{"id":"https://openalex.org/W7133557128","doi":"https://doi.org/10.48550/arxiv.2603.02943","title":"TC-Pad\u00e9: Trajectory-Consistent Pad\u00e9 Approximation for Diffusion Acceleration","display_name":"TC-Pad\u00e9: Trajectory-Consistent Pad\u00e9 Approximation for Diffusion Acceleration","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133557128","doi":"https://doi.org/10.48550/arxiv.2603.02943"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02943","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02943","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.2603.02943","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030151061","display_name":"Benlei Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cui, Benlei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111294571","display_name":"Shaoxuan He","orcid":"https://orcid.org/0009-0002-1571-2855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Shaoxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127811097","display_name":"Bukun Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Bukun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127807614","display_name":"Zhizeng Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Zhizeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128082184","display_name":"Yunyun Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yunyun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128096439","display_name":"Longtao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Longtao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128126904","display_name":"Hui Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Hui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128123319","display_name":"Yang Claire Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128105129","display_name":"Jingqun Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jingqun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128126733","display_name":"Zhou Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128125742","display_name":"Haiwen Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Haiwen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5030151061"],"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/T10531","display_name":"Advanced Vision and Imaging","score":0.2799000144004822,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.2799000144004822,"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":0.17399999499320984,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.06599999964237213,"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/acceleration","display_name":"Acceleration","score":0.7918000221252441},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7577999830245972},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7052000164985657},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6036999821662903},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5340999960899353},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.4977000057697296},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4494999945163727},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4296000003814697},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.42559999227523804}],"concepts":[{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7918000221252441},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7577999830245972},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7052000164985657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6650000214576721},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6036999821662903},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.4977000057697296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46149998903274536},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.42559999227523804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3944999873638153},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3822999894618988},{"id":"https://openalex.org/C2986012078","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling interval","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30820000171661377},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2603999972343445},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02943","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02943","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.2603.02943","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02943","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":[{"score":0.4310756027698517,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"achieving":[1],"state-of-the-art":[2],"generation":[3,167],"quality,":[4],"diffusion":[5],"models":[6],"are":[7],"hindered":[8],"by":[9],"the":[10,38,46,68,145,169],"substantial":[11],"computational":[12],"burden":[13],"of":[14,42,72,148,171],"their":[15],"iterative":[16],"sampling":[17,117,153],"process.":[18],"While":[19],"feature":[20,86,95,199],"caching":[21,64,200],"techniques":[22],"achieve":[23],"effective":[24],"acceleration":[25,178],"at":[26],"higher":[27],"step":[28,120],"counts":[29],"(e.g.,":[30],"50":[31],"steps),":[32],"they":[33],"exhibit":[34],"critical":[35],"limitations":[36],"in":[37,90],"practical":[39],"low-step":[40],"regime":[41],"20-30":[43],"steps.":[44],"As":[45],"interval":[47],"between":[48],"steps":[49],"increases,":[50],"polynomial-based":[51],"extrapolators":[52],"like":[53],"TaylorSeer":[54],"suffer":[55],"from":[56],"error":[57],"accumulation":[58],"and":[59,104,115,138,151,160,165,181,193],"trajectory":[60,136],"drift.":[61],"Meanwhile,":[62],"conventional":[63],"strategies":[65,142],"often":[66],"overlook":[67],"distinct":[69,146],"dynamical":[70],"properties":[71],"different":[73],"denoising":[74],"phases.":[75],"To":[76,112],"address":[77],"these":[78],"challenges,":[79],"we":[80],"propose":[81],"Trajectory-Consistent":[82],"Pad\u00e9":[83,91],"approximation,":[84],"a":[85],"prediction":[87,141],"framework":[88],"grounded":[89],"approximation.":[92],"By":[93],"modeling":[94],"evolution":[96],"through":[97],"rational":[98],"functions,":[99],"our":[100],"approach":[101],"captures":[102],"asymptotic":[103],"transitional":[105],"behaviors":[106],"more":[107],"accurately":[108],"than":[109],"Taylor-based":[110],"methods.":[111,201],"enable":[113],"stable":[114],"trajectory-consistent":[116],"under":[118],"reduced":[119],"counts,":[121],"TC-Pad\u00e9":[122,175],"incorporates":[123],"(1)":[124],"adaptive":[125],"coefficient":[126],"modulation":[127],"that":[128],"leverages":[129],"historical":[130],"cached":[131],"residuals":[132],"to":[133,144],"detect":[134],"subtle":[135],"transitions,":[137],"(2)":[139],"step-aware":[140],"tailored":[143],"dynamics":[147],"early,":[149],"mid,":[150],"late":[152],"stages.":[154],"Extensive":[155],"experiments":[156],"on":[157,179,183],"DiT-XL/2,":[158],"FLUX.1-dev,":[159],"Wan2.1":[161,184],"across":[162,189],"both":[163],"image":[164],"video":[166],"demonstrate":[168],"effectiveness":[170],"TC-Pad\u00e9.":[172],"For":[173],"instance,":[174],"achieves":[176],"2.88x":[177],"FLUX.1-dev":[180],"1.72x":[182],"while":[185],"maintaining":[186],"high":[187],"quality":[188],"FID,":[190],"CLIP,":[191],"Aesthetic,":[192],"VBench-2.0":[194],"metrics,":[195],"substantially":[196],"outperforming":[197],"existing":[198]},"counts_by_year":[],"updated_date":"2026-03-05T07:36:02.291473","created_date":"2026-03-05T00:00:00"}