{"id":"https://openalex.org/W4415937508","doi":"https://doi.org/10.18653/2026.emnlp-main.2266","title":"VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning","display_name":"VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415937508","doi":"https://doi.org/10.18653/2026.emnlp-main.2266"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.2266","doi":"https://doi.org/10.18653/2026.emnlp-main.2266","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.2266","pdf_url":"https://aclanthology.org/2026.emnlp-main.2266.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.2266.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104174550","display_name":"Xuanle Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanle Zhao","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102575213","display_name":"D. A. Jiang","orcid":"https://orcid.org/0009-0000-4471-6965","observed_orcids":["https://orcid.org/0009-0000-4471-6965"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyang Jiang","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhixiong Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixiong Zeng","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689319","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-2269-2912","observed_orcids":["https://orcid.org/0000-0002-2269-2912"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133150073","display_name":"Haoyue Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyue Yang","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036129573","display_name":"Haibo Qiu","orcid":"https://orcid.org/0000-0001-6179-2695","observed_orcids":["https://orcid.org/0000-0001-6179-2695"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Qiu","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124427124","display_name":"Jing Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037151071","display_name":"Liming Zheng","orcid":"https://orcid.org/0000-0003-3179-2162","observed_orcids":["https://orcid.org/0000-0003-3179-2162","https://orcid.org/0000-0002-7544-3020","https://orcid.org/0009-0000-5794-3139"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Zhong","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120467406","display_name":"Liming Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Zheng","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100537074","display_name":"Yilin Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Cao","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100324185","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0002-9810-956X","observed_orcids":["https://orcid.org/0000-0002-9810-956X"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":44.7686,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.99746934,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"51529","last_page":"51544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.7964000105857849,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.7964000105857849,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1859000027179718,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.003000000026077032,"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/visual-reinforcement-learning","display_name":"visual reinforcement learning","score":0.7940000295639038},{"id":"https://openalex.org/keywords/coarse-to-fine-refinement","display_name":"coarse-to-fine refinement","score":0.7540000081062317},{"id":"https://openalex.org/keywords/visual-similarity","display_name":"visual similarity","score":0.37400001287460327},{"id":"https://openalex.org/keywords/reward-modeling","display_name":"reward modeling","score":0.5799999833106995},{"id":"https://openalex.org/keywords/self-refinement","display_name":"self-refinement","score":0.6340000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796500027179718},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6858999729156494},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6324999928474426},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6245999932289124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805000066757202},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5062999725341797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4138999879360199},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.37130001187324524},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.2799000144004822},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.257099986076355}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.2266","doi":"https://doi.org/10.18653/2026.emnlp-main.2266","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.2266","pdf_url":"https://aclanthology.org/2026.emnlp-main.2266.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.00391","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.00391","pdf_url":"https://arxiv.org/pdf/2511.00391","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,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.00391","doi":"https://doi.org/10.48550/arxiv.2511.00391","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.00391","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.2266","doi":"https://doi.org/10.18653/2026.emnlp-main.2266","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.2266","pdf_url":"https://aclanthology.org/2026.emnlp-main.2266.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415937508.pdf","grobid_xml":"https://content.openalex.org/works/W4415937508.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W4366208220","https://openalex.org/W4391631327","https://openalex.org/W4399759273","https://openalex.org/W4400023954","https://openalex.org/W4407794264","https://openalex.org/W4411113317","https://openalex.org/W4411119616","https://openalex.org/W4411120254","https://openalex.org/W4412888781","https://openalex.org/W4412945118","https://openalex.org/W4414565054","https://openalex.org/W4414939355","https://openalex.org/W4414957333","https://openalex.org/W4414968805","https://openalex.org/W4414992111","https://openalex.org/W4415036291","https://openalex.org/W4415085924","https://openalex.org/W4415201012","https://openalex.org/W4415329388","https://openalex.org/W4415330511","https://openalex.org/W4415348594","https://openalex.org/W4415539272","https://openalex.org/W4415539825","https://openalex.org/W4415539870","https://openalex.org/W4416053382","https://openalex.org/W4416538152","https://openalex.org/W4416780398","https://openalex.org/W4417492227","https://openalex.org/W6891898817","https://openalex.org/W6910588990","https://openalex.org/W6929303426","https://openalex.org/W6929624052","https://openalex.org/W6948369276","https://openalex.org/W6948439803","https://openalex.org/W6967068517","https://openalex.org/W7077038961","https://openalex.org/W7077911270","https://openalex.org/W7101713915","https://openalex.org/W7160185532","https://openalex.org/W7160211734"],"related_works":["https://openalex.org/W6891898817","https://openalex.org/W7166812100","https://openalex.org/W7101713915","https://openalex.org/W4404783273","https://openalex.org/W7164887291","https://openalex.org/W7221795661","https://openalex.org/W4403842931","https://openalex.org/W7161029862","https://openalex.org/W7161295972","https://openalex.org/W7136798764"],"abstract_inverted_index":{"While":[0],"recent":[1],"specialized":[2],"multimodal":[3,39],"code":[4,40,68,142],"generation":[5,51],"models":[6],"excel":[7],"in":[8,88],"tasks":[9],"like":[10],"chart-to-code":[11],"generation,":[12],"their":[13],"reliance":[14],"on":[15],"single-task":[16],"training":[17],"limits":[18],"generalization":[19],"and":[20,53,115,143],"hinders":[21],"the":[22,63,83,134],"development":[23],"of":[24,85,136],"VIsioN":[25],"Code":[26],"Intelligence.In":[27],"this":[28],"work,":[29],"we":[30,74],"introduce":[31],"VinciCoder,":[32],"a":[33,44],"unified":[34],"framework":[35],"designed":[36],"for":[37],"generalized":[38],"generation.We":[41],"first":[42],"curate":[43],"large-scale":[45],"SFT":[46],"corpus":[47],"comprising":[48],"1.3M":[49],"direct":[50],"pairs":[52],"300k":[54],"visual-based":[55],"refinement":[56],"tasks.This":[57],"composition":[58],"fosters":[59],"selfrefinement":[60],"capabilities,":[61],"enabling":[62],"model":[64,144],"to":[65,69,81],"directly":[66],"rectify":[67],"align":[70],"with":[71],"input":[72,116],"images.Subsequently,":[73],"propose":[75],"coarse-to-fine":[76],"Visual":[77],"Reinforcement":[78],"Learning":[79],"(ViRL)":[80],"overcome":[82],"brittleness":[84],"textual":[86],"metrics":[87],"handling":[89],"semantically":[90],"equivalent":[91],"but":[92],"syntactically":[93],"diverse":[94,121],"code.By":[95],"quantifying":[96],"visual":[97],"similarity":[98],"across":[99,120],"multi-scale":[100],"patches,":[101],"ViRL":[102,139],"provides":[103],"an":[104],"implementation-agnostic":[105],"reward":[106],"mechanism":[107],"that":[108,124],"ensures":[109],"high-fidelity":[110],"alignment":[111],"between":[112],"rendered":[113],"outputs":[114],"visuals.Extensive":[117],"experimental":[118],"results":[119],"benchmarks":[122],"demonstrate":[123],"VinciCoder":[125],"achieves":[126],"superior":[127],"performance,":[128],"while":[129],"comprehensive":[130],"ablation":[131],"studies":[132],"validate":[133],"effectiveness":[135],"our":[137],"proposed":[138],"strategy.The":[140],"data,":[141],"are":[145],"available":[146],"at":[147],"https://github.com/":[148],"DocTron-hub/VinciCoder.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-11-05T00:00:00"}