{"id":"https://openalex.org/W4403791611","doi":"https://doi.org/10.1145/3664647.3681010","title":"AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering","display_name":"AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791611","doi":"https://doi.org/10.1145/3664647.3681010"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","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/A5113315313","display_name":"Mahiro Ukai","orcid":null},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mahiro Ukai","raw_affiliation_strings":["Institute of Science Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0001-6266-9477","affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4400009020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073732915","display_name":"Shuhei Kurita","orcid":"https://orcid.org/0000-0001-7415-3120"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuhei Kurita","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7415-3120","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038408644","display_name":"Atsushi Hashimoto","orcid":"https://orcid.org/0000-0002-0799-4269"},"institutions":[{"id":"https://openalex.org/I146230289","display_name":"Omron (Japan)","ror":"https://ror.org/00q0w1h45","country_code":"JP","type":"company","lineage":["https://openalex.org/I146230289"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Hashimoto","raw_affiliation_strings":["OMRON SINIC X, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0799-4269","affiliations":[{"raw_affiliation_string":"OMRON SINIC X, Tokyo, Japan","institution_ids":["https://openalex.org/I146230289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077707500","display_name":"Yoshitaka Ushiku","orcid":"https://orcid.org/0000-0002-9014-1389"},"institutions":[{"id":"https://openalex.org/I146230289","display_name":"Omron (Japan)","ror":"https://ror.org/00q0w1h45","country_code":"JP","type":"company","lineage":["https://openalex.org/I146230289"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshitaka Ushiku","raw_affiliation_strings":["OMRON SINIC X, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9014-1389","affiliations":[{"raw_affiliation_string":"OMRON SINIC X, Tokyo, Japan","institution_ids":["https://openalex.org/I146230289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041272440","display_name":"Nakamasa Inoue","orcid":"https://orcid.org/0000-0002-9761-4142"},"institutions":[{"id":"https://openalex.org/I4400009020","display_name":"Institute of Science Tokyo","ror":"https://ror.org/05dqf9946","country_code":null,"type":"education","lineage":["https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nakamasa Inoue","raw_affiliation_strings":["Institute of Science Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9761-4142","affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I4400009020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52161892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"9234","last_page":"9243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9986000061035156,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9890000224113464,"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/question-answering","display_name":"Question answering","score":0.8206348419189453},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6534383893013},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4828522801399231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3956061005592346},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0787251889705658}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.8206348419189453},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6534383893013},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4828522801399231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3956061005592346},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0787251889705658},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":26,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2142192571","https://openalex.org/W2560730294","https://openalex.org/W2745461083","https://openalex.org/W2963530300","https://openalex.org/W2963954913","https://openalex.org/W3174708387","https://openalex.org/W3180037928","https://openalex.org/W3194952564","https://openalex.org/W3196047368","https://openalex.org/W4304091788","https://openalex.org/W4304098310","https://openalex.org/W4308235822","https://openalex.org/W4308235961","https://openalex.org/W4308236544","https://openalex.org/W4312956471","https://openalex.org/W4385567182","https://openalex.org/W4385570707","https://openalex.org/W4387968292","https://openalex.org/W4387969662","https://openalex.org/W4388186932","https://openalex.org/W4389519226","https://openalex.org/W4389524473","https://openalex.org/W4390872747","https://openalex.org/W4402754165","https://openalex.org/W4402916317"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912"],"abstract_inverted_index":{"Visual":[0],"question":[1,105,114,155],"answering":[2],"aims":[3],"to":[4,7,20,38,47,123,126,135],"provide":[5,39],"responses":[6],"questions":[8,22],"given":[9,81],"visual":[10,13,154],"input.":[11],"Recently,":[12],"programmatic":[14],"models":[15,26],"(VPMs),":[16],"which":[17],"generate":[18,48,124],"programs":[19],"answer":[21,127],"through":[23],"large":[24],"language":[25],"(LLMs),":[27],"have":[28],"attracted":[29],"attention.":[30],"However,":[31],"they":[32],"often":[33],"require":[34],"long":[35],"input":[36],"prompts":[37],"the":[40,78,108,113,118,128,151],"LLM":[41],"with":[42,89],"sufficient":[43],"API":[44,87],"usage":[45],"details":[46],"relevant":[49],"code.":[50],"To":[51],"address":[52],"this":[53],"limitation,":[54],"we":[55,132],"propose":[56],"AdaCoder,":[57],"an":[58,74],"adaptive":[59],"prompt":[60],"compression":[61,71,79],"framework":[62],"for":[63],"VPMs.":[64],"AdaCoder":[65,111,134],"operates":[66],"in":[67],"two":[68],"phases:":[69],"a":[70,82,93,103],"phase":[72],"and":[73,116,137],"inference":[75,109],"phase.":[76],"In":[77,107,130],"phase,":[80,110],"preprompt":[83,122],"that":[84,139],"describes":[85],"all":[86],"definitions":[88],"example":[90],"code":[91,125],"snippets,":[92],"set":[94],"of":[95,153],"compressed":[96,121],"preprompts":[97],"is":[98],"generated,":[99],"each":[100],"depending":[101],"on":[102],"specific":[104],"type.":[106],"predicts":[112],"type":[115],"chooses":[117],"appropriate":[119],"corresponding":[120],"question.":[129],"experiments,":[131],"apply":[133],"ViperGPT":[136],"demonstrate":[138],"it":[140],"reduces":[141],"token":[142],"length":[143],"by":[144],"71.1%,":[145],"while":[146],"maintaining":[147],"or":[148],"even":[149],"improving":[150],"performance":[152],"answering.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}