{"id":"https://openalex.org/W7164130403","doi":"https://doi.org/10.48550/arxiv.2606.10277","title":"A Unified Adaptive Feature Composition Framework for Multi-Task Generalization in Wireless Foundation Models","display_name":"A Unified Adaptive Feature Composition Framework for Multi-Task Generalization in Wireless Foundation Models","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164130403","doi":"https://doi.org/10.48550/arxiv.2606.10277"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.10277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10277","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":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.2606.10277","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138383066","display_name":"Yuxuan Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138325293","display_name":"Tingting Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Tingting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068255150","display_name":"Kangning Ma","orcid":"https://orcid.org/0000-0002-3310-4637"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Kangning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138360093","display_name":"Liwen Jing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Liwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138366555","display_name":"Yuwei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022186711","display_name":"Mengfan Zheng","orcid":"https://orcid.org/0000-0001-9330-6479"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Mengfan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138357845","display_name":"Li Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Li","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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.3037000000476837,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.3037000000476837,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.07900000363588333,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.07010000199079514,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5008999705314636},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4875999987125397},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.46560001373291016},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45570001006126404},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43689998984336853},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.40220001339912415},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38960000872612},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.3691999912261963},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574999928474426},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48989999294281006},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.46560001373291016},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.40220001339912415},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.3375000059604645},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C104954878","wikidata":"https://www.wikidata.org/wiki/Q1648707","display_name":"Routing protocol","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.10277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10277","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":"doi:10.48550/arxiv.2606.10277","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10277","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Though":[0],"wireless":[1,135,147],"foundation":[2],"models":[3],"(WFMs)":[4],"have":[5],"shown":[6],"strong":[7],"potential":[8],"in":[9,60],"learning":[10],"universal":[11],"channel":[12],"representations,":[13],"their":[14],"adaptation":[15,155],"to":[16,38,107,126,189],"various":[17],"downstream":[18,43,124,191],"tasks":[19,148],"remains":[20],"constrained":[21],"by":[22],"existing":[23],"paradigms.":[24],"Fine-tuning":[25],"strategies":[26],"introduces":[27],"substantial":[28],"computational":[29],"and":[30,99,133,183],"storage":[31],"overhead,":[32],"while":[33,157],"frozen":[34],"feature":[35,54,104],"extraction":[36],"leads":[37],"sub-optimal":[39],"performance":[40],"across":[41],"diverse":[42,190],"tasks.":[44],"To":[45],"address":[46],"this":[47,81],"issue,":[48],"we":[49],"propose":[50],"a":[51,92,101,180],"unified":[52],"adaptive":[53],"composition":[55,105],"framework":[56,179],"for":[57,70,186],"multitask":[58],"generalization":[59],"WFMs,":[61],"where":[62],"the":[63,67,78,84,139,165,177],"key":[64],"component":[65],"is":[66],"Routing":[68],"Adapter":[69],"Feature":[71],"Composition":[72],"(RAFC).":[73],"Instead":[74],"of":[75,95,130,172],"extracting":[76],"only":[77],"final-layer":[79],"output,":[80],"router":[82],"treats":[83],"hidden":[85,97],"states":[86],"from":[87],"different":[88],"Transformer":[89],"depths":[90],"as":[91],"reusable":[93],"pool":[94],"multi-level":[96],"features,":[98],"employs":[100],"lightweight":[102],"task-driven":[103],"network":[106],"generate":[108],"layer-wise":[109],"aggregation":[110],"weights,":[111],"then":[112],"adaptively":[113],"combine":[114],"hierarchical":[115],"representations":[116],"through":[117],"weighted":[118],"summation.":[119],"This":[120],"design":[121],"enables":[122],"each":[123],"task":[125],"access":[127],"suitable":[128],"mixture":[129],"low-,":[131],"mid-,":[132],"high-level":[134],"features":[136],"without":[137],"modifying":[138],"pretrained":[140],"backbone.":[141],"Extensive":[142],"experiments":[143],"on":[144],"four":[145],"representative":[146],"demonstrate":[149],"that":[150],"RAFC":[151],"consistently":[152],"outperforms":[153],"conventional":[154],"baselines":[156],"introducing":[158],"fewer":[159],"than":[160],"50K":[161],"additional":[162],"parameters.":[163],"Moreover,":[164],"learned":[166],"routing":[167],"weights":[168],"provide":[169],"interpretable":[170],"evidence":[171],"task-specific":[173],"layer":[174],"preferences,":[175],"making":[176],"proposed":[178],"low-complexity,":[181],"scalable,":[182],"explainable":[184],"interface":[185],"adapting":[187],"WFMs":[188],"scenarios.":[192]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-11T00:00:00"}