{"id":"https://openalex.org/W4415316680","doi":"https://doi.org/10.48550/arxiv.2509.12771","title":"Contrastive Learning with Enhanced Abstract Representations using Grouped Loss of Abstract Semantic Supervision","display_name":"Contrastive Learning with Enhanced Abstract Representations using Grouped Loss of Abstract Semantic Supervision","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4415316680","doi":"https://doi.org/10.48550/arxiv.2509.12771"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.12771","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12771","pdf_url":"https://arxiv.org/pdf/2509.12771","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.12771","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081395585","display_name":"Omri Suissa","orcid":"https://orcid.org/0000-0002-9703-2222","observed_orcids":["https://orcid.org/0000-0002-9703-2222"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suissa, Omri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010308396","display_name":"M. Rafayet Ali","orcid":"https://orcid.org/0009-0003-1291-5689","observed_orcids":["https://orcid.org/0009-0003-1291-5689"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali, Muhiim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112181251","display_name":"Shengmai Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shengmai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cai, Yinuo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Yinuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Pradhan, Shekhar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pradhan, Shekhar","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":1.0,"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":1.0,"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":0.0,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0,"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/vision-language-models","display_name":"vision-language models","score":0.7559999823570251},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.8270000219345093},{"id":"https://openalex.org/keywords/emergent-abilities","display_name":"emergent capabilities","score":0.4909999966621399},{"id":"https://openalex.org/keywords/latent-semantic-space","display_name":"latent semantic space","score":0.48500001430511475}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.7644000053405762},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6929000020027161},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6513000130653381},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6340000033378601},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6162999868392944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5928000211715698},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5170999765396118},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4999000132083893},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C147358964","wikidata":"https://www.wikidata.org/wiki/Q1200992","display_name":"Abstraction layer","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.31769999861717224},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C48164120","wikidata":"https://www.wikidata.org/wiki/Q4491893","display_name":"Concept learning","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.12771","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12771","pdf_url":"https://arxiv.org/pdf/2509.12771","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.12771","doi":"https://doi.org/10.48550/arxiv.2509.12771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.12771","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,"listed_in":[],"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":"pmh:oai:arXiv.org:2509.12771","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.12771","pdf_url":"https://arxiv.org/pdf/2509.12771","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Humans":[0],"can":[1],"recognize":[2],"an":[3,6,152,180],"image":[4,82,115],"as":[5,149,151,179],"instance":[7],"of":[8,43,78,81,90,113,128,220],"a":[9,63,71,88,99,118,136,209,238],"general":[10],"concept,":[11],"beyond":[12],"simply":[13],"identifying":[14],"its":[15],"objects":[16],"and":[17,36,84,93],"their":[18],"relationships.":[19],"In":[20],"this":[21,32,60,67,233],"paper,":[22],"we":[23,69],"investigate":[24],"1.":[25],"The":[26],"extent":[27],"to":[28,58,62,104,108,125,189,203,216,248],"which":[29,76,155,240],"VLMs":[30],"have":[31,59],"concept":[33,176,245],"abstraction":[34,177],"capacity,":[35],"2.":[37],"Strategies":[38],"for":[39,85,205],"encoding":[40],"the":[41,51,106,111,120,129,157,163,170,175,184,190,198,201,217,221,225],"sort":[42],"higher-concept":[44],"information":[45,121],"in":[46,110,117,162,169,224,237,243],"images":[47,92],"that":[48,122,212,232],"would":[49],"enable":[50],"resulting":[52],"VLM":[53],"model":[54,107,173,185,202,239],"(CLEAR":[55],"GLASS":[56,172],"model)":[57],"capability":[61],"greater":[64],"degree.":[65],"To":[66],"end,":[68],"introduce":[70],"grouped":[72,137],"image-caption":[73,130,160,207],"dataset":[74],"(MAGIC),":[75],"consists":[77],"several":[79],"groups":[80,145],"captions":[83],"each":[86,114,195,206],"group":[87,119,208],"set":[89],"associated":[91,193],"higher-level":[94,191,222],"conceptual":[95],"labels.":[96],"We":[97],"use":[98],"novel":[100],"contrastive":[101,138,144,147],"loss":[102,139,154],"technique":[103],"induce":[105],"encode":[109],"representation":[112,211,219],"(caption)":[116],"is":[123,135,186],"common":[124],"all":[126],"members":[127],"group.":[131,164,196],"Our":[132,165,229],"main":[133],"contribution":[134],"function":[140],"based":[141],"on":[142],"text-image":[143],"(outer":[146],"loss)":[148],"well":[150],"inner":[153],"measures":[156],"distances":[158],"between":[159],"instances":[161],"training":[166,199,234],"methodology":[167,235],"results":[168,236],"CLEAR":[171],"having":[174],"capacity":[178,182],"emergent":[181],"because":[183],"not":[187],"exposed":[188],"concepts":[192,223],"with":[194],"Instead,":[197],"forces":[200],"create":[204],"semantic":[210,218,227],"brings":[213],"it":[214],"closer":[215],"latent":[226],"space.":[228],"experiments":[230],"show":[231],"shows":[241],"improvement":[242],"abstract":[244],"recognition":[246],"compared":[247],"SOTA":[249],"models.":[250]},"counts_by_year":[],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2025-10-18T00:00:00"}