{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:03:21Z","timestamp":1777889001517,"version":"3.51.4"},"reference-count":145,"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\/501100007937","name":"Peking University","doi-asserted-by":"publisher","award":["2024JK28"],"award-info":[{"award-number":["2024JK28"]}],"id":[{"id":"10.13039\/501100007937","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\/iccv51701.2025.00597","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6327-6341","source":"Crossref","is-referenced-by-count":0,"title":["NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigation"],"prefix":"10.1109","author":[{"given":"Peiran","family":"Xu","sequence":"first","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xicheng","family":"Gong","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yadong","family":"Mu","sequence":"additional","affiliation":[{"name":"Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref2","first-page":"2737","article-title":"Bevbert: Multimodal map pre-training for language-guided navigation","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"An","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref4","article-title":"Chasing ghosts: Instruction following as bayesian state tracking","volume":"32","author":"Anderson","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref5","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":"ref6","first-page":"1384","article-title":"The robotslang benchmark: Dialog-guided robot localization and navigation","volume-title":"Conference on Robot Learning","author":"Banerjee","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref8","first-page":"4283","article-title":"Semantic visual navigation by watching youtube videos","volume":"33","author":"Chang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"3909","article-title":"Q-transformer: Scalable offline reinforcement learning via autoregressive q -functions","volume-title":"Conference on Robot Learning","author":"Chebotar","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01501"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref13","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_37"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5627"},{"key":"ref18","article-title":"Generative languagegrounded policy in vision-and-language navigation with bayes\u2019rule","volume-title":"International Conference on Learning Representations","author":"Cho","year":"2020"},{"key":"ref19","article-title":"Frontier-enhanced topological memory with improved exploration awareness for embodied visual navigation","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Cui","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01106"},{"key":"ref21","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume":"33","author":"Deng","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_21"},{"key":"ref24","article-title":"Stop regressing: training value functions via classification for scalable deep rl","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Farebrother","year":"2024"},{"key":"ref25","article-title":"Speaker-follower models for vision-and-language navigation","volume":"31","author":"Fried","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01432"},{"key":"ref29","article-title":"Fast-slow testtime adaptation for online vision-and-language navigation","volume-title":"Forty-first International Conference on Machine Learning","author":"Gao"},{"key":"ref30","article-title":"Learning to map for active semantic goal navigation","volume-title":"The Tenth International Conference on Learning Representations (ICLR 2022)","author":"Georgakis","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref34","first-page":"652","article-title":"Landmark-rxr: Solving vision-and-language navigation with fine-grained alignment supervision","volume":"34","author":"He","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0193"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref38","article-title":"General scene adaptation for vision-and-language navigation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Hong","year":"2025"},{"key":"ref39","first-page":"7685","article-title":"Language and visual entity relationship graph for agent navigation","volume":"33","author":"Hong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.271"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00284"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1655"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1605"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00750"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02223"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00646"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01041"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01447"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25199"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_3"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01433"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0957"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.82"},{"key":"ref60","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25223"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.332"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20050"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560925"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3097435"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3273594"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25243"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3407759"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_22"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00764"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref76","author":"Lin","journal-title":"Q* agent: Optimizing language agents with q-guided exploration"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3436"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01544"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref82","article-title":"Selfmonitoring navigation agent via auxiliary progress estimation","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Ma","year":"2019"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref85","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28223"},{"key":"ref88","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":"ref89","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1063"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01281"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_4"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"key":"ref93","first-page":"5296","article-title":"Counterfactual vision-and-language navigation: Unravelling the unseen","volume":"33","author":"Parvaneh","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref94","article-title":"Agent q: Advanced reasoning and learning for autonomous ai agents","author":"Putta","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01498"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01416"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_27"},{"key":"ref102","article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Ramakrishnan"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.157"},{"key":"ref105","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","author":"Ross","year":"2011"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref107","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason","year":"2020"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref109","article-title":"Q*: Improving multi-step reasoning for 11 ms with deliberative planning","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_19"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_8"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00835"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2671"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01503"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00998"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/164"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01248"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01499"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01826"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_25"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01305"},{"key":"ref126","article-title":"Bootstrapping language-guided navigation learning with self-refining data flywheel","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang","year":"2025"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref129","first-page":"38989","article-title":"Q-learning decision transformer: Leveraging dynamic programming for conditional sequence modelling in offline rl","volume-title":"International Conference on Machine Learning","author":"Yamagata","year":"2023"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01003"},{"key":"ref131","first-page":"13328","article-title":"Curriculum learning for vision-and-language navigation","volume":"34","author":"Zhang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01553"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3039522"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.737"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/124"},{"key":"ref137","article-title":"Imaginenav: Prompting vision-language models as embodied navigator through scene imagination","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhao","year":"2025"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.229"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00162"}],"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\/11444394.pdf?arnumber=11444394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:46Z","timestamp":1777611886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444394\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":145,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00597","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}