{"id":"https://openalex.org/W7225411818","doi":"https://doi.org/10.5281/zenodo.24002130","title":"Online Adaptive Predictive Model Updating for Generative AI: Continuously Refining Computational Demand Forecasts from Incoming Requests","display_name":"Online Adaptive Predictive Model Updating for Generative AI: Continuously Refining Computational Demand Forecasts from Incoming Requests","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225411818","doi":"https://doi.org/10.5281/zenodo.24002130"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24002130","doi":"https://doi.org/10.5281/zenodo.24002130","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002130","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24002130","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100638045","display_name":"Jincheng Zhang","orcid":"https://orcid.org/0000-0001-7332-6704","observed_orcids":["https://orcid.org/0000-0001-7332-6704","https://orcid.org/0009-0005-1860-0009"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jincheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-1860-0009","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100638045"],"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.6669999957084656,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.6669999957084656,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.12269999831914902,"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/T14098","display_name":"Energy Efficiency in Computing","score":0.04560000076889992,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/online-model-updating","display_name":"online model updating","score":0.9169999957084656},{"id":"https://openalex.org/keywords/concept-drift-detection","display_name":"concept drift detection","score":0.7179999947547913},{"id":"https://openalex.org/keywords/adaptive-retraining","display_name":"adaptive retraining","score":0.6100000143051147},{"id":"https://openalex.org/keywords/model-recalibration","display_name":"model recalibration","score":0.7429999709129333},{"id":"https://openalex.org/keywords/prediction-error","display_name":"prediction error","score":0.7059999704360962},{"id":"https://openalex.org/keywords/gpu-scheduling","display_name":"GPU scheduling","score":0.6439999938011169},{"id":"https://openalex.org/keywords/precomputation","display_name":"precomputation","score":0.753000020980835},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"resource allocation","score":0.7450000047683716},{"id":"https://openalex.org/keywords/dynamic-electricity-pricing","display_name":"dynamic electricity pricing","score":0.8050000071525574},{"id":"https://openalex.org/keywords/cloud-resource-selection","display_name":"cloud resource selection","score":0.8629999756813049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896999716758728},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5788000226020813},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.552299976348877},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4941999912261963},{"id":"https://openalex.org/C193809577","wikidata":"https://www.wikidata.org/wiki/Q3409300","display_name":"Demand forecasting","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4259999990463257},{"id":"https://openalex.org/C83209312","wikidata":"https://www.wikidata.org/wiki/Q1053367","display_name":"Predictive analytics","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.3944000005722046},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.29829999804496765},{"id":"https://openalex.org/C32597650","wikidata":"https://www.wikidata.org/wiki/Q5255044","display_name":"Demand patterns","level":3,"score":0.2833000123500824},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24002130","doi":"https://doi.org/10.5281/zenodo.24002130","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002130","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Preprint"},{"id":"doi:10.5281/zenodo.24002131","doi":"https://doi.org/10.5281/zenodo.24002131","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24002130","doi":"https://doi.org/10.5281/zenodo.24002130","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24002130","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7225419399","https://openalex.org/W7225409594","https://openalex.org/W7225376051","https://openalex.org/W7225267314","https://openalex.org/W7225409378","https://openalex.org/W7225398588","https://openalex.org/W7225425116","https://openalex.org/W7225400169","https://openalex.org/W7225385268","https://openalex.org/W7225375373"],"abstract_inverted_index":{"Predictive":[0,97],"computing":[1,134],"for":[2,100,270],"generative":[3,256,380],"artificial":[4],"intelligence":[5],"(AI)":[6],"relies":[7],"on":[8,265,309],"the":[9,59,136,225,245,254,306],"ability":[10],"to":[11,28,196,223,244,280,294,344],"anticipate":[12],"future":[13,74,233,272,388],"computational":[14,40,111,119,144,238,275,300,389],"demand":[15,23,61,112,178,249,354,390],"before":[16],"corresponding":[17],"inference":[18,75,184,311],"requests":[19,56,173,273],"materialize.":[20],"However,":[21],"predictive":[22,65,110,133,200,266,328,363,371],"models":[24,66,113,128,201,251,258,268],"are":[25],"inherently":[26],"exposed":[27],"changing":[29,177],"user":[30],"behavior,":[31],"emerging":[32],"information":[33,175],"trends,":[34],"evolving":[35,143],"workload":[36],"distributions,":[37,183],"and":[38,58,88,121,168,188,236,252,274,286,305,313,336,356],"unexpected":[39],"requirements.":[41],"A":[42,217],"forecasting":[43,127,234,271,296],"model":[44,162,164,212,230,323,364],"trained":[45],"using":[46,114],"historical":[47],"request":[48,151],"distributions":[49],"may":[50,67],"gradually":[51],"become":[52],"inaccurate":[53,89],"as":[54,129,141,283,366,391],"new":[55,392],"arrive":[57],"underlying":[60,255],"patterns":[62],"change.":[63],"Static":[64],"therefore":[68],"produce":[69],"increasingly":[70],"unreliable":[71],"estimates":[72],"of":[73,132,370,387],"workloads,":[76,350],"potentially":[77],"resulting":[78,307],"in":[79],"unnecessary":[80],"precomputation,":[81,332],"inefficient":[82],"GPU":[83,186,329],"allocation,":[84],"inappropriate":[85],"resource":[86,189,315,338],"reservations,":[87],"economic":[90],"decisions.":[91],"This":[92],"paper":[93],"introduces":[94],"Online":[95],"Adaptive":[96],"Model":[98],"Updating":[99],"Generative":[101],"AI":[102,257,381],"(OAPMU-GAI),":[103],"a":[104,284,376],"conceptual":[105],"framework":[106,138,192,262,318],"that":[107],"continuously":[108,142],"refines":[109],"newly":[115],"observed":[116,172],"requests,":[117],"realized":[118],"outcomes,":[120],"prediction":[122,228,250,303],"errors.":[123],"Rather":[124],"than":[125],"treating":[126,278],"fixed":[130],"components":[131],"infrastructure,":[135],"proposed":[137,261],"considers":[139],"them":[140],"decision":[145],"mechanisms.":[146],"Its":[147,340],"architecture":[148],"integrates":[149],"incoming":[150],"monitoring,":[152],"prediction-outcome":[153],"comparison,":[154],"online":[155,322],"data":[156],"assimilation,":[157],"concept":[158],"drift":[159],"detection,":[160],"adaptive":[161,210],"updating,":[163],"evaluation,":[165],"update":[166,231,301],"scheduling,":[167,330],"controlled":[169],"deployment.":[170],"Newly":[171],"provide":[174],"about":[176],"frequencies,":[179],"query":[180],"characteristics,":[181],"token":[182],"costs,":[185],"utilization,":[187],"consumption.":[190],"The":[191,260,317],"uses":[193],"these":[194],"observations":[195],"determine":[197],"whether":[198],"existing":[199],"remain":[202],"sufficiently":[203],"accurate":[204],"or":[205,214],"require":[206],"incremental":[207],"parameter":[208],"updates,":[209],"retraining,":[211],"recalibration,":[213],"structural":[215],"modification.":[216],"unified":[218],"mathematical":[219],"formulation":[220],"is":[221,242,292],"developed":[222],"characterize":[224],"relationship":[226],"between":[227,247],"error,":[229],"expenditure,":[232],"performance,":[235],"downstream":[237],"benefits.":[239],"Particular":[240],"attention":[241],"given":[243],"distinction":[246],"updating":[248,253,324],"themselves.":[259],"focuses":[263],"primarily":[264],"infrastructure":[267],"responsible":[269],"requirements,":[276],"while":[277],"changes":[279],"foundation-model":[281],"parameters":[282],"separate":[285],"optional":[287],"extension.":[288],"An":[289],"experimental":[290],"methodology":[291],"established":[293],"evaluate":[295],"accuracy,":[297],"adaptation":[298],"speed,":[299],"overhead,":[302],"stability,":[304],"effects":[308],"proactive":[310],"preparation":[312],"economic-aware":[314],"allocation.":[316],"further":[319],"investigates":[320],"how":[321],"can":[325,383],"interact":[326],"with":[327],"off-peak":[331],"dynamic":[333],"electricity":[334],"pricing,":[335],"cloud":[337],"selection.":[339],"effectiveness":[341],"remains":[342],"subject":[343],"empirical":[345],"validation,":[346],"particularly":[347],"under":[348],"nonstationary":[349],"delayed":[351],"feedback,":[352],"sudden":[353],"changes,":[355],"limited":[357],"model-update":[358],"budgets.":[359],"By":[360],"introducing":[361],"continuous":[362],"refinement":[365],"an":[367],"explicit":[368],"component":[369],"computing,":[372],"this":[373],"research":[374],"explores":[375],"mechanism":[377],"through":[378],"which":[379],"infrastructures":[382],"adapt":[384],"their":[385],"understanding":[386],"operational":[393],"evidence":[394],"becomes":[395],"available.":[396]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}