{"id":"https://openalex.org/W7167767600","doi":null,"title":"Memory-centric AI: Optimizing Memory Systems for Large-Scale AI","display_name":"Memory-centric AI: Optimizing Memory Systems for Large-Scale AI","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7167767600"},"language":"en","primary_location":{"id":"pmh:oai:dash.harvard.edu:1/42744055","doi":null,"is_oa":true,"landing_page_url":"https://dash.harvard.edu/handle/1/42744055","pdf_url":"https://dash.harvard.edu/bitstreams/14c786b1-4a23-4437-8969-6274ce06a1cb/download","source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis or Dissertation"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dash.harvard.edu/bitstreams/14c786b1-4a23-4437-8969-6274ce06a1cb/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039877495","display_name":"Yunho Jin","orcid":"https://orcid.org/0000-0001-8428-057X","observed_orcids":["https://orcid.org/0000-0001-8428-057X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jin, Yunho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5039877495"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9359999895095825,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9359999895095825,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.014299999922513962,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.006800000090152025,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/memory-efficiency","display_name":"memory efficiency","score":0.7639999985694885},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9390000104904175},{"id":"https://openalex.org/keywords/memory-bottleneck","display_name":"memory bottleneck","score":0.5569999814033508},{"id":"https://openalex.org/keywords/data-movement","display_name":"data movement","score":0.6060000061988831},{"id":"https://openalex.org/keywords/memory-systems","display_name":"memory systems","score":0.4490000009536743},{"id":"https://openalex.org/keywords/model-scaling","display_name":"model scaling","score":0.5210000276565552},{"id":"https://openalex.org/keywords/inference-cost","display_name":"inference cost","score":0.45500001311302185},{"id":"https://openalex.org/keywords/hardware-architecture","display_name":"hardware architecture","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805400013923645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6281999945640564},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.40860000252723694},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C171675096","wikidata":"https://www.wikidata.org/wiki/Q1143380","display_name":"Extended memory","level":4,"score":0.29030001163482666},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.2897999882698059},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C56397880","wikidata":"https://www.wikidata.org/wiki/Q6044094","display_name":"Intelligent decision support system","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dash.harvard.edu:1/42744055","doi":null,"is_oa":true,"landing_page_url":"https://dash.harvard.edu/handle/1/42744055","pdf_url":"https://dash.harvard.edu/bitstreams/14c786b1-4a23-4437-8969-6274ce06a1cb/download","source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis or Dissertation"}],"best_oa_location":{"id":"pmh:oai:dash.harvard.edu:1/42744055","doi":null,"is_oa":true,"landing_page_url":"https://dash.harvard.edu/handle/1/42744055","pdf_url":"https://dash.harvard.edu/bitstreams/14c786b1-4a23-4437-8969-6274ce06a1cb/download","source":{"id":"https://openalex.org/S4306401540","display_name":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis or Dissertation"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7167767600.pdf","grobid_xml":"https://content.openalex.org/works/W7167767600.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W2736578080","https://openalex.org/W2779888504","https://openalex.org/W2950700477","https://openalex.org/W2978017171","https://openalex.org/W2988394319","https://openalex.org/W3001279689","https://openalex.org/W3015468748","https://openalex.org/W3030163527","https://openalex.org/W3043433718","https://openalex.org/W3045733172","https://openalex.org/W3091156754","https://openalex.org/W3118781290","https://openalex.org/W3130716829","https://openalex.org/W3144382362","https://openalex.org/W3159727696","https://openalex.org/W3177813494","https://openalex.org/W3195140297","https://openalex.org/W3210904070","https://openalex.org/W3213170663","https://openalex.org/W4221161695","https://openalex.org/W4285121610","https://openalex.org/W4308672130","https://openalex.org/W4308760184","https://openalex.org/W4320003957","https://openalex.org/W4321448364","https://openalex.org/W4322718191","https://openalex.org/W4324109433","https://openalex.org/W4324297016","https://openalex.org/W4362707004","https://openalex.org/W4376167141","https://openalex.org/W4383604511","https://openalex.org/W4387355948","https://openalex.org/W4389599514","https://openalex.org/W4389649385","https://openalex.org/W4390041933","https://openalex.org/W4392822190","https://openalex.org/W4393399908","https://openalex.org/W4394782013","https://openalex.org/W4400025607","https://openalex.org/W4402698921","https://openalex.org/W4402733601","https://openalex.org/W4404131920","https://openalex.org/W4405364446","https://openalex.org/W4405655184","https://openalex.org/W4406033152","https://openalex.org/W4412945375","https://openalex.org/W4414281281","https://openalex.org/W4415307805","https://openalex.org/W7133209886","https://openalex.org/W7133236450"],"related_works":["https://openalex.org/W7221371505","https://openalex.org/W4399657747","https://openalex.org/W7125134210","https://openalex.org/W4393145114","https://openalex.org/W7172534846","https://openalex.org/W6893574642","https://openalex.org/W4405308033","https://openalex.org/W7125218161","https://openalex.org/W7138982531","https://openalex.org/W4416429709"],"abstract_inverted_index":{"Artificial":[0],"Intelligence":[1],"(AI)":[2],"has":[3,62,107],"made":[4],"rapid":[5],"progress":[6,181],"in":[7,45,77,81,91],"both":[8],"accuracy":[9,170],"and":[10,41,50,93,116,120,129,207],"efficiency":[11],"over":[12],"the":[13,53,56,147,168,183],"past":[14],"decade.":[15],"Early":[16],"deep":[17],"learning":[18],"models":[19,34,61,123],"were":[20],"limited":[21],"to":[22,79],"relatively":[23],"simple":[24],"tasks":[25],"like":[26],"image":[27],"classification.":[28],"In":[29],"contrast,":[30],"modern":[31],"large":[32,122],"language":[33],"(LLMs)":[35],"now":[36],"solve":[37],"complex":[38],"reasoning":[39],"problems":[40],"enable":[42],"autonomous":[43],"systems":[44,94,152],"domains":[46],"such":[47,191],"as":[48,192],"vision":[49],"navigation.":[51],"At":[52],"same":[54],"time,":[55],"cost":[57],"of":[58,127,150,174,185],"deploying":[59],"frontier":[60],"decreased":[63],"dramatically.":[64],"For":[65],"example,":[66],"inference":[67],"with":[68],"ChatGPT":[69],"fell":[70],"from":[71],"$10":[72],"per":[73,172],"million":[74],"input":[75],"tokens":[76],"2023":[78],"$1.25":[80],"2025,":[82],"an":[83],"8\u00d7reduction":[84],"within":[85],"a":[86,138,162,198],"year,":[87],"demonstrating":[88],"simultaneous":[89],"advances":[90],"algorithms":[92],"efficiency.":[95],"These":[96],"improvements":[97],"have":[98],"been":[99],"largely":[100],"driven":[101],"by":[102],"scaling":[103],"model":[104],"size,":[105],"which":[106,166],"unlocked":[108],"emergent":[109],"capabilities":[110],"but":[111],"also":[112],"created":[113],"significant":[114],"computational":[115],"memory":[117,137,143,186],"challenges.":[118],"Training":[119],"serving":[121],"require":[124],"storing":[125],"billions":[126],"parameters":[128],"moving":[130],"data":[131,175],"at":[132],"extremely":[133],"high":[134],"throughput,":[135],"making":[136],"critical":[139],"bottleneck.":[140],"While":[141],"reducing":[142],"overhead":[144],"is":[145],"essential,":[146],"ultimate":[148],"goal":[149],"AI":[151,180],"remains":[153],"accuracy.":[154],"To":[155],"bridge":[156],"this":[157,159],"gap,":[158],"dissertation":[160],"introduces":[161],"new":[163],"metric:":[164],"accuracy-per-byte,":[165],"quantifies":[167],"predictive":[169],"obtained":[171],"unit":[173],"movement.":[176],"This":[177],"metric":[178],"reframes":[179],"through":[182],"lens":[184],"efficiency,":[187],"complementing":[188],"traditional":[189],"measures":[190],"FLOPs-per-byte.":[193],"Achieving":[194],"higher":[195],"accuracy-per-byte":[196],"demands":[197],"holistic,":[199],"cross-layer":[200],"approach":[201],"that":[202],"spans":[203],"algorithms,":[204],"software":[205],"systems,":[206],"hardware":[208],"architectures.":[209]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-07-09T00:00:00"}