{"id":"https://openalex.org/W7147647403","doi":"https://doi.org/10.48550/arxiv.2603.29756","title":"One-for-All: A Lightweight Stabilized and Parameter-Efficient Pre-trained LLM for Time Series Forecasting","display_name":"One-for-All: A Lightweight Stabilized and Parameter-Efficient Pre-trained LLM for Time Series Forecasting","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7147647403","doi":"https://doi.org/10.48550/arxiv.2603.29756"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29756","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29756","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.2603.29756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044362557","display_name":"Prasanjit Dey","orcid":"https://orcid.org/0000-0002-2248-1701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dey, Prasanjit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011772990","display_name":"Soumyabrata Dev","orcid":"https://orcid.org/0000-0002-0153-1095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dev, Soumyabrata","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013295291","display_name":"Bianca Schoen-Phelan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schoen-Phelan, Bianca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.3610999882221222,"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"}},"topics":[{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.3610999882221222,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.10180000215768814,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.057100001722574234,"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/software-deployment","display_name":"Software deployment","score":0.7541000247001648},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6248000264167786},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6071000099182129},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5647000074386597},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5415999889373779},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5062999725341797},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4514999985694885}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7541000247001648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741599977016449},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6248000264167786},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6071000099182129},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5647000074386597},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3955000042915344},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.27090001106262207}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29756","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29756","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.2603.29756","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29756","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":{"We":[0],"address":[1],"the":[2],"challenge":[3],"of":[4,40],"adapting":[5],"pre-trained":[6],"Large":[7],"Language":[8],"Models":[9],"(LLMs)":[10],"for":[11,183],"multivariate":[12],"time-series":[13,123],"analysis,":[14],"where":[15],"their":[16,146],"deployment":[17,179],"is":[18,153],"often":[19],"hindered":[20],"by":[21,45,95],"prohibitive":[22],"computational":[23],"and":[24,82,102,139,163,186],"memory":[25,111],"demands.":[26],"Our":[27,70],"solution,":[28],"One-for-All,":[29],"introduces":[30,48],"Gaussian":[31],"Rank-Stabilized":[32],"Low-Rank":[33],"Adapters":[34],"(rsLoRA)":[35],"to":[36],"enable":[37,178],"parameter-efficient":[38],"fine-tuning":[39],"frozen":[41],"LLMs.":[42],"While":[43],"inspired":[44],"LoRA,":[46],"rsLoRA":[47],"a":[49,62,108],"mathematically":[50],"grounded":[51],"rank-stabilization":[52],"mechanism":[53],"that":[54,126],"enables":[55],"provable":[56],"gradient":[57],"stability":[58,152],"at":[59],"low":[60],"ranks":[61],"novel":[63],"contribution":[64],"absent":[65],"in":[66,116],"prior":[67],"PEFT":[68],"methods.":[69],"framework":[71],"injects":[72],"trainable":[73,93],"rank":[74],"decomposition":[75],"matrices":[76],"(rank":[77],"16)":[78],"into":[79],"positional":[80],"embeddings":[81],"output":[83],"layers,":[84],"while":[85,106,144],"keeping":[86],"self-attention":[87],"weights":[88],"fixed.":[89],"This":[90],"design":[91],"reduces":[92],"parameters":[94,172],"6.8$\\times$":[96],"(vs.":[97,100,104],"TimesNet),":[98],"21$\\times$":[99,140],"GPT4TS),":[101],"11.8$\\times$":[103],"TIME-LLM),":[105],"achieving":[107],"168-1,776$\\times$":[109],"smaller":[110],"footprint":[112],"(2.2MiB":[113],"vs.":[114],"340MiB-4.18GiB":[115],"SOTA":[117],"models).":[118],"Rigorous":[119],"evaluation":[120],"across":[121,158],"six":[122],"tasks":[124],"demonstrates":[125],"One-for-All":[127],"achieves":[128],"state-of-the-art":[129],"efficiency-accuracy":[130],"trade-offs:":[131],"5.5$\\times$":[132],"higher":[133],"parameter":[134],"efficiency":[135],"(MSE=5.50)":[136],"than":[137,142,173],"TimesNet":[138],"better":[141],"GPT4TS,":[143],"matching":[145],"forecasting":[147],"accuracy":[148],"(MSE=0.33).":[149],"The":[150],"framework's":[151],"validated":[154],"through":[155],"consistent":[156],"performance":[157],"diverse":[159],"horizons":[160],"(96-720":[161],"steps)":[162],"datasets":[164],"(ETT,":[165],"Weather,":[166],"M3,":[167],"M4),":[168],"with":[169],"98.3%":[170],"fewer":[171],"conventional":[174],"transformers.":[175],"These":[176],"advances":[177],"on":[180],"edge":[181],"devices":[182],"healthcare,":[184],"finance,":[185],"environmental":[187],"monitoring":[188],"without":[189],"compromising":[190],"performance.":[191]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-02T00:00:00"}