{"id":"https://openalex.org/W4417280535","doi":"https://doi.org/10.1109/iccv51701.2025.01766","title":"Neighboring Autoregressive Modeling for Efficient Visual Generation","display_name":"Neighboring Autoregressive Modeling for Efficient Visual Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417280535","doi":"https://doi.org/10.1109/iccv51701.2025.01766"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10696","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001735290","display_name":"Yefei He","orcid":"https://orcid.org/0000-0002-2171-4518"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yefei He","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086133186","display_name":"Yuanyu He","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyu He","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111294571","display_name":"Shaoxuan He","orcid":"https://orcid.org/0009-0002-1571-2855"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoxuan He","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352722","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0002-8354-9319"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Feng Chen","raw_affiliation_strings":["The University of Adelaide,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide,Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112878209","display_name":"Hong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhou","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114126140","display_name":"Kaipeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaipeng Zhang","raw_affiliation_strings":["Shanghai AI Laboratory,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory,China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076928390","display_name":"Bohan Zhuang","orcid":"https://orcid.org/0000-0002-0074-0303"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Zhuang","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5001735290"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37924795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19000","last_page":"19010"},"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":0.9129999876022339,"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":0.9129999876022339,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03009999915957451,"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/T11448","display_name":"Face recognition and analysis","score":0.008899999782443047,"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":0.8730999827384949},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7764000296592712},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6017000079154968},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5415999889373779},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5088000297546387},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.424699991941452},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4104999899864197}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8730999827384949},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7764000296592712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106000185012817},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4982999861240387},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44119998812675476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43320000171661377},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.383899986743927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C104759252","wikidata":"https://www.wikidata.org/wiki/Q187120","display_name":"Time shifting","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C2775918612","wikidata":"https://www.wikidata.org/wiki/Q994794","display_name":"Noma","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.10696","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10696","pdf_url":"https://arxiv.org/pdf/2503.10696","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.10696","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10696","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10696","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10696","pdf_url":"https://arxiv.org/pdf/2503.10696","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[{"id":"https://openalex.org/G7283678196","display_name":null,"funder_award_id":"2022YFC3602601","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"autoregressive":[1,56],"models":[2],"typically":[3],"adhere":[4],"to":[5,37,138,183],"a":[6,51,60,65,117,129],"raster-order":[7],"``next-token":[8],"prediction\"":[9,68],"paradigm,":[10],"which":[11],"overlooks":[12],"the":[13,75,88,92,97,100,112,125,139,148,184,205],"spatial":[14],"and":[15,158,165,178],"temporal":[16],"locality":[17],"inherent":[18],"in":[19,80,91,111,144],"visual":[20,23,57],"content.":[21],"Specifically,":[22],"tokens":[24,35,77,110,136,141],"exhibit":[25],"significantly":[26],"stronger":[27],"correlations":[28],"with":[29,195],"their":[30,84],"spatially":[31],"or":[32],"temporally":[33],"adjacent":[34,109,137],"compared":[36,182],"those":[38],"that":[39,54,161],"are":[40,78,142],"distant.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,115],"propose":[46],"Neighboring":[47],"Autoregressive":[48],"Modeling":[49],"(NAR),":[50],"novel":[52],"paradigm":[53],"formulates":[55],"generation":[58,180,191],"as":[59],"progressive":[61],"outpainting":[62],"procedure,":[63],"following":[64],"near-to-far":[66],"``next-neighbor":[67],"mechanism.":[69],"Starting":[70],"from":[71,87],"an":[72],"initial":[73,89],"token,":[74],"remaining":[76],"decoded":[79,101,140],"ascending":[81],"order":[82],"of":[83,99,107,119,204],"Manhattan":[85],"distance":[86],"token":[90,127],"spatial-temporal":[93,113],"space,":[94,114],"progressively":[95],"expanding":[96],"boundary":[98],"region.":[102],"To":[103],"enable":[104],"parallel":[105],"prediction":[106],"multiple":[108],"introduce":[116],"set":[118],"dimension-oriented":[120],"decoding":[121],"heads,":[122],"each":[123],"predicting":[124],"next":[126],"along":[128],"mutually":[130],"orthogonal":[131],"dimension.":[132],"During":[133],"inference,":[134],"all":[135],"processed":[143],"parallel,":[145],"substantially":[146],"reducing":[147],"model":[149],"forward":[150],"steps":[151],"for":[152,175],"generation.":[153],"Experiments":[154],"on":[155,189],"ImageNet$256\\times":[156],"256$":[157],"UCF101":[159],"demonstrate":[160],"NAR":[162,194],"achieves":[163],"2.4$\\times$":[164],"8.6$\\times$":[166],"higher":[167],"throughput":[168],"respectively,":[169],"while":[170,200],"obtaining":[171],"superior":[172],"FID/FVD":[173],"scores":[174],"both":[176],"image":[177],"video":[179],"tasks":[181],"PAR-4X":[185],"approach.":[186],"When":[187],"evaluating":[188],"text-to-image":[190],"benchmark":[192],"GenEval,":[193],"0.8B":[196],"parameters":[197],"outperforms":[198],"Chameleon-7B":[199],"using":[201],"merely":[202],"0.4":[203],"training":[206],"data.":[207],"Code":[208],"is":[209],"available":[210],"at":[211],"https://github.com/ThisisBillhe/NAR.":[212]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}