{"id":"https://openalex.org/W7140095922","doi":"https://doi.org/10.48550/arxiv.2603.19567","title":"Efficiency Follows Global-Local Decoupling","display_name":"Efficiency Follows Global-Local Decoupling","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7140095922","doi":"https://doi.org/10.48550/arxiv.2603.19567"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.19567","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19567","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.19567","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130332138","display_name":"Zhenyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Zhenyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082756213","display_name":"Gensheng Pei","orcid":"https://orcid.org/0000-0002-7677-7487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei, Gensheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130329064","display_name":"Tao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101780760","display_name":"Yichao Zhou","orcid":"https://orcid.org/0009-0003-8632-446X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yichao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130404846","display_name":"Tianfei Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Tianfei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027545344","display_name":"Yazhou Yao","orcid":"https://orcid.org/0000-0002-0337-9410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Yazhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130350465","display_name":"Fumin Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Fumin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5130332138"],"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/T10036","display_name":"Advanced Neural Network Applications","score":0.4235999882221222,"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":0.4235999882221222,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.13979999721050262,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.12219999730587006,"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/decoupling","display_name":"Decoupling (probability)","score":0.5138999819755554},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5030999779701233},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.486299991607666},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4860000014305115},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4440999925136566},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.43529999256134033},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.40689998865127563},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.35850000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5995000004768372},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48570001125335693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4666000008583069},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3230000138282776},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2867000102996826},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.19567","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19567","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":"doi:10.48550/arxiv.2603.19567","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.19567","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"vision":[1],"models":[2],"must":[3],"capture":[4],"image-level":[5],"context":[6,52],"without":[7,75],"sacrificing":[8],"local":[9,31,73,92],"detail":[10],"while":[11],"remaining":[12],"computationally":[13],"affordable.":[14],"We":[15],"revisit":[16],"this":[17,35],"tradeoff":[18],"and":[19,30,59,94,106,120],"advance":[20],"a":[21,40,45,54,60],"simple":[22],"principle:":[23],"decouple":[24],"the":[25,133],"roles":[26],"of":[27,57],"global":[28,51,70,100],"reasoning":[29],"representation.":[32],"To":[33],"operationalize":[34],"principle,":[36],"we":[37],"introduce":[38],"ConvNeur,":[39],"two-branch":[41],"architecture":[42],"in":[43],"which":[44],"lightweight":[46],"neural":[47],"memory":[48],"branch":[49,62],"aggregates":[50],"on":[53],"compact":[55],"set":[56],"tokens,":[58],"locality-preserving":[61],"extracts":[63],"fine":[64],"structure.":[65],"A":[66],"learned":[67],"gate":[68],"lets":[69],"cues":[71],"modulate":[72],"features":[74],"entangling":[76],"their":[77],"objectives.":[78],"This":[79],"separation":[80],"yields":[81],"subquadratic":[82],"scaling":[83],"with":[84,91],"image":[85],"size,":[86],"retains":[87],"inductive":[88],"priors":[89],"associated":[90],"processing,":[93],"reduces":[95],"overhead":[96],"relative":[97],"to":[98],"fully":[99],"attention.":[101],"On":[102],"standard":[103],"classification,":[104],"detection,":[105],"segmentation":[107],"benchmarks,":[108],"ConvNeur":[109],"matches":[110],"or":[111,117],"surpasses":[112],"comparable":[113],"alternatives":[114],"at":[115,127],"similar":[116,128],"lower":[118],"compute":[119],"offers":[121],"favorable":[122],"accuracy":[123],"versus":[124],"latency":[125],"trade-offs":[126],"budgets.":[129],"These":[130],"results":[131],"support":[132],"view":[134],"that":[135],"efficiency":[136],"follows":[137],"global-local":[138],"decoupling.":[139]},"counts_by_year":[],"updated_date":"2026-03-24T06:04:31.470712","created_date":"2026-03-24T00:00:00"}