{"id":"https://openalex.org/W4403791409","doi":"https://doi.org/10.1145/3664647.3681584","title":"LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound","display_name":"LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791409","doi":"https://doi.org/10.1145/3664647.3681584"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681584","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681584","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":"conference-paper","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/A5018711512","display_name":"Xuechen Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158570","display_name":"Zhejiang University-University of Edinburgh Institute","ror":"https://ror.org/04jth1r26","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210158570","https://openalex.org/I76130692","https://openalex.org/I98677209"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuechen Guo","raw_affiliation_strings":["ZJU-UIUC Institute, Zhejiang University, Haining, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0005-0682-1138","affiliations":[{"raw_affiliation_string":"ZJU-UIUC Institute, Zhejiang University, Haining, Zhejiang, China","institution_ids":["https://openalex.org/I4210158570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103021774","display_name":"Wenhao Chai","orcid":"https://orcid.org/0000-0003-2611-0008"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenhao Chai","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2611-0008","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087948160","display_name":"Shiyan Li","orcid":"https://orcid.org/0000-0003-3574-7932"},"institutions":[{"id":"https://openalex.org/I2802390878","display_name":"Sir Run Run Shaw Hospital","ror":"https://ror.org/00ka6rp58","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2802390878"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-Yan Li","raw_affiliation_strings":["Zhejiang University School of Medicine Sir Run Run Shaw Hospital, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-3574-7932","affiliations":[{"raw_affiliation_string":"Zhejiang University School of Medicine Sir Run Run Shaw Hospital, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I2802390878","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089410490","display_name":"Gaoang Wang","orcid":"https://orcid.org/0000-0002-8403-1538"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoang Wang","raw_affiliation_strings":["ZJU-UIUC Institute, Zhejiang University & Shanghai Artificial Intelligence Laboratory, Haining, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-8403-1538","affiliations":[{"raw_affiliation_string":"ZJU-UIUC Institute, Zhejiang University & Shanghai Artificial Intelligence Laboratory, Haining, Zhejiang, China","institution_ids":["https://openalex.org/I4391012619","https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8845","last_page":"8854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8762999773025513,"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":0.8762999773025513,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.8137999773025513,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.7936999797821045,"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":0.6920045018196106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.413940966129303},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36731305718421936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920045018196106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.413940966129303},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36731305718421936}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681584","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681584","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":5,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W4386973901","https://openalex.org/W4389520259","https://openalex.org/W4390874575","https://openalex.org/W4402753899"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1,183],"Language":[2,185],"Model":[3],"(MLLM)":[4],"has":[5],"recently":[6],"garnered":[7],"attention":[8],"as":[9],"a":[10,20,77,93,126,152],"prominent":[11],"research":[12],"focus.":[13],"By":[14],"harnessing":[15],"powerful":[16],"LLM,":[17],"it":[18],"facilitates":[19],"transition":[21],"of":[22,125],"conversational":[23],"generative":[24],"AI":[25],"from":[26,159,169],"unimodal":[27],"text":[28,128,146,168],"to":[29,36,64,100,114,140,198],"performing":[30],"multimodal":[31,154],"tasks.":[32],"This":[33],"boom":[34],"begins":[35],"significantly":[37],"impact":[38],"medical":[39,51,61,84,105,115,199],"field.":[40],"However,":[41],"general":[42],"visual":[43,52,70,85,106],"language":[44],"model":[45,178],"(VLM)":[46],"lacks":[47],"sophisticated":[48],"comprehension":[49],"for":[50,60,82,103,189],"question":[53],"answering":[54],"(Med-VQA).":[55],"Even":[56],"models":[57,209],"specifically":[58],"tailored":[59],"domain":[62],"tend":[63],"produce":[65],"vague":[66],"answers":[67],"with":[68,96,130,137],"weak":[69],"relevance.":[71],"In":[72,123],"this":[73],"paper,":[74],"we":[75,91,109,133,150],"propose":[76],"fine-grained":[78,97],"adaptive":[79],"VLM":[80],"architecture":[81],"Chinese":[83,155,184],"conversations":[86],"through":[87],"parameter-efficient":[88],"tuning.":[89,175],"Specifically,":[90],"devise":[92],"fusion":[94],"module":[95],"vision":[98],"encoders":[99],"achieve":[101],"enhancement":[102],"subtle":[104],"semantics.":[107],"Then":[108],"note":[110],"data":[111,165],"redundancy":[112],"common":[113],"scenes":[116],"is":[117],"ignored":[118],"in":[119],"most":[120],"prior":[121],"works.":[122],"cases":[124],"single":[127],"paired":[129],"multiple":[131],"figures,":[132],"utilize":[134],"weighted":[135],"scoring":[136],"knowledge":[138],"distillation":[139],"adaptively":[141],"screen":[142],"valid":[143],"images":[144],"mirroring":[145],"descriptions.":[147],"For":[148],"execution,":[149],"leverage":[151],"large-scale":[153],"ultrasound":[156],"dataset":[157],"obtained":[158],"the":[160],"hospital.":[161],"We":[162],"create":[163],"instruction-following":[164],"based":[166],"on":[167,210],"professional":[170],"doctors,":[171],"which":[172],"ensures":[173],"effective":[174],"With":[176],"enhanced":[177],"and":[179,186,196],"quality":[180],"data,":[181],"our":[182],"Vision":[187],"Assistant":[188],"Ultra":[190],"sound":[191],"(LLaVA-Ultra)":[192],"shows":[193],"strong":[194],"capability":[195],"robustness":[197],"scenarios.":[200],"On":[201],"three":[202],"Med-VQA":[203],"datasets,":[204],"LLaVA-Ultra":[205],"surpasses":[206],"previous":[207],"state-of-the-art":[208],"various":[211],"metrics.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}