{"id":"https://openalex.org/W4405037468","doi":"https://doi.org/10.1109/iccv51701.2025.02109","title":"WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image","display_name":"WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405037468","doi":"https://doi.org/10.1109/iccv51701.2025.02109"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.02141","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuci Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuci Liang","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101206691","display_name":"Xinheng Lyu","orcid":"https://orcid.org/0009-0009-5342-5495"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinheng Lyu","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604603","display_name":"Wenting Chen","orcid":"https://orcid.org/0000-0001-7912-154X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenting Chen","raw_affiliation_strings":["City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021195613","display_name":"Meidan Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meidan Ding","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622779","display_name":"Jipeng Zhang","orcid":"https://orcid.org/0000-0002-3269-6992"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jipeng Zhang","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006921134","display_name":"Xiangjian He","orcid":"https://orcid.org/0000-0001-8962-540X"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangjian He","raw_affiliation_strings":["University of Nottingham Ningbo China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham Ningbo China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055454866","display_name":"Song Wu","orcid":"https://orcid.org/0000-0003-3504-1630"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Wu","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080589649","display_name":"Xiaohan Xing","orcid":"https://orcid.org/0000-0002-9992-3387"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohan Xing","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057464765","display_name":"Sen Yang","orcid":"https://orcid.org/0000-0002-0639-4122"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sen Yang","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061309609","display_name":"Xiyue Wang","orcid":"https://orcid.org/0000-0002-3597-9090"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiyue Wang","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106408451","display_name":"Linlin Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linlin Shen","raw_affiliation_strings":["Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22718","last_page":"22727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.933899998664856,"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":0.933899998664856,"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/computer-science","display_name":"Computer science","score":0.6227353811264038},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6028582453727722},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4389493465423584},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.437730073928833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4177300035953522},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3851314187049866},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.10784116387367249}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6227353811264038},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6028582453727722},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4389493465423584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.437730073928833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4177300035953522},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3851314187049866},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10784116387367249}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.02141","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.02141","pdf_url":"https://arxiv.org/pdf/2412.02141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.02141","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.02141","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.02141","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.02141","pdf_url":"https://arxiv.org/pdf/2412.02141","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3077804837","display_name":null,"funder_award_id":"82261138629,12326610,B0166","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,111,139],"computational":[3],"pathology":[4],"have":[5],"produced":[6],"patch-level":[7],"Multi-modal":[8],"Large":[9],"Language":[10],"Models":[11],"(MLLMs),":[12],"but":[13],"these":[14,44],"models":[15,130],"are":[16],"limited":[17],"by":[18],"their":[19,29],"inability":[20],"to":[21,31,66],"analyze":[22],"whole":[23],"slide":[24],"images":[25],"(WSIs)":[26],"comprehensively":[27],"and":[28,102,121,149],"tendency":[30],"bypass":[32],"crucial":[33,73],"morphological":[34,71,140,147],"features":[35],"that":[36,91,126],"pathologists":[37],"rely":[38],"on":[39],"for":[40,74,87],"diagnosis.":[41,76],"To":[42,106],"address":[43],"challenges,":[45],"we":[46,81,114],"first":[47],"introduce":[48],"WSI-Bench,":[49],"a":[50,84,93,136,143],"large-scale":[51],"morphology-aware":[52],"benchmark":[53],"containing":[54],"180k":[55],"VQA":[56],"pairs":[57],"from":[58],"9,850":[59],"WSIs":[60],"across":[61,131],"30":[62],"cancer":[63],"types,":[64],"designed":[65],"evaluate":[67],"MLLMs'":[68],"understanding":[69,90,148],"of":[70],"characteristics":[72],"accurate":[75],"Building":[77],"upon":[78],"this":[79],"benchmark,":[80],"present":[82],"WSI-LLaVA,":[83],"novel":[85],"framework":[86],"gigapixel":[88],"WSI":[89,118],"employs":[92],"three-stage":[94],"training":[95],"approach:":[96],"WSI-text":[97],"alignment,":[98,101],"feature":[99],"space":[100],"task-specific":[103],"instruction":[104],"tuning.":[105],"better":[107],"assess":[108],"model":[109],"performance":[110],"pathological":[112],"contexts,":[113],"develop":[115],"two":[116],"specialized":[117],"metrics:":[119],"WSI-Precision":[120],"WSI-Relevance.":[122],"Experimental":[123],"results":[124],"demonstrate":[125],"WSI-LLaVA":[127],"outperforms":[128],"existing":[129],"all":[132],"capability":[133],"dimensions,":[134],"with":[135],"significant":[137],"improvement":[138],"analysis,":[141],"establishing":[142],"clear":[144],"correlation":[145],"between":[146],"diagnostic":[150],"accuracy.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}