{"id":"https://openalex.org/W4415329274","doi":"https://doi.org/10.48550/arxiv.2505.15644","title":"Can VLMs Detect and Localize Fine-Grained AI-Edited Images?","display_name":"Can VLMs Detect and Localize Fine-Grained AI-Edited Images?","publication_year":2025,"publication_date":"2025-05-21","ids":{"openalex":"https://openalex.org/W4415329274","doi":"https://doi.org/10.48550/arxiv.2505.15644"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.15644","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15644","pdf_url":"https://arxiv.org/pdf/2505.15644","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sun, Zhen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Zhen","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020977814","display_name":"Ziyi Zhang","orcid":"https://orcid.org/0009-0000-7315-2062","observed_orcids":["https://orcid.org/0009-0000-7315-2062"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Ziyi","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693526","display_name":"Zeren Luo","orcid":"https://orcid.org/0009-0004-9726-0702","observed_orcids":["https://orcid.org/0009-0004-9726-0702"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Zeren","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhong, Zhiyuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Zhiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061607514","display_name":"Zeyang Sha","orcid":"https://orcid.org/0009-0006-5422-0342","observed_orcids":["https://orcid.org/0009-0006-5422-0342"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sha, Zeyang","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002440210","display_name":"Tianshuo Cong","orcid":"https://orcid.org/0000-0003-3189-8223","observed_orcids":["https://orcid.org/0000-0003-3189-8223"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong, Tianshuo","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101465924","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0003-4160-0849","observed_orcids":["https://orcid.org/0000-0003-4160-0849"]},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zheng","raw_affiliation_strings":["Shandong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039364160","display_name":"Shiwen Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui, Shiwen","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109203493","display_name":"Weiqiang Wang","orcid":"https://orcid.org/0000-0002-6159-619X","observed_orcids":["https://orcid.org/0000-0002-6159-619X","https://orcid.org/0000-0002-7185-2804","https://orcid.org/0000-0001-5734-1226"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Weiqiang","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049263948","display_name":"Jiaheng Wei","orcid":"https://orcid.org/0000-0003-3573-1711","observed_orcids":["https://orcid.org/0000-0003-3573-1711"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei, Jiaheng","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074889369","display_name":"Xinlei He","orcid":"https://orcid.org/0009-0007-3879-9080","observed_orcids":["https://orcid.org/0009-0007-3879-9080","https://orcid.org/0000-0001-5725-2848"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Xinlei","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350192","display_name":"Qi Li","orcid":"https://orcid.org/0000-0002-1672-6362","observed_orcids":["https://orcid.org/0000-0002-1672-6362"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Qi","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wang, Qian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Qian","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9984999895095825,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9984999895095825,"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":0.0012000000569969416,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":9.999999747378752e-05,"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/vision-language-models","display_name":"vision-language models","score":0.925000011920929},{"id":"https://openalex.org/keywords/cross-dataset-generalization","display_name":"cross-dataset generalization","score":0.7730000019073486},{"id":"https://openalex.org/keywords/lora","display_name":"LoRa","score":0.47999998927116394},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.6290000081062317},{"id":"https://openalex.org/keywords/qwen2-5-vl","display_name":"Qwen2.5-VL","score":0.9330000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349000215530396},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8205999732017517},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7233999967575073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6739000082015991},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6029999852180481},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5849999785423279},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5648999810218811},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4984999895095825},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37049999833106995},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.34290000796318054},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.33480000495910645},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.15644","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15644","pdf_url":"https://arxiv.org/pdf/2505.15644","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","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.2505.15644","doi":"https://doi.org/10.48550/arxiv.2505.15644","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15644","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15644","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15644","pdf_url":"https://arxiv.org/pdf/2505.15644","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","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415329274.pdf","grobid_xml":"https://content.openalex.org/works/W4415329274.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7172006881","https://openalex.org/W7106655390","https://openalex.org/W7136319008","https://openalex.org/W7163514023","https://openalex.org/W4417210231","https://openalex.org/W4414198490","https://openalex.org/W7127973575","https://openalex.org/W4405094436","https://openalex.org/W4414811217","https://openalex.org/W7140085814"],"abstract_inverted_index":{"Fine-grained":[0],"detection":[1],"and":[2,19,63,85,101,123,148,175,186,191,196,201,216],"localization":[3,56],"of":[4,91,171,199,224],"localized":[5],"image":[6,20],"edits":[7,47],"is":[8,66],"crucial":[9],"for":[10,54,120],"assessing":[11],"content":[12,226],"authenticity,":[13],"especially":[14],"as":[15,143],"modern":[16,69],"diffusion":[17],"models":[18,118,141],"editors":[21],"can":[22],"produce":[23,38],"highly":[24],"realistic":[25],"manipulations.":[26],"However,":[27],"this":[28,137,207],"problem":[29],"faces":[30],"three":[31],"key":[32],"challenges:":[33],"(1)":[34],"most":[35],"AIGC":[36],"detectors":[37],"only":[39],"a":[40,88,211],"global":[41],"real-or-fake":[42],"label":[43],"without":[44],"indicating":[45],"where":[46],"occur;":[48],"(2)":[49],"traditional":[50],"computer":[51],"vision":[52,116],"methods":[53],"edit":[55,104],"typically":[57],"rely":[58],"on":[59,107,136],"costly":[60],"pixel-level":[61],"annotations;":[62],"(3)":[64],"there":[65],"no":[67],"large-scale,":[68],"benchmark":[70,90],"specifically":[71],"targeting":[72],"edited-image":[73,121],"detection.":[74],"To":[75],"address":[76],"these":[77],"gaps,":[78],"we":[79,109],"develop":[80],"an":[81],"automated":[82],"data-generation":[83],"pipeline":[84],"construct":[86],"FragFake,":[87,108],"large-scale":[89],"AI-edited":[92],"images":[93],"spanning":[94],"multiple":[95],"source":[96],"datasets,":[97],"diverse":[98],"editing":[99],"models,":[100],"several":[102],"common":[103],"types.":[105],"Building":[106],"are":[110],"the":[111,169,194,197,222],"first":[112],"to":[113,214],"systematically":[114],"study":[115],"language":[117],"(VLMs)":[119],"classification":[122],"edited-region":[124],"localization.":[125],"Our":[126],"experiments":[127],"show":[128],"that":[129,206],"pretrained":[130],"VLMs,":[131],"including":[132],"GPT4o,":[133],"perform":[134],"poorly":[135],"task,":[138],"whereas":[139],"fine-tuned":[140],"such":[142],"Qwen2.5-VL":[144],"achieve":[145],"high":[146],"accuracy":[147],"substantially":[149],"higher":[150],"object":[151],"precision":[152],"across":[153],"all":[154],"settings.":[155],"We":[156,204],"further":[157],"explore":[158],"GRPO-based":[159],"RLVR":[160],"training,":[161],"which":[162],"yields":[163],"modest":[164],"metric":[165],"gains":[166],"while":[167],"improving":[168],"interpretability":[170],"model":[172],"outputs.":[173],"Ablation":[174],"transfer":[176],"analyses":[177],"reveal":[178],"how":[179],"data":[180],"balancing,":[181],"training":[182,187],"size,":[183],"LoRA":[184],"rank,":[185],"domain":[188,223],"affect":[189],"performance,":[190],"highlight":[192],"both":[193],"potential":[195],"limitations":[198],"cross-editor":[200],"cross-dataset":[202],"generalization.":[203],"anticipate":[205],"work":[208],"will":[209],"establish":[210],"solid":[212],"foundation":[213],"facilitate":[215],"inspire":[217],"subsequent":[218],"research":[219],"endeavors":[220],"in":[221],"multimodal":[225],"authenticity.":[227]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-19T00:00:00"}