{"id":"https://openalex.org/W7106102518","doi":"https://doi.org/10.1109/iccad66269.2025.11240876","title":"3D Acceleration for Mixture-of-Experts and Multi-Head Attention Spiking Transformers with Dynamic Head Pruning","display_name":"3D Acceleration for Mixture-of-Experts and Multi-Head Attention Spiking Transformers with Dynamic Head Pruning","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7106102518","doi":"https://doi.org/10.1109/iccad66269.2025.11240876"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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":null,"display_name":"Boxun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Boxun Xu","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,Santa Barbara,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,Santa Barbara,CA,USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junyoung Hwang","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":false,"raw_author_name":"Junyoung Hwang","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pruek Vanna-Iampikul","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":false,"raw_author_name":"Pruek Vanna-Iampikul","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuxuan Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxuan Yin","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,Santa Barbara,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,Santa Barbara,CA,USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sung Kyu Lim","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":false,"raw_author_name":"Sung Kyu Lim","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":null,"display_name":"Peng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,Santa Barbara,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,Santa Barbara,CA,USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51157546,"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":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.8938999772071838,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.8938999772071838,"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"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.07800000160932541,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0032999999821186066,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.6057999730110168},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5133000016212463},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4959999918937683},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4390000104904175},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.39579999446868896},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.38179999589920044},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.38089999556541443},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.37860000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875999808311462},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.6057999730110168},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5133000016212463},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4959999918937683},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4302999973297119},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4251999855041504},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.38179999589920044},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C190560348","wikidata":"https://www.wikidata.org/wiki/Q3245116","display_name":"Circuit design","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C530198007","wikidata":"https://www.wikidata.org/wiki/Q80831","display_name":"Integrated circuit","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2780728072","wikidata":"https://www.wikidata.org/wiki/Q5297","display_name":"Microprocessor","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9082485437393188,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1604973310","https://openalex.org/W2783525259","https://openalex.org/W2808720247","https://openalex.org/W2900336531","https://openalex.org/W3042725081","https://openalex.org/W3043692235","https://openalex.org/W3111761932","https://openalex.org/W3116977674","https://openalex.org/W4280536985","https://openalex.org/W4313046728","https://openalex.org/W4392745778","https://openalex.org/W4404134189","https://openalex.org/W4409285493","https://openalex.org/W4411486515","https://openalex.org/W4413361526"],"related_works":[],"abstract_inverted_index":{"Spiking":[0],"Neural":[1],"Networks":[2],"(SNNs)":[3],"provide":[4],"a":[5,53],"brain-inspired":[6,104],"and":[7,37,76,81,92,95,116],"event-driven":[8],"mechanism":[9],"that":[10],"is":[11,51],"believed":[12],"to":[13,16],"be":[14],"critical":[15],"unlock":[17],"energy-efficient":[18,97],"deep":[19],"learning.":[20],"On":[21],"the":[22,29,34,44,71],"other":[23],"hand,":[24],"mixture-of-experts":[25],"(MoE)":[26],"models":[27],"mirror":[28],"parallel":[30,60],"distributed":[31,61],"processing":[32,62],"of":[33,46,55,113],"nervous":[35],"system,":[36],"expand":[38],"model":[39],"capacity":[40],"without":[41],"scaling":[42],"up":[43],"number":[45],"computational":[47],"operations.":[48],"However,":[49],"there":[50],"currently":[52],"lack":[54],"hardware":[56,74],"support":[57],"for":[58,79],"highly":[59],"in":[63],"spiking":[64,84],"based":[65],"MoE":[66],"models.":[67],"This":[68],"paper":[69],"introduces":[70],"first":[72],"3D":[73,88],"architecture":[75],"design":[77],"methodology":[78],"Mixture-of-Experts":[80],"Multi-Head":[82],"Attention":[83],"transformers.":[85],"By":[86],"leveraging":[87],"integration":[89],"with":[90,106],"memory-on-logic":[91],"logic-on-logic":[93],"stacking":[94],"exploring":[96],"dynamic":[98],"head":[99],"pruning,":[100],"we":[101],"explore":[102],"such":[103],"accelerators":[105],"spatially":[107],"stackable":[108],"circuitry,":[109],"demonstrating":[110],"significant":[111],"improvements":[112],"energy":[114],"efficiency":[115],"latency":[117],"over":[118],"conventional":[119],"2D":[120],"CMOS":[121],"integration.":[122]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-20T00:00:00"}
