{"id":"https://openalex.org/W4414500046","doi":"https://doi.org/10.1109/aicas64808.2025.11173143","title":"MemQuant: Towards Memory-aware Post-Training Quantization for Multimodal Transformers","display_name":"MemQuant: Towards Memory-aware Post-Training Quantization for Multimodal Transformers","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4414500046","doi":"https://doi.org/10.1109/aicas64808.2025.11173143"},"language":"en","primary_location":{"id":"doi:10.1109/aicas64808.2025.11173143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas64808.2025.11173143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","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/A5118664092","display_name":"Kazi Barria Nine","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kazi Barria Nine","raw_affiliation_strings":["Georgia Institute of Technology,Dept. of ECE,Atlanta,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Dept. of ECE,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026872115","display_name":"Foroozan Karimzadeh","orcid":"https://orcid.org/0000-0001-8849-7784"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Foroozan Karimzadeh","raw_affiliation_strings":["Georgia Institute of Technology,Dept. of ECE,Atlanta,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Dept. of ECE,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076856438","display_name":"Zishen Wan","orcid":"https://orcid.org/0000-0002-2982-5351"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zishen Wan","raw_affiliation_strings":["Georgia Institute of Technology,Dept. of ECE,Atlanta,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Dept. of ECE,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091408102","display_name":"Arijit Raychowdhury","orcid":"https://orcid.org/0000-0001-8391-0576"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arijit Raychowdhury","raw_affiliation_strings":["Georgia Institute of Technology,Dept. of ECE,Atlanta,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Dept. of ECE,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5118664092"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14383414,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9502999782562256,"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":0.9502999782562256,"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/T10320","display_name":"Neural Networks and Applications","score":0.9340000152587891,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9264000058174133,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.698199987411499},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6414999961853027},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.515500009059906},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.5023000240325928},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5016000270843506},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.45019999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72079998254776},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.698199987411499},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6414999961853027},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.515500009059906},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.5023000240325928},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.400299996137619},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36579999327659607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3463999927043915},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aicas64808.2025.11173143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas64808.2025.11173143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","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":6,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2257408573","https://openalex.org/W2952122856","https://openalex.org/W2963122961","https://openalex.org/W2963532001","https://openalex.org/W4313069943"],"related_works":[],"abstract_inverted_index":{"Recently":[0],"Transformer":[1],"model":[2,100,107],"has":[3],"revolutionized":[4],"the":[5,92,135,138],"fields":[6],"of":[7,72,137,149],"natural":[8],"language":[9,99],"processing":[10],"(NLP)":[11],"and":[12,22,28,74,104,145],"computer":[13],"vision":[14],"(CV).":[15],"Even":[16],"though":[17],"it":[18,35],"shows":[19],"unprecedented":[20],"efficiency":[21],"accuracy":[23],"on":[24],"most":[25],"tasks,":[26],"memory":[27,70,118,132],"computation":[29],"overhead":[30],"can":[31,47],"be":[32,48],"huge,":[33],"making":[34],"inadequate":[36],"for":[37,98,101,108,134,142,147],"real-world":[38],"applications":[39],"such":[40],"as":[41],"edge":[42],"devices.":[43],"Post-training":[44],"quantization":[45],"(PTQ)":[46],"an":[49],"efficient":[50],"way":[51],"to":[52,88,129],"overcome":[53],"this":[54,57],"bottleneck.":[55],"In":[56],"paper,":[58],"we":[59,115],"propose":[60],"a":[61,105],"novel":[62],"memory-aware":[63],"mixed":[64],"precision":[65],"PTQ":[66],"which":[67,85],"will":[68],"consider":[69],"consumption":[71],"blocks":[73],"sub-blocks":[75],"inside":[76],"transformer":[77],"model.":[78,151],"Our":[79],"motivation":[80],"originates":[81],"from":[82],"profiling":[83],"result":[84],"varies":[86],"according":[87],"application.":[89],"We":[90,126],"evaluate":[91],"proposed":[93],"methodology":[94],"by":[95],"employing":[96],"both":[97],"translation":[102],"tasks":[103],"vision-to-language":[106,150],"image":[109],"captioning":[110],"tasks.":[111],"Through":[112],"our":[113],"approach,":[114],"achieve":[116,130],"significant":[117],"savings":[119,133],"while":[120],"experiencing":[121],"small":[122],"degradation":[123],"in":[124],"accuracy.":[125],"are":[127],"able":[128],"10\u00d7":[131],"weights":[136,148],"annotated":[139],"transformer,":[140],"5\u00d7":[141],"T5":[143],"text-to-text,":[144],"5.5\u00d7":[146]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
