{"id":"https://openalex.org/W7164916127","doi":"https://doi.org/10.48550/arxiv.2606.15188","title":"Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing","display_name":"Adaptive Inference-Time Scaling via Early-Step Latent Verification for Image Editing","publication_year":2026,"publication_date":"2026-06-13","ids":{"openalex":"https://openalex.org/W7164916127","doi":"https://doi.org/10.48550/arxiv.2606.15188"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15188","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":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.2606.15188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138756957","display_name":"Yue Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138730812","display_name":"Yang Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiao, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138736423","display_name":"Jiayu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138741605","display_name":"Qi Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138746068","display_name":"Jingjing Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jingjing","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":0.8777999877929688,"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":0.8777999877929688,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.011500000022351742,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.009499999694526196,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.7652000188827515},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5936999917030334},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5917999744415283},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.58160001039505},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4697999954223633},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.447299987077713},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.41269999742507935},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4018000066280365},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.37119999527931213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012999892234802},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7652000188827515},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5936999917030334},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5264000296592712},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3553999960422516},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2597000002861023},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15188","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.15188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15188","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Instruction-based":[0],"image":[1,118],"editing":[2,32,42,134,187,212],"has":[3],"made":[4],"notable":[5],"progress":[6],"with":[7,113],"recent":[8],"advances":[9],"in":[10,30,154],"generative":[11],"models.":[12],"However,":[13],"the":[14,17,24,81,155,191],"quality":[15],"of":[16,62,193],"edited":[18],"result":[19],"is":[20,75],"still":[21],"influenced":[22],"by":[23,51,145],"randomly":[25],"sampled":[26],"initial":[27,36,54,129],"noise,":[28],"particularly":[29],"complex":[31],"scenarios.":[33],"An":[34],"unsuitable":[35],"noise":[37,130],"may":[38],"lead":[39],"to":[40,186],"unsatisfactory":[41],"results.":[43],"Recent":[44],"inference-time":[45,110,179,215],"scaling":[46,111,216],"methods":[47],"address":[48,101],"this":[49,102],"issue":[50],"sampling":[52],"multiple":[53,200],"noises":[55],"and":[56,202,214],"selecting":[57],"better":[58],"candidates.":[59],"Nevertheless,":[60],"most":[61],"them":[63],"follow":[64],"a":[65,107,123,132],"decode-then-verify":[66],"scheme":[67],"which":[68],"introduces":[69],"an":[70,138,151,174],"efficiency-accuracy":[71],"trade-off.":[72],"When":[73],"decoding":[74,164],"performed":[76],"after":[77],"limited":[78],"inference":[79,183],"steps,":[80],"decoded":[82],"images":[83,94],"often":[84],"remain":[85],"too":[86],"noisy":[87],"for":[88,117,178],"reliable":[89],"assessment,":[90],"whereas":[91],"sufficiently":[92],"denoised":[93],"require":[95],"much":[96],"higher":[97],"computational":[98],"cost.":[99],"To":[100],"issue,":[103],"we":[104,121,171],"propose":[105,122],"VeriLatent,":[106],"plug-and-play":[108],"adaptive":[109,175],"framework":[112],"early-step":[114],"latent":[115],"verification":[116],"editing.":[119],"Specifically,":[120],"novel":[124],"verifier":[125],"that":[126,207],"scores":[127],"each":[128],"through":[131],"latent-space":[133],"activation":[135],"map":[136],"at":[137],"early":[139,161],"stage.":[140],"It":[141,181],"identifies":[142],"promising":[143],"candidates":[144],"assessing":[146],"whether":[147],"they":[148],"can":[149],"induce":[150],"effective":[152],"edit":[153],"correct":[156],"region.":[157],"This":[158],"enables":[159],"efficient":[160],"pruning":[162],"without":[163],"latents":[165],"into":[166],"images.":[167],"Building":[168],"on":[169,199],"this,":[170],"further":[172],"develop":[173],"search":[176],"strategy":[177],"scaling.":[180],"allocates":[182],"budgets":[184],"according":[185],"difficulty,":[188],"thereby":[189],"reducing":[190],"number":[192],"function":[194],"evaluations":[195],"(NFE).":[196],"Extensive":[197],"experiments":[198],"benchmarks":[201],"different":[203],"base":[204],"models":[205],"demonstrate":[206],"VeriLatent":[208],"consistently":[209],"improves":[210],"both":[211],"performance":[213],"efficiency.":[217]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}