{"id":"https://openalex.org/W7214926880","doi":"https://doi.org/10.48550/arxiv.2609.37227","title":"Interacting particle guidance for sampling reward-tilted generative priors","display_name":"Interacting particle guidance for sampling reward-tilted generative priors","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214926880","doi":"https://doi.org/10.48550/arxiv.2609.37227"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37227","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37227","pdf_url":"https://arxiv.org/pdf/2609.37227","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/2609.37227","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119915070","display_name":"Adhithyan Kalaivanan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Kalaivanan, Adhithyan","raw_affiliation_strings":["Link\u00f6ping University , Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Link\u00f6ping University , Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153616204","display_name":"Zheng Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhao, Zheng","raw_affiliation_strings":["Link\u00f6ping University , Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Link\u00f6ping University , Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032491456","display_name":"Jens Sj\u00f6lund","orcid":"https://orcid.org/0000-0002-9099-3522","observed_orcids":["https://orcid.org/0000-0002-9099-3522"]},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sj\u00f6lund, Jens","raw_affiliation_strings":["Uppsala University , Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University , Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045048407","display_name":"Fredrik Lindsten","orcid":"https://orcid.org/0000-0003-3749-5820","observed_orcids":["https://orcid.org/0000-0003-3749-5820"]},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Lindsten, Fredrik","raw_affiliation_strings":["Link\u00f6ping University , Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Link\u00f6ping University , Sweden","institution_ids":["https://openalex.org/I102134673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.00019999999494757503,"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":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.6970000267028809},{"id":"https://openalex.org/keywords/flow-based-generative-models","display_name":"flow-based generative models","score":0.828000009059906},{"id":"https://openalex.org/keywords/sequential-monte-carlo","display_name":"sequential Monte Carlo","score":0.9129999876022339},{"id":"https://openalex.org/keywords/weight-degeneracy","display_name":"weight degeneracy","score":0.9279999732971191},{"id":"https://openalex.org/keywords/reproducing-kernel-hilbert-space","display_name":"reproducing kernel Hilbert space","score":0.9430000185966492},{"id":"https://openalex.org/keywords/image-inpainting","display_name":"image inpainting","score":0.7559999823570251},{"id":"https://openalex.org/keywords/conditional-sampling","display_name":"conditional sampling","score":0.6100000143051147}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6837999820709229},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6549999713897705},{"id":"https://openalex.org/C2777727622","wikidata":"https://www.wikidata.org/wiki/Q5251772","display_name":"Degeneracy (biology)","level":2,"score":0.6477000117301941},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.6039999723434448},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.5989999771118164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5853000283241272},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5479000210762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4747999906539917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4708999991416931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4693000018596649},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C170593435","wikidata":"https://www.wikidata.org/wiki/Q4128565","display_name":"Slice sampling","level":4,"score":0.43799999356269836},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.4194999933242798},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.3864000141620636},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.3833000063896179},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.34929999709129333},{"id":"https://openalex.org/C187192777","wikidata":"https://www.wikidata.org/wiki/Q381699","display_name":"Rejection sampling","level":5,"score":0.3433000147342682},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C52483021","wikidata":"https://www.wikidata.org/wiki/Q4827310","display_name":"Auxiliary particle filter","level":5,"score":0.3280999958515167},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.32739999890327454},{"id":"https://openalex.org/C2778517922","wikidata":"https://www.wikidata.org/wiki/Q7140482","display_name":"Particle (ecology)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C27406209","wikidata":"https://www.wikidata.org/wiki/Q6394203","display_name":"Kernel smoother","level":5,"score":0.3057999908924103},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C81692654","wikidata":"https://www.wikidata.org/wiki/Q225926","display_name":"Kriging","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C200695384","wikidata":"https://www.wikidata.org/wiki/Q1739319","display_name":"Kernel regression","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37227","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37227","pdf_url":"https://arxiv.org/pdf/2609.37227","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.2609.37227","doi":"https://doi.org/10.48550/arxiv.2609.37227","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37227","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37227","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37227","pdf_url":"https://arxiv.org/pdf/2609.37227","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/G926497241","display_name":"Machine learning for complex spatio-temporal processes","funder_award_id":"2024-05011","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214926880.pdf","grobid_xml":"https://content.openalex.org/works/W7214926880.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2902858271","https://openalex.org/W4402954781","https://openalex.org/W4414979578","https://openalex.org/W7164171639"],"related_works":["https://openalex.org/W7167014156","https://openalex.org/W7202161899","https://openalex.org/W7161703096","https://openalex.org/W7215947970","https://openalex.org/W6947941759","https://openalex.org/W4387891228","https://openalex.org/W7162430035","https://openalex.org/W4416130940","https://openalex.org/W4415335903","https://openalex.org/W7220362718"],"abstract_inverted_index":{"Inference-time":[0],"steering":[1],"adapts":[2],"pretrained":[3],"diffusion":[4],"and":[5,53,79,112,149,154],"flow-based":[6],"models":[7],"to":[8,12,107,131,137],"new":[9],"tasks,":[10],"e.g.,":[11],"generate":[13],"samples":[14,20],"from":[15,32,40,76,103],"a":[16,33,119,125],"conditional":[17],"distribution":[18,42],"or":[19],"with":[21,93,133,146],"desired":[22],"properties,":[23],"without":[24],"retraining.":[25],"This":[26],"can":[27],"be":[28],"formalized":[29],"as":[30],"sampling":[31,39],"reward-tilted":[34],"generative":[35],"prior.":[36],"As":[37],"exact":[38,68],"this":[41,61],"is":[43,129],"intractable,":[44],"guidance-based":[45],"methods":[46,58],"rely":[47],"on":[48,143,150],"approximations":[49],"producing":[50],"biased":[51],"samples,":[52],"sequential":[54],"Monte":[55],"Carlo":[56],"(SMC)":[57],"correct":[59],"for":[60],"bias":[62],"using":[63],"importance":[64],"weights.":[65],"However,":[66],"while":[67],"in":[69,82,118],"the":[70,104,109,116,141],"large":[71],"particle":[72,80,87],"limit,":[73],"SMC":[74],"suffers":[75],"weight":[77],"degeneracy":[78],"collapse":[81],"practice.":[83],"We":[84,139],"propose":[85],"interacting":[86],"guidance":[88],"(IPG),":[89],"which":[90],"replaces":[91],"reweighting":[92,110],"transport.":[94],"The":[95],"particles":[96],"interact":[97],"through":[98],"an":[99],"additional":[100],"drift,":[101],"derived":[102],"Feynman--Kac":[105],"PDE":[106],"cancel":[108],"term,":[111],"remain":[113],"unweighted.":[114],"Choosing":[115],"drift":[117],"reproducing":[120],"kernel":[121],"Hilbert":[122],"space":[123],"yields":[124],"closed-form":[126],"solution":[127],"that":[128],"cheap":[130],"compute,":[132],"negligible":[134],"overhead":[135],"compared":[136],"SMC.":[138],"demonstrate":[140],"method":[142],"Gaussian":[144],"mixtures":[145],"known":[147],"posteriors,":[148],"high-dimensional":[151],"image":[152],"inpainting":[153],"protein":[155],"structure":[156],"inference":[157],"tasks.":[158]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}