{"id":"https://openalex.org/W4412945374","doi":"https://doi.org/10.18653/v1/2025.acl-long.525","title":"APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs","display_name":"APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945374","doi":"https://doi.org/10.18653/v1/2025.acl-long.525"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.525","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.525","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103140704","display_name":"Yuxiang Huang","orcid":"https://orcid.org/0000-0002-4380-2447"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxiang Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102743371","display_name":"Mingye Li","orcid":"https://orcid.org/0000-0002-1126-3178"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingye Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101224117","display_name":"Xu Han","orcid":"https://orcid.org/0009-0006-8542-8509"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014699953","display_name":"Chaojun Xiao","orcid":"https://orcid.org/0000-0001-6039-0942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaojun Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035433961","display_name":"Weilin Zhao","orcid":"https://orcid.org/0000-0001-9352-6252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weilin Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058302872","display_name":"Ao Sun","orcid":"https://orcid.org/0009-0001-0219-4780"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun Ao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017312552","display_name":"Jie Zhou","orcid":"https://orcid.org/0009-0009-5198-6782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320720","display_name":"Zhiyuan Liu","orcid":"https://orcid.org/0000-0002-4943-6572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046448314","display_name":"Maosong Sun","orcid":"https://orcid.org/0000-0002-6011-6115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maosong Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15007553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10708","last_page":"10727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9884999990463257,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9884999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7969884872436523},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7182133197784424},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6651994585990906},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6513550281524658},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.53659987449646},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34332090616226196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13764524459838867},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10284125804901123}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7969884872436523},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7182133197784424},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6651994585990906},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6513550281524658},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.53659987449646},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34332090616226196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13764524459838867},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10284125804901123},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.525","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.525","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2978729728","https://openalex.org/W4288966080","https://openalex.org/W2055243143","https://openalex.org/W2510374584","https://openalex.org/W2134852660","https://openalex.org/W1530347314","https://openalex.org/W2215785064","https://openalex.org/W4254638342","https://openalex.org/W2098482419","https://openalex.org/W2054468904"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
