{"id":"https://openalex.org/W4415125508","doi":"https://doi.org/10.1109/icnp65844.2025.11192368","title":"Mamba4Net: Distilled Hybrid Mamba Large Language Models For Networking","display_name":"Mamba4Net: Distilled Hybrid Mamba Large Language Models For Networking","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4415125508","doi":"https://doi.org/10.1109/icnp65844.2025.11192368"},"language":"en","primary_location":{"id":"doi:10.1109/icnp65844.2025.11192368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnp65844.2025.11192368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 33rd International Conference on Network Protocols (ICNP)","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":"https://openalex.org/A5050489444","display_name":"Long Xia","orcid":"https://orcid.org/0000-0002-1936-7617"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linhan Xia","raw_affiliation_strings":["Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"],"affiliations":[{"raw_affiliation_string":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653168","display_name":"Min Yang","orcid":"https://orcid.org/0000-0002-2319-8086"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingzhan Yang","raw_affiliation_strings":["Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"],"affiliations":[{"raw_affiliation_string":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426903","display_name":"Jingjing Wang","orcid":"https://orcid.org/0009-0003-5543-878X"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Wang","raw_affiliation_strings":["Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"],"affiliations":[{"raw_affiliation_string":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziwei Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziwei Yan","raw_affiliation_strings":["Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"],"affiliations":[{"raw_affiliation_string":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119975750","display_name":"Yakun Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yakun Ren","raw_affiliation_strings":["Sf Technology,Shenzhen,P.R.China"],"affiliations":[{"raw_affiliation_string":"Sf Technology,Shenzhen,P.R.China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119975751","display_name":"Guo Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210102308","display_name":"Lifetech Scientific (China)","ror":"https://ror.org/00qw2t413","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210102308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo Yu","raw_affiliation_strings":["GienTech Technology Co.,Ltd.,Shenzhen,P.R.China"],"affiliations":[{"raw_affiliation_string":"GienTech Technology Co.,Ltd.,Shenzhen,P.R.China","institution_ids":["https://openalex.org/I4210102308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078920845","display_name":"Kai Lei","orcid":"https://orcid.org/0000-0001-9197-895X"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Lei","raw_affiliation_strings":["Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China"],"affiliations":[{"raw_affiliation_string":"Peking University,ICNLab, Shenzhen Graduate School,Shenzhen,P.R.China","institution_ids":["https://openalex.org/I4210128628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5050489444"],"corresponding_institution_ids":["https://openalex.org/I4210128628"],"apc_list":null,"apc_paid":null,"fwci":2.2283,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90955947,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5989999771118164,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5989999771118164,"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/leverage","display_name":"Leverage (statistics)","score":0.5637999773025513},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5467000007629395},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49070000648498535},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48240000009536743},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4593999981880188},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.4108999967575073},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4058000147342682},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.3767000138759613},{"id":"https://openalex.org/keywords/time-complexity","display_name":"Time complexity","score":0.37380000948905945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5979999899864197},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5637999773025513},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5467000007629395},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49070000648498535},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4593999981880188},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2778090530","wikidata":"https://www.wikidata.org/wiki/Q2523931","display_name":"Viewport","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C179145077","wikidata":"https://www.wikidata.org/wiki/Q5154130","display_name":"Communication complexity","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2778037017","wikidata":"https://www.wikidata.org/wiki/Q6351981","display_name":"Kaleidoscope","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icnp65844.2025.11192368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnp65844.2025.11192368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 33rd International Conference on Network Protocols (ICNP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2907492528","https://openalex.org/W2968289224","https://openalex.org/W2968986602","https://openalex.org/W3021314748","https://openalex.org/W3094338163","https://openalex.org/W3121689374","https://openalex.org/W3150389638","https://openalex.org/W4213019189","https://openalex.org/W4224315052","https://openalex.org/W4281490773","https://openalex.org/W4290991577","https://openalex.org/W4296473472","https://openalex.org/W4304080763","https://openalex.org/W4313060559","https://openalex.org/W4318046977","https://openalex.org/W4322766882","https://openalex.org/W4367662893","https://openalex.org/W4387321091","https://openalex.org/W4391590983","https://openalex.org/W4391945358","https://openalex.org/W4392796722","https://openalex.org/W4401113704","https://openalex.org/W4402897234","https://openalex.org/W4402897363","https://openalex.org/W4403152483","https://openalex.org/W4403221502","https://openalex.org/W4403577522","https://openalex.org/W4403826584","https://openalex.org/W4404809244","https://openalex.org/W4404848609","https://openalex.org/W4404918643","https://openalex.org/W4405092734","https://openalex.org/W4405755985","https://openalex.org/W4405784845","https://openalex.org/W4405786528","https://openalex.org/W4405845747","https://openalex.org/W4407129833","https://openalex.org/W4414281281"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"large":[1],"language":[2],"models":[3,72],"(LLMs)":[4],"are":[5],"increasingly":[6],"being":[7],"adopted":[8],"in":[9,27,35,193],"networking":[10,122,194],"research":[11,205],"to":[12,70,90,134,149,185,202],"address":[13],"domain-specific":[14],"challenges.":[15],"However,":[16],"their":[17],"quadratic":[18,92],"time":[19,81],"complexity":[20,93],"and":[21,31,43,109,129,166,206],"substantial":[22],"model":[23,48,100],"sizes":[24],"often":[25],"result":[26],"significant":[28,157],"computational":[29,87,104],"overhead":[30],"memory":[32],"constraints,":[33],"particularly":[34],"resource-constrained":[36],"environments.":[37],"Drawing":[38],"inspiration":[39],"from":[40,67],"the":[41,46,50,75,91,98,187],"efficiency":[42,88,158],"performance":[44,108],"of":[45,94,152,170,173,190],"Deepseek-R1":[47],"within":[49],"knowledge":[51,66,192],"distillation":[52,61],"paradigm,":[53],"this":[54],"paper":[55],"introduces":[56],"Mamba4Net,":[57],"a":[58,161,167],"novel":[59],"cross-architecture":[60],"framework.":[62],"Mamba4Net":[63,116,142],"transfers":[64],"networking-specific":[65],"transformer-based":[68,95,153],"LLMs":[69],"student":[71],"built":[73],"on":[74],"Mamba":[76],"architecture,":[77],"which":[78],"features":[79],"linear":[80],"complexity.":[82],"This":[83],"design":[84],"substantially":[85],"enhances":[86],"compared":[89],"models,":[96],"while":[97],"reduced":[99],"size":[101],"further":[102,204],"minimizes":[103],"demands,":[105],"improving":[106],"overall":[107],"resource":[110],"utilization.":[111],"To":[112],"evaluate":[113],"its":[114],"effectiveness,":[115],"was":[117],"tested":[118],"across":[119],"three":[120],"diverse":[121],"tasks:":[123],"viewport":[124],"prediction,":[125],"adaptive":[126],"bitrate":[127],"streaming,":[128],"cluster":[130],"job":[131],"scheduling.":[132],"Compared":[133],"existing":[135],"methods":[136],"that":[137,174],"do":[138],"not":[139],"leverage":[140],"LLMs,":[141,154],"demonstrates":[143],"superior":[144],"task":[145],"performance.":[146],"Furthermore,":[147],"relative":[148],"direct":[150],"applications":[151],"it":[155],"achieves":[156],"gains,":[159],"including":[160],"throughput":[162],"3.96":[163],"times":[164],"higher":[165],"storage":[168],"footprint":[169],"only":[171],"5.48%":[172],"required":[175],"by":[176],"previous":[177],"LLM-based":[178],"approaches.":[179],"These":[180],"results":[181],"highlight":[182],"Mamba4Net\u2019s":[183],"potential":[184],"enable":[186],"cost-effective":[188],"application":[189],"LLM-derived":[191],"contexts.":[195],"The":[196],"source":[197],"code":[198],"is":[199],"openly":[200],"available":[201],"support":[203],"development.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-14T00:00:00"}