{"id":"https://openalex.org/W7165810407","doi":"https://doi.org/10.48550/arxiv.2606.24773","title":"Posterior Refinement: Fast Language Generation via Any-Order Flow Maps","display_name":"Posterior Refinement: Fast Language Generation via Any-Order Flow Maps","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7165810407","doi":"https://doi.org/10.48550/arxiv.2606.24773"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.24773","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24773","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.2606.24773","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126512794","display_name":"Manan Agarwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agarwal, Manan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139226514","display_name":"Sheel Shah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shah, Sheel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139259612","display_name":"Chanhyuk Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Chanhyuk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139263218","display_name":"Jaehoon Yoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoo, Jaehoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006022044","display_name":"J W Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jerry","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139292806","display_name":"Seunghoon Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Seunghoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139296794","display_name":"Aditi Raghunathan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raghunathan, Aditi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139219959","display_name":"Jinwoo Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Jinwoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134955794","display_name":"Nicholas M. Boffi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boffi, Nicholas M.","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/T10028","display_name":"Topic Modeling","score":0.3560999929904938,"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/T10028","display_name":"Topic Modeling","score":0.3560999929904938,"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":0.2320999950170517,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.08240000158548355,"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/leverage","display_name":"Leverage (statistics)","score":0.6039999723434448},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5788000226020813},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.525600016117096},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4575999975204468},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.38989999890327454},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.38609999418258667},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3765999972820282},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.3646000027656555},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.35530000925064087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781499981880188},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6039999723434448},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5440999865531921},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40400001406669617},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C2779346075","wikidata":"https://www.wikidata.org/wiki/Q7268763","display_name":"Quality Score","level":3,"score":0.34790000319480896},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.2671999931335449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.24773","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24773","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.2606.24773","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.24773","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":{"Non-autoregressive":[0],"generation":[1],"offers":[2],"a":[3,74,93,105,114,159],"powerful":[4],"paradigm":[5],"for":[6,60,162],"iterative":[7],"refinement,":[8],"allowing":[9],"models":[10,24],"to":[11,26,41,110,123],"recursively":[12],"critique,":[13],"erase":[14],"and":[15,155],"regenerate":[16],"arbitrary":[17],"subsets":[18],"of":[19,69,102,131],"tokens.":[20],"However,":[21],"existing":[22],"non-autoregressive":[23],"fail":[25],"realize":[27],"this":[28,54,78,109],"potential.":[29],"Masked":[30],"Diffusion":[31],"Models":[32,51],"(MDMs)":[33],"suffer":[34],"from":[35],"factorization":[36],"error,":[37],"causing":[38],"sample":[39],"quality":[40],"collapse":[42],"when":[43],"generating":[44,88],"multiple":[45],"tokens":[46],"simultaneously.":[47],"Flow":[48],"Map":[49],"Language":[50],"(FMLMs)":[52],"circumvent":[53],"bottleneck":[55],"via":[56],"joint":[57],"sequence":[58,91],"transport":[59],"excellent":[61],"few-step":[62],"generation,":[63],"but":[64],"sacrifice":[65],"the":[66,89,99,121,129,149],"inference-time":[67,116],"flexibility":[68],"MDMs.":[70],"We":[71,107],"introduce":[72,111],"FMLM+,":[73],"framework":[75],"that":[76,119,143],"bridges":[77],"gap":[79],"by":[80],"equipping":[81],"FMLM":[82,156],"with":[83,134,145],"masking-style":[84],"noise":[85],"schedules.":[86],"While":[87],"full":[90],"in":[92],"single":[94],"step,":[95],"FMLM+":[96,144],"simultaneously":[97],"scores":[98],"global":[100],"consistency":[101],"each":[103],"token":[104],"posteriori.":[106],"leverage":[108],"Posterior":[112,146],"Refinement,":[113],"novel":[115],"refinement":[117],"strategy":[118],"enables":[120],"model":[122],"adaptively":[124],"self-correct":[125],"its":[126],"outputs,":[127],"matching":[128],"performance":[130],"discrete":[132],"baselines":[133],"32x":[135],"fewer":[136],"NFEs.":[137],"Across":[138],"diverse":[139],"benchmarks,":[140],"we":[141],"demonstrate":[142],"Refinement":[147],"improves":[148],"speed--quality":[150],"tradeoff":[151],"over":[152],"both":[153],"MDM":[154],"families,":[157],"providing":[158],"scalable":[160],"foundation":[161],"high-fidelity":[163],"language":[164],"modeling.":[165]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-25T00:00:00"}