{"id":"https://openalex.org/W4412889836","doi":"https://doi.org/10.18653/v1/2025.acl-long.1375","title":"Value Residual Learning","display_name":"Value Residual Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889836","doi":"https://doi.org/10.18653/v1/2025.acl-long.1375"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1375","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1375","pdf_url":"https://aclanthology.org/2025.acl-long.1375.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1375.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhanchao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanchao Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007101740","display_name":"Tianyi Wu","orcid":"https://orcid.org/0000-0001-7434-0487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077940852","display_name":"Zhiyun Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyun Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181882","display_name":"Fares Obeid","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fares Obeid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103239171","display_name":"Zhenzhong Lan","orcid":"https://orcid.org/0000-0003-4763-6148"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenzhong Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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":0.08705342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28341","last_page":"28356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.7681000232696533,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.7681000232696533,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.7002000212669373,"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/residual","display_name":"Residual","score":0.6296814680099487},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.6109919548034668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.396902471780777},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16564872860908508},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13354817032814026}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6296814680099487},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6109919548034668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.396902471780777},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16564872860908508},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13354817032814026}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1375","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1375","pdf_url":"https://aclanthology.org/2025.acl-long.1375.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1375","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1375","pdf_url":"https://aclanthology.org/2025.acl-long.1375.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318567","display_name":"Westlake University","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889836.pdf","grobid_xml":"https://content.openalex.org/works/W4412889836.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2560215812","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2949601986"],"abstract_inverted_index":{"While":[0],"Transformer":[1],"models":[2],"have":[3],"achieved":[4],"remarkable":[5],"success":[6],"in":[7,33,51,124],"various":[8],"domains,":[9],"the":[10,65],"effectiveness":[11],"of":[12],"information":[13,32,44],"propagation":[14],"through":[15],"deep":[16],"networks":[17],"remains":[18],"a":[19,39,57,109],"critical":[20],"challenge.Standard":[21],"hidden":[22,54],"state":[23,55],"residuals":[24],"often":[25],"fail":[26],"to":[27,53,89],"adequately":[28],"preserve":[29],"initial":[30],"token-level":[31],"deeper":[34],"layers.This":[35],"paper":[36],"introduces":[37],"ResFormer,":[38],"novel":[40],"architecture":[41],"that":[42],"enhances":[43],"flow":[45],"by":[46,104,130],"incorporating":[47],"value":[48,68],"residual":[49],"connections":[50],"addition":[52],"residuals.And":[56],"variant":[58],"is":[59],"SVFormer,":[60],"where":[61],"all":[62],"layers":[63],"share":[64],"first":[66],"layer's":[67],"embedding.Comprehensive":[69],"empirical":[70],"evidence":[71],"demonstrates":[72],"ResFormer":[73],"achieves":[74],"equivalent":[75],"validation":[76],"loss":[77],"with":[78,107,117,127],"16.11%":[79],"fewer":[80],"model":[81],"parameters":[82],"and":[83,96,113,133],"20.3%":[84],"less":[85],"training":[86],"data":[87],"compared":[88],"Transformer,":[90],"while":[91],"maintaining":[92],"similar":[93],"memory":[94],"usage":[95],"computational":[97],"cost.Besides,":[98],"SVFormer":[99],"reduces":[100],"KV":[101,125],"cache":[102],"size":[103],"nearly":[105],"half":[106],"only":[108],"small":[110],"performance":[111,128],"penalty":[112],"can":[114],"be":[115],"integrated":[116],"other":[118],"KVefficient":[119],"methods,":[120],"yielding":[121],"further":[122],"reductions":[123],"cache,":[126],"influenced":[129],"sequence":[131],"length":[132],"cumulative":[134],"learning":[135],"rate.":[136]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}