{"id":"https://openalex.org/W7134852357","doi":"https://doi.org/10.48550/arxiv.2603.07860","title":"Guess & Guide: Gradient-Free Zero-Shot Diffusion Guidance","display_name":"Guess & Guide: Gradient-Free Zero-Shot Diffusion Guidance","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134852357","doi":"https://doi.org/10.48550/arxiv.2603.07860"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.07860","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128685775","display_name":"Abduragim Shtanchaev","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shtanchaev, Abduragim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128680139","display_name":"Albina Ilina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilina, Albina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060545264","display_name":"Yazid Janati","orcid":"https://orcid.org/0000-0002-7271-4104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Janati, Yazid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007961564","display_name":"Arip Asadulaev","orcid":"https://orcid.org/0000-0002-2581-935X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asadulaev, Arip","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128641162","display_name":"Martin Tak\u00e1c","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tak\u00e1c, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128654719","display_name":"Eric Moulines","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moulines, Eric","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5128685775"],"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.4189999997615814,"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":0.4189999997615814,"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":0.24560000002384186,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.056299999356269836,"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":0.7366999983787537},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5814999938011169},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5424000024795532},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.5382000207901001},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4474000036716461},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4316999912261963},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4300999939441681},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.4115999937057495},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.3862999975681305}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7366999983787537},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5652999877929688},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4474000036716461},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44290000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4388999938964844},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4300999939441681},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.4115999937057495},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.3862999975681305},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.38190001249313354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3790000081062317},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3650999963283539},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.35740000009536743},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3547999858856201},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C133514767","wikidata":"https://www.wikidata.org/wiki/Q5532448","display_name":"Generalized Pareto distribution","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.07860","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.07860","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07860","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.07860","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"Pretrained":[0],"diffusion":[1],"models":[2],"serve":[3],"as":[4],"effective":[5],"priors":[6,12],"for":[7,26,120],"Bayesian":[8,121],"inverse":[9,81,122],"problems.":[10,123],"These":[11],"enable":[13],"zero-shot":[14],"generation":[15],"by":[16],"sampling":[17],"from":[18],"the":[19,24,66,72,92,98,104,114],"conditional":[20],"distribution,":[21],"which":[22],"avoids":[23],"need":[25,67],"task-specific":[27],"retraining.":[28],"However,":[29],"a":[30,51,60],"major":[31],"limitation":[32],"of":[33],"existing":[34],"methods":[35],"is":[36],"their":[37],"reliance":[38],"on":[39],"surrogate":[40,63],"likelihoods":[41],"that":[42,64,88],"require":[43],"vector-Jacobian":[44],"products":[45],"at":[46],"each":[47],"denoising":[48],"step,":[49],"creating":[50],"substantial":[52],"computational":[53],"burden.":[54],"To":[55],"address":[56],"this,":[57],"we":[58,112],"introduce":[59],"lightweight":[61],"likelihood":[62],"eliminates":[65],"to":[68,78],"calculate":[69],"gradients":[70],"through":[71],"denoiser":[73],"network.":[74],"This":[75],"enables":[76],"us":[77],"handle":[79],"diverse":[80],"problems":[82],"without":[83],"backpropagation":[84],"overhead.":[85],"Experiments":[86],"confirm":[87],"using":[89],"our":[90,101],"method,":[91],"inference":[93],"cost":[94],"drops":[95],"dramatically.":[96],"At":[97],"same":[99],"time,":[100],"approach":[102],"delivers":[103],"highest":[105],"results":[106],"in":[107],"multiple":[108],"tasks.":[109],"Broadly":[110],"speaking,":[111],"propose":[113],"fastest":[115],"and":[116],"Pareto":[117],"optimal":[118],"method":[119]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-03-11T00:00:00"}