{"id":"https://openalex.org/W4414792179","doi":"https://doi.org/10.1109/iccv51701.2025.00009","title":"Scaling Laws for Native Multimodal Models","display_name":"Scaling Laws for Native Multimodal Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414792179","doi":"https://doi.org/10.1109/iccv51701.2025.00009"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.07951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111151249","display_name":"Mustafa Shukor","orcid":"https://orcid.org/0000-0002-3100-6689"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mustafa Shukor","raw_affiliation_strings":["Sorbonne University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne University","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066230537","display_name":"Enrico Fini","orcid":"https://orcid.org/0000-0002-1671-875X"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Enrico Fini","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057018101","display_name":"Victor G. Turrisi da Costa","orcid":"https://orcid.org/0000-0003-2597-4998"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Victor Guilherme Turrisi da Costa","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108118084","display_name":"Matthieu Cord","orcid":"https://orcid.org/0000-0002-0627-5844"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matthieu Cord","raw_affiliation_strings":["Sorbonne University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne University","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033404184","display_name":"Joshua M. Susskind","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joshua Susskind","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083505661","display_name":"Alaaeldin El-Nouby","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alaaeldin El-Nouby","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23473284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7623000144958496,"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/T12031","display_name":"Speech and dialogue systems","score":0.7623000144958496,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.7444999814033508,"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/scaling-law","display_name":"Scaling law","score":0.6313999891281128},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5882999897003174},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4422999918460846},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3937000036239624},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.385699987411499}],"concepts":[{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.6313999891281128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6254000067710876},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5882999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5314000248908997},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4422999918460846},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.367000013589859},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2980000078678131},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.07951","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.07951","pdf_url":"https://arxiv.org/pdf/2504.07951","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.07951","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.07951","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":"pmh:oai:arXiv.org:2504.07951","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.07951","pdf_url":"https://arxiv.org/pdf/2504.07951","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414792179.pdf","grobid_xml":"https://content.openalex.org/works/W4414792179.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Building":[0],"general-purpose":[1],"models":[2,65,84,151],"that":[3,144],"can":[4],"effectively":[5],"perceive":[6],"the":[7,59,69,113,135,139],"world":[8],"through":[9],"multimodal":[10,33,64],"signals":[11],"has":[12],"been":[13],"a":[14],"long-standing":[15],"goal.":[16],"Current":[17],"approaches":[18,37],"involve":[19],"integrating":[20],"separately":[21],"pre-trained":[22],"components,":[23],"such":[24,36,48],"as":[25],"connecting":[26],"vision":[27],"encoders":[28,109],"to":[29,97,126,131,152],"LLMs":[30],"and":[31,88,128],"continuing":[32],"training.":[34],"While":[35],"exhibit":[38],"remarkable":[39],"sample":[40],"efficiency,":[41],"it":[42],"remains":[43],"an":[44,76],"open":[45],"question":[46],"whether":[47],"late-fusion":[49,98],"architectures":[50,87,99],"are":[51],"inherently":[52],"superior.":[53],"In":[54],"this":[55],"work,":[56],"we":[57,142],"revisit":[58],"architectural":[60],"design":[61],"of":[62,138,147],"native":[63],"(NMMs)-those":[66],"trained":[67,83],"from":[68],"ground":[70],"up":[71],"on":[72,107],"all":[73],"modalities-and":[74],"conduct":[75],"extensive":[77],"scaling":[78],"laws":[79],"study,":[80],"spanning":[81],"457":[82],"with":[85],"different":[86],"training":[89],"mixtures.":[90],"Our":[91],"investigation":[92],"reveals":[93],"no":[94],"inherent":[95],"advantage":[96],"over":[100],"early-fusion":[101,115,140],"ones,":[102],"which":[103],"do":[104],"not":[105],"rely":[106],"image":[108],"or":[110],"tokenizers.":[111],"On":[112],"contrary,":[114],"exhibits":[116],"stronger":[117],"performance":[118,137],"at":[119],"lower":[120],"parameter":[121],"counts,":[122],"is":[123,129],"more":[124],"efficient":[125],"train,":[127],"easier":[130],"deploy.":[132],"Motivated":[133],"by":[134],"strong":[136],"architectures,":[141],"show":[143],"incorporating":[145],"Mixture":[146],"Experts":[148],"(MoEs)":[149],"allows":[150],"learn":[153],"modality-specific":[154],"weights,":[155],"significantly":[156],"benefiting":[157],"performance.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}