{"id":"https://openalex.org/W4416035109","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1799","title":"AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models","display_name":"AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035109","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1799"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1799","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1799","pdf_url":"https://aclanthology.org/2025.emnlp-main.1799.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1799.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100712406","display_name":"Sangjun Lee","orcid":"https://orcid.org/0000-0002-8687-8329"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sangjun Lee","raw_affiliation_strings":["Graduate School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119959281","display_name":"Seung-taek Woo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Seung-taek Woo","raw_affiliation_strings":["Graduate School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111984028","display_name":"Jun-gyu Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jun-gyu Jin","raw_affiliation_strings":["Graduate School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116568538","display_name":"Changhun Lee","orcid":"https://orcid.org/0000-0002-6043-034X"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Changhun Lee","raw_affiliation_strings":["Department of Convergence IT Engineering Pohang University of Science and Technology (POSTECH )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Convergence IT Engineering Pohang University of Science and Technology (POSTECH )","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064884832","display_name":"Eunhyeok Park","orcid":"https://orcid.org/0000-0002-7331-9819"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eunhyeok Park","raw_affiliation_strings":["Graduate School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Artificial Intelligence","institution_ids":["https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9041,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92328683,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"35520","last_page":"35538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20149999856948853,"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/T10028","display_name":"Topic Modeling","score":0.20149999856948853,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.19349999725818634,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.14499999582767487,"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/quantization","display_name":"Quantization (signal processing)","score":0.4065000116825104},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38519999384880066},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.33489999175071716},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.24160000681877136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6044999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.24160000681877136}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1799","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1799","pdf_url":"https://aclanthology.org/2025.emnlp-main.1799.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1799","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1799","pdf_url":"https://aclanthology.org/2025.emnlp-main.1799.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315121","display_name":"Samsung Advanced Institute of Technology","ror":null},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035109.pdf","grobid_xml":"https://content.openalex.org/works/W4416035109.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0],"enable":[1],"broader":[2],"deployment":[3],"of":[4],"Large":[5],"Language":[6],"Models":[7],"(LLMs),":[8],"it":[9],"is":[10,125],"essential":[11],"to":[12,34,71,78,88],"identify":[13],"the":[14,42,108,112],"best-performing":[15],"model":[16,37],"under":[17],"strict":[18],"memory":[19,40],"constraints.We":[20],"present":[21],"AMQ,":[22],"Automated":[23],"Mixed-Precision":[24],"Weight-Only":[25],"Quantization,":[26],"a":[27],"framework":[28],"that":[29,118],"assigns":[30],"layer-wise":[31],"quantization":[32,76],"bit-widths":[33],"optimally":[35],"balance":[36],"quality":[38,86],"and":[39,92,99,115,122],"usage.However,":[41],"combinatorial":[43],"search":[44,65],"space,":[45],"with":[46],"over":[47],"10":[48],"100":[49],"possible":[50],"configurations,":[51,74],"makes":[52],"conventional":[53],"black-box":[54],"optimization":[55],"infeasible.AMQ":[56],"overcomes":[57],"this":[58],"challenge":[59],"through":[60],"four":[61],"key":[62],"innovations:":[63],"(1)":[64],"space":[66],"pruning":[67],"using":[68],"prior":[69],"knowledge":[70],"exclude":[72],"unpromising":[73],"(2)":[75],"proxy":[77],"bypass":[79],"costly":[80],"format":[81],"conversions":[82],"during":[83],"search,":[84],"(3)":[85],"predictor":[87],"minimize":[89],"evaluation":[90],"overhead,":[91],"(4)":[93],"iterative":[94],"search-and-update":[95],"strategy":[96],"for":[97],"fast":[98],"stable":[100],"convergence.By":[101],"integrating":[102],"these":[103],"components,":[104],"AMQ":[105],"efficiently":[106],"explores":[107],"qualityefficiency":[109],"landscape,":[110],"reaching":[111],"Pareto":[113],"frontier":[114],"yielding":[116],"LLMs":[117],"are":[119],"both":[120],"compact":[121],"high-performing.Our":[123],"code":[124],"available":[126],"at":[127],"https://github.com/dlwns147/amq.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-11-08T00:00:00"}