{"id":"https://openalex.org/W7138005932","doi":"https://doi.org/10.1609/aaai.v40i31.39867","title":"ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering","display_name":"ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138005932","doi":"https://doi.org/10.1609/aaai.v40i31.39867"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i31.39867","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39867","pdf_url":null,"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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i31.39867","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129711729","display_name":"Xinyue Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyue Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129706196","display_name":"Yuheng Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuheng Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129714133","display_name":"Hui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129667806","display_name":"Junhui Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhui Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"31","first_page":"26588","last_page":"26596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19449999928474426,"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":0.19449999928474426,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.1599999964237213,"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/T10028","display_name":"Topic Modeling","score":0.13349999487400055,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.9031000137329102},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6323000192642212},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.569100022315979},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5306000113487244},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.4480000138282776},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.44279998540878296},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.40639999508857727},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4016999900341034}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.9031000137329102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850000262260437},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5695000290870667},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.569100022315979},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.527999997138977},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.4480000138282776},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.44279998540878296},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.40639999508857727},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4016999900341034},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.39750000834465027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37950000166893005},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.335999995470047},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.30649998784065247},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.26969999074935913},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i31.39867","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39867","pdf_url":null,"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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i31.39867","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39867","pdf_url":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Typical":[0],"deep":[1],"clustering":[2,12,38,69,123,131],"methods,":[3],"while":[4],"achieving":[5],"notable":[6],"progress,":[7],"can":[8,49],"only":[9],"provide":[10,36],"one":[11],"result":[13],"per":[14],"dataset.":[15],"This":[16],"limitation":[17],"arises":[18],"from":[19,114],"their":[20,57],"assumption":[21],"of":[22,80,97],"a":[23,121],"fixed":[24],"underlying":[25],"data":[26],"distribution,":[27],"which":[28],"may":[29],"fail":[30],"to":[31,52,59,103,111],"meet":[32],"user":[33],"needs":[34],"and":[35,75,82,107,142],"unsatisfactory":[37],"outcomes.":[39],"Our":[40],"work":[41],"investigates":[42],"how":[43],"multi-modal":[44],"large":[45],"language":[46],"models":[47],"(MLLMs)":[48],"be":[50],"leveraged":[51],"achieve":[53],"user-driven":[54],"clustering,":[55],"emphasizing":[56],"adaptability":[58],"user-specified":[60],"semantic":[61],"requirements.":[62],"However,":[63],"directly":[64],"using":[65],"MLLM":[66],"output":[67],"for":[68,72],"has":[70],"risks":[71],"producing":[73],"unstructured":[74],"generic":[76],"image":[77],"descriptions":[78],"instead":[79],"feature-specific":[81],"concrete":[83],"ones.":[84],"To":[85],"address":[86],"these":[87,109],"issues,":[88],"our":[89],"method":[90],"first":[91],"discovers":[92],"that":[93],"MLLMs'":[94],"hidden":[95],"states":[96],"text":[98],"tokens":[99],"are":[100],"strongly":[101],"related":[102],"the":[104],"corresponding":[105],"features,":[106],"leverages":[108],"embeddings":[110],"perform":[112],"clusterings":[113],"any":[115],"user-defined":[116],"criteria.":[117],"We":[118],"also":[119],"employ":[120],"lightweight":[122],"head":[124],"augmented":[125],"with":[126],"pseudo-label":[127],"learning,":[128],"significantly":[129],"enhancing":[130],"accuracy.":[132],"Extensive":[133],"experiments":[134],"demonstrate":[135],"its":[136],"competitive":[137],"performance":[138],"on":[139],"diverse":[140],"datasets":[141],"metrics.":[143]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}