{"id":"https://openalex.org/W7148388907","doi":"https://doi.org/10.1109/asru65441.2025.11434611","title":"OOQ: Outlier-Oriented Quantization for Efficient Large Language Models","display_name":"OOQ: Outlier-Oriented Quantization for Efficient Large Language Models","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148388907","doi":"https://doi.org/10.1109/asru65441.2025.11434611"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100427184","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0002-4314-6099"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyu Wang","raw_affiliation_strings":["AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132827527","display_name":"Bei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bei Liu","raw_affiliation_strings":["AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080901723","display_name":"Hang Shao","orcid":"https://orcid.org/0000-0002-1322-4789"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Shao","raw_affiliation_strings":["AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132748617","display_name":"Bo Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xiao","raw_affiliation_strings":["Meituan,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Meituan,Beijing,China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132822470","display_name":"Ke Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Zeng","raw_affiliation_strings":["Meituan,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Meituan,Beijing,China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072537055","display_name":"Guanglu Wan","orcid":"https://orcid.org/0009-0003-1061-3724"},"institutions":[{"id":"https://openalex.org/I4210087373","display_name":"Meizu (China)","ror":"https://ror.org/0067g4302","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210087373"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglu Wan","raw_affiliation_strings":["Meituan,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Meituan,Beijing,China","institution_ids":["https://openalex.org/I4210087373"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129685555","display_name":"Yanmin Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute School of Computer Science Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100427184"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87560625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2978000044822693,"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":0.2978000044822693,"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":0.12409999966621399,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.10010000318288803,"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":0.4250999987125397},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3504999876022339},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3343000113964081},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.26759999990463257},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.2529999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5753999948501587},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43529999256134033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4336000084877014},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3098999857902527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2946609015","https://openalex.org/W2998617917","https://openalex.org/W3194676777","https://openalex.org/W4393147284","https://openalex.org/W4402670692","https://openalex.org/W7133198810","https://openalex.org/W7133216168","https://openalex.org/W7133233472"],"related_works":[],"abstract_inverted_index":{"Parameter":[0],"quantization":[1,57,71,97],"for":[2,11],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"has":[7],"gained":[8],"significant":[9],"attention":[10],"reducing":[12],"memory":[13],"costs":[14],"and":[15],"improving":[16],"computational":[17],"efficiency.":[18],"However,":[19],"existing":[20],"methods":[21],"struggle":[22],"with":[23],"performance":[24],"degradation":[25],"in":[26,63,114],"low-bit":[27,116],"scenarios.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,50,67,90],"propose":[33],"Outlier-Oriented":[34],"Quantization":[35],"(OOQ),":[36],"a":[37],"novel":[38],"framework":[39],"designed":[40],"to":[41,55,73,80,125],"address":[42],"these":[43],"challenges":[44],"through":[45],"three":[46],"key":[47],"innovations.":[48],"First,":[49],"design":[51],"an":[52],"outlieroriented":[53],"metric":[54],"determine":[56],"precision":[58,72],"based":[59],"on":[60,100],"outlier":[61,82],"percentages":[62],"channel":[64],"parameters.":[65],"Second,":[66],"dynamically":[68],"allocate":[69],"varying":[70],"different":[74],"parts":[75],"of":[76],"the":[77,81,87,96],"model":[78],"according":[79],"distribution.":[83],"Finally,":[84],"guided":[85],"by":[86,123],"outlier-oriented":[88],"metric,":[89],"preserve":[91],"some":[92],"high-precision":[93],"outliers":[94],"during":[95],"process.":[98],"Experiments":[99],"LLaMA":[101],"models":[102],"demonstrate":[103],"that":[104],"OOQ":[105,119],"achieves":[106],"state-of-the-art":[107],"results":[108],"across":[109],"various":[110],"bit":[111],"settings,":[112],"particularly":[113],"extremely":[115],"regimes.":[117],"Additionally,":[118],"improves":[120],"inference":[121],"speed":[122],"up":[124],"24%.":[126]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}