{"id":"https://openalex.org/W4412889593","doi":"https://doi.org/10.18653/v1/2025.acl-long.1595","title":"Scalable Vision Language Model Training via High Quality Data Curation","display_name":"Scalable Vision Language Model Training via High Quality Data Curation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889593","doi":"https://doi.org/10.18653/v1/2025.acl-long.1595"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1595","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1595","pdf_url":"https://aclanthology.org/2025.acl-long.1595.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1595.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064268861","display_name":"Hongyuan Dong","orcid":"https://orcid.org/0000-0002-6772-0825"},"institutions":[{"id":"https://openalex.org/I4210161667","display_name":"Continental (United States)","ror":"https://ror.org/05yhca997","country_code":"US","type":"company","lineage":["https://openalex.org/I147869694","https://openalex.org/I4210161667"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyuan Dong","raw_affiliation_strings":["Content Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Content Group","institution_ids":["https://openalex.org/I4210161667"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zijian Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161667","display_name":"Continental (United States)","ror":"https://ror.org/05yhca997","country_code":"US","type":"company","lineage":["https://openalex.org/I147869694","https://openalex.org/I4210161667"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zijian Kang","raw_affiliation_strings":["Content Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Content Group","institution_ids":["https://openalex.org/I4210161667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112722849","display_name":"Weijie Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161667","display_name":"Continental (United States)","ror":"https://ror.org/05yhca997","country_code":"US","type":"company","lineage":["https://openalex.org/I147869694","https://openalex.org/I4210161667"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weijie Yin","raw_affiliation_strings":["Content Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Content Group","institution_ids":["https://openalex.org/I4210161667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060002878","display_name":"LiangXiao LiangXiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"LiangXiao LiangXiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097024819","display_name":"ChaoFeng ChaoFeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"ChaoFeng ChaoFeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076861802","display_name":"Ran Jiao","orcid":"https://orcid.org/0000-0003-0067-6679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ran Jiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33272","last_page":"33293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.8259000182151794,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.8259000182151794,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7578999996185303,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7483999729156494,"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/computer-science","display_name":"Computer science","score":0.8205640912055969},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7291820049285889},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.6205257177352905},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5454556941986084},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5014007091522217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4950474798679352},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4891717731952667},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45772749185562134},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43927866220474243},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42785608768463135},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.28266817331314087},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.25940054655075073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205640912055969},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7291820049285889},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.6205257177352905},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5454556941986084},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5014007091522217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4950474798679352},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4891717731952667},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45772749185562134},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43927866220474243},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42785608768463135},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28266817331314087},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25940054655075073},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1595","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1595","pdf_url":"https://aclanthology.org/2025.acl-long.1595.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1595","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1595","pdf_url":"https://aclanthology.org/2025.acl-long.1595.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889593.pdf","grobid_xml":"https://content.openalex.org/works/W4412889593.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4281758439"],"related_works":["https://openalex.org/W2701062589","https://openalex.org/W4308914582","https://openalex.org/W4388126069","https://openalex.org/W2389214306","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361","https://openalex.org/W2889043750","https://openalex.org/W4285322112","https://openalex.org/W4292794239"],"abstract_inverted_index":{"Hongyuan":[0],"Dong,":[1],"Zijian":[2],"Kang,":[3],"Weijie":[4],"Yin,":[5],"LiangXiao":[6],"LiangXiao,":[7],"ChaoFeng":[8],"ChaoFeng,":[9],"Ran":[10],"Jiao.":[11],"Proceedings":[12],"of":[13,18],"the":[14,19],"63rd":[15],"Annual":[16],"Meeting":[17],"Association":[20],"for":[21],"Computational":[22],"Linguistics":[23],"(Volume":[24],"1:":[25],"Long":[26],"Papers).":[27],"2025.":[28]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}