{"id":"https://openalex.org/W4403780643","doi":"https://doi.org/10.1145/3664647.3681369","title":"Q-MoE: Connector for MLLMs with Text-Driven Routing","display_name":"Q-MoE: Connector for MLLMs with Text-Driven Routing","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780643","doi":"https://doi.org/10.1145/3664647.3681369"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681369","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020836206","display_name":"Hanzi Wang","orcid":"https://orcid.org/0009-0005-2160-107X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hanzi Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024056452","display_name":"Jiamin Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Ren","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012664704","display_name":"Y. Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifeng Ding","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090424362","display_name":"Lei Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Ren","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113321413","display_name":"H. Jiang","orcid":"https://orcid.org/0000-0001-8046-0370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huixing Jiang","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113310638","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-6135-2697"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Li Auto Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Li Auto Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013283012","display_name":"Fangxiang Feng","orcid":"https://orcid.org/0000-0002-4798-4233"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxiang Feng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112115197","display_name":"Xiaojie Wang","orcid":"https://orcid.org/0000-0003-2015-0674"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5020836206"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55514312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"817","last_page":"825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9807999730110168,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9768999814987183,"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/computer-science","display_name":"Computer science","score":0.6147447824478149},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5764414072036743},{"id":"https://openalex.org/keywords/cable-gland","display_name":"Cable gland","score":0.5256691575050354},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.43240275979042053},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2952156662940979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6147447824478149},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5764414072036743},{"id":"https://openalex.org/C110925319","wikidata":"https://www.wikidata.org/wiki/Q12855","display_name":"Cable gland","level":2,"score":0.5256691575050354},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.43240275979042053},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2952156662940979}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681369","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2150884987","https://openalex.org/W2251512949","https://openalex.org/W2560730294","https://openalex.org/W2904565150","https://openalex.org/W2947312908","https://openalex.org/W2963518342","https://openalex.org/W2963622213","https://openalex.org/W3023989664","https://openalex.org/W3104279398","https://openalex.org/W3106859150","https://openalex.org/W4225323055","https://openalex.org/W4282028729","https://openalex.org/W4287121196","https://openalex.org/W4312846625","https://openalex.org/W4318718936","https://openalex.org/W4381802186","https://openalex.org/W6639102338","https://openalex.org/W6729503815","https://openalex.org/W6796487566","https://openalex.org/W6851592950"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W832519947","https://openalex.org/W3150514178","https://openalex.org/W2388088702","https://openalex.org/W2215963656","https://openalex.org/W2359908285","https://openalex.org/W2892897409","https://openalex.org/W1997449612"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1,20],"Language":[2,21],"Models":[3],"(MLLMs)":[4],"have":[5],"showcased":[6],"remarkable":[7],"advances":[8],"in":[9,61],"handling":[10],"various":[11],"vision-language":[12],"tasks.":[13],"These":[14],"models":[15],"typically":[16],"consist":[17],"of":[18,64,138],"a":[19,24,28,95],"Model":[22],"(LLM),":[23],"vision":[25,40],"encoder":[26],"and":[27,41,71,130],"connector":[29,48,97],"structure,":[30],"which":[31],"is":[32,44,115],"used":[33],"to":[34,49,58,101,117],"bridge":[35],"the":[36,47,51,59,89,136,139],"modality":[37],"gap":[38],"between":[39],"language.":[42],"It":[43],"challenging":[45],"for":[46,55,76],"filter":[50],"right":[52],"visual":[53,74,83],"information":[54,75,84,104],"LLM":[56],"according":[57],"task":[60],"hand.":[62],"Most":[63],"previous":[65],"connectors,":[66],"such":[67],"as":[68],"light-weight":[69],"projection":[70],"Q-former,":[72],"treat":[73],"diverse":[77],"tasks":[78,134],"uniformly,":[79],"therefore":[80],"lacking":[81],"task-specific":[82,103],"extraction":[85],"capabilities.":[86],"To":[87],"address":[88],"issue,":[90],"this":[91],"paper":[92],"proposes":[93],"Q-MoE,":[94],"query-based":[96],"with":[98,105],"Mixture-of-Experts":[99],"(MoE)":[100],"extract":[102],"text-driven":[106],"routing.":[107],"Furthermore,":[108],"an":[109,119],"optimal":[110,120],"path":[111],"based":[112],"training":[113],"strategy":[114],"proposed":[116],"find":[118],"expert":[121],"combination.":[122],"Extensive":[123],"experiments":[124],"on":[125],"two":[126],"popular":[127],"open-source":[128],"LLMs":[129],"several":[131],"different":[132],"visual-language":[133],"demonstrate":[135],"effectiveness":[137],"Q-MoE":[140],"connecter.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}