{"id":"https://openalex.org/W4414360464","doi":"https://doi.org/10.24963/ijcai.2025/926","title":"Beyond Fixed Length: Bucket Pre-training is All You Need","display_name":"Beyond Fixed Length: Bucket Pre-training is All You Need","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360464","doi":"https://doi.org/10.24963/ijcai.2025/926"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/926","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/926","pdf_url":"https://www.ijcai.org/proceedings/2025/0926.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0926.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100526333","display_name":"Qing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Yang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037239111","display_name":"Qiyao Peng","orcid":"https://orcid.org/0000-0002-2281-9143"},"institutions":[{"id":"https://openalex.org/I4210100390","display_name":"Financial Research (Hungary)","ror":"https://ror.org/00jf79q69","country_code":"HU","type":"company","lineage":["https://openalex.org/I4210100390"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Qiyao Peng","raw_affiliation_strings":["Du Xiaoman Financial Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Du Xiaoman Financial Technology","institution_ids":["https://openalex.org/I4210100390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444847","display_name":"Hongtao Liu","orcid":"https://orcid.org/0000-0002-6585-9954"},"institutions":[{"id":"https://openalex.org/I4210100390","display_name":"Financial Research (Hungary)","ror":"https://ror.org/00jf79q69","country_code":"HU","type":"company","lineage":["https://openalex.org/I4210100390"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Hongtao Liu","raw_affiliation_strings":["Du Xiaoman Financial Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Du Xiaoman Financial Technology","institution_ids":["https://openalex.org/I4210100390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101837477","display_name":"Kai Liu","orcid":"https://orcid.org/0000-0002-4219-5964"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Liu","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005181083","display_name":"Bing Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Qin","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418120","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0001-8904-8796"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35588235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8331","last_page":"8338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10280","display_name":"Shoulder Injury and Treatment","score":0.1784999966621399,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10280","display_name":"Shoulder Injury and Treatment","score":0.1784999966621399,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13946","display_name":"Musculoskeletal Disorders and Rehabilitation","score":0.1550000011920929,"subfield":{"id":"https://openalex.org/subfields/2742","display_name":"Rehabilitation"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13752","display_name":"Mechanics and Biomechanics Studies","score":0.14489999413490295,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/concatenation","display_name":"Concatenation (mathematics)","score":0.7738000154495239},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4823000133037567},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3885999917984009},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.37380000948905945},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.3709000051021576},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.36629998683929443},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.35690000653266907},{"id":"https://openalex.org/keywords/cornerstone","display_name":"Cornerstone","score":0.35190001130104065},{"id":"https://openalex.org/keywords/identifiability","display_name":"Identifiability","score":0.3276999890804291}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7738000154495239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591000199317932},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.36629998683929443},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35690000653266907},{"id":"https://openalex.org/C2780616401","wikidata":"https://www.wikidata.org/wiki/Q1133673","display_name":"Cornerstone","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3125},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2776299755","wikidata":"https://www.wikidata.org/wiki/Q432449","display_name":"Carry (investment)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/926","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/926","pdf_url":"https://www.ijcai.org/proceedings/2025/0926.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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":{"id":"doi:10.24963/ijcai.2025/926","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/926","pdf_url":"https://www.ijcai.org/proceedings/2025/0926.pdf","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414360464.pdf","grobid_xml":"https://content.openalex.org/works/W4414360464.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"exceptional":[6],"performance":[7],"across":[8],"various":[9],"tasks,":[10],"with":[11],"pre-training":[12,29],"stage":[13],"serving":[14],"as":[15,77,79,134],"the":[16,22,49,70,120,137,154,164,178],"cornerstone":[17],"of":[18,61,168,182],"their":[19],"capabilities.":[20],"However,":[21],"conventional":[23],"fixed-length":[24,121],"data":[25,96,115,128],"composition":[26,97,116,132],"strategy":[27],"for":[28,94,147],"presents":[30],"several":[31],"practical":[32],"challenges.":[33],"When":[34],"using":[35],"shorter":[36],"sequences,":[37],"documents":[38],"are":[39],"often":[40],"truncated,":[41],"potentially":[42],"leading":[43],"to":[44,52,129],"information":[45],"loss":[46],"and":[47,68,74,103,144,153,166],"affecting":[48],"model's":[50],"ability":[51],"capture":[53],"long-range":[54],"dependencies.":[55],"Conversely,":[56],"longer":[57],"sequences":[58],"require":[59,80],"concatenation":[60,104],"multiple":[62],"documents,":[63],"which":[64],"can":[65],"introduce":[66],"noise":[67],"affect":[69],"natural":[71],"document":[72],"boundaries":[73],"semantic":[75],"coherence":[76],"well":[78],"substantial":[81],"computational":[82],"overhead.":[83],"To":[84],"address":[85],"these":[86,108],"challenges,":[87],"we":[88,110],"first":[89],"establish":[90],"three":[91],"quantitative":[92],"metrics":[93],"evaluating":[95],"quality:":[98],"padding":[99],"ratio,":[100,102],"truncation":[101],"ratio.":[105],"Building":[106],"upon":[107],"metrics,":[109,139],"propose":[111],"a":[112,141],"novel":[113],"multi-bucket":[114],"method":[117,160,173],"that":[118,157],"transcends":[119],"paradigm.":[122],"Our":[123,171],"approach":[124,146],"adaptively":[125],"organizes":[126],"training":[127],"achieve":[130],"optimal":[131],"quality":[133],"measured":[135],"by":[136],"proposed":[138,159,172],"offering":[140],"more":[142],"flexible":[143],"efficient":[145],"pre-training.":[148,170],"We":[149],"conduct":[150],"extensive":[151],"experiments":[152],"results":[155],"demonstrate":[156],"our":[158],"significantly":[161],"enhances":[162],"both":[163],"efficiency":[165],"effectiveness":[167],"LLM":[169],"has":[174],"been":[175],"adopted":[176],"in":[177],"Du":[179],"Xiaoman\u2013XuanYuan":[180],"series":[181],"financial":[183],"large":[184],"language":[185],"models":[186],"at":[187],"https://github.com/Duxiaoman-DI/XuanYuan.":[188]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}