{"id":"https://openalex.org/W7140093848","doi":"https://doi.org/10.1109/access.2026.3676660","title":"Orchestrating Generative Models for Synthesizing Domain-Specific Vision\u2013Language Instructions","display_name":"Orchestrating Generative Models for Synthesizing Domain-Specific Vision\u2013Language Instructions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140093848","doi":"https://doi.org/10.1109/access.2026.3676660"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3676660","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3676660","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3676660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Linjiang Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126065","display_name":"Shanghai Electric (China)","ror":"https://ror.org/0314qy595","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linjiang Shang","raw_affiliation_strings":["Information and Communication Branch, State Grid Jiangsu Electric Power Company Ltd., Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information and Communication Branch, State Grid Jiangsu Electric Power Company Ltd., Nanjing, China","institution_ids":["https://openalex.org/I4210126065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huanyu Cheng","orcid":"https://orcid.org/0009-0002-3427-7924"},"institutions":[{"id":"https://openalex.org/I4210126065","display_name":"Shanghai Electric (China)","ror":"https://ror.org/0314qy595","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanyu Cheng","raw_affiliation_strings":["Information and Communication Branch, State Grid Jiangsu Electric Power Company Ltd., Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0002-3427-7924","affiliations":[{"raw_affiliation_string":"Information and Communication Branch, State Grid Jiangsu Electric Power Company Ltd., Nanjing, China","institution_ids":["https://openalex.org/I4210126065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052817188","display_name":"Cong Luo","orcid":"https://orcid.org/0009-0005-4358-1284"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Luo","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-4358-1284","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130400713","display_name":"Yan Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Gong","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090131668","display_name":"Xikang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xikang Chen","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-9544-8798","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28618824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"44992","last_page":"45005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3986000120639801,"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":0.3986000120639801,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.11940000206232071,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12031","display_name":"Speech and dialogue systems","score":0.09910000115633011,"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/generative-grammar","display_name":"Generative grammar","score":0.49619999527931213},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4104999899864197},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.2492000013589859},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.23980000615119934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8320000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264000296592712},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4104999899864197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2554999887943268},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2492000013589859},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.23980000615119934},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.22679999470710754},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22439999878406525}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3676660","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3676660","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2227d5c4e84b400e872afddce794db89","is_oa":true,"landing_page_url":"https://doaj.org/article/2227d5c4e84b400e872afddce794db89","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 44992-45005 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3676660","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3676660","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G658000049","display_name":null,"funder_award_id":"J2024168","funder_id":"https://openalex.org/F4320335967","funder_display_name":"Science and Technology Project of State Grid"}],"funders":[{"id":"https://openalex.org/F4320335967","display_name":"Science and Technology Project of State Grid","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"demonstrated":[4],"remarkable":[5],"performance":[6],"in":[7,178],"general":[8],"multimodal":[9],"tasks,":[10],"yet":[11],"their":[12],"effectiveness":[13],"significantly":[14,155],"deteriorates":[15],"when":[16],"applied":[17],"to":[18,27,71,114,132,174,185,198,227,229],"specialized":[19,230],"domains":[20],"such":[21],"as":[22],"electric":[23],"power":[24],"systems":[25],"due":[26],"the":[28,62,85,112,122,148,160,204,209],"scarcity":[29],"of":[30,87],"domain-specific":[31,52,68,222],"data":[32,195],"and":[33,50,95,109,118,138],"expert":[34],"annotations.":[35],"To":[36],"bridge":[37],"this":[38],"gap,":[39],"we":[40],"propose":[41],"a":[42,48,104,175,199],"novel,":[43],"scalable":[44],"pipeline":[45],"for":[46,121,220],"generating":[47],"high-fidelity":[49],"diverse":[51,80],"dataset.":[53],"Our":[54,213],"method":[55],"comprises":[56],"two":[57],"sequential":[58],"phases:":[59],"(1)":[60],"Feeding":[61],"collected":[63],"seed":[64,190,211],"images":[65,82,101],"together":[66],"with":[67,106,208],"edit":[69],"prompts":[70],"an":[72,141,217],"advanced":[73],"generative":[74],"image":[75],"editing":[76,93],"model,":[77],"which":[78],"produces":[79],"synthetic":[81,100,124,128,153],"that":[83,147],"preserve":[84],"identity":[86],"critical":[88],"objects":[89],"even":[90],"under":[91],"complex":[92],"instructions;":[94],"(2)":[96],"Filtering":[97],"out":[98],"low-quality":[99],"by":[102],"prompting":[103],"VLM":[105,113],"quality":[107],"criteria,":[108],"subsequently":[110],"using":[111],"construct":[115],"domain-aware":[116],"captions":[117],"visual":[119,162,170,223],"instructions":[120,154,171],"remaining":[123],"images.":[125],"The":[126],"resulting":[127],"dataset":[129],"is":[130],"used":[131],"finetune":[133],"mainstream":[134],"VLMs":[135,149,226],"(e.g.,":[136],"Qwen-VL":[137],"InternVL)":[139],"via":[140],"instruction-tuning":[142],"paradigm.":[143],"Extensive":[144],"experiments":[145],"demonstrate":[146],"finetuned":[150,158,166],"on":[151,159,167,180,189,203],"our":[152,168,193],"outperform":[156],"those":[157],"original":[161,210],"instructions.":[163],"Notably,":[164],"models":[165,186],"editing-augmented":[169],"achieve":[172],"up":[173,197],"25%":[176],"increase":[177],"F1-score":[179],"object":[181],"grounding":[182],"tasks":[183],"relative":[184,201],"trained":[187],"solely":[188],"data.":[191,212],"Furthermore,":[192],"synthesized":[194],"achieves":[196],"13.66%":[200],"gain":[202],"VQA":[205],"task":[206],"compared":[207],"study":[214],"thus":[215],"provides":[216],"effective":[218],"methodology":[219],"synthesizing":[221],"instructions,":[224],"enabling":[225],"adapt":[228],"industrial":[231],"domains.":[232]},"counts_by_year":[],"updated_date":"2026-03-28T06:11:35.319607","created_date":"2026-03-24T00:00:00"}