{"id":"https://openalex.org/W7138300466","doi":"https://doi.org/10.48550/arxiv.2603.13330","title":"RBF-Solver: A Multistep Sampler for Diffusion Probabilistic Models via Radial Basis Functions","display_name":"RBF-Solver: A Multistep Sampler for Diffusion Probabilistic Models via Radial Basis Functions","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7138300466","doi":"https://doi.org/10.48550/arxiv.2603.13330"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.13330","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13330","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":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.2603.13330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128178030","display_name":"Soochul Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Soochul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109263531","display_name":"Yeon Ju Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Yeon Ju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015188198","display_name":"Seongjin Yoon","orcid":"https://orcid.org/0000-0002-3487-3497"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoon, SeongJin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129709092","display_name":"Jiyub Shin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Jiyub","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129692127","display_name":"Juhee Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Juhee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034889119","display_name":"SeongWoon Jo","orcid":"https://orcid.org/0000-0002-1230-9086"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jo, Seongwoon","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":0.9361000061035156,"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":0.9361000061035156,"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":0.006300000008195639,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.006300000008195639,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6324999928474426},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.498199999332428},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4763000011444092},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4537000060081482},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.44999998807907104},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4165000021457672},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4047999978065491},{"id":"https://openalex.org/keywords/radial-basis-function","display_name":"Radial basis function","score":0.4018000066280365}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6324999928474426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5701000094413757},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4941999912261963},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4763000011444092},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.45190000534057617},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4426000118255615},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43720000982284546},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4165000021457672},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4047999978065491},{"id":"https://openalex.org/C98856871","wikidata":"https://www.wikidata.org/wiki/Q1588488","display_name":"Radial basis function","level":3,"score":0.4018000066280365},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C60782215","wikidata":"https://www.wikidata.org/wiki/Q3333679","display_name":"Probabilistic method","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.13330","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13330","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.13330","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13330","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":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":{"Diffusion":[0,189],"probabilistic":[1],"models":[2],"(DPMs)":[3],"are":[4,198],"widely":[5],"adopted":[6],"for":[7,46],"their":[8,13,29],"outstanding":[9],"generative":[10],"fidelity,":[11],"yet":[12],"sampling":[14,36,82],"is":[15],"computationally":[16],"demanding.":[17],"Polynomial-based":[18],"multistep":[19,57],"samplers":[20,137,146],"mitigate":[21],"this":[22,51],"cost":[23],"by":[24],"accelerating":[25],"inference;":[26],"however,":[27],"despite":[28],"theoretical":[30],"accuracy":[31],"guarantees,":[32],"they":[33],"generate":[34],"the":[35,90,100,108,119,148,157,187,201],"trajectory":[37],"according":[38],"to":[39,89,107,118,173,212],"a":[40,56,192,206],"predefined":[41],"scheme,":[42],"providing":[43],"no":[44],"flexibility":[45],"further":[47,171],"optimization.":[48],"To":[49],"address":[50],"limitation,":[52],"we":[53],"propose":[54],"RBF-Solver,":[55],"diffusion":[58],"sampler":[59],"that":[60],"interpolates":[61],"model":[62,190],"evaluations":[63,169],"with":[64,114,156,166,175,186],"Gaussian":[65,76,122],"radial":[66],"basis":[67],"functions":[68],"(RBFs).":[69],"By":[70],"leveraging":[71],"learnable":[72],"shape":[73,101],"parameters":[74,102],"in":[75,147,200,209],"RBFs,":[77,123],"RBF-Solver":[78,105,124,142],"explicitly":[79],"follows":[80],"optimal":[81],"trajectories.":[83],"At":[84,94],"first":[85],"order,":[86],"it":[87,160],"reduces":[88],"Euler":[91],"method":[92],"(DDIM).":[93],"second":[95],"order":[96,132],"or":[97,133],"higher,":[98,134],"as":[99],"approach":[103],"infinity,":[104],"converges":[106],"Adams":[109],"method,":[110],"ensuring":[111],"its":[112],"compatibility":[113],"existing":[115],"samplers.":[116,214],"Owing":[117],"locality":[120],"of":[121,164],"maintains":[125],"high":[126],"image":[127],"fidelity":[128],"even":[129],"at":[130,191],"fourth":[131],"where":[135],"previous":[136],"deteriorate.":[138],"For":[139,179],"unconditional":[140],"generation,":[141],"consistently":[143],"outperforms":[144],"polynomial-based":[145,213],"high-NFE":[149],"regime":[150],"(NFE":[151],">=":[152],"15).":[153],"On":[154],"CIFAR-10":[155],"Score-SDE":[158],"model,":[159],"achieves":[161],"an":[162],"FID":[163,210],"2.87":[165],"15":[167],"function":[168,177],"and":[170],"improves":[172],"2.48":[174],"40":[176],"evaluations.":[178],"conditional":[180],"ImageNet":[181],"256":[182,184],"x":[183],"generation":[185],"Guided":[188],"guidance":[193],"scale":[194],"8.0,":[195],"substantial":[196],"gains":[197],"achieved":[199],"low-NFE":[202],"range":[203],"(5-10),":[204],"yielding":[205],"16.12-33.73%":[207],"reduction":[208],"relative":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}