{"id":"https://openalex.org/W7164813937","doi":"https://doi.org/10.1145/3805622.3810788","title":"Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models","display_name":"Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164813937","doi":"https://doi.org/10.1145/3805622.3810788"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810788","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810788","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810788","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138656619","display_name":"Zijie Zhou","orcid":"https://orcid.org/0009-0005-9587-4361"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Zhou","raw_affiliation_strings":["China University of Petroleum (Beijing), Beijing, China and Hainan Institute of China University of Petroleum (Beijing), Sanya, Hainan, China"],"raw_orcid":"https://orcid.org/0009-0005-9587-4361","affiliations":[{"raw_affiliation_string":"China University of Petroleum (Beijing), Beijing, China and Hainan Institute of China University of Petroleum (Beijing), Sanya, Hainan, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505776","display_name":"Dandan Zhu","orcid":"https://orcid.org/0009-0004-6935-1623"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dandan Zhu","raw_affiliation_strings":["China University of Petroleum (Beijing), Beijing, China and Hainan Institute of China University of Petroleum (Beijing), Sanya, Hainan, China"],"raw_orcid":"https://orcid.org/0009-0004-6935-1623","affiliations":[{"raw_affiliation_string":"China University of Petroleum (Beijing), Beijing, China and Hainan Institute of China University of Petroleum (Beijing), Sanya, Hainan, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108922632","display_name":"H. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangxiangpan Wang","raw_affiliation_strings":["China University of Petroleum (Beijing), Beijing, China and Hainan Institute of China University of Petroleum (Beijing), Sanya, Hainan, China"],"raw_orcid":"https://orcid.org/0009-0009-7145-0125","affiliations":[{"raw_affiliation_string":"China University of Petroleum (Beijing), Beijing, China and Hainan Institute of China University of Petroleum (Beijing), Sanya, Hainan, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377411","display_name":"Hailong Zhang","orcid":"https://orcid.org/0000-0002-8951-7094"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Zhang","raw_affiliation_strings":["South China Normal University, Foshan, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0003-1699-322X","affiliations":[{"raw_affiliation_string":"South China Normal University, Foshan, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044042054","display_name":"\u5b0c\u8f1d \u7533","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huishen Jiao","raw_affiliation_strings":["China University of Petroleum (Beijing), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1974-1893","affiliations":[{"raw_affiliation_string":"China University of Petroleum (Beijing), Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138653235","display_name":"Yi Zhao","orcid":"https://orcid.org/0009-0008-2999-6469"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhao","raw_affiliation_strings":["China University of Petroleum (Beijing), Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-2999-6469","affiliations":[{"raw_affiliation_string":"China University of Petroleum (Beijing), Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.934496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"525","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9761000275611877,"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":0.9761000275611877,"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":0.0044999998062849045,"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":0.0026000000070780516,"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/parametric-statistics","display_name":"Parametric statistics","score":0.5625},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5374000072479248},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4544999897480011},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.4375},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38989999890327454},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.387800008058548},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.37880000472068787},{"id":"https://openalex.org/keywords/euclidean-space","display_name":"Euclidean space","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6693000197410583},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529999732971191},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4544999897480011},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4388999938964844},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.4375},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3066999912261963},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2897999882698059},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810788","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810788","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810788","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810788","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6603273153305054}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2150884987","https://openalex.org/W2307512708","https://openalex.org/W2963518342","https://openalex.org/W2979382951","https://openalex.org/W3120043490","https://openalex.org/W4285255856","https://openalex.org/W4389520274","https://openalex.org/W4389523832","https://openalex.org/W4402716381","https://openalex.org/W4402716477","https://openalex.org/W4402726948","https://openalex.org/W4402727764","https://openalex.org/W4403081466","https://openalex.org/W4404002404","https://openalex.org/W4404575065","https://openalex.org/W4413146977","https://openalex.org/W4416036076","https://openalex.org/W7133220561"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"demonstrated":[5],"impressive":[6],"performance":[7],"on":[8,186],"multimodal":[9],"tasks":[10],"through":[11,128,145],"scaled":[12],"architectures":[13],"and":[14,36,61,110,156,182],"extensive":[15],"training.":[16],"Recent":[17],"studies":[18],"introduce":[19],"Mixture":[20],"of":[21,76,177],"Experts":[22],"(MoE)":[23],"into":[24],"LVLMs":[25],"for":[26],"improved":[27],"computational":[28],"efficiency.":[29],"However,":[30],"existing":[31],"MoE":[32,180],"approaches":[33],"treat":[34],"visual":[35,78,109],"linguistic":[37,111],"modalities":[38,50],"with":[39,174],"symmetric":[40],"architectures,":[41],"overlooking":[42],"the":[43,107],"inherent":[44],"asymmetry":[45,54,127],"in":[46,92,106],"how":[47],"these":[48,115],"two":[49,56],"are":[51],"processed.":[52],"This":[53],"causes":[55],"critical":[57],"issues.":[58],"First,":[59],"text":[60,70],"vision":[62],"form":[63],"hierarchical":[64,142],"rather":[65],"than":[66],"parallel":[67],"relationships,":[68],"as":[69],"queries":[71],"typically":[72],"describe":[73],"partial":[74],"aspects":[75],"complete":[77],"scenes.":[79],"Euclidean":[80],"expert":[81,131],"space":[82],"struggles":[83],"to":[84,100,184,195],"encode":[85],"such":[86],"containment":[87],"structures.":[88],"Second,":[89],"language":[90,150],"experts":[91,134,140,151],"deeper":[93],"layers":[94],"progressively":[95],"shift":[96],"from":[97],"evidence-based":[98],"processing":[99],"parametric":[101,153],"memory":[102,154],"dependence,":[103],"losing":[104],"grounding":[105,159],"provided":[108],"information.":[112],"To":[113],"address":[114],"issues,":[116],"we":[117],"propose":[118],"AsyMoE,":[119],"a":[120],"novel":[121],"architecture":[122],"that":[123,166],"explicitly":[124],"models":[125],"this":[126],"three":[129],"specialized":[130],"groups.":[132],"Intra-modality":[133],"handle":[135],"modality-specific":[136],"processing.":[137],"Hyperbolic":[138],"inter-modality":[139],"capture":[141],"cross-modal":[143],"relationships":[144],"negative":[146],"curvature":[147],"geometry.":[148],"Evidence-priority":[149],"suppress":[152],"activation":[155],"maintain":[157],"contextual":[158],"throughout":[160],"network":[161],"depth.":[162],"Extensive":[163],"experiments":[164],"demonstrate":[165],"AsyMoE":[167,189],"achieves":[168],"consistent":[169],"improvements":[170],"over":[171,179],"baseline":[172],"methods,":[173],"average":[175],"gains":[176],"1.5%":[178],"variants":[181],"up":[183],"3.8%":[185],"hallucination-sensitive":[187],"tasks.":[188],"activates":[190],"25.45%":[191],"fewer":[192],"parameters":[193],"compared":[194],"dense":[196],"models.":[197]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}