{"id":"https://openalex.org/W7216018593","doi":"https://doi.org/10.48550/arxiv.2610.01933","title":"Error-Corrected Inference-Time Scaling for Imperfect Diffusion Models","display_name":"Error-Corrected Inference-Time Scaling for Imperfect Diffusion Models","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7216018593","doi":"https://doi.org/10.48550/arxiv.2610.01933"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.01933","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01933","pdf_url":"https://arxiv.org/pdf/2610.01933","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/2610.01933","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075099826","display_name":"Zuokai Wen","orcid":"https://orcid.org/0000-0001-8053-1626","observed_orcids":["https://orcid.org/0000-0001-8053-1626"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Zuokai","raw_affiliation_strings":["School of Artificial Intelligence , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048873755","display_name":"Louis Grenioux","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4387153999","display_name":"Flatiron Institute","ror":"https://ror.org/00sekdz59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210107338","https://openalex.org/I4387153999"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Grenioux, Louis","raw_affiliation_strings":["Center for Computational Mathematics , Flatiron Institute","School of Mathematical Sciences , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Mathematics , Flatiron Institute","institution_ids":["https://openalex.org/I4387153999"]},{"raw_affiliation_string":"School of Mathematical Sciences , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156184995","display_name":"Weinan E","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E, Weinan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5017947325","display_name":"Jiequn Han","orcid":"https://orcid.org/0000-0002-3553-7313","observed_orcids":["https://orcid.org/0000-0002-3553-7313"]},"institutions":[{"id":"https://openalex.org/I4387153999","display_name":"Flatiron Institute","ror":"https://ror.org/00sekdz59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210107338","https://openalex.org/I4387153999"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han, Jiequn","raw_affiliation_strings":["Center for Computational Mathematics , Flatiron Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Mathematics , Flatiron Institute","institution_ids":["https://openalex.org/I4387153999"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.9848999977111816,"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":0.9848999977111816,"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":0.002099999925121665,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.0017000000225380063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference-time-scaling","display_name":"inference-time scaling","score":0.972000002861023},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.8769999742507935},{"id":"https://openalex.org/keywords/error-correction","display_name":"error correction","score":0.5180000066757202},{"id":"https://openalex.org/keywords/sequential-monte-carlo","display_name":"sequential Monte Carlo","score":0.6940000057220459},{"id":"https://openalex.org/keywords/free-energy-profiles","display_name":"free energy profiles","score":0.5600000023841858},{"id":"https://openalex.org/keywords/alanine-dipeptide","display_name":"alanine dipeptide","score":0.7490000128746033},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.7760000228881836},{"id":"https://openalex.org/keywords/particle-systems","display_name":"particle systems","score":0.8999999761581421}],"concepts":[{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.7246000170707703},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.6173999905586243},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5249000191688538},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.5234000086784363},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.517300009727478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5020999908447266},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4945000112056732},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35120001435279846},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C132725507","wikidata":"https://www.wikidata.org/wiki/Q39879","display_name":"Monte Carlo integration","level":5,"score":0.3411000072956085},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2953000068664551},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C164602753","wikidata":"https://www.wikidata.org/wiki/Q567544","display_name":"Anomalous diffusion","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C86426650","wikidata":"https://www.wikidata.org/wiki/Q7452504","display_name":"Sequential estimation","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C13153151","wikidata":"https://www.wikidata.org/wiki/Q1639846","display_name":"Hybrid Monte Carlo","level":4,"score":0.2540000081062317},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.01933","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01933","pdf_url":"https://arxiv.org/pdf/2610.01933","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.2610.01933","doi":"https://doi.org/10.48550/arxiv.2610.01933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.01933","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:2610.01933","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01933","pdf_url":"https://arxiv.org/pdf/2610.01933","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216018593.pdf","grobid_xml":"https://content.openalex.org/works/W7216018593.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W4311027527","https://openalex.org/W4385327881","https://openalex.org/W4392182166","https://openalex.org/W7108215019","https://openalex.org/W7124460247","https://openalex.org/W7128042036","https://openalex.org/W7160920924","https://openalex.org/W7162508379","https://openalex.org/W7163216262","https://openalex.org/W7165732112","https://openalex.org/W7214895688"],"related_works":["https://openalex.org/W4415335903","https://openalex.org/W7083678743","https://openalex.org/W4414486464","https://openalex.org/W4407759809","https://openalex.org/W7161808386","https://openalex.org/W7214895688","https://openalex.org/W4417539665","https://openalex.org/W4406448016","https://openalex.org/W7161703096","https://openalex.org/W7160890202"],"abstract_inverted_index":{"Inference-time":[0],"scaling":[1,194],"adapts":[2],"pretrained":[3,29,141],"diffusion":[4,87,148],"models":[5,88],"to":[6],"new":[7],"sampling":[8,20,198],"tasks":[9],"without":[10],"additional":[11],"training.":[12],"Existing":[13],"methods":[14,45],"rely":[15],"primarily":[16],"on":[17,27,93,163],"Monte":[18,52,128],"Carlo":[19,53,129],"with":[21,130],"more":[22],"particles,":[23],"yet":[24],"are":[25],"premised":[26],"the":[28,40,58,61,64,68,72,78,94,112,118,135,140,147,153,156],"model":[30,41,119],"being":[31],"exact.":[32],"In":[33],"practice,":[34],"data":[35],"and":[36,43,63,122,150,158,171,182,188],"training":[37],"limitations":[38],"make":[39],"imperfect,":[42,121],"these":[44,91,124],"inherit":[46],"its":[47],"error.":[48],"More":[49],"particles":[50],"reduce":[51],"error":[54,69],"but":[55],"cannot":[56],"remove":[57,134],"mismatch":[59],"between":[60,155],"endpoint":[62,136],"desired":[65],"target":[66,159,180],"or":[67],"in":[70,111],"tracking":[71],"prescribed":[73,108],"probability":[74],"path.":[75],"We":[76,100],"introduce":[77],"Energy-based":[79],"Feynman-Kac":[80,103],"Corrector":[81],"(EBFKC),":[82],"a":[83,97,107,144],"framework":[84],"for":[85],"energy-based":[86],"that":[89,105,175],"corrects":[90],"errors":[92],"fly":[95],"given":[96],"reference":[98],"energy.":[99],"first":[101],"derive":[102],"dynamics":[104,125],"track":[106],"path":[109,149],"exactly":[110],"continuous-time":[113],"population":[114],"limit":[115],"even":[116],"when":[117],"is":[120],"approximate":[123],"using":[126],"sequential":[127],"variance-controlling":[131],"guidance.":[132],"To":[133],"mismatch,":[137],"we":[138],"use":[139],"energy":[142],"as":[143],"surrogate":[145],"along":[146],"progressively":[151],"incorporate":[152],"discrepancy":[154],"learned":[157],"terminal":[160],"energies.":[161],"Experiments":[162],"Gaussian":[164],"mixture":[165],"models,":[166],"particle":[167],"systems,":[168],"alanine":[169,172],"dipeptide,":[170],"tetrapeptide":[173],"show":[174],"our":[176],"method":[177],"closely":[178],"matches":[179],"distributions":[181],"molecular":[183],"free-energy":[184],"profiles":[185],"under":[186],"annealing":[187],"reward":[189],"tilting,":[190],"whereas":[191],"standard":[192],"inference-time":[193],"baselines":[195],"retain":[196],"substantial":[197],"errors.":[199]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}