{"id":"https://openalex.org/W7167053939","doi":"https://doi.org/10.48550/arxiv.2607.00371","title":"MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts","display_name":"MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7167053939","doi":"https://doi.org/10.48550/arxiv.2607.00371"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.00371","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00371","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,"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.2607.00371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100577502","display_name":"Nuoyan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Nuoyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139933158","display_name":"Zhijun Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Zhijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139893049","display_name":"Lei Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139865906","display_name":"Kun Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107311606","display_name":"J Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041816949","display_name":"N L Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Nannan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139863213","display_name":"Xinghao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xinghao","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":0.8650000095367432,"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":0.8650000095367432,"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":0.050200000405311584,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03319999948143959,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.8429999947547913},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6618000268936157},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6503000259399414},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5745999813079834},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4952999949455261},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4693000018596649},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.374099999666214},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.37380000948905945}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8429999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697700023651123},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6618000268936157},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6503000259399414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6219000220298767},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5745999813079834},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4952999949455261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48840001225471497},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3587000072002411},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.33410000801086426},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.271699994802475},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.00371","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00371","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,"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.2607.00371","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00371","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,"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":{"Visual":[0],"AutoRegressive":[1],"modeling":[2,102],"(VAR)":[3],"has":[4],"pioneered":[5],"a":[6,44,78,118,150,168,173],"coarse-to-fine":[7],"multi-scale":[8,26],"autoregressive":[9,57],"generative":[10],"paradigm,":[11],"demonstrating":[12],"strong":[13],"capabilities":[14],"in":[15,25,177],"image":[16],"generation.":[17],"However,":[18],"VAR":[19,126],"still":[20],"suffers":[21],"from":[22],"inherent":[23],"deficiencies":[24],"representation":[27,93],"learning.":[28],"Specifically,":[29],"lower":[30],"scales":[31,38,48,63,105],"primarily":[32],"capture":[33],"global":[34],"semantics,":[35],"while":[36,158],"higher":[37],"focus":[39],"on":[40],"fine-grained":[41],"details.":[42],"Employing":[43],"shared":[45],"architecture":[46],"across":[47,95],"induces":[49],"optimization":[50],"conflicts.":[51],"Moreover,":[52,180],"due":[53],"to":[54,124,154],"the":[55,69,125,143,155,163,181],"causal":[56],"process,":[58],"inaccurate":[59],"semantics":[60],"at":[61,103],"early":[62,104],"can":[64],"propagate":[65],"and":[66,116,139,167],"significantly":[67,134],"degrade":[68],"final":[70],"output.":[71],"To":[72],"address":[73],"these":[74],"issues,":[75],"we":[76,99,114],"introduce":[77],"scale-aware":[79],"token-routed":[80],"Mixture":[81],"of":[82,162],"Experts":[83],"(MoE)":[84],"architecture,":[85],"allowing":[86],"scale-adaptive":[87],"expert":[88],"selection,":[89],"thereby":[90],"facilitating":[91],"decoupled":[92],"learning":[94],"scales.":[96],"In":[97],"addition,":[98],"enhance":[100],"semantic":[101],"by":[106],"incorporating":[107],"external":[108],"self-supervised":[109],"features.":[110],"Unlike":[111],"naive":[112],"alignment,":[113],"analyse":[115],"design":[117],"residual":[119],"feature":[120],"aggregation":[121],"scheme":[122],"tailored":[123],"paradigm.":[127],"Extensive":[128],"experiments":[129],"show":[130],"that":[131],"our":[132,147],"method":[133],"improves":[135],"both":[136],"training":[137,165,178,188],"efficiency":[138],"generation":[140],"quality.":[141],"On":[142],"ImageNet":[144],"256*256":[145],"benchmark,":[146],"model":[148],"achieves":[149],"superior":[151],"FID":[152],"compared":[153],"dense":[156],"baseline":[157],"requiring":[159],"only":[160],"half":[161],"default":[164],"epochs":[166],"smaller":[169],"parameter":[170],"budget,":[171],"with":[172,186],"merely":[174],"marginal":[175],"increase":[176],"cost.":[179],"performance":[182],"gap":[183],"further":[184],"widens":[185],"larger":[187],"epochs.":[189]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-03T00:00:00"}