{"id":"https://openalex.org/W7222523950","doi":"https://doi.org/10.48550/arxiv.2610.21061","title":"Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion","display_name":"Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion","publication_year":2026,"publication_date":"2026-10-15","ids":{"openalex":"https://openalex.org/W7222523950","doi":"https://doi.org/10.48550/arxiv.2610.21061"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.21061","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.21061","pdf_url":"https://arxiv.org/pdf/2610.21061","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/2610.21061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5158920607","display_name":"Renxiang Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Renxiang","raw_affiliation_strings":["Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158904477","display_name":"Yuchen Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4388446366","display_name":"Indiana University Indianapolis","ror":"https://ror.org/03eftgw80","country_code":"US","type":"education","lineage":["https://openalex.org/I4388446366","https://openalex.org/I592451"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang, Yuchen","raw_affiliation_strings":["Department of Electrical and Computer Engineering , The Ohio State University , Columbus , OH , 43210 , USA","Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA","Luddy School of Informatics, Computing, and Engineering , Indiana University Indianapolis , Indianapolis , IN , 46202 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , The Ohio State University , Columbus , OH , 43210 , USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering , Indiana University Indianapolis , Indianapolis , IN , 46202 , USA","institution_ids":["https://openalex.org/I4388446366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158905717","display_name":"Yingbin Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4388446366","display_name":"Indiana University Indianapolis","ror":"https://ror.org/03eftgw80","country_code":"US","type":"education","lineage":["https://openalex.org/I4388446366","https://openalex.org/I592451"]},{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]},{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang, Yingbin","raw_affiliation_strings":["Department of Electrical and Computer Engineering , The Ohio State University , Columbus , OH , 43210 , USA","Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA","Luddy School of Informatics, Computing, and Engineering , Indiana University Indianapolis , Indianapolis , IN , 46202 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , The Ohio State University , Columbus , OH , 43210 , USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering , Indiana University Indianapolis , Indianapolis , IN , 46202 , USA","institution_ids":["https://openalex.org/I4388446366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035752536","display_name":"Ness B. Shroff","orcid":"https://orcid.org/0000-0002-4606-6879","observed_orcids":["https://orcid.org/0000-0002-4606-6879"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shroff, Ness","raw_affiliation_strings":["Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081715462","display_name":"Lifeng Lai","orcid":"https://orcid.org/0000-0002-9493-8248","observed_orcids":["https://orcid.org/0000-0002-9493-8248"]},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lai, Lifeng","raw_affiliation_strings":["Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering , University of California , Davis , Davis , CA , 95616 , USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"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":0.5907999873161316,"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":0.5907999873161316,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2506999969482422,"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/T10028","display_name":"Topic Modeling","score":0.05609999969601631,"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/discrete-diffusion-models","display_name":"discrete diffusion models","score":0.9610000252723694},{"id":"https://openalex.org/keywords/text-infilling","display_name":"text infilling","score":0.9269999861717224},{"id":"https://openalex.org/keywords/sentence-completion","display_name":"sentence completion","score":0.9860000014305115},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"sampling bias","score":0.503000020980835}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5979999899864197},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.45249998569488525},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4154999852180481},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.39629998803138733},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.36399999260902405},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3578000068664551},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35010001063346863},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C21430997","wikidata":"https://www.wikidata.org/wiki/Q5159279","display_name":"Conditional variance","level":4,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.21061","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.21061","pdf_url":"https://arxiv.org/pdf/2610.21061","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.2610.21061","doi":"https://doi.org/10.48550/arxiv.2610.21061","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.21061","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:2610.21061","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.21061","pdf_url":"https://arxiv.org/pdf/2610.21061","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/W7222523950.pdf","grobid_xml":"https://content.openalex.org/works/W7222523950.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4319240915","https://openalex.org/W4403621992","https://openalex.org/W4406549379"],"related_works":["https://openalex.org/W4403580065","https://openalex.org/W4409347549","https://openalex.org/W7090709548","https://openalex.org/W7221508438","https://openalex.org/W7171556953","https://openalex.org/W4404167116","https://openalex.org/W7170580859","https://openalex.org/W7133185417","https://openalex.org/W4387964173","https://openalex.org/W7129339926"],"abstract_inverted_index":{"Discrete":[0],"diffusion":[1,46,89],"models":[2,90],"have":[3],"become":[4],"a":[5,14,32,41,57,73,93,108,140,158],"powerful":[6],"framework":[7],"for":[8,86,164],"modeling":[9],"complex":[10],"discrete":[11,45,88],"distributions":[12],"across":[13],"range":[15],"of":[16,193],"applications.":[17],"While":[18],"theoretical":[19,84],"convergence":[20],"guarantees":[21],"depend":[22],"on":[23,60,153],"consistency":[24],"between":[25],"the":[26,61,82,102,129,146,171,179,191,194],"target":[27,75],"and":[28,91,120,134,150,187],"training":[29],"distributions,":[30],"such":[31,107],"case":[33],"rarely":[34],"holds":[35],"in":[36,44],"practice,":[37],"making":[38],"score":[39],"mismatch":[40],"central":[42],"challenge":[43],"sampling.":[47],"This":[48],"is":[49,64],"particularly":[50],"relevant":[51],"to":[52,70],"zero-shot":[53],"conditional":[54,74],"generation,":[55],"where":[56],"model":[58],"trained":[59],"unconditional":[62,180],"distribution":[63],"directly":[65],"reused":[66],"at":[67],"inference":[68],"time":[69],"sample":[71],"from":[72],"distribution.":[76],"In":[77],"this":[78,154],"paper,":[79],"we":[80,127,156],"provide":[81],"first":[83],"analysis":[85,111],"score-mismatched":[87],"derive":[92],"general":[94,122],"KL":[95],"divergence":[96],"upper":[97],"bound":[98],"that":[99,136,143,170],"clearly":[100],"identifies":[101],"additional":[103],"bias":[104,141],"caused":[105],"by":[106,178],"mismatch.":[109],"Our":[110],"covers":[112],"partial-observation":[113],"constraints,":[114],"including":[115],"text":[116],"infilling,":[117],"sentence":[118],"completion,":[119],"more":[121],"coordinatewise":[123,165],"set":[124,166],"constraints.":[125,167],"Specifically,":[126],"analyze":[128],"classical":[130],"Conditional":[131],"SEDD":[132],"sampler":[133,163],"show":[135,169],"it":[137],"can":[138,174],"incur":[139],"term":[142],"scales":[144],"with":[145,182],"dimension,":[147],"vocabulary":[148],"size,":[149],"compatibility.":[151],"Based":[152],"analysis,":[155],"propose":[157],"Randomized":[159],"Hard":[160],"Clamping":[161],"(RHC)":[162],"We":[168],"assignment":[172],"probabilities":[173],"be":[175],"expressed":[176],"exactly":[177],"scores":[181],"absorbing":[183],"rate.":[184],"Finally,":[185],"numerical":[186],"real-data":[188],"experiments":[189],"demonstrate":[190],"effectiveness":[192],"proposed":[195],"RHC":[196],"sampler.":[197]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-17T00:00:00"}