{"id":"https://openalex.org/W7148929845","doi":"https://doi.org/10.48550/arxiv.2604.01762","title":"FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models","display_name":"FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148929845","doi":"https://doi.org/10.48550/arxiv.2604.01762"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01762","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01762","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2604.01762","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132916750","display_name":"Juyong Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Juyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132912157","display_name":"Fan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132906757","display_name":"Hong Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132887156","display_name":"Sunghun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Sunghun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132918143","display_name":"Jing Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jing","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/T10028","display_name":"Topic Modeling","score":0.2676999866962433,"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/T10028","display_name":"Topic Modeling","score":0.2676999866962433,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09319999814033508,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.062300000339746475,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5565999746322632},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5460000038146973},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5252000093460083},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4408999979496002},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.41179999709129333},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.3856000006198883},{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.3634999990463257},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3522999882698059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598999738693237},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5565999746322632},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5252000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508899986743927},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4408000111579895},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.41179999709129333},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3296999931335449},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30160000920295715},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01762","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01762","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2604.01762","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01762","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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/7","display_name":"Affordable and clean energy","score":0.46041446924209595}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Parameter-efficient":[0],"fine-tuning":[1,27],"(PEFT)":[2],"has":[3],"emerged":[4],"as":[5,201],"a":[6,125,141],"crucial":[7],"paradigm":[8,206],"for":[9,119,207],"adapting":[10],"large":[11],"language":[12],"models":[13],"(LLMs)":[14],"under":[15],"constrained":[16],"computational":[17],"budgets.":[18],"However,":[19],"standard":[20],"PEFT":[21],"methods":[22],"often":[23],"struggle":[24],"in":[25,57,76,134,180],"multi-task":[26,184],"settings,":[28],"where":[29],"diverse":[30],"optimization":[31],"objectives":[32],"induce":[33],"task":[34],"interference":[35],"and":[36,66,92,150,171,183,204],"limited":[37],"parameter":[38,67],"budgets":[39],"lead":[40],"to":[41,50,128,131],"representational":[42],"deficiency.":[43],"While":[44],"recent":[45],"approaches":[46],"incorporate":[47],"mixture-of-experts":[48],"(MoE)":[49],"alleviate":[51],"these":[52,71,102],"issues,":[53],"they":[54],"predominantly":[55],"operate":[56],"the":[58,77,109,113,195],"spatial":[59,161],"domain,":[60],"which":[61,107],"may":[62],"introduce":[63],"structural":[64],"redundancy":[65],"overhead.":[68],"To":[69],"overcome":[70],"limitations,":[72],"we":[73,104],"reformulate":[74],"adaptation":[75,200],"spectral":[78,81],"domain.":[79],"Our":[80],"analysis":[82],"reveals":[83],"that":[84,93,174],"different":[85],"tasks":[86],"exhibit":[87],"distinct":[88,135],"frequency":[89,98,136],"energy":[90],"distributions,":[91],"LLM":[94,208],"layers":[95],"display":[96],"heterogeneous":[97],"sensitivities.":[99],"Motivated":[100],"by":[101],"insights,":[103],"propose":[105],"FourierMoE,":[106],"integrates":[108],"MoE":[110],"architecture":[111],"with":[112],"inverse":[114],"discrete":[115],"Fourier":[116],"transform":[117],"(IDFT)":[118],"frequency-aware":[120],"adaptation.":[121],"Specifically,":[122],"FourierMoE":[123,175],"employs":[124],"frequency-adaptive":[126],"router":[127],"dispatch":[129],"tokens":[130],"experts":[132],"specialized":[133],"bands.":[137],"Each":[138],"expert":[139,199],"learns":[140],"set":[142],"of":[143,197],"conjugate-symmetric":[144],"complex":[145],"coefficients,":[146],"preserving":[147],"complete":[148],"phase":[149],"amplitude":[151],"information":[152],"while":[153,186],"theoretically":[154],"guaranteeing":[155],"lossless":[156],"IDFT":[157],"reconstruction":[158],"into":[159],"real-valued":[160],"weights.":[162],"Extensive":[163],"evaluations":[164],"across":[165],"28":[166],"benchmarks,":[167],"multiple":[168],"model":[169],"architectures,":[170],"scales":[172],"demonstrate":[173],"consistently":[176],"outperforms":[177],"competitive":[178],"baselines":[179],"both":[181],"single-task":[182],"settings":[185],"using":[187],"significantly":[188],"fewer":[189],"trainable":[190],"parameters.":[191],"These":[192],"results":[193],"highlight":[194],"promise":[196],"spectral-domain":[198],"an":[202],"effective":[203],"parameter-efficient":[205],"fine-tuning.":[209]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-04T00:00:00"}