{"id":"https://openalex.org/W7214899797","doi":"https://doi.org/10.48550/arxiv.2609.37533","title":"E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models","display_name":"E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214899797","doi":"https://doi.org/10.48550/arxiv.2609.37533"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37533","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37533","pdf_url":"https://arxiv.org/pdf/2609.37533","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/2609.37533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137000015","display_name":"Arseny Ivanov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivanov, Arseny","raw_affiliation_strings":["Applied AI Institute , Moscow , Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Institute , Moscow , Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127854430","display_name":"Alexander Kolesov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kolesov, Alexander","raw_affiliation_strings":["Applied AI Institute , Moscow , Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Institute , Moscow , Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056141660","display_name":"Alexander Andreevich Korotin","orcid":"https://orcid.org/0000-0003-4286-925X","observed_orcids":["https://orcid.org/0000-0003-4286-925X","https://orcid.org/0000-0003-3773-342X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korotin, Alexander","raw_affiliation_strings":["Applied AI Institute , Moscow , Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Institute , Moscow , Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153657436","display_name":"Ivan Oseledets","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oseledets, Ivan","raw_affiliation_strings":["Applied AI Institute , Moscow , Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied AI Institute , Moscow , Russia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153625253","display_name":"Mikhail Goncharov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goncharov, Mikhail","raw_affiliation_strings":["1 AXXX , Moscow , Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 AXXX , Moscow , Russia","institution_ids":[]}]}],"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":true,"cited_by_count":1,"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":0.8690999746322632,"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":0.8690999746322632,"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":0.07689999788999557,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.014100000262260437,"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/mixture-of-experts","display_name":"mixture of experts","score":0.8980000019073486},{"id":"https://openalex.org/keywords/masked-diffusion-models","display_name":"masked diffusion models","score":0.8640000224113464},{"id":"https://openalex.org/keywords/expert-routing","display_name":"expert routing","score":0.8169999718666077},{"id":"https://openalex.org/keywords/posterior-collapse","display_name":"posterior collapse","score":0.8050000071525574},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.8330000042915344},{"id":"https://openalex.org/keywords/text-generation","display_name":"text generation","score":0.4129999876022339},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6837999820709229},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5723999738693237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5419999957084656},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.508400022983551},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4066999852657318},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.3458999991416931},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32899999618530273},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.314300000667572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2833999991416931},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37533","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37533","pdf_url":"https://arxiv.org/pdf/2609.37533","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.2609.37533","doi":"https://doi.org/10.48550/arxiv.2609.37533","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37533","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:2609.37533","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37533","pdf_url":"https://arxiv.org/pdf/2609.37533","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/W7214899797.pdf","grobid_xml":"https://content.openalex.org/works/W7214899797.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2547875792","https://openalex.org/W2581624817","https://openalex.org/W3177150392","https://openalex.org/W4387964173","https://openalex.org/W4403854036","https://openalex.org/W4404317990","https://openalex.org/W4407679583","https://openalex.org/W4415336572","https://openalex.org/W7131391977","https://openalex.org/W7133299406","https://openalex.org/W7160202939","https://openalex.org/W7162434238","https://openalex.org/W7167058132"],"related_works":["https://openalex.org/W7170188036","https://openalex.org/W7160907622","https://openalex.org/W4416959386","https://openalex.org/W7127380516","https://openalex.org/W7152030908","https://openalex.org/W4415334935","https://openalex.org/W7131076213","https://openalex.org/W7162295573","https://openalex.org/W7150718528","https://openalex.org/W4385569744"],"abstract_inverted_index":{"Masked":[0],"diffusion":[1],"models":[2],"(MDMs)":[3],"generate":[4],"sequences":[5],"by":[6,95],"progressively":[7],"unmasking":[8],"several":[9],"tokens":[10],"per":[11],"denoising":[12],"step,":[13],"but":[14,59],"their":[15],"reverse":[16,81],"process":[17,82],"is":[18,70],"typically":[19],"factorized":[20,87,110,125],"over":[21,34,89,108,124],"positions,":[22,58],"limiting":[23],"sample":[24],"quality":[25],"in":[26],"the":[27,68,80,96,109],"few-step":[28,122],"regime":[29],"where":[30,67],"diffusion's":[31],"speed":[32],"advantage":[33],"autoregressive":[35],"decoding":[36],"matters":[37],"most.":[38],"A":[39],"recent":[40],"line":[41],"of":[42,86,99],"work":[43],"introduces":[44],"a":[45,51,84,90,100],"continuous":[46],"Gaussian":[47],"latent,":[48],"trained":[49],"as":[50,83],"variational":[52],"autoencoder,":[53],"to":[54,64],"capture":[55],"correlations":[56],"across":[57],"such":[60],"approaches":[61],"are":[62],"prone":[63],"posterior":[65],"collapse,":[66],"latent":[69,93],"silently":[71],"ignored.":[72],"We":[73],"propose":[74],"Enhanced":[75],"Mixture-of-Experts":[76,101],"(E-MoE),":[77],"which":[78],"builds":[79],"mixture":[85],"distributions":[88],"discrete":[91],"shared":[92],"given":[94],"expert-routing":[97],"decisions":[98],"(MoE)":[102],"backbone,":[103],"without":[104],"increasing":[105],"active":[106],"parameters":[107],"baseline.":[111],"Across":[112],"synthetic":[113],"multi-modal":[114],"benchmarks,":[115],"binarized":[116],"MNIST,":[117],"and":[118],"LM1B,":[119],"E-MoE":[120],"improves":[121],"generation":[123],"baselines.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}