{"id":"https://openalex.org/W7171795614","doi":"https://doi.org/10.48550/arxiv.2607.26885","title":"SCALPEL: Semantic Cross-modal Alignment via LLM-Powered Encoder Learning for Medical Vision-Language Representation","display_name":"SCALPEL: Semantic Cross-modal Alignment via LLM-Powered Encoder Learning for Medical Vision-Language Representation","publication_year":2026,"publication_date":"2026-07-29","ids":{"openalex":"https://openalex.org/W7171795614","doi":"https://doi.org/10.48550/arxiv.2607.26885"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.26885","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.26885","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.26885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001053589","display_name":"Y Fu","orcid":"https://orcid.org/0000-0001-8810-6632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yunzhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132635042","display_name":"Enyu Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Enyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110984577","display_name":"Xiangyu Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144064854","display_name":"Yihao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136797062","display_name":"Chunbo Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Chunbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012288206","display_name":"Fangli Guan","orcid":"https://orcid.org/0000-0001-7409-2129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Fangli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143995488","display_name":"Liqi Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Liqi","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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8858000040054321,"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":0.8858000040054321,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03799999877810478,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.014700000174343586,"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/feature-learning","display_name":"Feature learning","score":0.5582000017166138},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.548799991607666},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5333999991416931},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5260999798774719},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/rotation-formalisms-in-three-dimensions","display_name":"Rotation formalisms in three dimensions","score":0.41670000553131104},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.384799987077713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411999702453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831999778747559},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5582000017166138},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4878000020980835},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4828000068664551},{"id":"https://openalex.org/C171018156","wikidata":"https://www.wikidata.org/wiki/Q7370306","display_name":"Rotation formalisms in three dimensions","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.384799987077713},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3479999899864197},{"id":"https://openalex.org/C2185349","wikidata":"https://www.wikidata.org/wiki/Q190558","display_name":"Negation","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C2776493592","wikidata":"https://www.wikidata.org/wiki/Q5158717","display_name":"Succinctness","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.26885","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.26885","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.26885","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.26885","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5884174108505249}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"pre-training":[1],"(VLP)":[2],"serves":[3],"as":[4],"a":[5,106,121],"cornerstone":[6],"for":[7],"medical":[8,14,41,84,187],"multimodal":[9],"representation":[10],"learning.":[11],"However,":[12],"existing":[13],"VLP":[15],"frameworks":[16],"are":[17],"often":[18],"constrained":[19],"by":[20,87],"the":[21,57,69,83],"limited":[22],"context":[23],"windows":[24],"and":[25,81,96,170,186],"shallow":[26],"representational":[27,59],"capacities":[28],"of":[29,61,73],"lightweight":[30],"text":[31,131],"encoders":[32],"when":[33],"processing":[34],"lengthy,":[35],"terminology-dense":[36],"clinical":[37,48,130],"reports.":[38],"While":[39],"integrating":[40],"large":[42,78],"language":[43],"models":[44],"(LLMs)":[45],"offers":[46],"unprecedented":[47],"reasoning":[49],"capabilities,":[50],"it":[51],"introduces":[52],"three":[53],"major":[54],"bottlenecks:":[55],"(i)":[56],"anisotropic":[58],"collapse":[60],"generative":[62,122],"LLMs":[63],"under":[64],"standard":[65],"contrastive":[66,89],"objectives,":[67],"(ii)":[68],"prohibitive":[70],"memory":[71],"overhead":[72],"joint":[74],"end-to-end":[75],"training":[76],"with":[77],"batch":[79],"sizes,":[80],"(iii)":[82],"hallucinations":[85],"induced":[86],"vanilla":[88],"losses":[90],"that":[91,153,175],"ignore":[92],"fine-grained":[93],"anatomical":[94],"laterality":[95,160],"negation":[97],"modifiers.":[98],"To":[99],"address":[100],"these":[101],"challenges,":[102],"we":[103,147],"propose":[104],"\\textbf{SCALPEL},":[105],"\\textbf{S}emantic":[107],"\\textbf{C}ross-modal":[108],"\\textbf{A}lignment":[109],"framework":[110],"via":[111,128],"\\textbf{L}LM-\\textbf{P}owered":[112],"\\textbf{E}ncoder":[113],"\\textbf{L}earning.":[114],"First,":[115],"Clinical":[116],"Report":[117],"Contrastive":[118],"fine-tuning":[119],"converts":[120],"LLM":[123],"into":[124],"an":[125,134,149],"isotropic":[126],"encoder":[127],"domain-specific":[129],"adaptation.":[132],"Second,":[133],"asymmetric":[135],"alignment":[136],"strategy":[137],"leverages":[138],"offline":[139],"feature":[140],"caching":[141],"to":[142],"enable":[143],"efficient":[144],"training.":[145],"Critically,":[146],"formulate":[148],"Anatomy-Negation":[150],"Aware":[151],"Objective":[152],"explicitly":[154],"penalizes":[155],"mismatched":[156],"image-text":[157],"pairs":[158],"involving":[159],"confusion":[161],"or":[162],"false":[163],"negations.":[164],"Extensive":[165],"experiments":[166],"across":[167],"MIMIC-CXR,":[168],"CheXpert,":[169],"IU":[171],"X-Ray":[172],"benchmarks":[173],"demonstrate":[174],"SCALPEL":[176],"achieves":[177],"state-of-the-art":[178],"performance":[179],"in":[180],"cross-modal":[181],"retrieval,":[182],"zero-shot":[183],"disease":[184],"classification":[185],"visual":[188],"question":[189],"answering.":[190]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2026-07-31T00:00:00"}