{"id":"https://openalex.org/W7154996772","doi":"https://doi.org/10.48550/arxiv.2604.16044","title":"Elucidating the SNR-t Bias of Diffusion Probabilistic Models","display_name":"Elucidating the SNR-t Bias of Diffusion Probabilistic Models","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7154996772","doi":"https://doi.org/10.48550/arxiv.2604.16044"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16044","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16044","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.16044","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134065861","display_name":"Meng Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134016027","display_name":"Lei Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079515428","display_name":"Jianhao Zeng","orcid":"https://orcid.org/0000-0002-1026-729X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Jianhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134065206","display_name":"Xiangxiang Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Xiangxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134079307","display_name":"Kun Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhan, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.8310999870300293,"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":0.8310999870300293,"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/T10581","display_name":"Neural dynamics and brain function","score":0.019600000232458115,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6929000020027161},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5924000144004822},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5748000144958496},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5286999940872192},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.42980000376701355},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4032000005245209},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3991999924182892},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.3919999897480011}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6929000020027161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6201000213623047},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6035000085830688},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5924000144004822},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3707999885082245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.364300012588501},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.35179999470710754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33309999108314514},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2777000069618225},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16044","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16044","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.16044","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16044","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":"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":{"Diffusion":[0],"Probabilistic":[1],"Models":[2],"have":[3,16],"demonstrated":[4],"remarkable":[5],"performance":[6],"across":[7],"a":[8,24,56,94],"wide":[9],"range":[10],"of":[11,38,55,150,165],"generative":[12],"tasks.":[13],"However,":[14,64],"we":[15,124],"observed":[17],"that":[18,107,142],"these":[19],"models":[20,109,153],"often":[21],"suffer":[22],"from":[23],"Signal-to-Noise":[25],"Ratio-timestep":[26],"(SNR-t)":[27],"bias.":[28,105],"This":[29],"bias":[30],"refers":[31],"to":[32,72,88,101,135],"the":[33,36,39,47,53,77,103,120,147],"misalignment":[34],"between":[35],"SNR":[37,54],"denoising":[40,122],"sample":[41,57],"and":[42,75,85,92,131,161],"its":[43,62],"corresponding":[44],"timestep":[45],"during":[46,51,69,119],"inference":[48],"phase.":[49],"Specifically,":[50],"training,":[52],"is":[58,67,174],"strictly":[59],"coupled":[60],"with":[61,168],"timestep.":[63],"this":[65,90],"correspondence":[66],"disrupted":[68],"inference,":[70],"leading":[71],"error":[73],"accumulation":[74],"impairing":[76],"generation":[78,148],"quality.":[79],"We":[80],"provide":[81],"comprehensive":[82],"empirical":[83],"evidence":[84],"theoretical":[86],"analysis":[87],"substantiate":[89],"phenomenon":[91],"propose":[93],"simple":[95],"yet":[96],"effective":[97],"differential":[98,133],"correction":[99,134],"method":[100],"mitigate":[102],"SNR-t":[104],"Recognizing":[106],"diffusion":[108,152],"typically":[110],"reconstruct":[111],"low-frequency":[112],"components":[113,130],"before":[114],"focusing":[115],"on":[116,163],"high-frequency":[117],"details":[118],"reverse":[121],"process,":[123],"decompose":[125],"samples":[126],"into":[127],"various":[128,151,166],"frequency":[129],"apply":[132],"each":[136],"component":[137],"individually.":[138],"Extensive":[139],"experiments":[140],"show":[141],"our":[143],"approach":[144],"significantly":[145],"improves":[146],"quality":[149],"(IDDPM,":[154],"ADM,":[155],"DDIM,":[156],"A-DPM,":[157],"EA-DPM,":[158],"EDM,":[159],"PFGM++,":[160],"FLUX)":[162],"datasets":[164],"resolutions":[167],"negligible":[169],"computational":[170],"overhead.":[171],"The":[172],"code":[173],"at":[175],"https://github.com/AMAP-ML/DCW.":[176]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-21T00:00:00"}