{"id":"https://openalex.org/W7148901140","doi":"https://doi.org/10.48550/arxiv.2604.01545","title":"RAE-AR: Taming Autoregressive Models with Representation Autoencoders","display_name":"RAE-AR: Taming Autoregressive Models with Representation Autoencoders","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148901140","doi":"https://doi.org/10.48550/arxiv.2604.01545"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01545","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.2604.01545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132913329","display_name":"Hu Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132881713","display_name":"Hang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132917020","display_name":"Jie Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040083129","display_name":"Zeyue Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Zeyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020769158","display_name":"Haoyang Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Haoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132885362","display_name":"Nan Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132903843","display_name":"Feng Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Feng","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":0.9279999732971191,"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":0.9279999732971191,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00989999994635582,"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/T11448","display_name":"Face recognition and analysis","score":0.008700000122189522,"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/autoencoder","display_name":"Autoencoder","score":0.8427000045776367},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5968999862670898},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5922999978065491},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5065000057220459},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.49399998784065247},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49239999055862427},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4763000011444092},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41350001096725464}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8427000045776367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7098000049591064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6606000065803528},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5968999862670898},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5922999978065491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49239999055862427},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41350001096725464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26190000772476196},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01545","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.2604.01545","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01545","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":{"The":[0,13],"latent":[1],"space":[2],"of":[3,55,73,91],"generative":[4,29,183],"modeling":[5,102,123],"is":[6],"long":[7],"dominated":[8],"by":[9,133],"the":[10,16,35,40,49,53,71,79,88,104,153,172],"VAE":[11,50],"encoder.":[12,51],"latents":[14],"from":[15],"pretrained":[17],"representation":[18,41,56,76,157],"encoders":[19],"(e.g.,":[20],"DINO,":[21],"SigLIP,":[22],"MAE)":[23],"are":[24],"previously":[25],"considered":[26],"inappropriate":[27],"for":[28,174],"modeling.":[30,184],"Recently,":[31],"RAE":[32],"method":[33],"lights":[34],"hope":[36],"and":[37,94,103,125,182],"reveals":[38],"that":[39,148],"autoencoder":[42,57,158],"can":[43],"also":[44],"achieve":[45,160],"competitive":[46],"performance":[47,154],"as":[48,83],"However,":[52],"integration":[54],"into":[58],"continuous":[59],"autoregressive":[60],"(AR)":[61],"models,":[62],"remains":[63],"largely":[64],"unexplored.":[65],"In":[66],"this":[67],"work,":[68],"we":[69,114,129],"investigate":[70],"challenges":[72],"employing":[74],"high-dimensional":[75],"autoencoders":[77],"within":[78],"AR":[80,92,167],"paradigm,":[81],"denoted":[82],"\\textit{RAE-AR}.":[84],"We":[85],"focus":[86],"on":[87,166],"unique":[89],"properties":[90],"models":[93],"identify":[95],"two":[96],"primary":[97],"hurdles:":[98],"complex":[99],"token-wise":[100],"distribution":[101,119],"high-dimensionality":[105],"amplified":[106],"training-inference":[107],"gap":[108],"(exposure":[109],"bias).":[110],"To":[111],"address":[112],"these,":[113],"introduce":[115],"token":[116],"simplification":[117],"via":[118],"normalization":[120],"to":[121,140,159,163],"ease":[122],"difficulty":[124],"improve":[126],"convergence.":[127],"Furthermore,":[128],"enhance":[130],"prediction":[131],"robustness":[132],"incorporating":[134],"Gaussian":[135],"noise":[136],"injection":[137],"during":[138],"training":[139],"mitigate":[141],"exposure":[142],"bias.":[143],"Our":[144],"empirical":[145],"results":[146,161],"demonstrate":[147],"these":[149],"modifications":[150],"substantially":[151],"bridge":[152],"gap,":[155],"enabling":[156],"comparable":[162],"traditional":[164],"VAEs":[165],"models.":[168],"This":[169],"work":[170],"paves":[171],"way":[173],"a":[175],"more":[176],"unified":[177],"architecture":[178],"across":[179],"visual":[180],"understanding":[181]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-04T00:00:00"}