{"id":"https://openalex.org/W7154145988","doi":"https://doi.org/10.48550/arxiv.2604.08894","title":"Ge$^\\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer","display_name":"Ge$^\\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer","publication_year":2026,"publication_date":"2026-04-10","ids":{"openalex":"https://openalex.org/W7154145988","doi":"https://doi.org/10.48550/arxiv.2604.08894"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.08894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2604.08894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073469736","display_name":"Zecheng Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Zecheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124776806","display_name":"Shenghao Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Shenghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133500960","display_name":"Kang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133489869","display_name":"Wenxuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Wenxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133502460","display_name":"Zhaofei Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Zhaofei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133495153","display_name":"Tiejun Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Tiejun","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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9519000053405762,"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":0.9519000053405762,"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":0.02449999935925007,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.012000000104308128,"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/efficient-energy-use","display_name":"Efficient energy use","score":0.7321000099182129},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6057999730110168},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5677000284194946},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5174000263214111},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5084999799728394},{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.46790000796318054},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4250999987125397},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.3917999863624573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842000126838684},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.7321000099182129},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6057999730110168},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5174000263214111},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5084999799728394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48840001225471497},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.46790000796318054},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.3917999863624573},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C14961307","wikidata":"https://www.wikidata.org/wiki/Q5377176","display_name":"Energy minimization","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2849999964237213},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2676999866962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.08894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2604.08894","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08894","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"id":"https://metadata.un.org/sdg/7","score":0.9086571335792542,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spiking":[0,26,97],"Neural":[1,10],"Networks":[2,11],"(SNNs)":[3],"offer":[4],"superior":[5,123],"energy":[6,50,127,157],"efficiency":[7,128],"over":[8],"Artificial":[9],"(ANNs).":[12],"However,":[13],"they":[14],"encounter":[15],"significant":[16],"deficiencies":[17],"in":[18,159],"training":[19,85],"and":[20,35,49,68,87,108,156],"inference":[21],"metrics":[22],"when":[23],"applied":[24],"to":[25,100,141],"Vision":[27],"Transformers":[28],"(S-ViTs).":[29],"Existing":[30],"paradigms":[31],"including":[32],"ANN-SNN":[33],"Conversion":[34],"Spatial-Temporal":[36],"Backpropagation":[37],"(STBP)":[38],"suffer":[39],"from":[40],"inherent":[41],"limitations,":[42],"precluding":[43],"concurrent":[44],"optimization":[45],"of":[46,151],"memory,":[47],"accuracy":[48],"consumption.":[51],"To":[52,132],"address":[53],"these":[54],"issues,":[55],"we":[56,73,94],"propose":[57],"Ge$^\\text{2}$mS-T,":[58],"a":[59,112],"novel":[60],"architecture":[61],"implementing":[62],"grouped":[63,145],"computation":[64,146],"across":[65],"temporal,":[66],"spatial":[67],"network":[69],"structure":[70],"dimensions.":[71],"Specifically,":[72],"introduce":[74],"the":[75,138,149],"Grouped-Exponential-Coding-based":[76],"IF":[77],"(ExpG-IF)":[78],"model,":[79],"enabling":[80],"lossless":[81],"conversion":[82],"with":[83,125],"constant":[84],"overhead":[86],"precise":[88],"regulation":[89],"for":[90,147],"spike":[91],"patterns.":[92],"Additionally,":[93],"develop":[95],"Group-wise":[96],"Self-Attention":[98],"(GW-SSA)":[99],"reduce":[101],"computational":[102],"complexity":[103],"via":[104],"multi-scale":[105],"token":[106],"grouping":[107],"multiplication-free":[109],"operations":[110],"within":[111],"hybrid":[113],"attention-convolution":[114],"framework.":[115],"Experiments":[116],"confirm":[117],"that":[118],"our":[119,133],"method":[120],"can":[121],"achieve":[122],"performance":[124],"ultra-high":[126],"on":[129],"challenging":[130],"benchmarks.":[131],"best":[134],"knowledge,":[135],"this":[136],"is":[137,162],"first":[139],"work":[140],"systematically":[142],"establish":[143],"multi-dimensional":[144],"resolving":[148],"triad":[150],"memory":[152],"overhead,":[153],"learning":[154],"capability":[155],"budget":[158],"S-ViTs.":[160],"Code":[161],"available":[163],"at":[164],"https://github.com/hzc1208/Ge2mST.":[165]},"counts_by_year":[],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2026-04-14T00:00:00"}