{"id":"https://openalex.org/W7138235459","doi":"https://doi.org/10.1609/aaai.v40i13.38017","title":"Efficient and Effective In-context Demonstration Selection with Coreset","display_name":"Efficient and Effective In-context Demonstration Selection with Coreset","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138235459","doi":"https://doi.org/10.1609/aaai.v40i13.38017"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38017","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38017","pdf_url":null,"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://doi.org/10.1609/aaai.v40i13.38017","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101444415","display_name":"Zihua Wang","orcid":"https://orcid.org/0009-0009-5127-0143"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zihua Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723519","display_name":"Jiarui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiarui Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129708876","display_name":"Haiyang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyang Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129660826","display_name":"Ming Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129719147","display_name":"Fei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129745604","display_name":"Xu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066964304","display_name":"Xiu-Shen Wei","orcid":"https://orcid.org/0000-0002-8200-1845"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiu-Shen Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049776286","display_name":"Siya Mi","orcid":"https://orcid.org/0000-0003-1751-7076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siya Mi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129737050","display_name":"Yu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101444415"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57494407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10458","last_page":"10466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8779000043869019,"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":0.8779000043869019,"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":0.03610000014305115,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.010099999606609344,"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/leverage","display_name":"Leverage (statistics)","score":0.7567999958992004},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7053999900817871},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5659000277519226},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.49570000171661377},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4214000105857849},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.30820000171661377}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7567999958992004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7542999982833862},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7053999900817871},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5157999992370605},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4643999934196472},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.2946000099182129},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38017","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38017","pdf_url":null,"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.v40i13.38017","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38017","pdf_url":null,"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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In-context":[0],"learning":[1],"(ICL)":[2],"has":[3],"emerged":[4],"as":[5],"a":[6,19,40,76,91,95,105,110,126,160],"powerful":[7],"paradigm":[8],"for":[9,163],"Large":[10],"Visual":[11],"Language":[12],"Models":[13],"(LVLMs),":[14],"enabling":[15],"them":[16],"to":[17,56,62,108,155],"leverage":[18],"few":[20],"examples":[21],"directly":[22],"from":[23],"input":[24],"contexts.":[25],"However,":[26],"the":[27,36,118,132,151,156],"effectiveness":[28,67],"of":[29,38],"this":[30,72],"approach":[31],"is":[32,43],"heavily":[33],"reliant":[34],"on":[35],"selection":[37,79,133,139],"demonstrations,":[39],"process":[41,134],"that":[42,88,113,130,146],"NP-hard.":[44],"Traditional":[45],"strategies,":[46,158],"including":[47],"random,":[48],"similarity-based":[49],"sampling":[50],"and":[51,66,165],"infoscore-based":[52],"sampling,":[53],"often":[54],"lead":[55],"inefficiencies":[57],"or":[58],"suboptimal":[59],"performance,":[60],"struggling":[61],"balance":[63],"both":[64],"efficiency":[65],"in":[68],"demonstration":[69,78,138,167],"selection.":[70,168],"In":[71],"paper,":[73],"we":[74,103,124],"propose":[75],"novel":[77],"framework":[80],"named":[81],"Coreset-based":[82],"Dual":[83],"Retrieval":[84],"(CoDR).":[85],"We":[86],"show":[87],"samples":[89],"within":[90],"diverse":[92,111],"subset":[93],"achieve":[94],"higher":[96],"expected":[97],"mutual":[98],"information.":[99],"To":[100],"implement":[101],"this,":[102],"introduce":[104],"cluster-pruning":[106],"method":[107,148],"construct":[109],"coreset":[112],"aligns":[114],"more":[115],"effectively":[116],"with":[117],"query":[119],"while":[120,140],"maintaining":[121],"diversity.":[122],"Additionally,":[123],"develop":[125],"dual":[127],"retrieval":[128],"mechanism":[129],"enhances":[131],"by":[135],"achieving":[136],"global":[137],"preserving":[141],"efficiency.":[142],"Experimental":[143],"results":[144],"demonstrate":[145],"our":[147],"significantly":[149],"improves":[150],"ICL":[152],"performance":[153],"compared":[154],"existing":[157],"providing":[159],"robust":[161],"solution":[162],"effective":[164],"efficient":[166]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}