{"id":"https://openalex.org/W7163448225","doi":"https://doi.org/10.48550/arxiv.2606.03180","title":"GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations","display_name":"GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163448225","doi":"https://doi.org/10.48550/arxiv.2606.03180"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03180","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03180","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.2606.03180","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137732960","display_name":"Jonggwon Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Jonggwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037884706","display_name":"SeongEun Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Seongeun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137766881","display_name":"Junhyun Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Junhyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108005605","display_name":"H.D. Yun","orcid":"https://orcid.org/0009-0005-9400-6474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun, Hannah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044747309","display_name":"Hyunwoong Kim","orcid":"https://orcid.org/0000-0002-7253-5114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Hyunwoong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133127171","display_name":"Sohyun Jeong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeong, Sohyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137790904","display_name":"Hyewon Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Hyewon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104251201","display_name":"Byungmu Yoon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoon, Byungmu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137792797","display_name":"Kyoyun Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Kyoyun","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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.5199999809265137,"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":0.5199999809265137,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1500999927520752,"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":0.11190000176429749,"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/segmentation","display_name":"Segmentation","score":0.6542999744415283},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6007000207901001},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5892999768257141},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5741000175476074},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5615000128746033},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5203999876976013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4401000142097473},{"id":"https://openalex.org/keywords/pairing","display_name":"Pairing","score":0.40720000863075256},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.40450000762939453},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289999723434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6675999760627747},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6007000207901001},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5892999768257141},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5741000175476074},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5615000128746033},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5368000268936157},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C14103023","wikidata":"https://www.wikidata.org/wiki/Q11681459","display_name":"Pairing","level":3,"score":0.40720000863075256},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C544519230","wikidata":"https://www.wikidata.org/wiki/Q32566","display_name":"Computed tomography","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03180","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03180","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.2606.03180","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03180","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":[{"display_name":"Quality Education","score":0.8291757106781006,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1,86],"(VLMs)":[2],"for":[3],"radiology":[4],"have":[5],"emerged":[6],"as":[7],"a":[8,24,32,50,70,82,99,104,108,142],"scalable":[9],"paradigm":[10],"by":[11],"leveraging":[12],"image-report":[13,46],"pairs":[14],"naturally":[15],"produced":[16],"in":[17,26,102],"clinical":[18],"workflows.":[19],"However,":[20],"this":[21,87],"pairing":[22],"reveals":[23],"mismatch":[25],"scale:":[27],"each":[28,119],"finding":[29],"occupies":[30],"only":[31,42,114],"small":[33],"region":[34],"of":[35],"the":[36,44,65,91,115,126,136,149,154,196,210],"image,":[37],"yet":[38],"supervision":[39],"is":[40,195,224],"provided":[41],"at":[43],"global":[45],"level.":[47],"This":[48],"poses":[49],"central":[51],"challenge:":[52],"prior":[53],"approaches":[54],"spread":[55],"weight":[56],"densely":[57],"across":[58],"all":[59],"patches":[60,116],"rather":[61],"than":[62],"concentrating":[63],"on":[64,202,215,242],"sparse":[66,88],"subset":[67],"relevant":[68,117],"to":[69,118,141,162,192,198],"given":[71],"query.":[72],"To":[73],"address":[74],"this,":[75],"we":[76,94,129],"present":[77],"GLINT":[78,181,234],"(Gated":[79],"Language-Image":[80],"alignmeNT),":[81],"framework":[83],"that":[84,153],"explicitly":[85],"correspondence.":[89],"On":[90,125],"alignment":[92],"side,":[93,128],"introduce":[95],"Sparsely":[96],"Gated":[97],"Alignment,":[98],"novel":[100],"architecture":[101],"which":[103,134],"sigmoid":[105],"gate":[106,110,155],"over":[107],"separate":[109],"embedding":[111],"space":[112],"activates":[113],"textual":[120],"query,":[121],"enforcing":[122],"explicit":[123],"sparsity.":[124],"representation":[127],"add":[130],"Dense":[131],"Feature":[132],"Regularization,":[133],"anchors":[135],"trainable":[137],"encoder's":[138],"intermediate":[139],"features":[140,152],"frozen":[143],"self-supervised":[144],"learning":[145],"(SSL)":[146],"teacher,":[147],"preserving":[148],"fine-grained":[150],"patch":[151],"relies":[156],"on.":[157],"The":[158],"same":[159],"recipe":[160],"applies":[161],"both":[163,236],"2D":[164],"chest":[165,170],"X-ray":[166],"(CXR)":[167],"and":[168,177,186,191,218,239,246],"3D":[169,203],"computed":[171],"tomography":[172],"(CT),":[173],"built":[174],"with":[175,227],"DINOv3":[176],"V-JEPA":[178],"2.1,":[179],"respectively.":[180],"enables":[182],"zero-shot":[183,200,216],"classification,":[184,243],"grounding,":[185],"segmentation":[187,201],"from":[188],"free-text":[189],"queries,":[190],"our":[193,228],"knowledge":[194],"first":[197],"demonstrate":[199],"CT":[204],"volumes":[205],"without":[206],"mask":[207],"supervision.":[208],"Notably,":[209],"most":[211],"pronounced":[212],"gains":[213],"arise":[214],"grounding":[217],"segmentation,":[219],"where":[220],"sparse,":[221],"query-specific":[222],"localization":[223],"required,":[225],"consistent":[226],"design":[229],"intent.":[230],"In":[231],"downstream":[232],"evaluation,":[233],"outperforms":[235],"SSL":[237],"encoders":[238],"medical":[240],"VLMs":[241],"report":[244],"generation,":[245],"segmentation.":[247]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-04T00:00:00"}