{"id":"https://openalex.org/W7155078075","doi":"https://doi.org/10.48550/arxiv.2604.16615","title":"Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation","display_name":"Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7155078075","doi":"https://doi.org/10.48550/arxiv.2604.16615"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16615","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.2604.16615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001844508","display_name":"Habibeh Naderi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naderi, Habibeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065059896","display_name":"Behrouz Haji Soleimani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soleimani, Behrouz Haji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042893723","display_name":"Stan Matwin","orcid":"https://orcid.org/0000-0001-6629-8434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matwin, Stan","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.5891000032424927,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.5891000032424927,"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/T10860","display_name":"Speech and Audio Processing","score":0.14069999754428864,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.05550000071525574,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6049000024795532},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5422000288963318},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.49320000410079956},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4767000079154968},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4652000069618225},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.445499986410141},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3790000081062317},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.36390000581741333},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.35530000925064087},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3472999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073000073432922},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6049000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5519000291824341},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.49320000410079956},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43320000171661377},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3790000081062317},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.34060001373291016},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.33480000495910645},{"id":"https://openalex.org/C101104100","wikidata":"https://www.wikidata.org/wiki/Q1063540","display_name":"Heteroscedasticity","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16615","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.2604.16615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16615","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"CoCo-LoRA,":[2],"a":[3,36,87,114,143,197,204,209],"multimodal,":[4],"uncertainty-aware":[5],"parameter-efficient":[6,212],"fine-tuning":[7],"method":[8],"for":[9,214],"text":[10,49],"prediction":[11],"tasks":[12,165],"accompanied":[13],"by":[14,60,85],"audio":[15,108,195],"context.":[16],"Existing":[17],"PEFT":[18,152,175],"approaches":[19],"such":[20,64],"as":[21,65,196,203],"LoRA":[22],"are":[23],"efficient":[24],"but":[25],"typically":[26],"deterministic,":[27],"while":[28,154],"recent":[29],"Bayesian":[30],"low-rank":[31,93],"adapters":[32],"model":[33],"uncertainty":[34,45,58,132,199],"in":[35,78,91,147],"lightweight":[37,122],"way":[38],"yet":[39],"remain":[40],"largely":[41],"unimodal":[42],"and":[43,101,118,133,166,176,211],"condition":[44],"primarily":[46],"on":[47,95,160,182],"internal":[48],"features.":[50],"This":[51],"leaves":[52],"them":[53],"poorly":[54],"equipped":[55],"to":[56,142],"reflect":[57],"driven":[59],"external":[61],"acoustic":[62],"factors":[63],"background":[66],"noise,":[67],"channel":[68],"variability,":[69],"or":[70,172],"speaking":[71],"style,":[72],"which":[73],"can":[74],"materially":[75],"affect":[76],"reliability":[77],"speech-centered":[79],"applications.":[80],"CoCo-LoRA":[81,169],"addresses":[82],"this":[83],"gap":[84],"conditioning":[86],"contextual":[88,198],"variational":[89],"posterior":[90],"the":[92,130,148],"space":[94,117],"both":[96],"local":[97],"text-derived":[98],"adapter":[99,131],"features":[100],"an":[102],"audio-derived":[103],"context":[104,116],"signal.":[105],"A":[106],"pooled":[107],"embedding":[109],"is":[110,140,188],"projected":[111],"once":[112],"into":[113],"shared":[115],"then":[119],"adapted":[120],"through":[121],"layer-wise":[123],"heads,":[124],"enabling":[125],"global-to-local,":[126],"depth-specific":[127],"modulation":[128],"of":[129],"update":[134],"without":[135],"high-dimensional":[136],"multimodal":[137,215],"fusion.":[138],"Stochasticity":[139],"confined":[141],"compact":[144],"latent":[145],"component":[146],"rank":[149],"space,":[150],"preserving":[151],"scalability":[153],"producing":[155],"audio-sensitive,":[156],"heteroscedastic":[157],"uncertainty.":[158],"Based":[159],"our":[161],"evaluations":[162],"across":[163],"diverse":[164],"backbone":[167],"combinations,":[168],"consistently":[170],"matches":[171],"outperforms":[173],"text-only":[174],"conventional":[177],"feature-fusion":[178],"transfer":[179],"baselines,":[180],"particularly":[181],"high-coverage":[183],"labels":[184],"where":[185],"reliable":[186],"adaptation":[187],"critical.":[189],"The":[190],"results":[191],"indicate":[192],"that":[193],"using":[194],"signal,":[200],"rather":[201],"than":[202],"fused":[205],"feature":[206],"stream,":[207],"provides":[208],"robust":[210],"alternative":[213],"low-resource":[216],"prediction.":[217]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-22T00:00:00"}