{"id":"https://openalex.org/W4412945522","doi":"https://doi.org/10.18653/v1/2025.acl-long.338","title":"Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling","display_name":"Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945522","doi":"https://doi.org/10.18653/v1/2025.acl-long.338"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.338","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.338","pdf_url":"https://aclanthology.org/2025.acl-long.338.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.338.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001491548","display_name":"Xianzhen Luo","orcid":"https://orcid.org/0000-0002-6629-9063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianzhen Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408482","display_name":"Yixuan Wang","orcid":"https://orcid.org/0009-0002-2367-8335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixuan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100584833","display_name":"Qingfu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingfu Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328664","display_name":"Zhiming Zhang","orcid":"https://orcid.org/0000-0002-5608-6590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiming Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002617009","display_name":"Xuanyu Zhang","orcid":"https://orcid.org/0009-0000-9240-7956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108154709","display_name":"Qing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341934","display_name":"Dongliang Xu","orcid":"https://orcid.org/0000-0002-6908-253X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongliang Xu","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":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6816","last_page":"6831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9941999912261963,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9941999912261963,"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/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"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/treasure","display_name":"Treasure","score":0.9441498517990112},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7284479141235352},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7079229950904846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6143738627433777},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42012882232666016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30842697620391846},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2634679973125458},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.17194807529449463},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.14086225628852844}],"concepts":[{"id":"https://openalex.org/C2776084483","wikidata":"https://www.wikidata.org/wiki/Q272937","display_name":"Treasure","level":2,"score":0.9441498517990112},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7284479141235352},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7079229950904846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6143738627433777},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42012882232666016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30842697620391846},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2634679973125458},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.17194807529449463},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.14086225628852844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.338","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.338","pdf_url":"https://aclanthology.org/2025.acl-long.338.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.338","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.338","pdf_url":"https://aclanthology.org/2025.acl-long.338.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":[{"id":"https://openalex.org/G2565984771","display_name":null,"funder_award_id":"62236004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3596954764","display_name":null,"funder_award_id":"62476073","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945522.pdf","grobid_xml":"https://content.openalex.org/works/W4412945522.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2492411721","https://openalex.org/W2223042459","https://openalex.org/W369913426","https://openalex.org/W2360017572","https://openalex.org/W4248194279","https://openalex.org/W1984795823","https://openalex.org/W1504426902","https://openalex.org/W2476851620","https://openalex.org/W4285698275","https://openalex.org/W378221013"],"abstract_inverted_index":{"Xianzhen":[0],"Luo,":[1],"Yixuan":[2],"Wang,":[3],"Qingfu":[4],"Zhu,":[5],"Zhiming":[6],"Zhang,":[7,9],"Xuanyu":[8],"Qing":[10],"Yang,":[11],"Dongliang":[12],"Xu.":[13],"Proceedings":[14],"of":[15,20],"the":[16,21],"63rd":[17],"Annual":[18],"Meeting":[19],"Association":[22],"for":[23],"Computational":[24],"Linguistics":[25],"(Volume":[26],"1:":[27],"Long":[28],"Papers).":[29],"2025.":[30]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
