{"id":"https://openalex.org/W7166802212","doi":"https://doi.org/10.18653/v1/2026.findings-acl.315","title":"CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering","display_name":"CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166802212","doi":"https://doi.org/10.18653/v1/2026.findings-acl.315"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.315","doi":"https://doi.org/10.18653/v1/2026.findings-acl.315","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.315","pdf_url":"https://aclanthology.org/2026.findings-acl.315.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.315.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102685914","display_name":"Xiyin Zeng","orcid":"https://orcid.org/0009-0000-4849-3949","observed_orcids":["https://orcid.org/0009-0000-4849-3949"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiyin Zeng","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139851654","display_name":"Yi Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Lu","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100446112","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-3086-3128","observed_orcids":["https://orcid.org/0000-0002-3086-3128","https://orcid.org/0000-0003-1662-2480"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405261251"],"apc_list":null,"apc_paid":null,"fwci":8.9044,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97367774,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6333","last_page":"6350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":9.999999747378752e-05,"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/visual-question-answering","display_name":"visual question answering","score":0.9750000238418579},{"id":"https://openalex.org/keywords/mixture-of-experts","display_name":"mixture of experts","score":0.9580000042915344},{"id":"https://openalex.org/keywords/expert-routing","display_name":"expert routing","score":0.902999997138977},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.8349999785423279}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.678600013256073},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.649399995803833},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5241000056266785},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C62360110","wikidata":"https://www.wikidata.org/wiki/Q96777007","display_name":"Circumscription","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3361000120639801},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.315","doi":"https://doi.org/10.18653/v1/2026.findings-acl.315","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.315","pdf_url":"https://aclanthology.org/2026.findings-acl.315.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.315","doi":"https://doi.org/10.18653/v1/2026.findings-acl.315","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.315","pdf_url":"https://aclanthology.org/2026.findings-acl.315.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335480","display_name":"Guangzhou Municipal Science and Technology Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166802212.pdf","grobid_xml":"https://content.openalex.org/works/W7166802212.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3204281258","https://openalex.org/W2937076652","https://openalex.org/W2553418567","https://openalex.org/W4414991672","https://openalex.org/W4413145967","https://openalex.org/W2800046969","https://openalex.org/W7117981893","https://openalex.org/W4394639892","https://openalex.org/W4411571913","https://openalex.org/W6941367375"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"requires":[4],"models":[5],"to":[6,38,69,81],"identify":[7],"the":[8,43,66,74,83,119],"correct":[9],"answer":[10,67],"options":[11,68],"based":[12,31],"on":[13,32],"both":[14],"visual":[15],"and":[16,101],"textual":[17],"evidence.Recent":[18],"Mixture-of-Experts":[19],"(MoE)":[20],"methods":[21],"improve":[22],"option":[23,77,99],"reasoning":[24],"by":[25],"grouping":[26],"similar":[27],"concepts":[28],"or":[29],"routing":[30,35,50],"examples.However,":[33],"unstable":[34],"can":[36],"lead":[37],"inconsistent":[39],"expert":[40,71],"selection":[41,72],"in":[42,73],"same":[44],"question":[45],"type,":[46],"while":[47],"overly":[48],"stable":[49],"may":[51],"reduce":[52],"flexibility.To":[53],"address":[54],"this,":[55],"we":[56],"propose":[57],"Concept-Guided":[58],"Routing":[59],"framework":[60],"(CoGR-MoE),":[61],"which":[62],"incorporates":[63],"semantics":[64],"of":[65,121],"guide":[70],"training":[75],"phase.Next,":[76],"features":[78],"are":[79,95],"used":[80,97],"reweight":[82],"selected":[84],"experts,":[85],"producing":[86],"discriminative":[87],"representations":[88,94],"for":[89,98],"each":[90],"candidate":[91],"option.These":[92],"optionlevel":[93],"further":[96],"comparison":[100],"optimized":[102],"via":[103],"contrastive":[104],"learning.The":[105],"experimental":[106],"results":[107],"indicate":[108],"that":[109],"CoGR-MoE":[110],"delivers":[111],"strong":[112],"performance":[113],"across":[114],"multiple":[115],"VQA":[116],"tasks,":[117],"demonstrating":[118],"effectiveness":[120],"our":[122],"approach.Our":[123],"code":[124],"is":[125,161],"available":[126],"at":[127],"CoGR-MoE.":[128],"Option-Aware":[129],"ReweightingRouter":[130],"T":[131],"\u2026":[132],"(I,":[133],"Q)":[134],"a.":[135],"Cornish":[136],"Cat":[137],"large":[138],"ears":[139,145,152],"broad":[140],"face":[141,147],"b.Devon":[142],"Rex":[143,154],"low":[144],"narrow":[146],"c.Sphnyx":[148],"hairless":[149],"skin":[150],"small":[151],"d.Selkirk":[153],"wide":[155],"eyes":[156],"sparse":[157],"coat":[158],"What":[159],"breed":[160],"this":[162],"cat?":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}