{"id":"https://openalex.org/W4410583234","doi":"https://doi.org/10.23919/date64628.2025.10992997","title":"SparseInfer: Training-free Prediction of Activation Sparsity for Fast LLM Inference","display_name":"SparseInfer: Training-free Prediction of Activation Sparsity for Fast LLM Inference","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410583234","doi":"https://doi.org/10.23919/date64628.2025.10992997"},"language":"en","primary_location":{"id":"doi:10.23919/date64628.2025.10992997","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","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/A5055766787","display_name":"Jiho Shin","orcid":"https://orcid.org/0000-0002-2697-8221"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jiho Shin","raw_affiliation_strings":["University of Seoul,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul,Seoul,South Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026611490","display_name":"Hoeseok Yang","orcid":"https://orcid.org/0000-0002-7929-7470"},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hoeseok Yang","raw_affiliation_strings":["Santa Clara University,Santa Clara,CA,USA"],"affiliations":[{"raw_affiliation_string":"Santa Clara University,Santa Clara,CA,USA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029634385","display_name":"Youngmin Yi","orcid":"https://orcid.org/0000-0001-9802-2109"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngmin Yi","raw_affiliation_strings":["Sogang University,Seoul,South Korea"],"affiliations":[{"raw_affiliation_string":"Sogang University,Seoul,South Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055766787"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":14.2071,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98542735,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9742000102996826,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9742000102996826,"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":0.9714000225067139,"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":0.9556000232696533,"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/computer-science","display_name":"Computer science","score":0.715586245059967},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7139123678207397},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6597128510475159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5000219345092773},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.479813814163208},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47241106629371643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715586245059967},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7139123678207397},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6597128510475159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5000219345092773},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.479813814163208},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47241106629371643},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date64628.2025.10992997","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","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":11,"referenced_works":["https://openalex.org/W2948634622","https://openalex.org/W4385571157","https://openalex.org/W4404401018","https://openalex.org/W6653677989","https://openalex.org/W6739901393","https://openalex.org/W6779683180","https://openalex.org/W6838633097","https://openalex.org/W6850625674","https://openalex.org/W6852962002","https://openalex.org/W6853251322","https://openalex.org/W6857551316"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Leveraging":[0],"sparsity":[1,36,74,81],"is":[2,82,107],"crucial":[3],"for":[4,72,96,117],"optimizing":[5,118],"large":[6],"language":[7],"model":[8],"(LLM)":[9],"inference;":[10],"however,":[11],"modern":[12],"LLMs":[13],"employing":[14],"SiLU":[15,29],"as":[16,113],"their":[17],"activation":[18,22,35,73,80],"function":[19],"exhibit":[20],"minimal":[21],"sparsity.":[23,59],"Recent":[24],"research":[25],"has":[26],"proposed":[27,122],"replacing":[28],"with":[30,133],"ReLU":[31],"to":[32,56],"induce":[33],"significant":[34],"and":[37,69,92],"showed":[38],"no":[39],"downstream":[40],"task":[41],"accuracy":[42,135],"degradation":[43],"through":[44],"fine-tuning.":[45],"However,":[46],"taking":[47],"full":[48],"advantage":[49],"of":[50,75,90,103,137],"it":[51],"required":[52],"training":[53],"a":[54,66,114],"predictor":[55,71],"estimate":[57],"this":[58,61],"In":[60],"paper,":[62],"we":[63],"introduce":[64],"Sparselnfer,":[65],"simple,":[67],"lightweight,":[68],"training-free":[70],"ReLU-fied":[76],"LLMs,":[77],"in":[78],"which":[79,109],"predicted":[83],"by":[84],"comparing":[85],"only":[86],"the":[87,104,131],"sign":[88],"bits":[89],"inputs":[91],"weights.":[93],"To":[94],"compensate":[95],"possible":[97],"prediction":[98],"inaccuracy,":[99],"an":[100],"adaptive":[101],"tuning":[102],"predictor's":[105],"conservativeness":[106],"enabled,":[108],"can":[110],"also":[111],"serve":[112],"control":[115],"knob":[116],"LLM":[119],"inference.":[120],"The":[121],"method":[123],"achieves":[124],"approximately":[125],"21%":[126],"faster":[127],"inference":[128],"speed":[129],"over":[130],"state-of-the-art,":[132],"negligible":[134],"loss":[136],"within":[138],"1":[139],"%":[140],"p.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}