{"id":"https://openalex.org/W4415338238","doi":"https://doi.org/10.48550/arxiv.2509.25989","title":"Towards Reliable and Holistic Visual In-Context Learning Prompt Selection","display_name":"Towards Reliable and Holistic Visual In-Context Learning Prompt Selection","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4415338238","doi":"https://doi.org/10.48550/arxiv.2509.25989"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.25989","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.25989","pdf_url":"https://arxiv.org/pdf/2509.25989","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.25989","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070502941","display_name":"Wenxiao Wu","orcid":"https://orcid.org/0009-0005-9951-3846"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wu, Wenxiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079361172","display_name":"Jing\u2010Hao Xue","orcid":"https://orcid.org/0000-0003-1174-610X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Jing-Hao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101908952","display_name":"Chengming Xu","orcid":"https://orcid.org/0000-0003-3891-2227"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chengming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100322187","display_name":"Chen Liu","orcid":"https://orcid.org/0000-0002-9532-7721"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076341654","display_name":"Xinwei Sun","orcid":"https://orcid.org/0000-0001-6962-7985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xinwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035295689","display_name":"Changxin Gao","orcid":"https://orcid.org/0000-0003-2736-3920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Changxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013734579","display_name":"Nong Sang","orcid":"https://orcid.org/0000-0002-9167-1496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sang, Nong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084959430","display_name":"Yanwei Fu","orcid":"https://orcid.org/0000-0002-6595-6893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yanwei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5070502941"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9973999857902527,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9973999857902527,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9915000200271606,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9914000034332275,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.7854999899864197},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7355999946594238},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6532999873161316},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.5313000082969666},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4458000063896179},{"id":"https://openalex.org/keywords/preference-elicitation","display_name":"Preference elicitation","score":0.42649999260902405},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.39579999446868896},{"id":"https://openalex.org/keywords/jackknife-resampling","display_name":"Jackknife resampling","score":0.38580000400543213}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7854999899864197},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7355999946594238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6671000123023987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6633999943733215},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6532999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129000186920166},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.5313000082969666},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4458000063896179},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.42649999260902405},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C81790035","wikidata":"https://www.wikidata.org/wiki/Q847158","display_name":"Jackknife resampling","level":3,"score":0.38580000400543213},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.25989","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.25989","pdf_url":"https://arxiv.org/pdf/2509.25989","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.25989","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.25989","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.25989","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.25989","pdf_url":"https://arxiv.org/pdf/2509.25989","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415338238.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"In-Context":[1],"Learning":[2],"(VICL)":[3],"has":[4],"emerged":[5],"as":[6,31,43,63],"a":[7,32,59,90,99,151,162],"prominent":[8],"approach":[9,166],"for":[10,75,135],"adapting":[11],"visual":[12,189],"foundation":[13],"models":[14],"to":[15,58,106,156,167],"novel":[16],"tasks,":[17],"by":[18],"effectively":[19],"exploiting":[20],"contextual":[21],"information":[22],"embedded":[23],"in":[24,49,78,143],"in-context":[25,65,81,141],"examples,":[26],"which":[27],"can":[28,104],"be":[29],"formulated":[30],"global":[33,87,120],"ranking":[34,88],"problem":[35],"of":[36,92,112,132,140,173],"potential":[37],"candidates.":[38],"Current":[39],"VICL":[40],"methods,":[41],"such":[42],"Partial2Global":[44,84,133,186],"and":[45,109,137,161,170,184],"VPR,":[46],"are":[47],"grounded":[48],"the":[50,118],"similarity-priority":[51],"assumption":[52],"that":[53,179],"images":[54],"more":[55],"visually":[56],"similar":[57],"query":[60],"image":[61],"serve":[62],"better":[64],"examples.":[66,82],"This":[67],"foundational":[68],"assumption,":[69],"while":[70],"intuitive,":[71],"lacks":[72],"sufficient":[73],"justification":[74],"its":[76,86],"efficacy":[77],"selecting":[79],"optimal":[80],"Furthermore,":[83],"constructs":[85],"from":[89],"series":[91],"randomly":[93],"sampled":[94],"pairwise":[95,174],"preference":[96],"predictions.":[97],"Such":[98],"reliance":[100],"on":[101],"random":[102],"sampling":[103,165],"lead":[105],"incomplete":[107],"coverage":[108,172],"redundant":[110],"samplings":[111],"comparisons,":[113],"thus":[114],"further":[115],"adversely":[116],"impacting":[117],"final":[119],"ranking.":[121],"To":[122],"address":[123],"these":[124],"issues,":[125],"this":[126],"paper":[127],"introduces":[128],"an":[129],"enhanced":[130],"variant":[131],"designed":[134],"reliable":[136,158],"holistic":[138],"selection":[139],"examples":[142],"VICL.":[144],"Our":[145],"proposed":[146],"method,":[147],"dubbed":[148],"RH-Partial2Global,":[149],"leverages":[150],"jackknife":[152],"conformal":[153],"prediction-guided":[154],"strategy":[155],"construct":[157],"alternative":[159],"sets":[160],"covering":[163],"design-based":[164],"ensure":[168],"comprehensive":[169],"uniform":[171],"preferences.":[175],"Extensive":[176],"experiments":[177],"demonstrate":[178],"RH-Partial2Global":[180],"achieves":[181],"excellent":[182],"performance":[183],"outperforms":[185],"across":[187],"diverse":[188],"tasks.":[190]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-19T00:00:00"}