{"id":"https://openalex.org/W7225009090","doi":"https://doi.org/10.5281/zenodo.23829413","title":"Lookahead Training-Example Selection Intervention Optimization (LTESIO): A Prospective Training-Utility Framework for Adaptive Data Selection in Diffusion Models","display_name":"Lookahead Training-Example Selection Intervention Optimization (LTESIO): A Prospective Training-Utility Framework for Adaptive Data Selection in Diffusion Models","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7225009090","doi":"https://doi.org/10.5281/zenodo.23829413"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23829413","doi":"https://doi.org/10.5281/zenodo.23829413","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829413","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","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23829413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133561621","display_name":"Jincheng Zhang","orcid":"https://orcid.org/0009-0005-1860-0009","observed_orcids":["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/A5133561621"],"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/T12535","display_name":"Machine Learning and Data Classification","score":0.6371999979019165,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.6371999979019165,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1720000058412552,"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":0.07010000199079514,"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/diffusion-models","display_name":"diffusion models","score":0.8999999761581421},{"id":"https://openalex.org/keywords/training-sample-selection","display_name":"training data selection","score":0.8320000171661377},{"id":"https://openalex.org/keywords/batch-selection","display_name":"batch selection","score":0.5540000200271606},{"id":"https://openalex.org/keywords/intervention-optimization","display_name":"intervention optimization","score":0.515999972820282},{"id":"https://openalex.org/keywords/training-loss","display_name":"training loss","score":0.4339999854564667},{"id":"https://openalex.org/keywords/computational-budget-allocation","display_name":"computational budget allocation","score":0.8389999866485596},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.5770000219345093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6456999778747559},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6248999834060669},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5710999965667725},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5691999793052673},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46299999952316284},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.4146000146865845},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.39329999685287476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.37209999561309814},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23829413","doi":"https://doi.org/10.5281/zenodo.23829413","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829413","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.23829414","doi":"https://doi.org/10.5281/zenodo.23829414","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829414","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.23829413","doi":"https://doi.org/10.5281/zenodo.23829413","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829413","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/W7224998545","https://openalex.org/W7223700108","https://openalex.org/W7224095212","https://openalex.org/W7224103118","https://openalex.org/W7224106096","https://openalex.org/W7224116079","https://openalex.org/W7224121502","https://openalex.org/W7224097879","https://openalex.org/W7224107942","https://openalex.org/W7224098275"],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"are":[2,325],"commonly":[3],"trained":[4],"using":[5,149],"batches":[6,32,77,125],"sampled":[7],"from":[8,184],"a":[9,17,136,198,204,295,332],"predefined":[10],"training":[11,22,31,60,100,109,114,128,139,176,186,222,262,308,358,376],"distribution.":[12],"Although":[13],"random":[14],"sampling":[15],"provides":[16,285],"straightforward":[18],"and":[19,48,165,233,254,271,289,314,322,335,366,369],"statistically":[20],"convenient":[21],"procedure,":[23],"it":[24],"does":[25,72,340],"not":[26,73,195,341],"explicitly":[27],"consider":[28],"whether":[29,95,281],"alternative":[30,127,264],"may":[33,55,194,211],"produce":[34,80,197],"different":[35,57],"downstream":[36,99,160],"effects":[37,161],"on":[38],"model":[39,53,86,145,217,310],"performance.":[40],"Difficult":[41],"examples,":[42,309],"rare":[43,207],"scenes,":[44],"underrepresented":[45,209],"visual":[46],"concepts,":[47],"samples":[49,64],"associated":[50,134],"with":[51,135,190],"current":[52,68,119,192],"failures":[54],"provide":[56,103,212],"forms":[58],"of":[59,98,112,162,304,356,373],"information.":[61],"However,":[62],"selecting":[63,107],"according":[65],"to":[66,172,279],"their":[67,118],"difficulty":[69,183],"or":[70,208],"loss":[71,193],"necessarily":[74,196,347],"identify":[75],"the":[76,81,143,158,174,298,353,360,370],"that":[78,343],"will":[79],"greatest":[82],"improvement":[83,200],"in":[84,201],"future":[85,216],"capabilities.":[87],"Lookahead":[88,255],"Training-Example":[89],"Selection":[90],"Intervention":[91],"Optimization":[92],"(LTESIO)":[93],"investigates":[94],"prospective":[96,138,185,282,344],"estimates":[97,157,171],"utility":[101,265],"can":[102],"useful":[104,213],"information":[105,214,286],"for":[106,215],"subsequent":[108],"batches.":[110],"Instead":[111],"evaluating":[113,374],"examples":[115,210],"exclusively":[116],"through":[117],"losses,":[120],"LTESIO":[121,219,328],"considers":[122,221],"multiple":[123],"candidate":[124,131,163,375],"as":[126,236,331],"interventions.":[129],"Each":[130],"intervention":[132],"is":[133,147,278,329],"short":[137],"computation,":[140],"after":[141],"which":[142],"resulting":[144],"state":[146],"evaluated":[148],"an":[150,166],"independent":[151],"validation":[152,224,312,318,364],"set.":[153],"A":[154,188],"training-utility":[155,283],"predictor":[156],"expected":[159],"batches,":[164],"intervention-selection":[167],"mechanism":[168],"uses":[169],"these":[170],"select":[173],"next":[175],"batch.":[177],"The":[178,240,274],"proposed":[179,299],"framework":[180,334],"distinguishes":[181],"current-example":[182],"utility.":[187],"batch":[189,205,345],"high":[191],"substantial":[199],"generalization,":[202,368],"whereas":[203],"containing":[206],"behavior.":[218],"therefore":[220],"loss,":[223],"performance,":[225],"distributional":[226],"coverage,":[227],"estimated":[228],"learning":[229],"progress,":[230],"predictive":[231,354],"uncertainty,":[232],"computational":[234,323,371],"cost":[235,372],"potentially":[237],"relevant":[238],"signals.":[239],"experimental":[241,276],"design":[242],"compares":[243],"four":[244],"principal":[245],"approaches:":[246],"Random":[247],"Sampling,":[248],"Current-Loss-Based":[249],"Selection,":[250,253],"Conventional":[251],"Diversity-Aware":[252],"Training-Utility":[256],"Selection.":[257],"Additional":[258],"ablations":[259],"investigate":[260],"short-horizon":[261,357],"previews,":[263,359],"predictors,":[266],"candidate-pool":[267],"composition,":[268],"uncertainty-aware":[269],"selection,":[270],"computational-budget":[272],"allocation.":[273],"primary":[275],"objective":[277],"determine":[280],"prediction":[284],"beyond":[287],"current-loss-based":[288],"conventional":[290],"data-selection":[291],"strategies.":[292],"To":[293],"ensure":[294],"controlled":[296,382],"comparison,":[297],"evaluation":[300],"requires":[301],"equivalent":[302],"numbers":[303],"optimizer":[305],"updates,":[306],"processed":[307],"architectures,":[311],"procedures,":[313],"data-access":[315],"budgets.":[316],"Independent":[317],"metrics,":[319],"generated-image":[320],"evaluation,":[321],"overhead":[324],"considered":[326],"jointly.":[327],"presented":[330],"methodological":[333],"testable":[336],"research":[337],"hypothesis.":[338],"It":[339],"assume":[342],"selection":[346],"improves":[348],"diffusion-model":[349],"training.":[350],"In":[351],"particular,":[352],"reliability":[355],"relationship":[361],"between":[362],"immediate":[363],"changes":[365],"long-term":[367],"interventions":[377],"remain":[378],"empirical":[379],"questions":[380],"requiring":[381],"investigation.":[383]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-11-01T00:00:00"}