{"id":"https://openalex.org/W4404303902","doi":"https://doi.org/10.48550/arxiv.2410.14687","title":"BrainTransformers: SNN-LLM","display_name":"BrainTransformers: SNN-LLM","publication_year":2024,"publication_date":"2024-10-03","ids":{"openalex":"https://openalex.org/W4404303902","doi":"https://doi.org/10.48550/arxiv.2410.14687"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.14687","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.14687","pdf_url":"https://arxiv.org/pdf/2410.14687","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.14687","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114616968","display_name":"Zhengzheng Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Zhengzheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114616969","display_name":"Eva Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Eva","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":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/T10241","display_name":"Functional Brain Connectivity Studies","score":0.7235000133514404,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.7235000133514404,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.27908456325531006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.27908456325531006}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.14687","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.14687","pdf_url":"https://arxiv.org/pdf/2410.14687","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.14687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.14687","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.14687","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.14687","pdf_url":"https://arxiv.org/pdf/2410.14687","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404303902.pdf","grobid_xml":"https://content.openalex.org/works/W4404303902.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,94],"study":[1],"introduces":[2],"BrainTransformers,":[3],"an":[4,33],"innovative":[5],"Large":[6],"Language":[7],"Model":[8],"(LLM)":[9],"implemented":[10],"using":[11],"Spiking":[12],"Neural":[13],"Networks":[14],"(SNN).":[15],"Our":[16,51],"key":[17],"contributions":[18],"include:":[19],"(1)":[20],"designing":[21],"SNN-compatible":[22],"Transformer":[23],"components":[24],"such":[25],"as":[26],"SNNMatmul,":[27],"SNNSoftmax,":[28],"and":[29,41,69,78,107,122],"SNNSiLU;":[30],"(2)":[31],"implementing":[32],"SNN":[34,119],"approximation":[35],"of":[36],"the":[37],"SiLU":[38],"activation":[39],"function;":[40],"(3)":[42],"developing":[43,117],"a":[44,84],"Synapsis":[45],"module":[46],"to":[47],"simulate":[48],"synaptic":[49,91],"plasticity.":[50],"3-billion":[52],"parameter":[53],"model,":[54],"BrainTransformers-3B-Chat,":[55],"demonstrates":[56],"competitive":[57],"performance":[58],"across":[59],"various":[60],"benchmarks,":[61],"including":[62,88],"MMLU":[63],"(63.2),":[64],"BBH":[65],"(54.1),":[66],"ARC-C":[67],"(54.3),":[68],"GSM8K":[70],"(76.3),":[71],"while":[72],"potentially":[73],"offering":[74],"improved":[75],"energy":[76],"efficiency":[77],"biological":[79],"plausibility.":[80],"The":[81],"model":[82],"employs":[83],"three-stage":[85],"training":[86],"approach,":[87],"SNN-specific":[89],"neuronal":[90],"plasticity":[92],"training.":[93],"research":[95],"opens":[96],"new":[97],"avenues":[98],"for":[99],"brain-like":[100],"AI":[101],"systems":[102],"in":[103,126],"natural":[104],"language":[105],"processing":[106],"neuromorphic":[108],"computing.":[109],"Future":[110],"work":[111],"will":[112],"focus":[113],"on":[114],"hardware":[115],"optimization,":[116],"specialized":[118],"fine-tuning":[120],"tools,":[121],"exploring":[123],"practical":[124],"applications":[125],"energy-efficient":[127],"computing":[128],"environments.":[129]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}