{"id":"https://openalex.org/W7160914762","doi":"https://doi.org/10.48550/arxiv.2605.08110","title":"BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models","display_name":"BaLoRA: Bayesian Low-Rank Adaptation of Large Scale Models","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7160914762","doi":"https://doi.org/10.48550/arxiv.2605.08110"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.08110","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08110","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.2605.08110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081391708","display_name":"Dario Coscia","orcid":"https://orcid.org/0000-0001-8833-6833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Coscia, Dario","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054183161","display_name":"Sindy L\u00f6we","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L\u00f6we, Sindy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135935931","display_name":"Max Welling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Welling, Max","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":0.18559999763965607,"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":0.18559999763965607,"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":0.11140000075101852,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.08919999748468399,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6478000283241272},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5751000046730042},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5145999789237976},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.49869999289512634},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.47909998893737793},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4372999966144562},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.41119998693466187},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.4000999927520752}],"concepts":[{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6478000283241272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6032000184059143},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5751000046730042},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.49869999289512634},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.47909998893737793},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4474000036716461},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4332999885082245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41909998655319214},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37619999051094055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C149569020","wikidata":"https://www.wikidata.org/wiki/Q25098598","display_name":"Bayesian average","level":5,"score":0.3571000099182129},{"id":"https://openalex.org/C37903108","wikidata":"https://www.wikidata.org/wiki/Q4874474","display_name":"Bayesian linear regression","level":4,"score":0.3431999981403351},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.3319000005722046},{"id":"https://openalex.org/C71983512","wikidata":"https://www.wikidata.org/wiki/Q7915687","display_name":"Variable-order Bayesian network","level":4,"score":0.31779998540878296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3082999885082245},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.08110","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08110","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.2605.08110","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08110","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Low-Rank":[0],"Adaptation":[1],"(LoRA)":[2],"has":[3],"become":[4],"the":[5,77,85,98],"standard":[6],"for":[7],"fine-tuning":[8,30,102],"large":[9],"pre-trained":[10],"models":[11],"at":[12],"reduced":[13],"computational":[14],"cost.":[15],"However,":[16],"its":[17,39],"low-rank":[18],"point-estimate":[19],"updates":[20],"limit":[21],"expressiveness,":[22],"leave":[23],"a":[24,53,59,134],"persistent":[25],"gap":[26,99,115],"relative":[27],"to":[28,113],"full":[29,101],"accuracy,":[31,96],"and":[32,71,108,140],"provide":[33],"no":[34],"built-in":[35],"uncertainty":[36,82,124],"quantification,":[37],"limiting":[38],"applicability":[40],"in":[41,117],"settings":[42],"where":[43],"reliability":[44],"matters":[45],"as":[46,48],"much":[47],"accuracy.":[49,147],"We":[50],"introduce":[51],"BaLoRA,":[52],"Bayesian":[54,62,78],"extension":[55,79],"of":[56,64,137],"LoRA":[57,65,138],"with":[58,100,130,143],"novel":[60],"input-adaptive":[61],"parameterization":[63],"matrices":[66],"that":[67,126],"adds":[68],"minimal":[69],"parameters":[70],"compute.":[72],"Surprisingly,":[73],"not":[74],"only":[75],"does":[76],"yield":[80],"well-calibrated":[81],"estimates,":[83],"but":[84],"adaptive":[86],"noise":[87],"injection":[88],"underlying":[89],"our":[90],"approach":[91],"also":[92],"significantly":[93],"improves":[94],"prediction":[95,116],"narrowing":[97],"across":[103],"both":[104],"natural":[105],"language":[106],"reasoning":[107],"vision":[109],"tasks.":[110],"When":[111],"applied":[112],"band":[114],"metal-organic":[118],"frameworks,":[119],"BaLoRA":[120],"produces":[121],"zero-shot":[122],"test-time":[123],"estimates":[125],"correlate":[127],"more":[128],"strongly":[129],"model":[131],"error":[132],"than":[133],"trained":[135],"ensemble":[136],"models,":[139],"improve":[141],"monotonically":[142],"compute":[144],"without":[145],"sacrificing":[146]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-13T00:00:00"}