{"id":"https://openalex.org/W4412886823","doi":"https://doi.org/10.18653/v1/2025.acl-long.127","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","display_name":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886823","doi":"https://doi.org/10.18653/v1/2025.acl-long.127"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.127","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.127","pdf_url":"https://aclanthology.org/2025.acl-long.127.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.127.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028107927","display_name":"Benjamin C. Warner","orcid":"https://orcid.org/0000-0002-9213-3825"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Warner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090399761","display_name":"Antoine Chaffin","orcid":"https://orcid.org/0000-0003-3605-4097"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoine Chaffin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028618964","display_name":"Benjamin Clavi\u00e9","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Clavi\u00e9","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056096860","display_name":"Orion Weller","orcid":"https://orcid.org/0000-0003-4148-5430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Orion Weller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115560629","display_name":"Oskar Hallstr\u00f6m","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oskar Hallstr\u00f6m","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115560630","display_name":"Said Taghadouini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Said Taghadouini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068032024","display_name":"Alexis Gallagher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Gallagher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Raja Biswas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raja Biswas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074277807","display_name":"Faisal Ladhak","orcid":"https://orcid.org/0009-0009-5730-3866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faisal Ladhak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115560628","display_name":"Tom Aarsen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Aarsen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034426796","display_name":"Griffin Adams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Griffin Thomas Adams","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007075789","display_name":"Jeremy Howard","orcid":"https://orcid.org/0000-0002-3102-9282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeremy Howard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047474914","display_name":"Iacopo Poli","orcid":"https://orcid.org/0000-0002-0964-0624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iacopo Poli","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":99.8669,"has_fulltext":true,"cited_by_count":128,"citation_normalized_percentile":{"value":0.9998817,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2526","last_page":"2547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8585000038146973,"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":0.8585000038146973,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.7502999901771545,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.7276999950408936,"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":0.7814844250679016},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6717164516448975},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5239855647087097},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4743284583091736},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4238567054271698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26817166805267334},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.05258205533027649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814844250679016},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6717164516448975},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5239855647087097},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4743284583091736},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4238567054271698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26817166805267334},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.05258205533027649},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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.127","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.127","pdf_url":"https://aclanthology.org/2025.acl-long.127.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.127","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.127","pdf_url":"https://aclanthology.org/2025.acl-long.127.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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886823.pdf","grobid_xml":"https://content.openalex.org/works/W4412886823.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/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Benjamin":[0,4],"Warner,":[1],"Antoine":[2],"Chaffin,":[3],"Clavi\u00e9,":[5],"Orion":[6],"Weller,":[7],"Oskar":[8],"Hallstr\u00f6m,":[9],"Said":[10],"Taghadouini,":[11],"Alexis":[12],"Gallagher,":[13],"Raja":[14],"Biswas,":[15],"Faisal":[16],"Ladhak,":[17],"Tom":[18],"Aarsen,":[19],"Griffin":[20],"Thomas":[21],"Adams,":[22],"Jeremy":[23],"Howard,":[24],"Iacopo":[25],"Poli.":[26],"Proceedings":[27],"of":[28,33],"the":[29,34],"63rd":[30],"Annual":[31],"Meeting":[32],"Association":[35],"for":[36],"Computational":[37],"Linguistics":[38],"(Volume":[39],"1:":[40],"Long":[41],"Papers).":[42],"2025.":[43]},"counts_by_year":[{"year":2026,"cited_by_count":57},{"year":2025,"cited_by_count":71}],"updated_date":"2026-07-08T08:33:18.762332","created_date":"2025-10-10T00:00:00"}
