{"id":"https://openalex.org/W4416748620","doi":"https://doi.org/10.1109/iros60139.2025.11247068","title":"Weakly-supervised VLM-guided Partial Contrastive Learning for Visual Language Navigation","display_name":"Weakly-supervised VLM-guided Partial Contrastive Learning for Visual Language Navigation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748620","doi":"https://doi.org/10.1109/iros60139.2025.11247068"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100653711","display_name":"Ruoyu Wang","orcid":"https://orcid.org/0000-0002-7240-558X"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ruoyu Wang","raw_affiliation_strings":["University of New South Wales,Sydney,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales,Sydney,Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767817","display_name":"Tong Yu","orcid":"https://orcid.org/0000-0002-1819-5614"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Yu","raw_affiliation_strings":["Adobe Research,San Jose,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,San Jose,United States","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035658564","display_name":"Junda Wu","orcid":"https://orcid.org/0000-0001-6464-7813"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junda Wu","raw_affiliation_strings":["University of California San Diego,La Jolla,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego,La Jolla,United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100463071","display_name":"Yao Liu","orcid":"https://orcid.org/0000-0002-2775-1643"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Liu","raw_affiliation_strings":["Northeastern University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021827617","display_name":"Julian McAuley","orcid":"https://orcid.org/0000-0003-0955-7588"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":["University of California San Diego,La Jolla,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego,La Jolla,United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["CSIRO’s Data61 and University of New South Wales,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO’s Data61 and University of New South Wales,Australia","institution_ids":["https://openalex.org/I42894916"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100653711"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":1.0724,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83698268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"15328","last_page":"15335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9613000154495239,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9613000154495239,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.004699999932199717,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.7160999774932861},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5940999984741211},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5860000252723694},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5787000060081482},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5309000015258789},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4302999973297119},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4302000105381012},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.42089998722076416}],"concepts":[{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.7160999774932861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132999897003174},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5940999984741211},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5860000252723694},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5787000060081482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690000057220459},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4302000105381012},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.42089998722076416},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.36640000343322754},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30390000343322754},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2709999978542328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2926977875","https://openalex.org/W2962744691","https://openalex.org/W2963800628","https://openalex.org/W2963846044","https://openalex.org/W2964935470","https://openalex.org/W2970231061","https://openalex.org/W2974759213","https://openalex.org/W2981799368","https://openalex.org/W3034500398","https://openalex.org/W3034578524","https://openalex.org/W3035232877","https://openalex.org/W3109097593","https://openalex.org/W3172675210","https://openalex.org/W3176495323","https://openalex.org/W3192009892","https://openalex.org/W3195026654","https://openalex.org/W3211462570","https://openalex.org/W4221167437","https://openalex.org/W4226052928","https://openalex.org/W4312581490","https://openalex.org/W4383108296","https://openalex.org/W4383108519","https://openalex.org/W4383108576","https://openalex.org/W4383109289","https://openalex.org/W4386065508","https://openalex.org/W4390871755","https://openalex.org/W4390873167","https://openalex.org/W4390874160","https://openalex.org/W4392172801","https://openalex.org/W4393154152","https://openalex.org/W4401042755","https://openalex.org/W4401413869","https://openalex.org/W4401414396","https://openalex.org/W4401415806","https://openalex.org/W4401416066","https://openalex.org/W4401417232","https://openalex.org/W4401417236","https://openalex.org/W4402684154","https://openalex.org/W4402703032","https://openalex.org/W4402727020","https://openalex.org/W4402727189","https://openalex.org/W4402944034","https://openalex.org/W4408841099","https://openalex.org/W4413917085","https://openalex.org/W4413917742"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Language":[1],"Navigation":[2],"(VLN)":[3],"is":[4,65],"a":[5,112],"fundamental":[6],"task":[7],"within":[8],"the":[9,16,30,56,63,77,135,145,167,175],"field":[10],"of":[11,18,79,180],"Embodied":[12],"AI,":[13],"focusing":[14],"on":[15,25,46,170],"ability":[17,118,147],"agents":[19],"to":[20,76,119,148,152],"navigate":[21],"complex":[22],"environments":[23],"based":[24],"natural":[26],"language":[27],"instructions.":[28],"Despite":[29],"progress":[31],"made":[32],"by":[33,128],"existing":[34],"methods,":[35],"these":[36,103],"methods":[37,169],"often":[38],"present":[39],"some":[40],"common":[41],"challenges.":[42],"First,":[43],"they":[44],"rely":[45],"pre-trained":[47,69,131],"backbone":[48],"models":[49],"for":[50],"visual":[51],"perception,":[52],"which":[53,173],"struggle":[54],"with":[55],"dynamic":[57,123],"viewpoints":[58,124],"in":[59,125],"VLN":[60,80,126],"scenarios.":[61],"Second,":[62],"performance":[64],"limited":[66],"when":[67],"using":[68],"LLMs":[70,86],"or":[71],"VLMs":[72,88],"without":[73,99,138],"fine-tuning,":[74],"due":[75],"absence":[78],"domain":[81],"knowledge.":[82],"Third,":[83],"while":[84,155],"fine-tuning":[85],"and":[87,150,178],"can":[89],"improve":[90],"results,":[91],"their":[92],"computational":[93,157],"costs":[94],"are":[95],"higher":[96],"than":[97],"those":[98],"fine-tuning.":[100,141],"To":[101],"address":[102],"limitations,":[104],"we":[105],"propose":[106],"Weakly-supervised":[107],"Partial":[108],"Contrastive":[109],"Learning":[110],"(WPCL),":[111],"method":[113,143,165],"that":[114,163],"enhances":[115,144],"an":[116],"agent\u2019s":[117,146],"identify":[120],"objects":[121],"from":[122],"scenarios":[127],"effectively":[129],"integrating":[130],"VLM":[132,140],"knowledge":[133],"into":[134],"perception":[136],"process,":[137],"requiring":[139],"Our":[142],"interpret":[149],"respond":[151],"environmental":[153],"cues":[154],"ensuring":[156],"efficiency.":[158],"Experimental":[159],"results":[160],"have":[161],"shown":[162],"our":[164,181],"outperforms":[166],"baseline":[168],"multiple":[171],"benchmarks,":[172],"validates":[174],"effectiveness,":[176],"robustness,":[177],"generalizability":[179],"method.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-11-28T00:00:00"}