{"id":"https://openalex.org/W7138298415","doi":"https://doi.org/10.1609/aaai.v40i13.38066","title":"Injection Without Distortion: Geometrically Constrained Knowledge Enhancement for Vision-Language Models","display_name":"Injection Without Distortion: Geometrically Constrained Knowledge Enhancement for Vision-Language Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138298415","doi":"https://doi.org/10.1609/aaai.v40i13.38066"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i13.38066","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38066","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38066/42028","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://ojs.aaai.org/index.php/AAAI/article/download/38066/42028","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031663078","display_name":"Zhongze Wu","orcid":"https://orcid.org/0000-0002-4854-0263"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongze Wu","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129742312","display_name":"Xiu Su","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Su","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129677359","display_name":"Feng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Yang","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713592","display_name":"Shan You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan You","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129697898","display_name":"Jun Long","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Long","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029010292","display_name":"Yueyi Luo","orcid":"https://orcid.org/0000-0002-1516-3457"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueyi Luo","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55555556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10897","last_page":"10905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7954999804496765,"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":0.7954999804496765,"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":0.13459999859333038,"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":0.02500000037252903,"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/feature","display_name":"Feature (linguistics)","score":0.5748000144958496},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5052000284194946},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.40070000290870667},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.36570000648498535},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.33550000190734863},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3149000108242035},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.3109999895095825},{"id":"https://openalex.org/keywords/general-knowledge","display_name":"General knowledge","score":0.30489999055862427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6204000115394592},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38670000433921814},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C49929091","wikidata":"https://www.wikidata.org/wiki/Q1930471","display_name":"General knowledge","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C84685590","wikidata":"https://www.wikidata.org/wiki/Q1540472","display_name":"Knowledge engineering","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C56814567","wikidata":"https://www.wikidata.org/wiki/Q1323686","display_name":"Explicit knowledge","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i13.38066","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38066","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38066/42028","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"},{"id":"pmh:oai:ojs.aaai.org:article/38066","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38066","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38066","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38066/42028","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":[{"score":0.7006200551986694,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7596948744","display_name":null,"funder_award_id":"2021YFC3340800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320316125","display_name":"China Railway","ror":"https://ror.org/044wv3489"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138298415.pdf","grobid_xml":"https://content.openalex.org/works/W7138298415.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"are":[3],"widely":[4],"used":[5],"in":[6],"tasks":[7],"like":[8],"Open-Vocabulary":[9],"Object":[10],"Detection":[11],"and":[12,126],"zero-shot":[13],"Classification,":[14],"owing":[15],"to":[16,63],"their":[17],"powerful":[18],"generalization.":[19],"However,":[20],"recent":[21],"research":[22],"reveals":[23],"that":[24,80,136],"VLMs":[25,84],"exhibit":[26],"significant":[27],"performance":[28,64,139,150],"instability":[29],"when":[30],"tasked":[31],"with":[32,85],"recognizing":[33],"concepts":[34],"at":[35],"varying":[36],"granularities":[37],"(e.g.,":[38,131],"``animal''":[39],"vs.":[40],"``dog'').":[41],"Prevailing":[42],"methods":[43],"inject":[44],"external":[45,86],"knowledge":[46,87,97,114,127],"from":[47,128],"Large":[48],"Language":[49],"Models,":[50],"but":[51],"this":[52],"unconstrained":[53],"approach":[54],"distorts":[55],"the":[56,99,110,146],"VLM's":[57],"inherent":[58],"hierarchical":[59,90],"orthogonal":[60],"geometry,":[61],"leading":[62],"collapse":[65,151],"on":[66,152],"general":[67,113,153],"concepts.":[68,154],"To":[69],"address":[70],"this,":[71],"we":[72],"introduce":[73],"GeCoin,":[74],"an":[75,141],"innovative":[76],"Geometrically":[77],"Constrained":[78],"framework":[79],"safely":[81],"enhances":[82],"existing":[83],"for":[88],"improved":[89],"understanding,":[91],"without":[92],"additional":[93],"training.":[94],"By":[95],"projecting":[96],"into":[98],"null-space":[100],"of":[101,112,143],"a":[102],"query":[103],"concept's":[104],"feature":[105],"space,":[106],"GeCoin":[107,137],"mathematically":[108],"guarantees":[109],"preservation":[111],"while":[115],"integrating":[116],"specialized":[117],"information.":[118],"Extensive":[119],"experiments":[120],"across":[121],"large-scale":[122],"benchmarks,":[123],"diverse":[124],"VLMs,":[125],"various":[129],"LLMs":[130],"GPT-3.5,":[132],"Claude-3,":[133],"Gemini-Pro)":[134],"show":[135],"boosts":[138],"by":[140],"average":[142],"3.9%":[144],"over":[145],"strongest":[147],"baseline\u2014crucially":[148],"eradicating":[149]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}