{"id":"https://openalex.org/W7162502477","doi":"https://doi.org/10.48550/arxiv.2605.26449","title":"Cross-scale Aligned Supervision for Training GANs","display_name":"Cross-scale Aligned Supervision for Training GANs","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162502477","doi":"https://doi.org/10.48550/arxiv.2605.26449"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26449","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26449","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.26449","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137154872","display_name":"Sangeek Hyun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyun, Sangeek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137151048","display_name":"MinKyu Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, MinKyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137140473","display_name":"Jae-Pil Heo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heo, Jae-Pil","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":0.5515999794006348,"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":0.5515999794006348,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.29319998621940613,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.04580000042915344,"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/adversarial-system","display_name":"Adversarial system","score":0.9233999848365784},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6233999729156494},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5493000149726868},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5450000166893005},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5394999980926514},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4968999922275543},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4912000000476837},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4250999987125397}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9233999848365784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287999987602234},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6233999729156494},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5493000149726868},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5394999980926514},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4968999922275543},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4912000000476837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26669999957084656},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26449","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26449","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.26449","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26449","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":"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"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7157911062240601}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"GANs":[1],"often":[2],"introduce":[3],"adversarial":[4,32,93,147],"supervision":[5,33],"on":[6],"intermediate":[7,42,156,173],"generator":[8],"outputs":[9,63,174],"and":[10,200],"interpret":[11],"the":[12,48,67,72,88,106,121,151,176],"resulting":[13],"multi-stage":[14],"synthesis":[15],"as":[16,82,129],"coarse-to-fine":[17,39],"hierarchical":[18],"generation.":[19,148],"In":[20],"this":[21,25,56,127],"work,":[22],"we":[23,138],"challenge":[24],"interpretation.":[26],"We":[27,124],"argue":[28],"that":[29,62,171],"standard":[30],"scale-wise":[31,57],"does":[34,59],"not":[35,60,80],"construct":[36],"a":[37,97,115,130,141,166],"proper":[38],"hierarchy:":[40],"each":[41,77,155],"image":[43,74],"is":[44,79,158],"independently":[45],"pushed":[46],"toward":[47,114],"real":[49],"distribution":[50],"at":[51,76,160],"its":[52,92,161],"own":[53,162],"resolution,":[54,163],"but":[55],"realism":[58],"ensure":[61],"across":[64],"stages":[65,103],"represent":[66],"identical":[68],"generated":[69],"sample.":[70],"Moreover,":[71],"scale-specific":[73,98],"produced":[75],"stage":[78],"used":[81],"an":[83,184],"explicit":[84],"refinement":[85],"target":[86],"for":[87,145],"subsequent":[89],"stage.":[90],"Therefore,":[91],"loss":[94],"can":[95],"improve":[96],"output":[99,157],"without":[100],"constraining":[101],"later":[102],"to":[104,112,126],"preserve":[105],"same":[107],"sample":[108,117],"trajectory,":[109],"allowing":[110],"them":[111],"move":[113],"different":[116],"rather":[118],"than":[119],"refine":[120],"previous":[122],"output.":[123,178],"refer":[125],"problem":[128],"cross-scale":[131],"trajectory":[132],"misalignment":[133],"problem.":[134],"To":[135],"resolve":[136],"it,":[137],"propose":[139],"CAT,":[140],"Cross-scale":[142],"Aligned":[143],"Transformer":[144],"multi-scale":[146],"CAT":[149],"keeps":[150],"discriminator":[152],"scale-wise,":[153],"so":[154],"evaluated":[159],"while":[164],"adding":[165],"simple":[167],"generator-side":[168],"consistency":[169],"regularization":[170],"aligns":[172],"with":[175,188],"final":[177],"On":[179],"class-conditional":[180],"ImageNet-256,":[181],"CAT-H/2":[182],"achieves":[183],"FID-50K":[185],"of":[186],"1.56":[187],"one-step":[189,198],"inference":[190],"after":[191],"only":[192],"60":[193],"training":[194],"epochs,":[195],"outperforming":[196],"strong":[197],"GAN":[199],"diffusion/flow":[201],"baselines.":[202]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-28T00:00:00"}