{"id":"https://openalex.org/W7203712939","doi":"https://doi.org/10.48550/arxiv.2608.15698","title":"ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval","display_name":"ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval","publication_year":2026,"publication_date":"2026-08-16","ids":{"openalex":"https://openalex.org/W7203712939","doi":"https://doi.org/10.48550/arxiv.2608.15698"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.15698","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15698","pdf_url":"https://arxiv.org/pdf/2608.15698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.15698","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143975730","display_name":"Chunyi Peng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Chunyi","raw_affiliation_strings":["Northeastern University Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125533133","display_name":"Zhipeng Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Zhipeng","raw_affiliation_strings":["Northeastern University Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125406624","display_name":"Yukun Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan, Yukun","raw_affiliation_strings":["Tsinghua University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147423475","display_name":"Liu Zhenghao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Zhenghao","raw_affiliation_strings":["Northeastern University Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147441721","display_name":"Yu Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Shi","raw_affiliation_strings":["Tsinghua University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875685","display_name":"Sen Mei","orcid":"https://orcid.org/0009-0008-2181-5440","observed_orcids":["https://orcid.org/0009-0008-2181-5440"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei, Sen","raw_affiliation_strings":["Tsinghua University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113823230","display_name":"Sun Yubo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Yubo","raw_affiliation_strings":["Peking University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University Beijing , China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146593270","display_name":"Yongheng Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Yongheng","raw_affiliation_strings":["Tsinghua University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147395705","display_name":"Zhou Jie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Jie","raw_affiliation_strings":["Tsinghua University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013145169","display_name":"Yu Gu","orcid":"https://orcid.org/0000-0001-7422-6254","observed_orcids":["https://orcid.org/0000-0001-7422-6254","https://orcid.org/0000-0003-4181-6041"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gu, Yu","raw_affiliation_strings":["Northeastern University Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124793309","display_name":"Yu Ge","orcid":"https://orcid.org/0009-0003-0487-5138","observed_orcids":["https://orcid.org/0009-0003-0487-5138"]},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Ge","raw_affiliation_strings":["Northeastern University Shenyang , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University Shenyang , China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147416970","display_name":"Sun Maosong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Maosong","raw_affiliation_strings":["Tsinghua University Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6743000149726868,"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":0.6743000149726868,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.20679999887943268,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.04650000110268593,"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/vision-language-models","display_name":"vision-language models","score":0.7139999866485596},{"id":"https://openalex.org/keywords/multimodal-retrieval-augmented-generation","display_name":"multimodal retrieval-augmented generation","score":0.8140000104904175},{"id":"https://openalex.org/keywords/evidence-representation","display_name":"evidence representation","score":0.3540000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860999703407288},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5527999997138977},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4961000084877014},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4848000109195709},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.4675999879837036},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4514000117778778},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.3928000032901764},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3840999901294708},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2572999894618988}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.15698","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15698","pdf_url":"https://arxiv.org/pdf/2608.15698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.15698","doi":"https://doi.org/10.48550/arxiv.2608.15698","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.15698","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.15698","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.15698","pdf_url":"https://arxiv.org/pdf/2608.15698","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203712939.pdf","grobid_xml":"https://content.openalex.org/works/W7203712939.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2908510526","https://openalex.org/W4297808394","https://openalex.org/W4395474395","https://openalex.org/W4400531953","https://openalex.org/W4402345917","https://openalex.org/W4403324120","https://openalex.org/W4403746919","https://openalex.org/W4405254469","https://openalex.org/W4405354512","https://openalex.org/W4406139274","https://openalex.org/W4414488845","https://openalex.org/W4414968495","https://openalex.org/W4416060568","https://openalex.org/W4416452771","https://openalex.org/W4416654759","https://openalex.org/W4417160737","https://openalex.org/W7129938410","https://openalex.org/W7141460672","https://openalex.org/W7148651267","https://openalex.org/W7160423250","https://openalex.org/W7161057124","https://openalex.org/W7163578588","https://openalex.org/W7166710457","https://openalex.org/W7167905942"],"related_works":["https://openalex.org/W7153003918","https://openalex.org/W4416654759","https://openalex.org/W7165689667","https://openalex.org/W7221138438","https://openalex.org/W4400373146","https://openalex.org/W7204478860","https://openalex.org/W7172397956","https://openalex.org/W7221971028","https://openalex.org/W4416035358","https://openalex.org/W7147075592"],"abstract_inverted_index":{"Visual":[0],"document":[1,17,82,161],"retrieval":[2,162,180,187,221],"is":[3,21],"a":[4,74,119],"critical":[5],"component":[6],"of":[7,63,128,153],"multimodal":[8],"retrieval-augmented":[9],"generation,":[10],"aiming":[11],"to":[12,123,140,207],"identify":[13],"query-relevant":[14,86],"pages":[15],"from":[16],"collections":[18],"where":[19],"evidence":[20,45,87,98,200],"distributed":[22],"across":[23],"text,":[24],"layout,":[25],"charts,":[26],"and":[27,60,99,132,147,169,182,213,224],"visual":[28,42,55,81,97,113,160,179,199,216],"structures.":[29],"Recent":[30],"efforts":[31],"toward":[32],"finer-grained":[33],"supervision":[34,49],"primarily":[35],"rely":[36],"on":[37,111,158],"textual":[38,105,211],"descriptions":[39],"or":[40,57,108],"localized":[41,96,198],"regions":[43],"as":[44,88,136],"proxies.":[46],"However,":[47],"such":[48],"signals":[50],"may":[51],"either":[52,104],"overlook":[53],"complex":[54,214],"structures":[56,217],"provide":[58],"incomplete":[59],"inaccurate":[61],"representations":[62,107],"the":[64,126,142,151,154,177,183,205],"underlying":[65],"evidence.":[66],"To":[67],"address":[68],"these":[69,134],"limitations,":[70],"we":[71],"propose":[72],"ConceptFormer,":[73],"latent":[75,91,129,194],"concept":[76,130],"representation":[77,139],"learning":[78,152],"framework":[79],"for":[80],"retrieval.":[83],"ConceptFormer":[84,117,166],"models":[85],"continuous,":[89],"query-conditioned":[90],"concepts":[92,135,195],"that":[93,165,193],"explicitly":[94],"bridge":[95,141],"semantic":[100,143,202],"relevance,":[101,203],"without":[102],"requiring":[103],"intermediate":[106,138],"direct":[109],"reliance":[110],"raw":[112],"annotations.":[114],"During":[115],"training,":[116],"employs":[118],"strong":[120,220],"vision-language":[121],"model":[122],"dynamically":[124],"determine":[125],"number":[127],"tokens":[131],"uses":[133],"an":[137],"gap":[144],"between":[145],"queries":[146],"documents,":[148],"thereby":[149],"guiding":[150],"embedding":[155],"space.":[156],"Experiments":[157],"diverse":[159],"benchmarks":[163],"demonstrate":[164],"achieves":[167],"16.7\\%":[168],"22.1\\%":[170],"relative":[171],"improvements":[172],"in":[173],"average":[174],"NDCG@10":[175],"over":[176],"strongest":[178,184],"baseline":[181],"OCR-based":[185],"text":[186],"baseline,":[188],"respectively.":[189],"Further":[190],"analysis":[191],"reveals":[192],"effectively":[196],"connect":[197],"with":[201],"enabling":[204],"retriever":[206],"capture":[208],"both":[209],"fine-grained":[210],"cues":[212],"document-level":[215],"while":[218],"preserving":[219],"alignment.":[222],"Codes":[223],"data":[225],"are":[226],"available":[227],"at":[228],"https://github.com/Neuir/ConceptFormer.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-19T00:00:00"}