{"id":"https://openalex.org/W4414359451","doi":"https://doi.org/10.24963/ijcai.2025/1203","title":"Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors (Extended Abstract)","display_name":"Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors (Extended Abstract)","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359451","doi":"https://doi.org/10.24963/ijcai.2025/1203"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1203","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015110895","display_name":"Ido Amos","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Ido Amos","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045872048","display_name":"Jonathan Berant","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jonathan Berant","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022754114","display_name":"Ankit Gupta","orcid":"https://orcid.org/0000-0002-1054-6133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankit Gupta","raw_affiliation_strings":["IBM Research"],"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015110895"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31259364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10846","last_page":"10851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.5839999914169312,"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"}},"topics":[{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.5839999914169312,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.5623000264167786,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.49729999899864197,"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/initialization","display_name":"Initialization","score":0.7791000008583069},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.7735999822616577},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5651999711990356},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.40959998965263367},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3693999946117401},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.3549000024795532}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7791000008583069},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7735999822616577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824000239372253},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5651999711990356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.558899998664856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5429999828338623},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3693999946117401},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3041999936103821},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1203","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"This":[0],"paper":[1],"is":[2,19,122],"an":[3],"extended":[4],"abstract":[5],"of":[6],"our":[7],"ICLR":[8],"2024":[9],"Outstanding":[10],"Paper":[11],"Award":[12],"work.":[13],"Modeling":[14],"long-range":[15],"dependencies":[16],"across":[17,61],"sequences":[18],"a":[20],"longstanding":[21],"goal":[22],"in":[23],"machine":[24],"learning.":[25],"While":[26],"state":[27,70],"space":[28,71],"models":[29,72],"reportedly":[30],"outperform":[31],"Transformers":[32,68,80],"on":[33,53,84,92,114],"benchmarks":[34],"like":[35],"Long":[36,85],"Range":[37,86],"Arena,":[38],"we":[39],"show":[40],"that":[41,76],"random":[42],"initialization":[43],"significantly":[44],"overestimates":[45],"architectural":[46],"differences.":[47],"Pretraining":[48],"with":[49,109],"standard":[50],"denoising":[51],"objectives":[52],"downstream":[54],"task":[55],"data":[56],"leads":[57],"to":[58],"dramatic":[59],"gains":[60],"architectures":[62,113],"and":[63,69,88],"minimal":[64],"performance":[65,83,126],"gaps":[66],"between":[67],"(SSMs).":[73],"We":[74],"demonstrate":[75],"properly":[77],"pretrained":[78],"vanilla":[79],"match":[81],"S4":[82],"Arena":[87],"improve":[89],"SSM":[90],"results":[91],"PathX-256":[93],"by":[94],"20":[95],"absolute":[96],"points.":[97],"Our":[98],"analysis":[99],"shows":[100],"previously-proposed":[101],"structured":[102],"parameterizations":[103],"for":[104,124],"SSMs":[105],"become":[106],"largely":[107],"redundant":[108],"pretraining.":[110],"When":[111],"evaluating":[112],"supervised":[115],"tasks,":[116],"incorporating":[117],"data-driven":[118],"priors":[119],"via":[120],"pretraining":[121],"essential":[123],"reliable":[125],"estimation.":[127]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}