{"id":"https://openalex.org/W7131638568","doi":"https://doi.org/10.48550/arxiv.2602.21716","title":"TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection","display_name":"TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection","publication_year":2026,"publication_date":"2026-02-25","ids":{"openalex":"https://openalex.org/W7131638568","doi":"https://doi.org/10.48550/arxiv.2602.21716"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.21716","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126866383","display_name":"Wenbin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Wenbin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006016056","display_name":"Yuge Huang","orcid":"https://orcid.org/0000-0001-5387-5992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yuge","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085698218","display_name":"Jianqing Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jianqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126939317","display_name":"Yue Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122925762","display_name":"Jiangtao Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Jiangtao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126945805","display_name":"Shouhong Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Shouhong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126915353","display_name":"Pan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Pan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126863851","display_name":"Yong Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5126866383"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.18870000541210175,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.18870000541210175,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.131400004029274,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.11150000244379044,"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/bridging","display_name":"Bridging (networking)","score":0.6274999976158142},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.6136999726295471},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5275999903678894},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.47510001063346863},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4036000072956085},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.3797000050544739},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33180001378059387},{"id":"https://openalex.org/keywords/information-fusion","display_name":"Information fusion","score":0.3222000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833999991416931},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5964999794960022},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.47510001063346863},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4036000072956085},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3797000050544739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3617999851703644},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30000001192092896},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.21716","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.21716","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.21716","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.21716","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6566976308822632}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Rapid":[0],"advances":[1],"in":[2],"AI-generated":[3],"image":[4],"(AIGI)":[5],"technology":[6],"enable":[7],"highly":[8],"realistic":[9],"synthesis,":[10],"threatening":[11],"public":[12],"information":[13,113,126],"integrity":[14],"and":[15,75,102,117,146],"security.":[16],"Recent":[17],"studies":[18],"have":[19],"demonstrated":[20],"that":[21,46,95,120,141],"incorporating":[22],"texture-level":[23],"artifact":[24,47,76,101,112,128],"features":[25,28,48],"alongside":[26],"semantic":[27,74,103,115,125],"into":[29,114,127],"multimodal":[30],"large":[31],"language":[32],"models":[33],"(MLLMs)":[34],"can":[35],"enhance":[36],"their":[37],"AIGI":[38,133],"detection":[39,134],"capability.":[40],"However,":[41],"our":[42,142],"preliminary":[43],"analyses":[44],"reveal":[45],"exhibit":[49],"high":[50],"intra-feature":[51],"similarity,":[52],"leading":[53],"to":[54,110,123,150],"an":[55,118],"almost":[56],"uniform":[57],"attention":[58,67],"map":[59],"after":[60],"the":[61,97],"softmax":[62],"operation.":[63],"This":[64],"phenomenon":[65],"causes":[66],"dilution,":[68],"thereby":[69],"hindering":[70],"effective":[71],"fusion":[72,86],"between":[73,100],"features.":[77,129],"To":[78],"overcome":[79],"this":[80],"limitation,":[81],"we":[82],"propose":[83],"a":[84,91,107],"lightweight":[85],"adapter,":[87],"TranX-Adapter,":[88],"which":[89],"integrates":[90],"Task-aware":[92],"Optimal-Transport":[93],"Fusion":[94],"leverages":[96],"Jensen-Shannon":[98],"divergence":[99],"prediction":[104],"probabilities":[105],"as":[106],"cost":[108],"matrix":[109],"transfer":[111,124],"features,":[116],"X-Fusion":[119],"employs":[121],"cross-attention":[122],"Experiments":[130],"on":[131],"standard":[132],"benchmarks":[135],"upon":[136],"several":[137],"advanced":[138],"MLLMs,":[139],"show":[140],"TranX-Adapter":[143],"brings":[144],"consistent":[145],"significant":[147],"improvements":[148],"(up":[149],"+6%":[151],"accuracy).":[152]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-27T00:00:00"}