{"id":"https://openalex.org/W7160398560","doi":"https://doi.org/10.48550/arxiv.2605.03317","title":"AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers","display_name":"AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160398560","doi":"https://doi.org/10.48550/arxiv.2605.03317"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.03317","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03317","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.03317","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135444736","display_name":"Ruibin Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Min, Ruibin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135460371","display_name":"Yexin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yexin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104198782","display_name":"Aimin Pan","orcid":"https://orcid.org/0009-0004-9823-1436"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Aimin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135430231","display_name":"Changsheng Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Changsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135453268","display_name":"Jiafei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jiafei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135463461","display_name":"Kelu Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Kelu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135446515","display_name":"Xiaogang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xiaogang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135474641","display_name":"Harry Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Harry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5135444736"],"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":0.5404999852180481,"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":0.5404999852180481,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09470000118017197,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.09009999781847,"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/granularity","display_name":"Granularity","score":0.7809000015258789},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6225000023841858},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5649999976158142},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5540000200271606},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43810001015663147},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.42809998989105225},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.3930000066757202},{"id":"https://openalex.org/keywords/image-stitching","display_name":"Image stitching","score":0.36899998784065247},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.3580999970436096}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.7809000015258789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145000100135803},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6225000023841858},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5649999976158142},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4855000078678131},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43810001015663147},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.3930000066757202},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36559998989105225},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3440999984741211},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2718999981880188},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.03317","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03317","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":"doi:10.48550/arxiv.2605.03317","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03317","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Representation":[0],"alignment":[1,18,29,55,101,124,148,188],"has":[2],"recently":[3],"emerged":[4],"as":[5,146],"an":[6],"effective":[7],"paradigm":[8],"for":[9,107],"accelerating":[10],"Diffusion":[11],"Transformer":[12],"training.":[13,220],"Despite":[14],"their":[15],"success,":[16],"existing":[17],"methods":[19],"typically":[20],"impose":[21],"a":[22,27,104,122,142],"fixed":[23,28],"supervision":[24,64,218],"target":[25],"or":[26,47],"granularity":[30,61,189],"throughout":[31],"the":[32,37,59,68,88,128,134,147,182,187,191],"entire":[33],"denoising":[34,183],"trajectory,":[35,184],"whether":[36],"guidance":[38],"is":[39,56],"provided":[40],"by":[41],"external":[42,216],"vision":[43],"encoders,":[44],"internal":[45],"self-representations,":[46],"VAE-derived":[48],"features.":[49],"We":[50],"argue":[51],"that":[52,126,155,199],"such":[53],"timestep-agnostic":[54],"suboptimal":[57],"because":[58],"useful":[60],"of":[62,139],"representation":[63],"changes":[65],"systematically":[66],"with":[67,190],"signal-to-noise":[69],"ratio.":[70],"In":[71],"high-noise":[72],"regimes,":[73,87],"diffusion":[74],"models":[75],"benefit":[76],"more":[77],"from":[78,160],"coarse":[79,167],"semantic":[80,168],"and":[81,95,163,176,203,208],"layout-level":[82],"anchoring,":[83],"whereas":[84],"in":[85,133],"low-noise":[86],"training":[89,194],"signal":[90],"should":[91],"emphasize":[92],"spatially":[93],"detailed":[94],"structurally":[96],"faithful":[97],"refinement.":[98],"This":[99],"non-stationary":[100],"behavior":[102],"creates":[103],"representational":[105],"mismatch":[106],"static":[108],"single-level":[109],"supervisors.":[110],"To":[111],"address":[112],"this":[113],"issue,":[114],"we":[115],"propose":[116],"Adaptive":[117],"Hierarchical":[118],"Prior":[119],"Alignment":[120],"(AHPA),":[121],"lightweight":[123],"framework":[125],"exploits":[127],"hierarchical":[129,179],"representations":[130],"naturally":[131],"embedded":[132],"frozen":[135],"VAE":[136,153],"encoder.":[137],"Instead":[138],"using":[140],"only":[141],"single":[143],"compressed":[144],"latent":[145],"target,":[149],"AHPA":[150,200],"extracts":[151],"multi-level":[152],"features":[154],"provide":[156],"complementary":[157],"priors":[158,180],"ranging":[159],"local":[161],"geometry":[162],"spatial":[164],"topology":[165],"to":[166],"layout.":[169],"A":[170],"timestep-conditioned":[171],"Dynamic":[172],"Router":[173],"adaptively":[174],"selects":[175],"weights":[177],"these":[178],"along":[181],"thereby":[185],"synchronizing":[186],"model's":[192],"evolving":[193],"needs.":[195],"Extensive":[196],"experiments":[197],"show":[198],"improves":[201],"convergence":[202],"generation":[204],"quality":[205],"over":[206],"baselines":[207],"incurs":[209],"no":[210],"additional":[211],"inference":[212],"cost":[213],"while":[214],"avoiding":[215],"encoder":[217],"during":[219]},"counts_by_year":[],"updated_date":"2026-05-07T06:12:12.454206","created_date":"2026-05-07T00:00:00"}