{"id":"https://openalex.org/W7163551379","doi":"https://doi.org/10.48550/arxiv.2606.04385","title":"Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models","display_name":"Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163551379","doi":"https://doi.org/10.48550/arxiv.2606.04385"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04385","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":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.2606.04385","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125512238","display_name":"Shuwen Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Shuwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137848558","display_name":"Zhanxuan Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zhanxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137830960","display_name":"Yi Zhao","orcid":"https://orcid.org/0000-0002-0074-8188"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137876947","display_name":"Yonghang Tai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tai, Yonghang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137843115","display_name":"Huafeng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Huafeng","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4832000136375427,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4832000136375427,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.34540000557899475,"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":0.09350000321865082,"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/discriminative-model","display_name":"Discriminative model","score":0.6510999798774719},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5453000068664551},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5335999727249146},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.44110000133514404},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4235000014305115},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.38999998569488525},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.3889999985694885},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.365200012922287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483999729156494},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6510999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.597599983215332},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5335999727249146},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4235000014305115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36739999055862427},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3479999899864197},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04385","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":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.2606.04385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04385","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":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/10","display_name":"Reduced inequalities","score":0.7598336338996887}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Foundation":[0],"models":[1,16,21],"have":[2],"driven":[3],"rapid":[4],"progress":[5],"in":[6,126],"computer":[7],"vision,":[8],"yet":[9],"the":[10,57,83,87,95],"two":[11],"dominant":[12],"paradigms,":[13],"vision-language":[14],"foundation":[15,20],"(VLMs)":[17],"and":[18,62,76,93,107,123,130],"vision-only":[19],"(VFMs),":[22],"remain":[23],"only":[24,109],"partially":[25],"compatible.":[26],"VLMs":[27],"offer":[28],"language-grounded":[29],"semantic":[30,45,89],"alignment":[31],"but":[32,43],"are":[33],"often":[34],"visually":[35],"coarse,":[36],"while":[37],"VFMs":[38,61],"learn":[39],"discriminative":[40],"perceptual":[41],"geometry":[42,92],"lack":[44],"grounding.":[46],"We":[47],"propose":[48],"GPUA":[49,68,104],"(Geometry-Preserving":[50],"Unsupervised":[51],"Alignment),":[52],"a":[53,73],"framework":[54],"that":[55,81],"integrates":[56],"complementary":[58],"strengths":[59],"of":[60],"VLMs.":[63],"Inspired":[64],"by":[65],"cross-lingual":[66],"alignment,":[67],"treats":[69],"VFM":[70,84],"features":[71],"as":[72],"visual":[74],"language":[75],"learns":[77],"an":[78],"orthogonal":[79],"mapping":[80],"translates":[82],"space":[85],"into":[86],"VLM":[88],"space,":[90],"preserving":[91],"narrowing":[94],"modality":[96],"gap":[97],"without":[98],"labels":[99],"or":[100],"model":[101],"parameter":[102],"updates.":[103],"is":[105,136],"task-agnostic":[106],"requires":[108],"feature-level":[110],"access":[111],"to":[112],"pretrained":[113],"models.":[114],"Experiments":[115],"across":[116],"diverse":[117],"benchmarks":[118],"demonstrate":[119],"improved":[120],"cross-model":[121],"compatibility":[122],"strong":[124],"gains":[125],"downstream":[127],"zero-shot":[128],"recognition":[129],"segmentation":[131],"with":[132],"negligible":[133],"overhead.":[134],"Code":[135],"available":[137],"at":[138],"https://github.com/Yuteam14/GPUA":[139]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-05T00:00:00"}