{"id":"https://openalex.org/W7160602787","doi":"https://doi.org/10.48550/arxiv.2605.05736","title":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","display_name":"SDFlow: Similarity-Driven Flow Matching for Time Series Generation","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160602787","doi":"https://doi.org/10.48550/arxiv.2605.05736"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05736","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.05736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135682027","display_name":"Wei Li","orcid":"https://orcid.org/0000-0003-2543-2558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135725981","display_name":"Shibo Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Shibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135678697","display_name":"Pengcheng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Pengcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135682464","display_name":"Min Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Xingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135639151","display_name":"Peilin Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Min","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhao, Peilin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Peilin","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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.815500020980835,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.815500020980835,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04270000010728836,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.019500000402331352,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7290999889373779},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6388000249862671},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6194000244140625},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4902999997138977},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.47699999809265137},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4424000084400177},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.427700012922287},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42399999499320984},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.3901999890804291}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7290999889373779},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6388000249862671},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6133999824523926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5062999725341797},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4902999997138977},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2754000127315521},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C68757728","wikidata":"https://www.wikidata.org/wiki/Q911082","display_name":"DEVS","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05736","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.05736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05736","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7273344993591309}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vector":[0],"quantization":[1],"(VQ)":[2],"with":[3,91,109],"autoregressive":[4,167],"(AR)":[5],"token":[6,89,102],"modeling":[7],"is":[8,177],"a":[9,53,92,105,110,129,136],"widely":[10],"adopted":[11],"and":[12,65,118,151,173],"highly":[13],"competitive":[14],"paradigm":[15],"for":[16,156],"time-series":[17],"generation.":[18,43,159],"However,":[19],"such":[20],"models":[21],"are":[22],"fundamentally":[23],"limited":[24],"by":[25,86,127],"exposure":[26,84],"bias:":[27],"during":[28],"inference,":[29],"errors":[30],"can":[31],"accumulate":[32],"across":[33],"sequential":[34],"predictions,":[35],"leading":[36],"to":[37],"pronounced":[38],"quality":[39],"degradation":[40],"in":[41,59,78],"long-horizon":[42],"To":[44],"address":[45],"this,":[46],"we":[47],"propose":[48],"SDFlow":[49,144,161],"($\\textbf{S}$imilarity-$\\textbf{D}$riven":[50],"$\\textbf{Flow}$":[51],"Matching),":[52],"non-autoregressive":[54],"framework":[55],"that":[56,143],"operates":[57],"entirely":[58],"the":[60,98,115],"frozen":[61],"VQ":[62,101],"latent":[63,116],"space":[64],"enables":[66],"parallel":[67],"sequence":[68],"generation":[69],"via":[70,104],"flow":[71],"matching.":[72],"We":[73],"tackle":[74],"three":[75],"key":[76],"challenges":[77],"making":[79],"this":[80],"transition:":[81],"(1)":[82],"eliminating":[83],"bias":[85],"replacing":[87],"step-wise":[88],"prediction":[90],"global":[93],"transport":[94,125],"map;":[95],"(2)":[96],"mitigating":[97],"high-dimensionality":[99],"of":[100],"spaces":[103],"low-rank":[106],"manifold":[107],"decomposition":[108],"learned":[111],"anchor":[112],"prior":[113],"over":[114,132,166],"manifold;":[117],"(3)":[119],"incorporating":[120],"discrete":[121],"supervision":[122],"into":[123],"continuous":[124],"dynamics":[126],"introducing":[128],"categorical":[130],"posterior":[131],"codebook":[133],"indices":[134],"within":[135],"variational":[137],"flow-matching":[138],"formulation.":[139],"Extensive":[140],"experiments":[141],"show":[142],"achieves":[145],"state-of-the-art":[146],"performance,":[147],"improving":[148],"Discriminative":[149],"Score":[150],"substantially":[152],"reducing":[153],"Context-FID,":[154],"particularly":[155],"challenging":[157],"long-sequence":[158],"Moreover,":[160],"provides":[162],"significant":[163],"inference":[164],"speedups":[165],"baselines,":[168],"offering":[169],"both":[170],"high":[171],"fidelity":[172],"computational":[174],"efficiency.":[175],"Code":[176],"available":[178],"at":[179],"https://anonymous.4open.science/r/SDFlow-D6F3/":[180]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-09T00:00:00"}