{"id":"https://openalex.org/W7163525333","doi":"https://doi.org/10.48550/arxiv.2606.04063","title":"LLM Compression with Jointly Optimizing Architectural and Quantization choices","display_name":"LLM Compression with Jointly Optimizing Architectural and Quantization choices","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163525333","doi":"https://doi.org/10.48550/arxiv.2606.04063"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04063","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.04063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137850815","display_name":"Hoang-Loc La","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"La, Hoang-Loc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128023380","display_name":"Truong-Thanh Le","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Truong-Thanh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081026876","display_name":"Amir Taherkordi","orcid":"https://orcid.org/0000-0003-1672-054X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taherkordi, Amir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029307415","display_name":"Phuong Hoai Ha","orcid":"https://orcid.org/0000-0001-8366-5590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ha, Phuong Hoai","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":null,"has_fulltext":false,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.44110000133514404,"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":0.44110000133514404,"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":0.17000000178813934,"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":0.07280000299215317,"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/pruning","display_name":"Pruning","score":0.590399980545044},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5866000056266785},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.535099983215332},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.522599995136261},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.4366999864578247},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4237000048160553},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4122999906539917},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.39309999346733093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445999979972839},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.590399980545044},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3741999864578247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36410000920295715},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28529998660087585},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04063","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.04063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04063","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5520172119140625}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"large":[1],"language":[2,25],"models":[3,26,100],"(LLMs)":[4],"is":[5],"challenging":[6],"due":[7],"to":[8,103,116],"their":[9],"significant":[10],"memory":[11],"and":[12,47,65,81],"computational":[13],"requirements.":[14],"While":[15],"some":[16],"methods":[17],"address":[18],"this":[19],"by":[20],"developing":[21],"small":[22],"or":[23,114],"tiny":[24],"from":[27,68],"scratch,":[28],"these":[29],"approaches":[30,59],"demand":[31],"extensive":[32],"GPU":[33],"training.":[34],"Compressing":[35],"pre-trained":[36],"LLMs":[37],"for":[38,89],"edge":[39],"devices":[40],"offers":[41],"a":[42,72],"compelling":[43],"alternative.":[44],"Beyond":[45],"pruning":[46],"quantization,":[48],"Neural":[49],"Architecture":[50],"Search":[51],"(NAS)":[52],"enables":[53],"effective":[54],"compression,":[55],"yet":[56],"prior":[57],"NAS":[58,74],"often":[60],"limit":[61],"the":[62,78],"search":[63],"space":[64,80],"decouple":[66],"architecture":[67],"quantization.":[69],"We":[70],"introduce":[71],"differentiable":[73],"framework":[75],"that":[76],"explores":[77],"entire":[79],"jointly":[82],"optimizes":[83],"architectural":[84],"configurations":[85],"alongside":[86],"mixed-precision":[87],"quantization":[88],"linear":[90],"layers":[91],"of":[92],"LLMs.":[93],"Experiments":[94],"demonstrate":[95],"superior":[96],"accuracy-latency":[97],"trade-offs:":[98],"our":[99],"achieve":[101],"up":[102,115],"1.4x":[104],"faster":[105],"inference":[106],"than":[107],"sequential":[108],"NAS-then-quantization":[109],"baselines":[110],"at":[111,125],"comparable":[112],"accuracy,":[113],"6%":[117],"higher":[118],"average":[119],"accuracy":[120],"across":[121],"seven":[122],"reasoning":[123],"tasks":[124],"equivalent":[126],"latency.":[127]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-05T00:00:00"}