{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:22:43Z","timestamp":1778257363563,"version":"3.51.4"},"reference-count":131,"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\/iccv51701.2025.00731","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7794-7807","source":"Crossref","is-referenced-by-count":1,"title":["SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts"],"prefix":"10.1109","author":[{"given":"Gengze","family":"Zhou","sequence":"first","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yicong","family":"Hong","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zun","family":"Wang","sequence":"additional","affiliation":[{"name":"UNC, Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"UNSW Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohit","family":"Bansal","sequence":"additional","affiliation":[{"name":"UNC, Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wu","sequence":"additional","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01652"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475282"},{"key":"ref3","article-title":"Bevbert: Topo-metric map pre-training for language-guided navigation","author":"An","year":"2022","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3386695"},{"key":"ref5","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref8","author":"Batra","year":"2020","journal-title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref10","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Singh Chaplot","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01289"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34526"},{"key":"ref13","article-title":"Mapgpt: Mapguided prompting for unified vision-and-language navigation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01112"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3594204"},{"key":"ref16","article-title":"a2 nav: Action-aware zero-shot robot navigation by exploiting vision-and-language ability of foundation models","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","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":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_37"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref22","article-title":"Octavius: Mitigating task interference in mllms via moe","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0433"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.322"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00447"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"issue":"120","key":"ref30","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02219"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00308"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3678087"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref36","first-page":"26661","article-title":"No rl, no simulation: Learning to navigate without navigating","volume":"34","author":"Hahn","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681640"},{"key":"ref39","volume-title":"Learning Language-Guided Visual Navigation","author":"Hong","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00169"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01500"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1655"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00750"},{"key":"ref44","article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","author":"Ilharco","year":"2019","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref46","article-title":"Mixtral of experts","author":"Q Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01041"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01549"},{"key":"ref52","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"Kolve","year":"2017","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref56","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Panogen: Text-conditioned panoramic environment generation for vision-and-language navigation","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01497"},{"key":"ref61","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref64","article-title":"Cornav: Autonomous agent with self-corrected planning for zeroshot vision-and-language navigation","author":"Liang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Navcot: Boosting llm-based vision-andlanguage navigation via learning disentangled reasoning","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01544"},{"key":"ref69","article-title":"Task-customized masked autoencoder via mixture of cluster-conditional experts","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Discuss before moving: Visual language navigation via multiexpert discussions","author":"Long","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Instructnav: Zero-shot system for generic instruction navigation in unexplored environment","author":"Long","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2018"},{"key":"ref73","article-title":"Selfmonitoring navigation agent via auxiliary progress estimation","author":"Ma","year":"2019","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01509"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0695"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"key":"ref80","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":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234243"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref84","article-title":"Open-nav: Exploring zero-shot vision-and-language navigation in continuous environment with open-source 11 ms","author":"Qiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_27"},{"key":"ref86","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref87","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":"Kumar Ramakrishnan","year":"2021"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01716"},{"key":"ref91","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref92","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, pages 627\u2013635. JMLR Workshop and Conference Proceedings","author":"Ross","year":"2011"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref95","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.758"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342093"},{"key":"ref98","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv preprint"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1514"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref101","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Conference on Robot Learning","author":"Thomason","year":"2020"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_19"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01248"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_25"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.388"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref110","article-title":"Navigating the nuances: A finegrained evaluation of vision-language navigation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref111","first-page":"666","article-title":"Last-mile embodied visual navigation","volume-title":"Conference on Robot Learning","author":"Wasserman"},{"key":"ref112","article-title":"DD-PPO: Learning near-perfect pointgoal navigators from 2.5 billion frames","volume-title":"International Conference on Learning Representations (ICLR)","author":"Wijmans","year":"2020"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref114","article-title":"Openmoe: An early effort on open mixture-of-experts language models","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref115","article-title":"Offline visual representation learning for embodied navigation","volume-title":"Workshop on Reincarnating Reinforcement Learning at ICLR 2023","author":"Yadav","year":"2023"},{"key":"ref116","article-title":"Visual semantic navigation using scene priors","author":"Yang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01581"},{"key":"ref118","article-title":"Homerobot: Open-vocabulary mobile manipulation","author":"Yenamandra","year":"2023","journal-title":"arXiv preprint"},{"key":"ref119","article-title":"Mc-gpt: Empowering vision-and-language navigation with memory map and reasoning chains","author":"Zhan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.638"},{"key":"ref122","article-title":"Vision-and-language navigation today and tomorrow: A survey in the era of foundation models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611736"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548281"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01293"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref131","article-title":"Stmoe: Designing stable and transferable sparse expert models","author":"Zoph","year":"2022","journal-title":"arXiv preprint"}],"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\/11444992.pdf?arnumber=11444992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:47Z","timestamp":1777611287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":131,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00731","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}