{"id":"https://openalex.org/W7167677466","doi":"https://doi.org/10.48550/arxiv.2607.05533","title":"Multi-Teacher Contrastive Distillation for Edge-Efficient Pathology Foundation Models","display_name":"Multi-Teacher Contrastive Distillation for Edge-Efficient Pathology Foundation Models","publication_year":2026,"publication_date":"2026-07-06","ids":{"openalex":"https://openalex.org/W7167677466","doi":"https://doi.org/10.48550/arxiv.2607.05533"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.05533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.05533","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2607.05533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113076192","display_name":"Tim Lenz","orcid":"https://orcid.org/0000-0002-9034-2535"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lenz, Tim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140232747","display_name":"Maurice Heide","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heide, Maurice","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045228374","display_name":"Marco Gustav","orcid":"https://orcid.org/0009-0009-3598-5720"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gustav, Marco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136158486","display_name":"Nic G. Reitsam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reitsam, Nic G.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140284486","display_name":"Jakob Nikolas Kather","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kather, Jakob Nikolas","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/T10862","display_name":"AI in cancer detection","score":0.9778000116348267,"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"}},"topics":[{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9778000116348267,"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/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.00570000009611249,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.002099999925121665,"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/distillation","display_name":"Distillation","score":0.6171000003814697},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5820000171661377},{"id":"https://openalex.org/keywords/digital-pathology","display_name":"Digital pathology","score":0.44920000433921814},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.42879998683929443},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.3792000114917755},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3732999861240387},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.36649999022483826},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.3529999852180481},{"id":"https://openalex.org/keywords/raspberry-pi","display_name":"Raspberry pi","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6362000107765198},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194000005722046},{"id":"https://openalex.org/C2777522853","wikidata":"https://www.wikidata.org/wiki/Q5276128","display_name":"Digital pathology","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3732999861240387},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3571000099182129},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C2985745059","wikidata":"https://www.wikidata.org/wiki/Q245","display_name":"Raspberry pi","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35100001096725464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.310699999332428},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3003999888896942},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.05533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.05533","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":"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":"doi:10.48550/arxiv.2607.05533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.05533","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6488619446754456}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Computational":[0],"pathology":[1,20,176],"foundation":[2],"models":[3],"(PFMs)":[4],"have":[5],"advanced":[6],"whole-slide":[7],"image":[8],"analysis.":[9],"However,":[10],"their":[11],"size":[12,103],"and":[13,50,66,83,109,132,137,147],"inference":[14],"cost":[15],"hinder":[16],"local":[17],"deployment":[18],"in":[19],"departments.":[21],"We":[22,72],"propose":[23],"MuCoDi,":[24],"a":[25,54,151],"pretraining":[26],"framework":[27],"that":[28,174],"distills":[29],"frozen":[30,85],"tile":[31],"embeddings":[32,68],"from":[33,59,79],"multiple":[34],"PFMs":[35],"into":[36],"compact":[37],"edge-oriented":[38],"encoders.":[39],"Instead":[40],"of":[41,106,119],"regressing":[42],"individual":[43],"teacher":[44,122],"features,":[45],"MuCoDi":[46],"trains":[47],"lightweight":[48],"MobileOne":[49,156],"RepViT":[51],"students":[52,74,96,157],"with":[53,143],"contrastive":[55],"distillation":[56],"objective":[57],"adapted":[58],"MoCo":[60],"v3,":[61],"where":[62],"cached":[63],"Virchow2,":[64],"UNI2,":[65],"H-Optimus-1":[67],"replace":[69],"momentum-encoder":[70],"keys.":[71],"pretrain":[73],"on":[75,87],"14.3M":[76],"TCGA":[77],"tiles":[78],"only":[80,144],"11.8K":[81],"WSIs":[82],"evaluate":[84],"encoders":[86],"23":[88],"clinically":[89],"curated":[90],"downstream":[91],"classification":[92],"tasks.":[93],"RepViT-based":[94],"MuCoEdge":[95],"retain":[97],"near-teacher":[98],"performance":[99],"while":[100,125,166],"reducing":[101],"model":[102],"by":[104],"orders":[105],"magnitude:":[107],"MuCoEdge-R2.3":[108,126],"MuCoEdge-R1.5":[110],"reach":[111],"71.0%":[112],"external":[113,130,171],"AUROC,":[114,172],"within":[115],"0.8":[116],"percentage":[117],"points":[118],"the":[120,128,133],"best":[121,129],"(Virchow2,":[123],"71.8%),":[124],"obtains":[127],"F1":[131],"second-best":[134],"AUPRC":[135],"(51.8%":[136],"53.3%).":[138],"MuCoEdge-R1.0":[139],"reaches":[140],"70.9%":[141],"AUROC":[142],"6.4M":[145],"parameters":[146],"1.12":[148],"GFLOPs.":[149],"On":[150],"Raspberry":[152],"Pi":[153],"5,":[154],"sub-million-parameter":[155],"achieve":[158],"up":[159],"to":[160,169],"605-fold":[161],"single-tile":[162],"speedup":[163],"over":[164],"Virchow2":[165],"retaining":[167],"66.5%":[168],"66.9%":[170],"demonstrating":[173],"PFM-quality":[175],"representations":[177],"can":[178],"be":[179],"moved":[180],"toward":[181],"practical":[182],"edge":[183],"deployment.":[184],"Code":[185],"is":[186],"available":[187],"at":[188],"https://anonymous.4open.science/r/mucodi-6243.":[189]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-09T00:00:00"}