{"id":"https://openalex.org/W7214790822","doi":"https://doi.org/10.48550/arxiv.2609.32941","title":"Generative Priors Conditioned on Natural Language for Bayesian Inversion in PDEs","display_name":"Generative Priors Conditioned on Natural Language for Bayesian Inversion in PDEs","publication_year":2026,"publication_date":"2026-09-26","ids":{"openalex":"https://openalex.org/W7214790822","doi":"https://doi.org/10.48550/arxiv.2609.32941"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32941","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32941","pdf_url":"https://arxiv.org/pdf/2609.32941","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.32941","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153498328","display_name":"Pengyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhang, Pengyu","raw_affiliation_strings":["Department of Engineering University of Cambridge Cambridge , CB3 0FA , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering University of Cambridge Cambridge , CB3 0FA , UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045384249","display_name":"Mark Girolami","orcid":"https://orcid.org/0000-0003-3008-253X","observed_orcids":["https://orcid.org/0000-0003-3008-253X","https://orcid.org/0009-0000-6991-0633"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Girolami, Mark","raw_affiliation_strings":["Department of Engineering University of Cambridge Cambridge , CB3 0FA , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering University of Cambridge Cambridge , CB3 0FA , UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011557874","display_name":"Arnaud Vadeboncoeur","orcid":"https://orcid.org/0000-0003-4124-6763","observed_orcids":["https://orcid.org/0000-0003-4124-6763"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vadeboncoeur, Arnaud","raw_affiliation_strings":["Department of Engineering University of Cambridge Cambridge , CB3 0FA , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering University of Cambridge Cambridge , CB3 0FA , UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.8115000128746033,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.8115000128746033,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.14059999585151672,"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/T10928","display_name":"Probabilistic and Robust Engineering Design","score":0.018400000408291817,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bayesian-inversion","display_name":"Bayesian inversion","score":0.6449999809265137},{"id":"https://openalex.org/keywords/partial-differential-equations","display_name":"partial differential equations","score":0.8220000267028809},{"id":"https://openalex.org/keywords/generative-priors","display_name":"generative priors","score":0.9020000100135803},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"uncertainty quantification","score":0.9169999957084656},{"id":"https://openalex.org/keywords/conditional-diffusion","display_name":"conditional diffusion","score":0.6809999942779541},{"id":"https://openalex.org/keywords/conditional-autoencoder","display_name":"conditional autoencoder","score":0.996999979019165},{"id":"https://openalex.org/keywords/qualitative-data","display_name":"qualitative data","score":0.4000000059604645},{"id":"https://openalex.org/keywords/quantities-of-interest","display_name":"quantities of interest","score":0.7559999823570251},{"id":"https://openalex.org/keywords/steady-state-heat-equation","display_name":"steady-state heat equation","score":0.8180000185966492},{"id":"https://openalex.org/keywords/sensor-data","display_name":"sensor data","score":0.36899998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6427000164985657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849999785423279},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5831000208854675},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5419999957084656},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.43149998784065247},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4260999858379364},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41179999709129333},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C101112237","wikidata":"https://www.wikidata.org/wiki/Q4874481","display_name":"Bayesian statistics","level":4,"score":0.28870001435279846},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C24552861","wikidata":"https://www.wikidata.org/wiki/Q2670177","display_name":"Data assimilation","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32941","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32941","pdf_url":"https://arxiv.org/pdf/2609.32941","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.32941","doi":"https://doi.org/10.48550/arxiv.2609.32941","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32941","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.32941","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32941","pdf_url":"https://arxiv.org/pdf/2609.32941","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1646158229","display_name":null,"funder_award_id":"EP/Y028805/","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2548145559","display_name":"Revolutionising Operational Safety and Economy for High-value Infrastructure using Population-based SHM (ROSEHIPS)","funder_award_id":"EP/W005816/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3055379240","display_name":"Digital Roads","funder_award_id":"EP/V056441/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3693794890","display_name":"Ubiquitous Optical Healthcare Technologies (ubOHT) Programme Grant","funder_award_id":"EP/X037770/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3860585748","display_name":"AI HUB IN GENERATIVE MODELS","funder_award_id":"EP/Y028805/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320005","display_name":"Royal Academy of Engineering","ror":"https://ror.org/0526snb40"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214790822.pdf","grobid_xml":"https://content.openalex.org/works/W7214790822.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2964121744","https://openalex.org/W4224035735","https://openalex.org/W4403818631","https://openalex.org/W4405903187","https://openalex.org/W4414565273","https://openalex.org/W4417351823","https://openalex.org/W7125782207","https://openalex.org/W7151025370","https://openalex.org/W7165936063"],"related_works":["https://openalex.org/W2963313981","https://openalex.org/W7083511821","https://openalex.org/W4313131545","https://openalex.org/W6929343196","https://openalex.org/W3006534708","https://openalex.org/W3013795978","https://openalex.org/W3112689972","https://openalex.org/W4400024311","https://openalex.org/W3167256391","https://openalex.org/W2971666491"],"abstract_inverted_index":{"Inferring":[0],"quantities":[1],"of":[2,49,52,76,133],"interest":[3],"(QoI)":[4],"from":[5,137],"data":[6,25,30,43],"is":[7,69,207,222],"a":[8,73,97,109,130],"central":[9],"task":[10,63],"in":[11,46,66],"Science":[12],"and":[13,26,58,80,128,144,164,169,179,188,200,212,232],"Engineering.":[14],"In":[15],"such":[16,104],"contexts,":[17],"we":[18,64,84,113,155],"often":[19],"have":[20],"access":[21],"to":[22,86,95,141],"both":[23,171],"quantitative":[24,81],"qualitative":[27,42,78,122],"data.":[28,236],"Quantitative":[29],"may":[31,44],"be":[32,45],"represented":[33],"by":[34],"noisy":[35,134],"sensor":[36,135],"measurements,":[37],"simulation":[38],"data,":[39,83],"re-analysis":[40],"data;":[41],"the":[47,70,88,92,118,125,149,165,225],"form":[48],"text":[50,79,123],"descriptions":[51],"experimental":[53],"setups,":[54],"expected":[55],"experiment":[56],"outcomes,":[57],"human-perceived":[59],"system":[60],"behaviours.":[61],"The":[62,220],"address":[65],"this":[67,153],"paper":[68],"following.":[71],"Given":[72],"training":[74,119],"set":[75],"paired":[77],"QoI":[82,218],"learn":[85,96],"exploit":[87],"inherent":[89],"correlation":[90],"between":[91],"two":[93,157],"modalities":[94],"highly":[98],"informative":[99],"data-driven":[100],"natural-language-conditional":[101],"Bayesian":[102,174],"prior,":[103],"that":[105,138],"when":[106],"presented":[107],"with":[108,216],"new":[110,126,139],"physical":[111],"system,":[112,127,140],"can":[114],"coherently":[115],"combine":[116],"(i)":[117],"dataset,":[120],"(ii)":[121],"describing":[124],"(iii)":[129],"small":[131],"number":[132],"readings":[136],"perform":[142],"inference":[143],"uncertainty":[145],"quantification":[146],"(UQ)":[147],"over":[148],"QoI.":[150],"To":[151],"achieve":[152],"task,":[154],"develop":[156],"parallel":[158],"approaches,":[159],"one":[160],"uses":[161],"conditional":[162,167,190,205],"diffusion":[163,206],"other":[166],"autoencoders,":[168],"compare":[170],"against":[172],"classical":[173],"methodology,":[175],"unconditional":[176],"generative":[177],"models":[178],"deterministic":[180],"supervised":[181],"methods.":[182],"Each":[183],"approach":[184,221],"has":[185],"specific":[186],"strengths":[187],"tradeoffs;":[189],"autoencoder":[191],"offers":[192],"theoretical":[193],"tractability,":[194],"allows":[195],"for":[196,209],"fast":[197],"posterior":[198],"sampling,":[199],"provides":[201],"better-calibrated":[202],"UQ,":[203],"whereas":[204],"explored":[208],"greater":[210],"expressiveness":[211],"capturing":[213],"complex":[214],"posteriors":[215],"irregular":[217],"fields.":[219],"tested":[223],"on":[224],"steady-state":[226],"heat":[227],"equation,":[228,231],"damped":[229],"Helmholtz":[230],"UK":[233],"weather":[234],"reanalysis":[235]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}