{"id":"https://openalex.org/W4416140579","doi":"https://doi.org/10.1109/tnnls.2025.3624691","title":"Unseen From Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation","display_name":"Unseen From Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416140579","doi":"https://doi.org/10.1109/tnnls.2025.3624691","pmid":"https://pubmed.ncbi.nlm.nih.gov/41212700"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3624691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3624691","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.18065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103119777","display_name":"Ziming Wei","orcid":"https://orcid.org/0009-0008-5350-7805"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziming Wei","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-5350-7805","affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101923104","display_name":"Bingqian Lin","orcid":"https://orcid.org/0000-0002-8763-9530"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingqian Lin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8763-9530","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053967353","display_name":"Yunshuang Nie","orcid":"https://orcid.org/0009-0000-9717-2308"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunshuang Nie","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-9717-2308","affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434210","display_name":"Jiaqi Chen","orcid":"https://orcid.org/0009-0002-5126-3460"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaqi Chen","raw_affiliation_strings":["University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0002-5126-3460","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100594712","display_name":"Shikui Ma","orcid":"https://orcid.org/0000-0002-8340-9762"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shikui Ma","raw_affiliation_strings":["Hunan Artificial Intelligence and Robotics Institute Company Ltd., Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-8340-9762","affiliations":[{"raw_affiliation_string":"Hunan Artificial Intelligence and Robotics Institute Company Ltd., Changsha, China","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041457457","display_name":"Hang Xu","orcid":"https://orcid.org/0000-0003-3645-8972"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Xu","raw_affiliation_strings":["Huawei Noah’s Ark Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3645-8972","affiliations":[{"raw_affiliation_string":"Huawei Noah’s Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3213-3062","affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103119777"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.962,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8142884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"37","issue":"4","first_page":"1726","last_page":"1738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9796000123023987,"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":0.9796000123023987,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0034000000450760126,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0027000000700354576,"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/rewriting","display_name":"Rewriting","score":0.8422999978065491},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.745199978351593},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5494999885559082},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.46549999713897705},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.37770000100135803},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.36410000920295715},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3628000020980835}],"concepts":[{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.8422999978065491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559999823570251},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.745199978351593},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5231000185012817},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.37770000100135803},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26809999346733093}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2025.3624691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3624691","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41212700","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41212700","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:2503.18065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.18065","pdf_url":"https://arxiv.org/pdf/2503.18065","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.18065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.18065","pdf_url":"https://arxiv.org/pdf/2503.18065","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1763039448","display_name":null,"funder_award_id":"PCL2024A04","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3099805375","display_name":null,"funder_award_id":"PCL2025A12","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6220011100","display_name":null,"funder_award_id":"BX20250379","funder_id":"https://openalex.org/F4320335768","funder_display_name":"National Postdoctoral Program for Innovative Talents"},{"id":"https://openalex.org/G6630003392","display_name":null,"funder_award_id":"62476293","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8966190457","display_name":null,"funder_award_id":"2025M771521","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320335768","display_name":"National Postdoctoral Program for Innovative Talents","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Data":[0],"scarcity":[1],"is":[2],"a":[3,62,165,170],"long-standing":[4],"challenge":[5],"in":[6,92],"the":[7,15,35,38,46,55,72,155,190,204],"vision-language":[8,111],"navigation":[9],"(VLN)":[10],"field,":[11],"which":[12,69,145],"extremely":[13],"hinders":[14],"generalization":[16,209],"of":[17,211],"agents":[18],"to":[19,33,53,98,119,153],"unseen":[20,73],"environments.":[21],"Previous":[22],"works":[23],"primarily":[24],"rely":[25],"on":[26,188],"additional":[27],"simulator":[28,39],"data":[29,48,177,183],"or":[30],"web-collected":[31,47],"images/videos":[32],"improve":[34],"generalization.":[36,100],"However,":[37],"environments":[40,192,200],"still":[41],"face":[42],"limited":[43],"diversity,":[44],"and":[45,95,114,131,159,195,198,207],"often":[49],"require":[50],"extensive":[51],"labor":[52],"remove":[54],"noise.":[56],"In":[57],"this":[58],"article,":[59],"we":[60,102,109,140],"propose":[61,141],"Rewriting-driven":[63],"AugMentation":[64],"(RAM)":[65],"paradigm":[66],"for":[67],"VLN,":[68],"directly":[70],"creates":[71],"observation-instruction":[74,87],"pairs":[75,88],"via":[76,134],"rewriting":[77,84],"human-annotated":[78],"training":[79,167],"data.":[80],"Benefiting":[81],"from":[82],"our":[83,212],"mechanism,":[85],"new":[86,160],"can":[89],"be":[90],"obtained":[91],"both":[93,189],"simulator-free":[94],"labor-saving":[96],"manners":[97],"promote":[99],"Specifically,":[101],"first":[103],"introduce":[104],"object-enriched":[105,122],"observation":[106,126,172],"rewriting,":[107,144],"where":[108],"combine":[110],"models":[112,117,137],"(VLMs)":[113],"large":[115],"language":[116],"(LLMs)":[118],"derive":[120],"rewritten":[121,148],"scene":[123],"descriptions,":[124],"enabling":[125],"synthesis":[127],"with":[128,169],"diverse":[129],"objects":[130],"spatial":[132],"layouts":[133],"text-to-image":[135],"generation":[136],"(T2IMs).":[138],"Then,":[139],"observation-contrast":[142],"instruction":[143],"generates":[146],"observation-aligned":[147],"instructions":[149],"by":[150],"requiring":[151],"LLMs":[152],"reason":[154],"difference":[156],"between":[157],"original":[158],"observations.":[161],"We":[162],"further":[163],"develop":[164],"mixing-then-focusing":[166],"strategy":[168],"random":[171],"cropping":[173],"scheme,":[174],"effectively":[175],"enhancing":[176],"distribution":[178],"diversity":[179],"while":[180],"suppressing":[181],"augmentation":[182],"noise":[184],"during":[185],"training.":[186],"Experiments":[187],"discrete":[191],"(R2R,":[193],"REVERIE,":[194],"R4R":[196],"datasets)":[197],"continuous":[199],"(R2R-CE":[201],"dataset)":[202],"show":[203],"superior":[205],"performance":[206],"impressive":[208],"ability":[210],"method.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-04T09:04:59.091469","created_date":"2025-10-10T00:00:00"}