{"id":"https://openalex.org/W7138137432","doi":"https://doi.org/10.1609/aaai.v40i6.42471","title":"Vision-MoR: Scaling Vision Transformer via Patch-Level Mixture-of-Recursions","display_name":"Vision-MoR: Scaling Vision Transformer via Patch-Level Mixture-of-Recursions","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138137432","doi":"https://doi.org/10.1609/aaai.v40i6.42471"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i6.42471","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42471","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i6.42471","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086544825","display_name":"Y G He","orcid":"https://orcid.org/0009-0007-4368-9767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunhong He","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713812","display_name":"Zhengqing Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengqing Yuan","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129739258","display_name":"Weixiang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weixiang Sun","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129740929","display_name":"Yiyang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiyang Li","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680541","display_name":"Yixin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixin Liu","raw_affiliation_strings":["Lehigh University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129720378","display_name":"Yanfang Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanfang Ye","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129689699","display_name":"Lichao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lichao Sun","raw_affiliation_strings":["Lehigh University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25221187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"6","first_page":"4699","last_page":"4707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8924999833106995,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8924999833106995,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.041600000113248825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.01269999984651804,"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/flops","display_name":"FLOPS","score":0.5498999953269958},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5335999727249146},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.47099998593330383},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.435699999332428},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4228000044822693},{"id":"https://openalex.org/keywords/router","display_name":"Router","score":0.4124000072479248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6362000107765198},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5335999727249146},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39750000834465027},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3443000018596649},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.3183000087738037},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i6.42471","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42471","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/42471","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/42471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i6.42471","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i6.42471","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4106118977069855,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scaling":[0],"Vision":[1],"Transformers":[2],"(ViTs)":[3],"has":[4],"yielded":[5],"remarkable":[6],"advancements":[7],"in":[8],"diverse":[9],"vision":[10,175],"tasks,":[11],"albeit":[12],"at":[13,119],"the":[14,153],"cost":[15],"of":[16],"escalating":[17],"computational,":[18],"memory,":[19,32],"and":[20,56,91,110,116,129,136,141],"parameter":[21,51,93],"demands.":[22],"Existing":[23],"efficiency":[24],"techniques":[25],"typically":[26],"address":[27],"only":[28],"one":[29],"dimension,":[30],"computation,":[31,55],"or":[33],"parameters,":[34,112],"lacking":[35],"a":[36,45,60,65,79,169],"cohesive":[37],"approach.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"introduce":[43],"Vision-MoR,":[44],"novel":[46],"ViT":[47],"architecture":[48],"that":[49],"unifies":[50],"sharing,":[52],"spatially":[53],"adaptive":[54],"memory-efficient":[57],"design":[58],"into":[59],"single":[61],"framework.":[62],"Vision-MoR":[63,101,123,147],"employs":[64],"spatial-aware":[66],"router":[67],"with":[68,78,107,152],"shifted-window":[69],"attention":[70],"to":[71],"dynamically":[72],"assign":[73],"per-patch":[74],"recursion":[75],"depths,":[76],"coupled":[77],"recursive":[80,92],"Transformer":[81],"loop":[82],"enabling":[83],"token-wise":[84],"early":[85],"exiting.":[86],"This":[87],"facilitates":[88],"content-adaptive":[89],"processing":[90],"reuse":[94],"while":[95],"preserving":[96],"spatial":[97],"locality.":[98],"On":[99,143],"ImageNet-1K,":[100],"Small":[102],"attains":[103],"74.6%":[104],"Top-1":[105,128],"accuracy":[106,132],"140M":[108],"FLOPs":[109],"5.7M":[111],"outperforming":[113],"EfficientViT-M2":[114],"(70.8%)":[115],"SHViT-S1":[117],"(72.8%)":[118],"superior":[120],"throughput.":[121],"The":[122],"X-Large":[124,148],"variant":[125],"achieves":[126],"80.4%":[127],"95.2%":[130],"Top-5":[131],"using":[133],"14.3M":[134],"parameters":[135],"2044M":[137],"FLOPs,":[138],"surpassing":[139],"ResNet-50":[140],"EfficientNet-B1.":[142],"COCO":[144],"object":[145],"detection,":[146],"yields":[149],"39.1":[150],"AP":[151],"lowest":[154],"latency":[155],"among":[156],"comparable":[157],"models.":[158],"These":[159],"results":[160],"underscore":[161],"Vision-MoR's":[162],"state-of-the-art":[163],"accuracy-efficiency":[164],"trade-offs,":[165],"positioning":[166],"it":[167],"as":[168],"scalable,":[170],"deployment-friendly":[171],"backbone":[172],"for":[173],"real-time":[174],"applications.":[176]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}