{"id":"https://openalex.org/W7167011869","doi":"https://doi.org/10.48550/arxiv.2607.00162","title":"FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts","display_name":"FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7167011869","doi":"https://doi.org/10.48550/arxiv.2607.00162"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.00162","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00162","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":"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.2607.00162","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139939970","display_name":"Tom Saliencro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saliencro, Tom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139870629","display_name":"Maya Lindqvist","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lindqvist, Maya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120323995","display_name":"Rohan Desai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Desai, Rohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139896855","display_name":"Priya Nair","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nair, Priya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139896567","display_name":"Daniel Whitmore","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Whitmore, Daniel","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3481999933719635,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3481999933719635,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.1386999934911728,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10769999772310257,"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/domain","display_name":"Domain (mathematical analysis)","score":0.49570000171661377},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.47530001401901245},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4596000015735626},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.43050000071525574},{"id":"https://openalex.org/keywords/fourier-series","display_name":"Fourier series","score":0.33869999647140503},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.31310001015663147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6583999991416931},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4596000015735626},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40230000019073486},{"id":"https://openalex.org/C207864730","wikidata":"https://www.wikidata.org/wiki/Q179467","display_name":"Fourier series","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30889999866485596},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.2903999984264374},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.28540000319480896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.00162","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00162","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":"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.2607.00162","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00162","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":"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":[{"score":0.659397304058075,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Parameter-efficient":[0],"fine-tuning":[1],"(PEFT)":[2],"reparameterizes":[3],"weight":[4],"updates":[5],"in":[6,13,25,69,115,229],"a":[7,18,26,39,66,74,93,150,157],"fixed":[8,27],"basis:":[9],"low-rank":[10,113],"adapters":[11],"operate":[12],"the":[14,33,82,89,109,116,136,161,213,221],"spatial":[15,83],"domain,":[16],"while":[17,211],"recent":[19],"line":[20],"of":[21,35,42,64,128,174,195],"spectral":[22,94,202],"methods":[23],"operates":[24],"Fourier":[28,90],"domain.":[29],"We":[30,60],"argue":[31],"that":[32,44,49,78,100,220],"choice":[34],"domain":[36,84,91,117],"is":[37,53,120,149,163],"itself":[38],"design":[40],"degree":[41],"freedom":[43],"should":[45],"be":[46],"learned,":[47],"and":[48,88,123,143,160,186,191,201,208,217,227],"no":[50],"single":[51,151],"basis":[52],"optimal":[54],"across":[55],"tasks,":[56],"layers,":[57],"or":[58],"tokens.":[59],"introduce":[61],"Fractional-Fourier":[62,172,193],"Mixture":[63,173,194],"Experts,":[65],"mixture-of-experts":[67],"adapter":[68],"which":[70,140],"every":[71],"expert":[72],"carries":[73],"learnable":[75],"fractional-Fourier":[76,126],"order":[77,148],"continuously":[79],"interpolates":[80],"between":[81],"(recovering":[85,92],"vanilla":[86],"LoRA)":[87],"adapter).":[95],"Routing":[96],"tokens":[97],"through":[98],"experts":[99,137],"occupy":[101],"different":[102,129],"points":[103],"on":[104,189],"this":[105],"spatial-spectral":[106],"continuum":[107],"lets":[108],"model":[110],"place":[111],"each":[112],"update":[114],"where":[118],"it":[119],"most":[121],"compact,":[122],"--":[124,134,204,210],"because":[125],"operators":[127],"orders":[130,223],"are":[131],"mutually":[132],"incoherent":[133],"makes":[135],"naturally":[138],"decorrelated,":[139],"reduces":[141],"interference":[142],"improves":[144,197],"multi-task":[145],"composition.":[146],"The":[147],"scalar":[152],"per":[153],"expert,":[154],"trained":[155],"with":[156,165],"separate":[158],"optimizer,":[159],"transform":[162],"computed":[164],"an":[166],"$\\mathcal{O}(d\\log":[167],"d)$":[168],"chirp--FFT":[169],"surrogate,":[170],"so":[171],"Experts":[175,196],"adds":[176],"negligible":[177],"cost":[178],"over":[179,198],"standard":[180],"MoE-LoRA.":[181],"Across":[182],"commonsense,":[183],"mathematical,":[184],"code,":[185],"knowledge":[187],"benchmarks":[188],"LLaMA-3.1-8B":[190],"Qwen2.5-7B,":[192],"strong":[199],"MoE-LoRA":[200],"baselines":[203],"including":[205],"FlyLoRA,":[206],"FourierMoE,":[207],"HMoRA":[209],"keeping":[212],"active-parameter":[214],"budget":[215],"small,":[216],"analysis":[218],"shows":[219],"learned":[222],"specialize":[224],"by":[225],"task":[226],"layer":[228],"interpretable":[230],"ways.":[231]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-03T00:00:00"}