{"id":"https://openalex.org/W7128524751","doi":"https://doi.org/10.48550/arxiv.2602.08817","title":"Kirin: Improving ANN efficiency with SNN Hybridization","display_name":"Kirin: Improving ANN efficiency with SNN Hybridization","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128524751","doi":"https://doi.org/10.48550/arxiv.2602.08817"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.08817","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125583964","display_name":"Chenyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125556075","display_name":"Zhanglu Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Zhanglu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125534809","display_name":"Zhi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125570286","display_name":"Xu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125569208","display_name":"Weng-Fai Wong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wong, Weng-Fai","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13598456,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.6830000281333923,"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":0.6830000281333923,"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":0.07680000364780426,"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"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.06459999829530716,"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/quantization","display_name":"Quantization (signal processing)","score":0.6491000056266785},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6273000240325928},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.5347999930381775},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48350000381469727},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44609999656677246},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4196000099182129},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4106000065803528},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.39340001344680786},{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.35929998755455017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6942999958992004},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6491000056266785},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6273000240325928},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5361999869346619},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.5347999930381775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48350000381469727},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.35929998755455017},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2909946758","wikidata":"https://www.wikidata.org/wiki/Q194277","display_name":"Spike train","level":3,"score":0.2583000063896179}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.08817","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.08817","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08817","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:doi:10.48550/arxiv.2602.08817","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.911297082901001,"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":{"Artificial":[0],"neural":[1,19],"networks":[2,20],"(ANNs),":[3],"particularly":[4],"large":[5],"language":[6],"models":[7],"(LLMs),":[8],"demonstrate":[9,202],"powerful":[10],"inference":[11],"capabilities":[12],"but":[13],"consume":[14],"substantial":[15],"energy.":[16],"Conversely,":[17],"spiking":[18],"(SNNs)":[21],"exhibit":[22],"exceptional":[23],"energy":[24,102,132,215],"efficiency":[25],"due":[26],"to":[27,52,123,150,180,193,219],"their":[28],"binary":[29,79,156],"and":[30,88,100,118,131,197,221],"event-driven":[31],"characteristics,":[32],"thus":[33],"motivating":[34],"the":[35,57,61,69,90,94,101,160,167,182,188,194],"study":[36],"of":[37,60,97,104,170,184],"ANN-to-SNN":[38,127],"conversion.":[39],"In":[40],"this":[41],"process,":[42],"quantization":[43,76,208],"plays":[44],"a":[45,116,138,176,206],"pivotal":[46],"role,":[47],"mapping":[48],"LLMs'":[49],"floating-point":[50],"parameters":[51,55,147],"discrete":[53],"SNN":[54,122,171],"via":[56],"temporal":[58],"dimension":[59],"time":[62,83,130,152,223],"window.":[63],"However,":[64],"several":[65],"challenges":[66],"remain":[67],"in":[68,107,162],"conversion":[70,128],"process:":[71],"(i)":[72],"converting":[73],"high":[74],"bit-width":[75,146],"values":[77],"into":[78,155],"spikes":[80,157],"requires":[81],"longer":[82],"windows,":[84],"increasing":[85],"system":[86],"latency;":[87],"(ii)":[89],"inherent":[91],"trade-off":[92],"between":[93],"information":[95],"loss":[96],"single-spike":[98,185],"schemes":[99],"costs":[103],"multi-spike":[105],"ones":[106],"SNN.":[108],"To":[109],"address":[110],"these":[111],"challenges,":[112],"we":[113,135,174],"propose":[114,137],"Kirin,":[115,204],"integer":[117,163],"spike":[119],"hybrid":[120],"based":[121],"achieve":[124],"accuracy":[125,212],"lossless":[126],"with":[129],"efficiency.":[133],"Specifically,":[134],"first":[136],"Spike":[139],"Matrix":[140],"Hybridization":[141],"strategy":[142],"that":[143,148,203],"encoding":[144],"low":[145],"leading":[149],"small":[151],"window":[153],"size":[154],"while":[158,213],"preserving":[159],"rest":[161],"format,":[164],"thereby":[165],"reducing":[166,214],"overall":[168],"latency":[169],"execution.":[172],"Second,":[173],"introduce":[175],"silence":[177],"threshold":[178],"mechanism":[179],"regulate":[181],"timing":[183],"firing,":[186],"ensuring":[187],"output":[189,196],"is":[190],"mathematically":[191],"equivalent":[192],"LLM's":[195],"preserves":[198],"accuracy.":[199],"Experimental":[200],"results":[201],"under":[205],"W4A4\\&8":[207],"setting,":[209],"achieves":[210],"near-FP16":[211],"consumption":[216],"by":[217,225],"up":[218],"84.66\\%":[220],"shortening":[222],"steps":[224],"93.75\\%.":[226]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-02-11T00:00:00"}