{"id":"https://openalex.org/W4412888573","doi":"https://doi.org/10.18653/v1/2025.findings-acl.459","title":"Achieving binary weight and activation for LLMs using Post-Training Quantization","display_name":"Achieving binary weight and activation for LLMs using Post-Training Quantization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888573","doi":"https://doi.org/10.18653/v1/2025.findings-acl.459"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.459","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.459","pdf_url":"https://aclanthology.org/2025.findings-acl.459.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.459.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080001189","display_name":"Siqing Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siqing Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434689","display_name":"Chuang Wang","orcid":"https://orcid.org/0000-0002-3081-9776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387940","display_name":"Ruiqi Wang","orcid":"https://orcid.org/0000-0002-8025-7089"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui-Qi Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114269491","display_name":"Yi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101963686","display_name":"Xuyao Zhang","orcid":"https://orcid.org/0000-0003-4301-0666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu-Yao Zhang","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":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83416987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8782","last_page":"8795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.25679999589920044,"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/T10320","display_name":"Neural Networks and Applications","score":0.25679999589920044,"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/T11122","display_name":"Online Learning and Analytics","score":0.23880000412464142,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.23880000412464142,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/quantization","display_name":"Quantization (signal processing)","score":0.6658299565315247},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.566738486289978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5301369428634644},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.47828301787376404},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16169968247413635},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.13944727182388306},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12875699996948242},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09461742639541626}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6658299565315247},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.566738486289978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5301369428634644},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.47828301787376404},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16169968247413635},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.13944727182388306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12875699996948242},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09461742639541626},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.459","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.459","pdf_url":"https://aclanthology.org/2025.findings-acl.459.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.459","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.459","pdf_url":"https://aclanthology.org/2025.findings-acl.459.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":[],"awards":[{"id":"https://openalex.org/G1886734199","display_name":null,"funder_award_id":"62222609","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G549457566","display_name":null,"funder_award_id":"2022ZD0116500","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G7414039522","display_name":null,"funder_award_id":"YSBR-083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7812820956","display_name":null,"funder_award_id":"2022ZD0116500","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888573.pdf","grobid_xml":"https://content.openalex.org/works/W4412888573.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/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Quantizing":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"to":[5,46,61],"1-bit":[6],"precision":[7],"significantly":[8],"reduces":[9,111],"computational":[10],"costs,":[11],"but":[12],"existing":[13,133],"quantization":[14,37,85,107,113,122,135],"techniques":[15],"suffer":[16],"from":[17],"noticeable":[18],"performance":[19],"degradation":[20],"when":[21],"using":[22],"weight":[23,73],"and":[24,57,99],"activation":[25,87],"precisions":[26],"below":[27],"4":[28,95],"bits":[29],"(W4A4).In":[30],"this":[31],"paper,":[32],"we":[33,75,89],"propose":[34,76],"a":[35,65,94],"post-training":[36],"framework":[38],"with":[39,49,64,82],"W(1+1)A(14)":[40],"configuration,":[41],"where":[42],"weights":[43],"are":[44,59],"quantized":[45,60],"1":[47,52,62],"bit":[48,53,63],"an":[50,83],"additional":[51],"for":[54],"fine-grain":[55],"grouping":[56,80],"activations":[58,92],"4-fold":[66],"increase":[67],"in":[68,115],"the":[69,102,112,130],"number":[70],"of":[71,132],"channels.For":[72],"quantization,":[74,88],"utilizing":[77],"Hessian-aware":[78],"fine-grained":[79],"along":[81],"EM-based":[84],"scheme.For":[86],"decompose":[90],"INT4-quantized":[91],"into":[93],"INT1":[96],"format":[97],"equivalently":[98],"simultaneously":[100],"smooth":[101],"scaling":[103],"factors":[104],"based":[105],"on":[106,124],"errors,":[108],"which":[109],"further":[110],"errors":[114],"activations.Our":[116],"method":[117],"surpasses":[118],"state-of-the-art":[119],"(SOTA)":[120],"LLM":[121,134],"baselines":[123],"W2A4":[125],"across":[126],"multiple":[127],"tasks,":[128],"pushing":[129],"boundaries":[131],"methods":[136],"toward":[137],"fully":[138],"binarized":[139],"models.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}