{"id":"https://openalex.org/W4404088721","doi":"https://doi.org/10.48550/arxiv.2410.15509","title":"Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training","display_name":"Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4404088721","doi":"https://doi.org/10.48550/arxiv.2410.15509"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.15509","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15509","pdf_url":"https://arxiv.org/pdf/2410.15509","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2410.15509","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054410152","display_name":"Rohan Saha","orcid":"https://orcid.org/0000-0001-9747-0057","observed_orcids":["https://orcid.org/0000-0001-9747-0057"]},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210143490","display_name":"Computing Center","ror":"https://ror.org/0557kgc34","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210143490","https://openalex.org/I4210148470"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Saha, Rohan","raw_affiliation_strings":["Department of Computing Science ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science ,","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210143490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098954215","display_name":"Abrar Fahim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210143490","display_name":"Computing Center","ror":"https://ror.org/0557kgc34","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210143490","https://openalex.org/I4210148470"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Fahim, Abrar","raw_affiliation_strings":["Department of Computing Science ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science ,","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210143490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085831385","display_name":"Alona Fyshe","orcid":"https://orcid.org/0000-0003-4367-0306","observed_orcids":["https://orcid.org/0000-0003-4367-0306"]},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210143490","display_name":"Computing Center","ror":"https://ror.org/0557kgc34","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210143490","https://openalex.org/I4210148470"]}],"countries":["CA","CN","RU"],"is_corresponding":false,"raw_author_name":"Fyshe, Alona","raw_affiliation_strings":["Department of Computing Science ,","Department of Psychology University of Alberta {rsaha , afahim2 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science ,","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210143490"]},{"raw_affiliation_string":"Department of Psychology University of Alberta {rsaha , afahim2 ,","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":null,"display_name":"Murphy, Alex","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210143490","display_name":"Computing Center","ror":"https://ror.org/0557kgc34","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210143490","https://openalex.org/I4210148470"]}],"countries":["CN","RU"],"is_corresponding":false,"raw_author_name":"Murphy, Alex","raw_affiliation_strings":["Department of Computing Science ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science ,","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210143490"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9824000000953674,"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":0.9824000000953674,"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":0.010900000110268593,"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/T10028","display_name":"Topic Modeling","score":0.0032999999821186066,"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/curriculum-learning","display_name":"curriculum learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.800000011920929},{"id":"https://openalex.org/keywords/multimodal-pretraining","display_name":"multimodal pre-training","score":0.699999988079071},{"id":"https://openalex.org/keywords/model-size","display_name":"model size","score":0.6290000081062317}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6703276038169861},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.6608314514160156},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5845173597335815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5256741642951965},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4171852171421051},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3914872705936432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35098689794540405},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.19646039605140686},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08681279420852661},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0857362151145935},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.15509","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15509","pdf_url":"https://arxiv.org/pdf/2410.15509","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.15509","doi":"https://doi.org/10.48550/arxiv.2410.15509","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.15509","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":"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":"pmh:oai:arXiv.org:2410.15509","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15509","pdf_url":"https://arxiv.org/pdf/2410.15509","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6164000034332275,"display_name":"Quality education"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404088721.pdf","grobid_xml":"https://content.openalex.org/works/W4404088721.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"For":[0],"specialized":[1],"domains,":[2],"there":[3],"is":[4],"often":[5],"not":[6],"a":[7,39,50,93,109],"wealth":[8],"of":[9,58,89,104,115,119,146],"data":[10,22,46,111],"with":[11,33,182],"which":[12],"to":[13,30,49,64,84,179,199],"train":[14],"large":[15],"machine":[16,79],"learning":[17,67,73,80,160,166,177],"models.":[18],"In":[19],"such":[20,35,204],"limited":[21,110],"/":[23,61],"compute":[24],"settings,":[25],"various":[26],"methods":[27],"exist":[28],"aiming":[29],"$\\textit{do":[31],"more":[32],"less}$,":[34],"as":[36,45,113,198],"finetuning":[37],"from":[38,71],"pretrained":[40],"model,":[41],"modulating":[42],"difficulty":[43],"levels":[44],"are":[47],"presented":[48],"model":[51,59,134],"(curriculum":[52],"learning),":[53],"and":[54,140,151,195],"considering":[55,75],"the":[56,86,102,116,120],"role":[57,103],"type":[60],"size.":[62],"Approaches":[63],"efficient":[65],"$\\textit{machine}$":[66],"also":[68],"take":[69],"inspiration":[70],"$\\textit{human}$":[72],"by":[74,92],"use":[76],"cases":[77],"where":[78],"systems":[81],"have":[82],"access":[83],"approximately":[85],"same":[87],"number":[88],"words":[90],"experienced":[91],"13":[94],"year":[95],"old":[96],"child":[97],"(100M":[98],"words).":[99],"We":[100,123,136,156,187],"investigate":[101],"3":[105],"primary":[106],"variables":[107,139],"in":[108],"regime":[112],"part":[114],"multimodal":[117,149,162],"track":[118],"BabyLM":[121],"challenge.":[122],"contrast:":[124],"(i)":[125],"curriculum":[126,159,176],"learning,":[127],"(ii),":[128],"pretraining":[129],"(with":[130],"text-only":[131,171,174],"data),":[132],"(iii)":[133],"type.":[135],"modulate":[137],"these":[138],"assess":[141],"them":[142],"on":[143,192],"two":[144],"types":[145],"tasks:":[147],"(a)":[148],"(text+image),":[150],"(b)":[152],"unimodal":[153],"(text-only)":[154],"tasks.":[155],"find":[157],"that":[158],"benefits":[161],"evaluations":[163],"over":[164],"non-curriclum":[165],"models,":[167],"particularly":[168],"when":[169],"combining":[170],"pretraining.":[172],"On":[173],"tasks,":[175],"appears":[178],"help":[180],"models":[181],"smaller":[183],"trainable":[184],"parameter":[185],"counts.":[186],"suggest":[188],"possible":[189],"reasons":[190],"based":[191],"architectural":[193],"differences":[194],"training":[196],"designs":[197],"why":[200],"one":[201],"might":[202],"observe":[203],"results.":[205]},"counts_by_year":[],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2025-10-10T00:00:00"}
