{"id":"https://openalex.org/W7156106415","doi":"https://doi.org/10.48550/arxiv.2604.22575","title":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","display_name":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7156106415","doi":"https://doi.org/10.48550/arxiv.2604.22575"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.22575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22575","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.2604.22575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134697298","display_name":"Yuqi Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Yuqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134740899","display_name":"Jinghao Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Jinghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134735784","display_name":"Yupeng Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yupeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134726295","display_name":"Fangzhi Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Fangzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134663916","display_name":"Siyu Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Siyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134684536","display_name":"Xuerui Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Xuerui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027424643","display_name":"Shaowei Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Shaowei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134724897","display_name":"Bohan Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Bohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134682043","display_name":"Zhiyong Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Zhiyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134704979","display_name":"Yibo Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126230434","display_name":"Lingtao Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Lingtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134661251","display_name":"Kun Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007848499","display_name":"Zehao Liu","orcid":"https://orcid.org/0009-0008-2509-1099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zehao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113151651","display_name":"Yuhong Chou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chou, Yuhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134731630","display_name":"Shurong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shurong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134700565","display_name":"Anjie Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Anjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134678250","display_name":"Han Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134744893","display_name":"Bo Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134675001","display_name":"Guoqi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Guoqi","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":0.909600019454956,"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":0.909600019454956,"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":0.036400001496076584,"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":0.010200000368058681,"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/speedup","display_name":"Speedup","score":0.8374000191688538},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7311999797821045},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5293999910354614},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.43709999322891235},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4341000020503998},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.41200000047683716},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3873000144958496},{"id":"https://openalex.org/keywords/backward-chaining","display_name":"Backward chaining","score":0.3675000071525574},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.3594000041484833}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8374000191688538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860999703407288},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7311999797821045},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5293999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46709999442100525},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42309999465942383},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4196000099182129},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41200000047683716},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C129916263","wikidata":"https://www.wikidata.org/wiki/Q1141183","display_name":"Backward chaining","level":4,"score":0.3675000071525574},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.36169999837875366},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.33559998869895935},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3328000009059906},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C151927369","wikidata":"https://www.wikidata.org/wiki/Q1981312","display_name":"Neuromorphic engineering","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.22575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22575","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.2604.22575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22575","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":[{"id":"https://metadata.un.org/sdg/9","score":0.4229110777378082,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scaling":[0],"context":[1,158],"length":[2],"is":[3,23],"reshaping":[4],"large-model":[5],"development,":[6],"yet":[7],"full-attention":[8,171],"Transformers":[9],"suffer":[10],"from":[11],"prohibitive":[12],"computation":[13],"and":[14,31,49,76,126,134,159,190,198,201,230],"inference":[15,105,185],"bottlenecks":[16],"at":[17,156,188,204],"long":[18],"sequences.":[19],"A":[20],"key":[21],"challenge":[22],"to":[24],"design":[25],"foundation":[26,216],"models":[27,172],"that":[28,45],"maintain":[29],"performance":[30],"long-context":[32,87],"efficiency":[33,51],"with":[34,120,144,196,225],"minimal":[35],"training":[36,50],"overhead.":[37],"We":[38,62,113],"introduce":[39],"SpikingBrain2.0":[40,207],"(SpB2.0),":[41],"a":[42,152,209],"5B":[43],"model":[44],"advances":[46],"both":[47],"architecture":[48],"of":[52,71,138,221],"its":[53],"predecessor.":[54],"Our":[55],"contributions":[56],"are":[57],"two-fold.":[58],"(1)":[59],"Architectural":[60],"Innovation:":[61],"propose":[63],"Dual-Space":[64],"Sparse":[65,72,77],"Attention":[66,74,79],"(DSSA),":[67],"an":[68,82,115],"inter-layer":[69],"hybrid":[70],"Softmax":[73],"(MoBA)":[75],"Linear":[78],"(SSE),":[80],"achieving":[81],"improved":[83],"performance-efficiency":[84],"trade-off":[85],"for":[86,124,212,228],"modeling.":[88],"SpB2.0":[89,150],"further":[90],"supports":[91,160],"dual":[92,121],"quantization":[93],"paths:":[94],"INT8-Spiking":[95],"coding":[96,103],"enables":[97],"sparse":[98],"event-driven":[99],"computation,":[100],"while":[101],"FP8":[102,183],"accelerates":[104],"on":[106,164],"modern":[107],"GPUs.":[108],"(2)":[109],"Enhanced":[110],"Training":[111],"Strategy:":[112],"develop":[114],"optimized":[116],"Transformer-to-Hybrid":[117],"(T2H)":[118],"pipeline":[119],"conversion":[122],"paths":[123],"LLMs":[125],"VLMs":[127],"using":[128],"curated":[129],"open-source":[130],"data.":[131],"Empirically,":[132],"SpB2.0-5B":[133],"SpB2.0-VL-5B":[135],"recover":[136],"most":[137],"the":[139,219],"base":[140],"Transformer":[141],"(Qwen3-4B)":[142],"capability":[143],"under":[145,168],"7k":[146],"A100":[147,166],"GPU":[148,184],"hours.":[149],"achieves":[151],"10.13x":[153],"TTFT":[154],"speedup":[155,187],"4M":[157],"over":[161],"10M":[162],"tokens":[163],"8":[165],"GPUs":[167],"vLLM,":[169],"where":[170],"exceed":[173],"memory":[174],"limits.":[175],"It":[176],"also":[177],"demonstrates":[178],"strong":[179],"cross-platform":[180],"compatibility,":[181],"enabling":[182],"(2.52x":[186],"250k)":[189],"efficient":[191,226],"neuromorphic":[192],"execution":[193],"(64.31%":[194],"sparsity,":[195],"70.6%":[197],"46.5%":[199],"area":[200],"power":[202],"reduction":[203],"500MHz).":[205],"Overall,":[206],"provides":[208],"practical":[210],"pathway":[211],"lightweight,":[213],"multimodal,":[214],"spiking":[215],"models,":[217],"highlighting":[218],"potential":[220],"combining":[222],"brain-inspired":[223],"mechanisms":[224],"architectures":[227],"resource-constrained":[229],"edge":[231],"scenarios.":[232]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2026-04-28T00:00:00"}