{"id":"https://openalex.org/W4404781870","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.221","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","display_name":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404781870","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.221"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.221","pdf_url":"https://aclanthology.org/2024.findings-emnlp.221.pdf","source":null,"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: EMNLP 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-emnlp.221.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113656054","display_name":"Songtao Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Songtao Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101287188","display_name":"Tuo Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuo Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019954538","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0002-2598-8321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040632841","display_name":"Yeying Jin","orcid":"https://orcid.org/0000-0001-7818-9534"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeying Jin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088584278","display_name":"Yuan Li","orcid":"https://orcid.org/0000-0002-6804-0792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024343415","display_name":"Zuozhu Liu","orcid":"https://orcid.org/0000-0002-7816-502X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuozhu Liu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5113656054"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.6139,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.99294276,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3843","last_page":"3860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9433000087738037,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9433000087738037,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9366000294685364,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6041557788848877},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49979424476623535},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.487150639295578},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4084189236164093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36364489793777466},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28760209679603577},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10911014676094055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6041557788848877},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49979424476623535},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.487150639295578},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4084189236164093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36364489793777466},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28760209679603577},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10911014676094055},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-emnlp.221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.221","pdf_url":"https://aclanthology.org/2024.findings-emnlp.221.pdf","source":null,"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: EMNLP 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.221","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.221","pdf_url":"https://aclanthology.org/2024.findings-emnlp.221.pdf","source":null,"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: EMNLP 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4474290519","display_name":null,"funder_award_id":"LZ23F020008","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8976068546","display_name":null,"funder_award_id":"62106222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404781870.pdf","grobid_xml":"https://content.openalex.org/works/W4404781870.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2057033141","https://openalex.org/W4252103056","https://openalex.org/W2917823318","https://openalex.org/W2917572814","https://openalex.org/W4242858628","https://openalex.org/W2979406678","https://openalex.org/W2915857720","https://openalex.org/W2916715723","https://openalex.org/W3006129753"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,50],"general-purpose":[3],"or":[4,24,31,174],"domain-specific":[5,87,132],"multimodal":[6,69,79,91,104],"large":[7],"language":[8],"models":[9],"(LLMs)":[10],"have":[11],"witnessed":[12],"remarkable":[13],"progress":[14],"for":[15,21,102,116],"medical":[16,70,80,92,105,149],"decision-making.However,":[17],"they":[18],"are":[19,135],"designated":[20],"specific":[22],"classification":[23,155],"generative":[25,68],"tasks,":[26],"and":[27,39,58,67,84,86,138,153,163,190,195],"require":[28],"model":[29,101,123,168,187],"training":[30],"finetuning":[32],"on":[33,145,175],"large-scale":[34],"datasets":[35,158],"with":[36,94,107,111,130,177],"sizeable":[37],"parameters":[38],"tremendous":[40],"computing,":[41],"hindering":[42],"their":[43],"clinical":[44],"utility":[45,197],"across":[46,119,157],"diverse":[47],"resource-constrained":[48],"scenarios":[49],"practice.In":[51],"this":[52],"paper,":[53],"we":[54,97],"propose":[55],"a":[56,112],"novel":[57],"lightweight":[59],"framework":[60],"Med-MoE":[61,74],"(Mixture-of-Experts)":[62],"that":[63,166],"tackles":[64],"both":[65,146],"discriminative":[66],"tasks.The":[71],"learning":[72],"of":[73,76,185,198],"consists":[75],"three":[77],"steps:":[78],"alignment,":[81],"instruction":[82,108],"tuning":[83],"routing,":[85],"MoE":[88],"tuning.After":[89],"aligning":[90],"images":[93],"LLM":[95],"tokens,":[96],"then":[98],"enable":[99],"the":[100,122,128,193],"different":[103],"tasks":[106,156],"tuning,":[109],"together":[110],"trainable":[113],"router":[114,129],"tailored":[115],"expert":[117],"selection":[118],"input":[120],"modalities.Finally,":[121],"is":[124],"tuned":[125],"by":[126,141],"integrating":[127],"multiple":[131],"experts,":[133],"which":[134],"selectively":[136],"activated":[137,186],"further":[139],"empowered":[140],"meta":[142],"expert.Comprehensive":[143],"experiments":[144],"open-and":[147],"close-end":[148],"question":[150],"answering":[151],"(Med-VQA)":[152],"image":[154],"such":[159],"as":[160],"VQA-RAD,":[161],"SLAKE":[162],"Path-VQA":[164],"demonstrate":[165],"our":[167,199],"can":[169],"achieve":[170],"performance":[171],"superior":[172],"to":[173],"par":[176],"state-of-the-art":[178],"baselines,":[179],"while":[180],"only":[181],"requiring":[182],"approximately":[183],"30%-50%":[184],"parameters.Extensive":[188],"analysis":[189],"ablations":[191],"corroborate":[192],"effectiveness":[194],"practical":[196],"method.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}