{"id":"https://openalex.org/W7162789391","doi":"https://doi.org/10.48550/arxiv.2605.30062","title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","display_name":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162789391","doi":"https://doi.org/10.48550/arxiv.2605.30062"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.30062","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30062","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.30062","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124958532","display_name":"Leqi Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Leqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137313038","display_name":"Junyan Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Junyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137380244","display_name":"Kaiqing Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Kaiqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137353175","display_name":"Zhiyuan Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Zhiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137322211","display_name":"Conghui He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Conghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137349131","display_name":"Weijia Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Weijia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5094000101089478,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5094000101089478,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1589999943971634,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.13420000672340393,"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/robustness","display_name":"Robustness (evolution)","score":0.675000011920929},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6241999864578247},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6021000146865845},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4830000102519989},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45669999718666077},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4034000039100647},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.35260000824928284},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.34040001034736633}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7376000285148621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6998999714851379},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.675000011920929},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6241999864578247},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6021000146865845},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4350999891757965},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2776240099","wikidata":"https://www.wikidata.org/wiki/Q327018","display_name":"Interrogation","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.30062","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30062","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.30062","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30062","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,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7026804685592651,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,12,44,148,186],"generative":[3],"artificial":[4],"intelligence":[5],"technologies":[6],"has":[7],"propelled":[8],"the":[9,70,103,106,133,145,157,166,183],"visual":[10],"realism":[11],"synthetic":[13,79],"images":[14],"to":[15,57,68,125],"an":[16,127],"unprecedented":[17],"level.":[18],"Although":[19],"current":[20],"interpretable":[21,178],"detection":[22,80,179],"methods":[23,188],"based":[24],"on":[25,37],"Large":[26],"Multimodal":[27],"Models":[28],"(LMMs)":[29],"have":[30],"made":[31],"certain":[32],"progress,":[33],"they":[34,48],"still":[35],"rely":[36],"imitation":[38],"learning":[39],"derived":[40],"from":[41],"massive":[42],"volumes":[43],"forged":[45],"data.":[46],"Consequently,":[47],"lack":[49],"genuine":[50],"causal":[51],"reasoning":[52],"capabilities":[53,76],"and":[54,194],"are":[55],"prone":[56],"explanatory":[58],"hallucinations.":[59],"To":[60],"overcome":[61],"this":[62,87],"bottleneck,":[63],"we":[64,131],"propose":[65],"FakeVLM-R1,":[66],"aiming":[67],"endow":[69],"model":[71,107],"with":[72,95,136],"human-like":[73],"critical":[74],"thinking":[75],"when":[77],"performing":[78],"tasks.":[81],"Building":[82],"upon":[83],"Supervised":[84],"Fine-Tuning":[85],"(SFT),":[86],"framework":[88],"integrates":[89],"Group":[90],"Relative":[91],"Policy":[92],"Optimization":[93],"(GRPO)":[94],"a":[96,109,116,152],"Critical":[97],"Thinking":[98],"Chain-of-Thought":[99],"(CoT)":[100],"mechanism.":[101],"During":[102],"inference":[104],"phase,":[105],"executes":[108],"\"bidirectional":[110],"dialectical":[111],"reasoning\"":[112],"process:":[113],"while":[114],"proposing":[115],"forgery":[117],"hypothesis,":[118],"it":[119],"must":[120],"simultaneously":[121],"invoke":[122],"physical":[123,146],"commonsense":[124],"construct":[126],"authenticity":[128,154],"counter-proof.":[129],"Furthermore,":[130],"constructed":[132],"FakeClue++":[134],"dataset":[135],"high-quality":[137],"samples,":[138],"which":[139],"extensively":[140],"introduces":[141],"annotations":[142],"guided":[143],"by":[144],"laws":[147],"authentic":[149],"images,":[150,191],"providing":[151],"unified":[153],"anchor":[155],"for":[156],"model.":[158],"Experiments":[159],"confirm":[160],"that":[161],"FakeVLM-R1":[162],"achieves":[163,175],"SOTA":[164],"performance":[165],"evaluated":[167],"models":[168],"across":[169],"multiple":[170],"benchmarks.":[171],"It":[172],"not":[173],"only":[174],"high-precision,":[176],"logically":[177],"but":[180],"also":[181],"resolves":[182],"over-rejection":[184],"bias":[185],"existing":[187],"against":[189,196],"real":[190],"demonstrating":[192],"generalization":[193],"robustness":[195],"perturbations.":[197]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-30T00:00:00"}