref23","article-title":"Openvla: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_34"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref27","author":"Li","year":"2022","journal-title":"Language-driven semantic segmentation"},{"key":"ref28","article-title":"Behavior-1k: A human-centered, embodied ai benchmark with 1,000 everyday activities and realistic simulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802055"},{"key":"ref32","article-title":"Mo-vln: A multi-task benchmark for open-set zero-shot vision-and-language navigation","author":"Liang","year":"2023","journal-title":"Computing Research Repository ar Xiv Preprints"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.745"},{"key":"ref34","article-title":"Learning humanoid locomotion with perceptive internal model","author":"Long","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Hybrid internal model: Learning agile legged locomotion with simulated robot response","author":"Long","year":"2024","journal-title":"ICLR"},{"key":"ref36","article-title":"Instructnav: Zero-shot system for generic instruction navigation in unexplored environment","author":"Long","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"ref38","first-page":"7357","article-title":"Soat: A scene-and object-aware transformer for vision-and-language navigation","volume":"34","author":"Moudgil","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3551230"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref44","article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks. Curran","author":"Santhosh","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.328"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610665"},{"key":"ref49","first-page":"477","article-title":"Behavior: Benchmark for everyday household activities in virtual, interactive, and ecological environments","volume-title":"Conference on robot learning","author":"Srivastava","year":"2022"},{"key":"ref50","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref52","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason","year":"2020"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref54","article-title":"Grutopia: Dream general robots in a city at scale","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/164"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01248"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref58","article-title":"Sim-to-real transfer via 3d feature fields for vision-and-language navigation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"All robots in one: A new standard and unified dataset for versatile, general-purpose embodied agents","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00802"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.093"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_18"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.079"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"}],"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\/11445553.pdf?arnumber=11445553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:26Z","timestamp":1777529966000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00882","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}