{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T13:10:32Z","timestamp":1778159432109,"version":"3.51.4"},"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11247068","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"15328-15335","source":"Crossref","is-referenced-by-count":2,"title":["Weakly-supervised VLM-guided Partial Contrastive Learning for Visual Language Navigation"],"prefix":"10.1109","author":[{"given":"Ruoyu","family":"Wang","sequence":"first","affiliation":[{"name":"University of New South Wales,Sydney,Australia"}]},{"given":"Tong","family":"Yu","sequence":"additional","affiliation":[{"name":"Adobe Research,San Jose,United States"}]},{"given":"Junda","family":"Wu","sequence":"additional","affiliation":[{"name":"University of California San Diego,La Jolla,United States"}]},{"given":"Yao","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University,China"}]},{"given":"Julian","family":"McAuley","sequence":"additional","affiliation":[{"name":"University of California San Diego,La Jolla,United States"}]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"CSIRO’s Data61 and University of New South Wales,Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.524"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00169"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3554559"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.60"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01551"},{"key":"ref17","first-page":"12 979","article-title":"Contrastive learning inverts the data generating process","volume-title":"International conference on machine learning","author":"Zimmermann"},{"key":"ref18","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref19","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref20","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00696"},{"issue":"7","key":"ref25","first-page":"8","article-title":"Bevbert: Topometric map pre-training for language-guided navigation","volume":"2","author":"An","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01248"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127306"},{"key":"ref33","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref34","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"issue":"70","key":"ref35","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref36","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref37","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref40","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref41","article-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023"},{"key":"ref42","first-page":"19 730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160612"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610117"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00689"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00690"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01007"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611256"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610575"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00254"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161289"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160511"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128436"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610980"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_16"},{"key":"ref58","article-title":"Panogen: Text-conditioned panoramic environment generation for vision-and-language navigation","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01503"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00750"},{"key":"ref62","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","author":"Ma","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_3"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610499"}],"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\/11247068.pdf?arnumber=11247068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:37:45Z","timestamp":1766061465000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11247068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11247068","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}