{"id":"https://openalex.org/W7160502145","doi":"https://doi.org/10.48550/arxiv.2605.04504","title":"SpecPL: Disentangling Spectral Granularity for Prompt Learning","display_name":"SpecPL: Disentangling Spectral Granularity for Prompt Learning","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160502145","doi":"https://doi.org/10.48550/arxiv.2605.04504"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.04504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04504","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.2605.04504","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135566691","display_name":"Jingtao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jingtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062463711","display_name":"Xirui Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Xirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067176504","display_name":"Feiyang Huang","orcid":"https://orcid.org/0000-0002-7241-1509"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Feiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5038133707","display_name":"Lai-Man Po","orcid":"https://orcid.org/0000-0002-5185-1492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Po, Lai-Man","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5877000093460083,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5877000093460083,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.24709999561309814,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.030899999663233757,"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/granularity","display_name":"Granularity","score":0.828000009059906},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.5641000270843506},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5511999726295471},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5235000252723694},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.29750001430511475}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.828000009059906},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6744999885559082},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.5641000270843506},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5511999726295471},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5235000252723694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49480000138282776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C2779681140","wikidata":"https://www.wikidata.org/wiki/Q47433","display_name":"Banknote","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2655999958515167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.04504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04504","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.2605.04504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.04504","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":[{"id":"https://metadata.un.org/sdg/10","score":0.6428885459899902,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"prompt":[1,46],"learning":[2,47],"for":[3,29,40],"VLMs":[4],"exhibits":[5],"a":[6,49,60,118,141],"modality":[7],"asymmetry,":[8],"predominantly":[9],"optimizing":[10],"text":[11,81],"tokens":[12],"while":[13],"still":[14],"relying":[15],"on":[16,133],"frozen":[17,61,76],"visual":[18,65,109],"encoder":[19],"as":[20,117],"holistic":[21],"extractor":[22],"and":[23,71,127],"neglecting":[24],"the":[25,104,160,163],"spectral":[26,51,153],"granularity":[27,110],"essential":[28],"fine-grained":[30,90],"discrimination.":[31],"To":[32],"bridge":[33],"this,":[34],"we":[35,58,102],"introduce":[36],"Disentangling":[37],"Spectral":[38],"Granularity":[39],"Prompt":[41],"Learning":[42],"(SpecPL),":[43],"which":[44],"approaches":[45],"from":[48,111],"novel":[50],"perspective":[52],"via":[53,129],"Counterfactual":[54],"Granule":[55],"Supervision.":[56],"Specifically,":[57],"leverage":[59],"VAE":[62],"to":[63,83,106],"decompose":[64],"signals":[66],"into":[67],"semantic":[68,112],"low-frequency":[69,85],"bands":[70],"granular":[72],"high-frequency":[73,100],"details.":[74],"A":[75],"Visual":[77],"Semantic":[78],"Bank":[79],"anchors":[80],"representations":[82],"universal":[84,119],"invariants,":[86],"mitigating":[87],"overfitting.":[88],"Crucially,":[89],"discrimination":[91],"is":[92,167],"driven":[93],"by":[94,98],"counterfactual":[95,156],"granule":[96],"training:":[97],"permuting":[99],"signals,":[101],"compel":[103],"model":[105],"explicitly":[107],"distinguish":[108],"invariance.":[113],"Uniquely,":[114],"SpecPL":[115],"serves":[116],"plug-and-play":[120],"booster,":[121],"revitalizing":[122],"text-oriented":[123],"baselines":[124],"like":[125],"CoOp":[126],"MaPLe":[128],"visual-side":[130],"guidance.":[131],"Experiments":[132],"11":[134],"benchmarks":[135],"demonstrate":[136],"competitive":[137],"state-of-the-art":[138],"performance,":[139],"achieving":[140],"new":[142],"performance":[143],"ceiling":[144],"of":[145],"81.51\\%":[146],"harmonic-mean":[147],"accuracy.":[148],"These":[149],"results":[150],"validate":[151],"that":[152],"disentanglement":[154],"with":[155],"supervision":[157],"effectively":[158],"bridges":[159],"gap":[161],"in":[162],"stability-generalization":[164],"trade-off.":[165],"Code":[166],"released":[168],"at":[169],"https://github.com/Mlrac1e/SpecPL-Prompt-Learning.":[170]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-08T00:00:00"}