{"id":"https://openalex.org/W4416031498","doi":"https://doi.org/10.1109/iccv51701.2025.00338","title":"Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis","display_name":"Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416031498","doi":"https://doi.org/10.1109/iccv51701.2025.00338"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00338","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/2503.08741","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090657130","display_name":"Letian Zhang","orcid":"https://orcid.org/0000-0001-6275-6506"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Letian Zhang","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047876341","display_name":"Quan Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Cui","raw_affiliation_strings":["Bytedance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047606433","display_name":"Bingchen Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bingchen Zhao","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060417049","display_name":"Cheng Yang","orcid":"https://orcid.org/0000-0001-7821-0030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Yang","raw_affiliation_strings":["Bytedance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"3542","last_page":"3551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7906000018119812,"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":0.7906000018119812,"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/T10860","display_name":"Speech and Audio Processing","score":0.020500000566244125,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.019500000402331352,"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/process","display_name":"Process (computing)","score":0.6448000073432922},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5741999745368958},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5648999810218811},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5182999968528748},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5094000101089478},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4756999909877777},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4422000050544739},{"id":"https://openalex.org/keywords/image-synthesis","display_name":"Image synthesis","score":0.38609999418258667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342000246047974},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6448000073432922},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5182999968528748},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5094000101089478},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4754999876022339},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4422000050544739},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3508000075817108},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C10272871","wikidata":"https://www.wikidata.org/wiki/Q929972","display_name":"Software inspection","level":5,"score":0.27869999408721924},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00338","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:2503.08741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08741","pdf_url":"https://arxiv.org/pdf/2503.08741","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.08741","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.08741","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:2503.08741","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.08741","pdf_url":"https://arxiv.org/pdf/2503.08741","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,30,132],"success":[1],"of":[2,21,35,130,144],"multi-modal":[3,37,48,69],"large":[4,93],"language":[5],"models":[6],"(MLLMs)":[7],"has":[8],"been":[9],"largely":[10],"attributed":[11],"to":[12,27,46,66,83,138],"the":[13,18,41,84,88,105,128,141],"large-scale":[14],"training":[15,19,49],"data.":[16],"However,":[17],"data":[20,38,50,70,89,106,112],"many":[22],"MLLMs":[23],"is":[24],"unavailable":[25],"due":[26],"privacy":[28],"concerns.":[29],"expensive":[31],"and":[32,55,113,147],"labor-intensive":[33],"process":[34],"collecting":[36],"further":[39],"exacerbates":[40],"problem.":[42],"Is":[43],"it":[44],"possible":[45],"synthesize":[47,67],"automatically":[51],"without":[52],"compromising":[53],"diversity":[54,90],"quality?":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"propose":[61],"a":[62,92,98],"new":[63],"method,":[64],"Oasis,":[65],"high-quality":[68],"with":[71],"only":[72,81],"images.":[73],"Oasis":[74],"breaks":[75],"through":[76],"traditional":[77],"methods":[78],"by":[79,91],"prompting":[80],"images":[82],"MLLMs,":[85],"thus":[86],"extending":[87],"margin.":[94],"Our":[95],"method":[96,102,124],"features":[97],"delicate":[99],"quality":[100],"control":[101],"which":[103],"ensures":[104],"quality.":[107],"We":[108],"collected":[109],"over":[110],"500k":[111],"conducted":[114],"incremental":[115],"experiments":[116,120],"on":[117,140],"LLaVA-NeXT.":[118],"Extensive":[119],"demonstrate":[121],"that":[122],"our":[123],"can":[125],"significantly":[126],"improve":[127],"performance":[129],"MLLMs.":[131,145],"image-based":[133],"synthesis":[134],"also":[135],"allows":[136],"us":[137],"focus":[139],"specific-domain":[142],"ability":[143],"Code":[146],"dataset":[148],"are":[149],"publicly":[150],"available":[151],"at":[152],"https://github.com/Letian2003/MM_INF.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}