{"id":"https://openalex.org/W7165052625","doi":"https://doi.org/10.48550/arxiv.2606.17660","title":"TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins","display_name":"TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7165052625","doi":"https://doi.org/10.48550/arxiv.2606.17660"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.17660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17660","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.17660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138781137","display_name":"Yuxiang Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yuxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138791536","display_name":"Haonan Long","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Haonan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138788710","display_name":"Chen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089014957","display_name":"Qiqi Duan","orcid":"https://orcid.org/0000-0002-4518-1701"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Qiqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138819196","display_name":"Xiaotian Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xiaotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138765359","display_name":"Yanwei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yanwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138782758","display_name":"Yuyu Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yuyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066369450","display_name":"Weikai Yang","orcid":"https://orcid.org/0000-0002-6520-1642"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Weikai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138814861","display_name":"Nan Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Nan","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/T10028","display_name":"Topic Modeling","score":0.2687999904155731,"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/T10028","display_name":"Topic Modeling","score":0.2687999904155731,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2630999982357025,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.06669999659061432,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7803000211715698},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.7497000098228455},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5916000008583069},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5698000192642212},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4343999922275543},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.41200000047683716},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.3930000066757202},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.38440001010894775}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7803000211715698},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.7497000098228455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6836000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5938000082969666},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5916000008583069},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5313000082969666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4381999969482422},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.17660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17660","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.17660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17660","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"is":[5],"compute-intensive":[6],"and":[7,16,19,115,133],"error-prone:":[8],"model":[9,25],"performance":[10,35,84],"depends":[11],"sensitively":[12],"on":[13,104],"data":[14],"quality":[15],"hyperparameter":[17],"choices,":[18],"na\u00efve":[20],"runs":[21,103],"can":[22,156],"even":[23],"degrade":[24],"performance.":[26,54],"This":[27],"raises":[28],"a":[29,39,46,61,74,118],"practical":[30,151],"question:can":[31],"we":[32],"predict":[33],"fine-tuning":[34,53,102,160],"before":[36],"committing":[37],"to":[38,83],"full":[40,159],"training":[41],"run?":[42],"We":[43],"present":[44],"TUNEAHEAD,":[45],"lightweight":[47],"framework":[48],"for":[49],"pre-hoc":[50],"prediction":[51],"of":[52,122,129,136,142],"TUNEAHEAD":[55,106,125],"encodes":[56],"each":[57],"candidate":[58],"run":[59],"as":[60,112],"meta-feature":[62],"vector":[63],"that":[64,92,155],"combines":[65],"static":[66],"dataset":[67],"descriptors":[68],"with":[69],"dynamic":[70],"probe":[71],"features":[72,82,96],"from":[73],"short":[75],"standardized":[76],"probe.":[77],"A":[78],"predictor":[79],"maps":[80],"these":[81],"estimates,":[85],"while":[86,161],"SHAP-based":[87],"attributions":[88],"provide":[89],"interpretable":[90],"diagnostics":[91],"reveal":[93],"which":[94],"specific":[95],"drive":[97],"the":[98,143],"prediction.":[99],"Across":[100],"1,300+":[101],"Qwen2.5-7B-Instruct,":[105],"consistently":[107],"outperforms":[108],"strong":[109],"baselines":[110],"such":[111],"Early-Stop":[113],"Extrapolation":[114],"ProxyLM.":[116],"On":[117],"held-out":[119],"test":[120],"set":[121],"370":[123],"runs,":[124],"achieves":[126],"an":[127],"RMSE":[128],"1.47":[130],"percentage":[131,140],"points":[132,141],"places":[134],"95.1%":[135],"predictions":[137,149],"within":[138],"+3/-3":[139],"true":[144],"score.":[145],"These":[146],"accurate":[147],"continuous":[148],"support":[150],"go/no-go":[152],"screening":[153],"policies":[154],"reduce":[157],"unnecessary":[158],"retaining":[162],"most":[163],"promising":[164],"runs.":[165]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-18T00:00:00"}