{"id":"https://openalex.org/W4416749828","doi":"https://doi.org/10.1109/iros60139.2025.11247345","title":"QueryAdapter: Rapid Adaptation of Vision-Language Models in Response to Natural Language Queries","display_name":"QueryAdapter: Rapid Adaptation of Vision-Language Models in Response to Natural Language Queries","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749828","doi":"https://doi.org/10.1109/iros60139.2025.11247345"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247345","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":"conference-paper","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/A5103112442","display_name":"N Chapman","orcid":"https://orcid.org/0000-0003-3002-8330"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Nicolas Harvey Chapman","raw_affiliation_strings":["Queensland University of Technology,School of Electrical Engineering and Robotics,Brisbane,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology,School of Electrical Engineering and Robotics,Brisbane,Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091323624","display_name":"Feras Dayoub","orcid":"https://orcid.org/0000-0002-4234-7374"},"institutions":[{"id":"https://openalex.org/I2802355861","display_name":"Australian Institute of Business","ror":"https://ror.org/01wf5jq34","country_code":"AU","type":"education","lineage":["https://openalex.org/I2802355861"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feras Dayoub","raw_affiliation_strings":["University of Adelaide,School of Computer Science and the Australian Institute of Machine Learning,Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide,School of Computer Science and the Australian Institute of Machine Learning,Adelaide,Australia","institution_ids":["https://openalex.org/I2802355861","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065533636","display_name":"Will N. Browne","orcid":"https://orcid.org/0000-0001-8979-2224"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Will Browne","raw_affiliation_strings":["Queensland University of Technology,School of Electrical Engineering and Robotics,Brisbane,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology,School of Electrical Engineering and Robotics,Brisbane,Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081617215","display_name":"Chris Lehnert","orcid":"https://orcid.org/0000-0002-4230-8068"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christopher Lehnert","raw_affiliation_strings":["Queensland University of Technology,School of Electrical Engineering and Robotics,Brisbane,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queensland University of Technology,School of Electrical Engineering and Robotics,Brisbane,Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42580285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9606","last_page":"9613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9811000227928162,"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":0.9811000227928162,"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":0.0044999998062849045,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.004399999976158142,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6062999963760376},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.54339998960495},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.52920001745224},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.5059000253677368},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4934000074863434},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41359999775886536},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4050000011920929},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.38100001215934753},{"id":"https://openalex.org/keywords/natural-language-user-interface","display_name":"Natural language user interface","score":0.38040000200271606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288000226020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126000285148621},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6062999963760376},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5001999735832214},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.38040000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3346000015735626},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.271699994802475}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247345","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2964115968","https://openalex.org/W3039883906","https://openalex.org/W3090386798","https://openalex.org/W3174702694","https://openalex.org/W3198377975","https://openalex.org/W3201048198","https://openalex.org/W3205786327","https://openalex.org/W4312291425","https://openalex.org/W4312310776","https://openalex.org/W4312323912","https://openalex.org/W4312424618","https://openalex.org/W4312651322","https://openalex.org/W4312956471","https://openalex.org/W4382365403","https://openalex.org/W4383108296","https://openalex.org/W4386071509","https://openalex.org/W4386790226","https://openalex.org/W4390871707","https://openalex.org/W4390872744","https://openalex.org/W4390873101","https://openalex.org/W4390874575","https://openalex.org/W4401414715","https://openalex.org/W4401990649","https://openalex.org/W4402354022","https://openalex.org/W4402754294","https://openalex.org/W4402778061","https://openalex.org/W4403012122","https://openalex.org/W4409262080","https://openalex.org/W4411244521"],"related_works":[],"abstract_inverted_index":{"A":[0],"domain":[1],"shift":[2],"exists":[3],"between":[4],"the":[5,17,29,88,119,135,177],"large-scale,":[6],"internet":[7],"data":[8,74,128],"used":[9],"to":[10,45,66,79,87,118,145,166,182],"train":[11],"a":[12,23,32,40,55,61,67,108],"Vision-Language":[13],"Model":[14],"(VLM)":[15],"and":[16,95,171,186],"raw":[18],"image":[19],"streams":[20],"collected":[21,75],"by":[22],"robot.":[24],"Existing":[25],"adaptation":[26],"strategies":[27],"require":[28],"definition":[30],"of":[31,34,110,137],"closed-set":[33],"classes,":[35],"which":[36],"is":[37],"impractical":[38],"for":[39,58,99,129],"robot":[41],"that":[42,158],"must":[43],"respond":[44],"diverse":[46],"natural":[47,68],"language":[48,69],"queries.":[49],"In":[50,131],"response,":[51],"we":[52,133],"present":[53],"QueryAdapter;":[54],"novel":[56],"framework":[57],"rapidly":[59],"adapting":[60],"pre-trained":[62],"VLM":[63,81,169],"in":[64,107],"response":[65],"query.":[70,89],"QueryAdapter":[71,159],"leverages":[72],"unlabelled":[73],"during":[76,151],"previous":[77],"deployments":[78],"align":[80],"features":[82],"with":[83,124],"semantic":[84],"classes":[85],"related":[86],"By":[90],"optimising":[91],"learnable":[92],"prompt":[93],"tokens":[94],"actively":[96],"selecting":[97],"objects":[98,116],"training,":[100],"an":[101],"adapted":[102],"model":[103],"can":[104],"be":[105,122],"produced":[106],"matter":[109],"minutes.":[111],"We":[112],"also":[113],"explore":[114],"how":[115],"unrelated":[117],"query":[120],"should":[121],"dealt":[123],"when":[125],"using":[126],"real-world":[127],"adaptation.":[130,152],"turn,":[132],"propose":[134],"use":[136],"object":[138,162],"captions":[139],"as":[140,190],"negative":[141],"class":[142],"labels,":[143],"helping":[144],"produce":[146],"better":[147],"calibrated":[148],"confidence":[149],"scores":[150],"Extensive":[153],"experiments":[154],"on":[155],"ScanNet++":[156],"demonstrate":[157],"significantly":[160],"enhances":[161],"retrieval":[163],"performance":[164],"compared":[165],"state-of-the-art":[167],"unsupervised":[168],"adapters":[170],"3D":[172],"scene":[173],"graph":[174],"methods.":[175],"Furthermore,":[176],"approach":[178],"exhibits":[179],"robust":[180],"generalization":[181],"abstract":[183],"affordance":[184],"queries":[185],"other":[187],"datasets,":[188],"such":[189],"Ego4D.":[191]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}