{"id":"https://openalex.org/W7165370558","doi":"https://doi.org/10.48550/arxiv.2606.20538","title":"Multi-Task Bayesian In-Context Learning","display_name":"Multi-Task Bayesian In-Context Learning","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165370558","doi":"https://doi.org/10.48550/arxiv.2606.20538"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.20538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.20538","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.2606.20538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139000057","display_name":"Qingyang Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Qingyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060570681","display_name":"Eric K. Oermann","orcid":"https://orcid.org/0000-0002-1876-5963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oermann, Eric Karl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138988880","display_name":"Kyunghyun Cho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cho, Kyunghyun","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.20730000734329224,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.20730000734329224,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.20309999585151672,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1340000033378601,"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/prior-probability","display_name":"Prior probability","score":0.8037999868392944},{"id":"https://openalex.org/keywords/predictive-inference","display_name":"Predictive inference","score":0.6632999777793884},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6089000105857849},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5498999953269958},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5338000059127808},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.48100000619888306},{"id":"https://openalex.org/keywords/frequentist-inference","display_name":"Frequentist inference","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.8037999868392944},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6747999787330627},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.6632999777793884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6297000050544739},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6089000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914999842643738},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5338000059127808},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5031999945640564},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.41999998688697815},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.3257000148296356},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C37903108","wikidata":"https://www.wikidata.org/wiki/Q4874474","display_name":"Bayesian linear regression","level":4,"score":0.25920000672340393},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.20538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.20538","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.2606.20538","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.20538","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":{"Bayesian":[0,100,154],"predictive":[1,35,56,101],"inference":[2,17,102],"provides":[3],"a":[4,92,109,134,169],"principled":[5],"framework":[6,96],"for":[7,75,97],"uncertainty":[8],"quantification,":[9],"data":[10],"efficiency,":[11],"and":[12,21,39,71,121,144],"robust":[13],"generalization.":[14],"However,":[15],"exact":[16],"is":[18,176],"often":[19],"intractable,":[20],"scalable":[22],"approximations":[23],"may":[24],"remain":[25],"computationally":[26],"expensive":[27],"or":[28],"require":[29],"restrictive":[30],"modeling":[31],"assumptions":[32],"that":[33,103],"degrade":[34],"performance.":[36],"Prior-Data":[37],"Fitted":[38],"in-context":[40,94,112],"models":[41],"have":[42],"recently":[43],"emerged":[44],"as":[45,108],"an":[46],"amortized":[47,98],"alternative":[48],"by":[49],"learning":[50,95],"to":[51,55,64,77,125],"map":[52],"datasets":[53],"directly":[54],"distributions,":[57],"but":[58],"existing":[59],"approaches":[60],"are":[61],"tightly":[62],"coupled":[63],"the":[65,68],"support":[66],"of":[67,111,119,131,136,159],"training":[69],"prior":[70,106,120],"lack":[72],"explicit":[73],"mechanisms":[74],"adapting":[76],"new":[78],"priors":[79,143,145],"at":[80,178],"test":[81],"time,":[82],"resulting":[83],"in":[84],"limited":[85],"robustness":[86],"under":[87],"distribution":[88],"shift.":[89],"We":[90,162],"introduce":[91],"multi-task":[93],"hierarchical":[99],"explicitly":[104],"represents":[105],"information":[107],"prefix":[110],"datasets.":[113],"A":[114],"transformer":[115],"trained":[116],"on":[117,168],"sequences":[118],"target":[122],"tasks":[123],"learns":[124],"adapt":[126],"its":[127,165],"predictions":[128],"across":[129],"families":[130],"priors.":[132],"On":[133],"suite":[135],"evaluations":[137],"with":[138,146],"increasing":[139],"difficulty,":[140],"including":[141],"out-of-meta-distribution":[142],"high-dimensional":[147],"latent":[148],"structures,":[149],"our":[150],"method":[151],"matches":[152],"oracle":[153],"predictors":[155],"while":[156],"being":[157],"orders":[158],"magnitude":[160],"faster.":[161],"further":[163],"demonstrate":[164],"practical":[166],"relevance":[167],"real-world":[170],"spatiotemporal":[171],"temperature":[172],"prediction":[173],"benchmark.":[174],"Code":[175],"available":[177],"https://github.com/martianmartina/multi-task-bayesian-icl/.":[179]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-20T00:00:00"}