{"id":"https://openalex.org/W4412888210","doi":"https://doi.org/10.18653/v1/2025.findings-acl.595","title":"InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformation","display_name":"InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888210","doi":"https://doi.org/10.18653/v1/2025.findings-acl.595"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.595","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.595","pdf_url":"https://aclanthology.org/2025.findings-acl.595.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.595.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102699817","display_name":"Bowen Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bowen Cao","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100839199","display_name":"Deng Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Deng Cai","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015842499","display_name":"Wai Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11402","last_page":"11415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.7613999843597412,"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"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.7613999843597412,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.751800000667572,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.7321000099182129,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/term","display_name":"Term (time)","score":0.6352023482322693},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5903650522232056},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5729806423187256},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5449246168136597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5434517860412598},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.4921116232872009},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15942254662513733},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1320047378540039},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07516595721244812},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.058337122201919556}],"concepts":[{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6352023482322693},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5903650522232056},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5729806423187256},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5449246168136597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5434517860412598},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.4921116232872009},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15942254662513733},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1320047378540039},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07516595721244812},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.058337122201919556},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.595","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.595","pdf_url":"https://aclanthology.org/2025.findings-acl.595.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.595","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.595","pdf_url":"https://aclanthology.org/2025.findings-acl.595.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888210.pdf","grobid_xml":"https://content.openalex.org/works/W4412888210.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2390901981","https://openalex.org/W2109115373","https://openalex.org/W4230691760","https://openalex.org/W4391923333","https://openalex.org/W2393847170","https://openalex.org/W85049056","https://openalex.org/W158465905","https://openalex.org/W2980611886","https://openalex.org/W577521963","https://openalex.org/W42295635"],"abstract_inverted_index":{"In-context":[0],"learning":[1],"(ICL)":[2],"is":[3,13],"critical":[4],"for":[5],"large":[6],"language":[7],"models":[8],"(LLMs),":[9],"but":[10],"its":[11],"effectiveness":[12],"constrained":[14],"by":[15,90,148],"finite":[16],"context":[17,32,49,71,77,88,154],"windows,":[18],"particularly":[19],"in":[20,35,41],"ultra-long":[21],"contexts.To":[22],"overcome":[23],"this,":[24],"we":[25],"introduce":[26],"InfiniteICL,":[27],"a":[28],"framework":[29],"that":[30,84],"parallels":[31],"and":[33,67,81,105,144],"parameters":[34],"LLMs":[36,147],"with":[37],"short-and":[38],"long-term":[39],"memory":[40,58],"human":[42],"cognitive":[43],"systems,":[44],"focusing":[45],"on":[46,113],"transforming":[47],"temporary":[48],"knowledge":[50,78],"into":[51],"permanent":[52],"parameter":[53],"updates.This":[54],"approach":[55,124],"significantly":[56],"reduces":[57,87],"usage,":[59],"maintains":[60],"robust":[61],"performance":[62,96],"across":[63,100],"varying":[64],"input":[65],"lengths,":[66],"theoretically":[68],"enables":[69],"infinite":[70],"integration":[72],"through":[73],"the":[74,133,142,150],"principles":[75],"of":[76,97,132,146,152],"elicitation,":[79],"selection,":[80],"consolidation.Evaluations":[82],"demonstrate":[83],"our":[85,123],"method":[86],"length":[89,118],"90%":[91],"while":[92,128],"achieving":[93],"103%":[94],"average":[95],"full-context":[98,126],"prompting":[99,127],"fact":[101],"recall,":[102],"grounded":[103],"reasoning,":[104],"skill":[106],"acquisition":[107],"tasks.When":[108],"conducting":[109],"sequential":[110],"multi-turn":[111],"transformations":[112],"complex,":[114],"realworld":[115],"contexts":[116],"(with":[117],"up":[119],"to":[120,140],"2M":[121],"tokens),":[122],"surpasses":[125],"using":[129],"only":[130],"0.4%":[131],"original":[134],"contexts.These":[135],"findings":[136],"highlight":[137],"InfiniteICL's":[138],"potential":[139],"enhance":[141],"scalability":[143],"efficiency":[145],"breaking":[149],"limitations":[151],"conventional":[153],"window":[155],"sizes.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}