{"id":"https://openalex.org/W7138902137","doi":"https://doi.org/10.1609/aaai.v40i40.40681","title":"Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach","display_name":"Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138902137","doi":"https://doi.org/10.1609/aaai.v40i40.40681"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i40.40681","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i40.40681","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40681/44642","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40681/44642","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101864077","display_name":"Biao Wu","orcid":"https://orcid.org/0000-0003-3752-146X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Biao Wu","raw_affiliation_strings":["University of Technology Sydney"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101421958","display_name":"Manquan Fang","orcid":"https://orcid.org/0000-0002-9816-9415"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":["University of Liverpool"],"affiliations":[{"raw_affiliation_string":"University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069988750","display_name":"Ling Chen","orcid":"https://orcid.org/0000-0002-6468-5729"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ling Chen","raw_affiliation_strings":["University of Technology Sydney"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129998556","display_name":"Ke Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ke Xu","raw_affiliation_strings":["University of Liverpool"],"affiliations":[{"raw_affiliation_string":"University of Liverpool","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047024062","display_name":"Tao Cheng","orcid":"https://orcid.org/0000-0001-6278-5286"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tao Cheng","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129953735","display_name":"Jun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University College London"],"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101864077"],"corresponding_institution_ids":["https://openalex.org/I114017466"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92164179,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"40","first_page":"33890","last_page":"33898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.921999990940094,"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":0.921999990940094,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.030799999833106995,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.006300000008195639,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/interpretability","display_name":"Interpretability","score":0.894599974155426},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6557000279426575},{"id":"https://openalex.org/keywords/geolocation","display_name":"Geolocation","score":0.6541000008583069},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47929999232292175},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.45500001311302185},{"id":"https://openalex.org/keywords/global-positioning-system","display_name":"Global Positioning System","score":0.3822000026702881},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.3400999903678894}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.894599974155426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516999840736389},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6557000279426575},{"id":"https://openalex.org/C22041718","wikidata":"https://www.wikidata.org/wiki/Q638949","display_name":"Geolocation","level":2,"score":0.6541000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6420000195503235},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4625999927520752},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.45500001311302185},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C41856607","wikidata":"https://www.wikidata.org/wiki/Q483130","display_name":"Geographic information system","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i40.40681","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i40.40681","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40681/44642","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i40.40681","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i40.40681","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40681/44642","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138902137.pdf","grobid_xml":"https://content.openalex.org/works/W7138902137.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"vision-language":[3],"models":[4],"have":[5],"opened":[6],"up":[7],"new":[8,151],"possibilities":[9],"for":[10,154],"reasoning-driven":[11],"image":[12,25,158],"geolocalization.":[13,159],"However,":[14],"existing":[15,48],"approaches":[16],"often":[17],"rely":[18],"on":[19,87,93,106],"synthetic":[20,90],"reasoning":[21,45,67,124],"annotations":[22],"or":[23,89],"external":[24],"retrieval,":[26],"which":[27],"can":[28],"limit":[29],"interpretability":[30],"and":[31,51,135,156,164,170],"generalizability.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,95],"present":[37],"Geo-R,":[38,148],"a":[39,64,97,150],"retrieval-free":[40,152],"framework":[41],"that":[42,69],"uncovers":[43],"structured":[44,122],"paths":[46],"from":[47],"ground-truth":[49],"coordinates":[50,77],"optimizes":[52],"geolocation":[53],"accuracy":[54],"via":[55],"reinforcement":[56,99],"learning.":[57],"We":[58],"propose":[59],"the":[60,110,145,168],"Chain":[61],"of":[62,147],"Region,":[63],"rule-based":[65],"hierarchical":[66],"paradigm":[68,153],"generates":[70],"precise,":[71],"interpretable":[72,157],"supervision":[73],"by":[74],"mapping":[75],"GPS":[76],"to":[78,112],"geographic":[79,123],"entities":[80],"(e.g.,":[81],"country,":[82],"province,":[83],"city)":[84],"without":[85],"relying":[86],"model-generated":[88],"labels.":[91],"Building":[92],"this,":[94],"introduce":[96],"lightweight":[98],"learning":[100],"strategy":[101],"with":[102,125],"coordinate-aligned":[103],"rewards":[104],"based":[105],"Haversine":[107],"distance,":[108],"enabling":[109],"model":[111,169],"refine":[113],"predictions":[114],"through":[115],"spatially":[116],"meaningful":[117],"feedback.":[118],"Our":[119],"approach":[120],"bridges":[121],"direct":[126],"spatial":[127],"supervision,":[128],"yielding":[129],"improved":[130],"localization":[131],"accuracy,":[132],"stronger":[133],"generalization,":[134],"more":[136],"transparent":[137],"inference.":[138],"Experimental":[139],"results":[140],"across":[141],"multiple":[142],"benchmarks":[143],"confirm":[144],"effectiveness":[146],"establishing":[149],"scalable":[155],"To":[160],"facilitate":[161],"further":[162],"research":[163],"ensure":[165],"reproducibility,":[166],"both":[167],"code":[171],"will":[172],"be":[173],"made":[174],"publicly":[175],"available.":[176]},"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}