{"id":"https://openalex.org/W7164196648","doi":"https://doi.org/10.48550/arxiv.2606.09861","title":"Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models","display_name":"Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models","publication_year":2026,"publication_date":"2026-05-31","ids":{"openalex":"https://openalex.org/W7164196648","doi":"https://doi.org/10.48550/arxiv.2606.09861"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.09861","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09861","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.2606.09861","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102900748","display_name":"Yunhao Zhang","orcid":"https://orcid.org/0000-0003-3575-1122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yunhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071280656","display_name":"Ruiying Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Ruiying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138344926","display_name":"Jiale Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Jiale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138340712","display_name":"Jianfeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jianfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138333021","display_name":"Lujia Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Lujia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087158377","display_name":"Junchi Yan","orcid":"https://orcid.org/0000-0001-9639-7679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Junchi","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":0.6243000030517578,"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":0.6243000030517578,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.11400000005960464,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.07559999823570251,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.5695000290870667},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5008000135421753},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48539999127388},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4846999943256378},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.4528000056743622},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4058000147342682},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.40130001306533813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583000063896179},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5289999842643738},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4058000147342682},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26080000400543213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.09861","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09861","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.2606.09861","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.09861","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Next-Token":[1],"Prediction":[2],"(NTP)":[3],"has":[4],"unified":[5,145],"LLM":[6,105],"pretraining,":[7],"its":[8],"adaptation":[9],"to":[10,130],"unbounded,":[11],"continuous":[12],"time":[13],"series":[14,125],"(TS)":[15],"remains":[16],"open.":[17],"To":[18],"bridge":[19],"the":[20],"gap,":[21],"we":[22],"introduce":[23],"UniTok,":[24],"a":[25,36,47,77,86,95,143],"universal":[26],"tokenizer":[27],"that":[28,51,142],"transforms":[29],"TS":[30],"into":[31],"discrete":[32],"tokens,":[33],"and":[34,54,62,92,94,139,150,160],"UniTok-FM,":[35],"foundation":[37,49,158],"model":[38,50],"pretrained":[39],"via":[40,64],"NTP":[41,118],"on":[42,113,119,136],"these":[43],"tokens.":[44],"UniTok-FM":[45,101,146],"is":[46,76],"general-purpose":[48],"supports":[52],"zero-shot":[53],"prompt-boosted":[55],"forecasting,":[56,137],"as":[57,59],"well":[58],"few-shot":[60],"generation":[61],"classification":[63,140],"training-free":[65,163],"in-context":[66,164],"inference--a":[67],"capability":[68],"not":[69],"achieved":[70],"by":[71,123],"prior":[72],"works.":[73],"Technically,":[74],"UniTok":[75],"vector-quantized":[78],"autoencoder":[79],"incorporating":[80],"prefix":[81],"normalization":[82],"for":[83,90,99],"scale":[84],"stabilization,":[85],"progressive-resolution":[87],"causal":[88],"architecture":[89,106],"encoding":[91],"decoding,":[93],"structure-preserving":[96],"reconstruction":[97],"loss":[98],"training.":[100],"adopts":[102],"an":[103],"off-the-shelf":[104],"without":[107],"TS-specific":[108],"modifications.":[109],"Instead":[110],"of":[111],"pretraining":[112],"isolated":[114],"TS,":[115],"it":[116],"performs":[117],"context":[120],"windows":[121],"formed":[122],"multiple":[124],"with":[126,156],"similar":[127],"patterns,":[128],"aiming":[129],"capture":[131],"their":[132],"shared":[133],"dynamics.":[134],"Experiments":[135],"generation,":[138],"show":[141],"single":[144],"consistently":[147],"outperforms":[148],"statistical":[149],"supervised":[151],"baselines,":[152],"achieves":[153],"competitive":[154],"performance":[155],"task-specific":[157],"models,":[159],"uniquely":[161],"enables":[162],"inference":[165],"across":[166],"tasks.":[167]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-11T00:00:00"}