{"id":"https://openalex.org/W4415161155","doi":"https://doi.org/10.1109/iccv51701.2025.01930","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","display_name":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415161155","doi":"https://doi.org/10.1109/iccv51701.2025.01930"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01930","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/2504.10462","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039070189","display_name":"Weixian Lei","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Weixian Lei","raw_affiliation_strings":["Bytedance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045825621","display_name":"Jiacong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jiacong Wang","raw_affiliation_strings":["Bytedance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645300","display_name":"Haochen Wang","orcid":"https://orcid.org/0000-0003-3178-6125"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Haochen Wang","raw_affiliation_strings":["Bytedance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049449805","display_name":"Xiangtai Li","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Xiangtai Li","raw_affiliation_strings":["Bytedance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098937299","display_name":"Jun Hao Liew","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jun Hao Liew","raw_affiliation_strings":["Bytedance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668696","display_name":"Jiashi Feng","orcid":"https://orcid.org/0000-0001-6843-0064"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jiashi Feng","raw_affiliation_strings":["Bytedance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101462087","display_name":"Zilong Huang","orcid":"https://orcid.org/0000-0002-6744-0671"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Zilong Huang","raw_affiliation_strings":["Bytedance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance Seed","institution_ids":["https://openalex.org/I231086526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I231086526"],"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":"20758","last_page":"20769"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.2791000008583069,"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":0.2791000008583069,"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/scalability","display_name":"Scalability","score":0.6796000003814697},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6690000295639038},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6629999876022339},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4250999987125397},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4025000035762787},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3896999955177307},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.37299999594688416},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.33219999074935913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756999731063843},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6796000003814697},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6690000295639038},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6629999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5328999757766724},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4025000035762787},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36329999566078186},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25529998540878296}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01930","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:2504.10462","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.10462","pdf_url":"https://arxiv.org/pdf/2504.10462","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":"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.2504.10462","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.10462","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":"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:2504.10462","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.10462","pdf_url":"https://arxiv.org/pdf/2504.10462","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":"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/W4415161155.pdf","grobid_xml":"https://content.openalex.org/works/W4415161155.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"SAIL,":[3],"a":[4,22,32,42,47],"single":[5],"transformer":[6,35],"unified":[7],"multimodal":[8,63],"large":[9],"language":[10,19],"model":[11,102],"(MLLM)":[12],"that":[13],"integrates":[14],"raw":[15],"pixel":[16],"encoding":[17],"and":[18,62,75,88,101,121,151],"decoding":[20],"within":[21],"singular":[23],"architecture.":[24],"Unlike":[25],"existing":[26],"modular":[27,94,109],"MLLMs,":[28],"which":[29],"rely":[30],"on":[31,139],"pre-trained":[33],"vision":[34,44,144],"(ViT),":[36],"SAIL":[37,58,104,131],"eliminates":[38],"the":[39,70,112],"need":[40],"for":[41],"separate":[43],"encoder,":[45],"presenting":[46],"more":[48],"minimalist":[49],"architecture":[50],"design.":[51],"Instead":[52],"of":[53,73,93,114],"introducing":[54],"novel":[55],"architectural":[56],"components,":[57],"adapts":[59],"mix-attention":[60],"mechanisms":[61],"positional":[64],"encodings":[65],"to":[66,108],"better":[67],"align":[68],"with":[69,141],"distinct":[71],"characteristics":[72],"visual":[74,89,134],"textual":[76],"modalities.":[77],"We":[78],"systematically":[79],"compare":[80],"SAIL's":[81,119],"properties-including":[82],"scalability,":[83],"cross-modal":[84,126],"information":[85,127],"flow":[86,128],"patterns,":[87],"representation":[90,135],"capabilities-with":[91],"those":[92],"MLLMs.":[95,110],"By":[96],"scaling":[97],"both":[98],"training":[99],"data":[100],"size,":[103],"achieves":[105],"performance":[106],"comparable":[107],"Notably,":[111],"removal":[113],"pretrained":[115],"ViT":[116],"components":[117],"enhances":[118],"scalability":[120],"results":[122,138],"in":[123,143],"significantly":[124],"different":[125],"patterns.":[129],"Moreover,":[130],"demonstrates":[132],"strong":[133],"capabilities,":[136],"achieving":[137],"par":[140],"ViT-22B":[142],"tasks":[145],"such":[146],"as":[147],"semantic":[148],"segmentation.":[149],"Code":[150],"models":[152],"are":[153],"available":[154],"at":[155],"https://github.com/bytedance/SAIL.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-14T00:00:00"}