{"id":"https://openalex.org/W7123342453","doi":"https://doi.org/10.1109/cdc57313.2025.11312278","title":"Kalman Bayesian Transformer","display_name":"Kalman Bayesian Transformer","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123342453","doi":"https://doi.org/10.1109/cdc57313.2025.11312278"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037434482","display_name":"Haoming Jing","orcid":"https://orcid.org/0009-0009-9324-2669"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoming Jing","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,Pennsylvania,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,Pennsylvania,United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001259459","display_name":"Oren Wright","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oren Wright","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,Pennsylvania,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,Pennsylvania,United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122853332","display_name":"Jos\u00e9 M. F. Moura","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 M. F. Moura","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,Pennsylvania,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,Pennsylvania,United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084147009","display_name":"Yorie Nakahira","orcid":"https://orcid.org/0000-0003-3324-4602"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yorie Nakahira","raw_affiliation_strings":["Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,Pennsylvania,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Department of Electrical and Computer Engineering,Pittsburgh,Pennsylvania,United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78629078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"198","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.21850000321865082,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.21850000321865082,"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":0.16940000653266907,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.13510000705718994,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6445000171661377},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5648999810218811},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.51910001039505},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48730000853538513},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.48019999265670776},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46399998664855957},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.4562000036239624},{"id":"https://openalex.org/keywords/sequential-estimation","display_name":"Sequential estimation","score":0.3431999981403351},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.3391999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.675599992275238},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6445000171661377},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5648999810218811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217000246047974},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48730000853538513},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.48019999265670776},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46059998869895935},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C86426650","wikidata":"https://www.wikidata.org/wiki/Q7452504","display_name":"Sequential estimation","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.3391999900341034},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C68022304","wikidata":"https://www.wikidata.org/wiki/Q842217","display_name":"Bayes estimator","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5058850646018982}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sequential":[0],"fine-tuning":[1,79],"of":[2,29,95,105,108,140,151],"transformers":[3],"is":[4,45,50,143],"useful":[5],"when":[6,48],"new":[7,33,124],"data":[8,30],"arrive":[9],"sequentially,":[10],"especially":[11],"with":[12],"shifting":[13],"distributions.":[14],"Unlike":[15],"batch":[16],"learning,":[17],"sequential":[18,78,136,149],"learning":[19,58],"demands":[20],"that":[21,76],"training":[22,49],"be":[23,52,63],"stabilized":[24],"despite":[25],"a":[26,73,81,86,152],"small":[27],"amount":[28],"by":[31,65,68,158],"balancing":[32,121],"information":[34,125],"and":[35,57,62,102,119,134,161],"previously":[36],"learned":[37],"knowledge":[38],"in":[39,54],"the":[40,106],"pre-trained":[41,115],"models.":[42],"This":[43],"challenge":[44],"further":[46],"complicated":[47],"to":[51,155],"completed":[53],"latency-critical":[55],"environments":[56],"must":[59],"additionally":[60],"quantify":[61],"mediated":[64],"uncertainty.":[66],"Motivated":[67],"these":[69],"challenges,":[70],"we":[71],"propose":[72],"novel":[74],"method":[75,131,142],"frames":[77],"as":[80,117],"posterior":[82],"inference":[83],"problem":[84],"within":[85],"Bayesian":[87,99],"framework.":[88],"Our":[89],"approach":[90],"integrates":[91],"closed-form":[92],"moment":[93],"propagation":[94],"random":[96],"variables,":[97],"Kalman":[98],"Neural":[100],"Networks,":[101],"Taylor":[103],"approximations":[104],"moments":[107],"softmax":[109],"functions.":[110],"By":[111],"explicitly":[112],"accounting":[113],"for":[114],"models":[116],"priors":[118],"adaptively":[120],"them":[122],"against":[123],"based":[126],"on":[127],"quantified":[128],"uncertainty,":[129],"our":[130,141],"achieves":[132],"robust":[133],"data-efficient":[135],"learning.":[137],"The":[138],"effectiveness":[139],"demonstrated":[144],"through":[145],"numerical":[146],"simulations":[147],"involving":[148],"adaptation":[150],"decision":[153],"transformer":[154],"tasks":[156],"characterized":[157],"distribution":[159],"shifts":[160],"limited":[162],"memory":[163],"resources.":[164]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-01-14T00:00:00"}