{"id":"https://openalex.org/W7148765888","doi":"https://doi.org/10.48550/arxiv.2604.01552","title":"ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor","display_name":"ZEUS: Accelerating Diffusion Models with Only Second-Order Predictor","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148765888","doi":"https://doi.org/10.48550/arxiv.2604.01552"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01552","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.2604.01552","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132859206","display_name":"Yixiao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Yixiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132872794","display_name":"Ting Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Ting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102696700","display_name":"Zishan Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Zishan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000892367","display_name":"Hancheng Ye","orcid":"https://orcid.org/0000-0002-6272-2792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Hancheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132837936","display_name":"Jingwei Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jingwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132922381","display_name":"Mingyuan Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Mingyuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132913122","display_name":"Jianyi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jianyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132840293","display_name":"Yiran Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yiran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132913894","display_name":"Hai \"Helen\" Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hai","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5132859206"],"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":0.9395999908447266,"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":0.9395999908447266,"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":0.006300000008195639,"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/T11019","display_name":"Image Enhancement Techniques","score":0.006200000178068876,"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":0.6718999743461609},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6471999883651733},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5957000255584717},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5511000156402588},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4560000002384186},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3614000082015991},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.3379000127315521},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3370000123977661},{"id":"https://openalex.org/keywords/zeus","display_name":"ZEUS (particle detector)","score":0.3292999863624573}],"concepts":[{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6718999743461609},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6471999883651733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5989000201225281},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4986000061035156},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2776444479","wikidata":"https://www.wikidata.org/wiki/Q8063038","display_name":"ZEUS (particle detector)","level":5,"score":0.3292999863624573},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3230000138282776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2800999879837036},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01552","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.2604.01552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01552","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":{"Denoising":[0],"generative":[1],"models":[2],"deliver":[3],"high-fidelity":[4],"generation":[5],"but":[6],"remain":[7],"bottlenecked":[8],"by":[9,27],"inference":[10],"latency":[11,26],"due":[12],"to":[13,163],"the":[14,30,35,78,86,154],"many":[15],"iterative":[16],"denoiser":[17,103],"calls":[18],"required":[19],"during":[20],"sampling.":[21],"Training-free":[22],"acceleration":[23,40,98],"methods":[24,41],"reduce":[25],"either":[28],"sparsifying":[29],"model":[31],"architecture":[32],"or":[33],"shortening":[34],"sampling":[36],"trajectory.":[37],"Current":[38],"training-free":[39,159],"are":[42],"more":[43],"complex":[44],"than":[45],"necessary:":[46],"higher-order":[47],"predictors":[48],"amplify":[49],"error":[50],"under":[51],"aggressive":[52,111],"speedups,":[53],"and":[54,81,109,130,134,143,148],"architectural":[55,132],"modifications":[56],"hinder":[57],"deployment.":[58],"Beyond":[59],"2x":[60],"acceleration,":[61],"step":[62],"skipping":[63,113],"creates":[64],"structural":[65],"scarcity":[66],"--":[67,76],"at":[68],"most":[69],"one":[70],"fresh":[71],"evaluation":[72],"per":[73],"local":[74],"window":[75],"leaving":[77],"computed":[79],"output":[80],"its":[82],"backward":[83],"difference":[84],"as":[85],"only":[87],"causally":[88],"grounded":[89],"information.":[90],"Based":[91],"on":[92],"this,":[93],"we":[94],"propose":[95],"ZEUS,":[96],"an":[97,115],"method":[99],"that":[100,118],"predicts":[101],"reduced":[102],"evaluations":[104],"using":[105],"a":[106],"second-order":[107],"predictor,":[108],"stabilizes":[110],"consecutive":[112],"with":[114,138],"interleaved":[116],"scheme":[117],"avoids":[119],"back-to-back":[120],"extrapolations.":[121],"ZEUS":[122,151],"adds":[123],"essentially":[124],"zero":[125],"overhead,":[126],"no":[127,131],"feature":[128],"caches,":[129],"modifications,":[133],"it":[135],"is":[136,173],"compatible":[137],"different":[139],"backbones,":[140],"prediction":[141],"objectives,":[142],"solver":[144],"choices.":[145],"Across":[146],"image":[147],"video":[149],"generation,":[150],"consistently":[152],"improves":[153],"speed-fidelity":[155],"performance":[156],"over":[157],"recent":[158],"baselines,":[160],"achieving":[161],"up":[162],"3.2x":[164],"end-to-end":[165],"speedup":[166],"while":[167],"maintaining":[168],"perceptual":[169],"quality.":[170],"Our":[171],"code":[172],"available":[174],"at:":[175],"https://github.com/Ting-Justin-Jiang/ZEUS.":[176]},"counts_by_year":[],"updated_date":"2026-04-04T06:15:33.020886","created_date":"2026-04-04T00:00:00"}