{"id":"https://openalex.org/W7127586129","doi":"https://doi.org/10.48550/arxiv.2602.02927","title":"Training-Free Self-Correction for Multimodal Masked Diffusion Models","display_name":"Training-Free Self-Correction for Multimodal Masked Diffusion Models","publication_year":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7127586129","doi":"https://doi.org/10.48550/arxiv.2602.02927"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.02927","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/A5005136271","display_name":"Yidong Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ouyang, Yidong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043898209","display_name":"Panwen Hu","orcid":"https://orcid.org/0000-0001-6183-6598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Panwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124825817","display_name":"Zhengyan Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Zhengyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125004195","display_name":"Zhe Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125070649","display_name":"Liyan Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Liyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124983142","display_name":"Dmitriy Bespalov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bespalov, Dmitriy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124980186","display_name":"Ying Nian Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Ying Nian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125093548","display_name":"Guang Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Guang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125087064","display_name":"Hongyuan Zha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zha, Hongyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125060808","display_name":"Qiang Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Qiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5005136271"],"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":0.8842999935150146,"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":0.8842999935150146,"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":0.0142000000923872,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.012600000016391277,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6922000050544739},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6430000066757202},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4778999984264374},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4268999993801117},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.37929999828338623},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.37770000100135803},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3343999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142999768257141},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6922000050544739},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6430000066757202},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4778999984264374},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42570000886917114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4097999930381775},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37770000100135803},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2985139394","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Sampling scheme","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.02927","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.02927","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.02927","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.02927","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49365729093551636,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Masked":[0],"diffusion":[1,76,111],"models":[2],"have":[3],"emerged":[4],"as":[5,26],"a":[6,64],"powerful":[7],"framework":[8,67,106],"for":[9],"text":[10],"and":[11,22,48,95,116],"multimodal":[12,96],"generation.":[13],"However,":[14],"their":[15],"sampling":[16,101],"procedure":[17],"updates":[18],"multiple":[19],"tokens":[20,25],"simultaneously":[21],"treats":[23],"generated":[24],"immutable,":[27],"which":[28],"may":[29],"lead":[30],"to":[31],"error":[32],"accumulation":[33],"when":[34],"early":[35],"mistakes":[36],"cannot":[37],"be":[38,121],"revised.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"revisit":[44],"existing":[45],"self-correction":[46,66],"methods":[47],"identify":[49],"limitations":[50],"stemming":[51],"from":[52],"additional":[53],"training":[54],"requirements":[55],"or":[56,82],"reliance":[57],"on":[58,92],"misaligned":[59],"likelihood":[60],"estimates.":[61],"We":[62],"propose":[63],"training-free":[65],"that":[68],"exploits":[69],"the":[70,104],"inductive":[71],"biases":[72],"of":[73],"pre-trained":[74],"masked":[75,110],"models.":[77],"Without":[78],"modifying":[79],"model":[80],"parameters":[81],"introducing":[83],"auxiliary":[84],"evaluators,":[85],"our":[86],"method":[87],"significantly":[88],"improves":[89],"generation":[90,94],"quality":[91],"text-to-image":[93],"understanding":[97],"tasks":[98],"with":[99],"reduced":[100],"steps.":[102],"Moreover,":[103],"proposed":[105],"generalizes":[107],"across":[108],"different":[109],"architectures,":[112],"highlighting":[113],"its":[114],"robustness":[115],"practical":[117],"applicability.":[118],"Code":[119],"can":[120],"found":[122],"in":[123],"https://github.com/huge123/FreeCorrection.":[124]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-06T00:00:00"}