{"id":"https://openalex.org/W7160649904","doi":"https://doi.org/10.48550/arxiv.2605.06553","title":"Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance","display_name":"Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160649904","doi":"https://doi.org/10.48550/arxiv.2605.06553"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.06553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06553","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.06553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092172038","display_name":"Gal Vinograd","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinograd, Gal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015308298","display_name":"Idan Achituve","orcid":"https://orcid.org/0000-0002-1388-9182"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Achituve, Idan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053007211","display_name":"Ethan Fetaya","orcid":"https://orcid.org/0000-0003-3125-1665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fetaya, Ethan","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8863999843597412,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8863999843597412,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.01510000042617321,"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/T11448","display_name":"Face recognition and analysis","score":0.010900000110268593,"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/marginal-distribution","display_name":"Marginal distribution","score":0.551800012588501},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4950999915599823},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.49410000443458557},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.4740000069141388},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.42309999465942383},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.40689998865127563},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.38670000433921814},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.36329999566078186},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.36309999227523804}],"concepts":[{"id":"https://openalex.org/C165216359","wikidata":"https://www.wikidata.org/wiki/Q670653","display_name":"Marginal distribution","level":3,"score":0.551800012588501},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.4740000069141388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4717999994754791},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45329999923706055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43479999899864197},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.4311000108718872},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.42309999465942383},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40139999985694885},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3513000011444092},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3287999927997589},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C96469262","wikidata":"https://www.wikidata.org/wiki/Q1324364","display_name":"Homogeneous space","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C121448008","wikidata":"https://www.wikidata.org/wiki/Q1755722","display_name":"Large eddy simulation","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.06553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06553","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.06553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.06553","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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,46],"present":[1],"EDDY":[2,26,118],"(Exact-marginal":[3],"Diversification":[4],"via":[5],"Divergence-free":[6],"dYnamics),":[7],"a":[8],"guidance":[9,85],"mechanism":[10],"for":[11],"diffusion":[12],"and":[13,106,113],"flow":[14],"matching":[15],"models":[16],"that":[17,36,117],"promotes":[18],"diversity":[19,66,120],"among":[20],"samples":[21],"generated":[22],"while":[23,40,72,121],"maintaining":[24,122],"quality.":[25],"exploits":[27],"symmetries":[28],"of":[29],"the":[30,42,58,68,84],"Fokker-Planck":[31],"equation,":[32],"using":[33],"drift":[34],"perturbations":[35],"change":[37],"particle":[38,70],"trajectories":[39],"preserving":[41,73],"evolving":[43],"marginal":[44,76],"distribution.":[45],"instantiate":[47],"this":[48],"principle":[49],"through":[50],"kernel-based":[51],"anti-symmetric":[52],"pairwise":[53],"matrix":[54],"fields,":[55],"constructed":[56],"from":[57],"repulsive":[59],"directions.":[60],"The":[61],"resulting":[62],"divergence-free":[63],"dynamics":[64],"promote":[65],"at":[67],"joint":[69],"level":[71],"each":[74],"particle's":[75],"distribution":[77],"without":[78],"any":[79],"additional":[80],"training.":[81],"As":[82],"computing":[83],"can":[86],"be":[87],"computationally":[88],"expensive":[89],"in":[90],"cases":[91],"such":[92],"as":[93,103],"text-to-image":[94,114],"generation":[95,115],"with":[96],"perceptual":[97],"embeddings,":[98],"we":[99],"propose":[100],"practical":[101],"approximations":[102],"an":[104],"effective":[105],"efficient":[107],"solution.":[108],"Experiments":[109],"on":[110],"synthetic":[111],"distributions":[112],"show":[116],"improves":[119],"strong":[123],"distributional":[124],"fidelity":[125],"compared":[126],"to":[127],"common":[128],"baselines.":[129]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-09T00:00:00"}