{"id":"https://openalex.org/W7104872810","doi":"https://doi.org/10.48550/arxiv.2511.05832","title":"Hilbert-Guided Sparse Local Attention","display_name":"Hilbert-Guided Sparse Local Attention","publication_year":2025,"publication_date":"2025-11-08","ids":{"openalex":"https://openalex.org/W7104872810","doi":"https://doi.org/10.48550/arxiv.2511.05832"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2511.05832","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.05832","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2511.05832","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li, Yunge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yunge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xu, Lanyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Lanyu","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/T10036","display_name":"Advanced Neural Network Applications","score":0.3158000111579895,"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":0.3158000111579895,"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/T11019","display_name":"Image Enhancement Techniques","score":0.11710000038146973,"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":0.08969999849796295,"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/quadratic-equation","display_name":"Quadratic equation","score":0.6360999941825867},{"id":"https://openalex.org/keywords/hilbert-curve","display_name":"Hilbert curve","score":0.45089998841285706},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.4415999948978424},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.39590001106262207},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.3521000146865845},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.3409000039100647},{"id":"https://openalex.org/keywords/hilbert\u2013huang-transform","display_name":"Hilbert\u2013Huang transform","score":0.32519999146461487},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.3174999952316284}],"concepts":[{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6010000109672546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4771000146865845},{"id":"https://openalex.org/C2781142347","wikidata":"https://www.wikidata.org/wiki/Q1366592","display_name":"Hilbert curve","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.4415999948978424},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.39590001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34769999980926514},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C25570617","wikidata":"https://www.wikidata.org/wiki/Q1006462","display_name":"Hilbert\u2013Huang transform","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32010000944137573},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C76103427","wikidata":"https://www.wikidata.org/wiki/Q5761197","display_name":"Hilbert R-tree","level":5,"score":0.30880001187324524},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2986090443","wikidata":"https://www.wikidata.org/wiki/Q77870413","display_name":"Local structure","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C2777319359","wikidata":"https://www.wikidata.org/wiki/Q6664444","display_name":"Local language","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C28799612","wikidata":"https://www.wikidata.org/wiki/Q685437","display_name":"Hilbert transform","level":3,"score":0.26669999957084656},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C135320971","wikidata":"https://www.wikidata.org/wiki/Q1868524","display_name":"Local search (optimization)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2511.05832","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.05832","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2511.05832","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.05832","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6052928566932678}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"quadratic":[1],"compute":[2],"and":[3,67,83,85,105,129,137,143,158,184],"memory":[4],"costs":[5],"of":[6,32,117,164,191],"global":[7],"self-attention":[8],"severely":[9],"limit":[10],"its":[11],"use":[12],"in":[13,54],"high-resolution":[14],"images.":[15,196],"Local":[16],"attention":[17,22,38,136,139,177,194],"reduces":[18],"complexity":[19],"by":[20,140],"restricting":[21],"to":[23,42,113,187],"neighborhoods.":[24],"Block-sparse":[25],"kernels":[26,112,180],"can":[27,106,133],"further":[28],"improve":[29,114],"the":[30,55,71,91,115,124,149,154,159,189],"efficiency":[31,116,190],"local":[33,37,119,176,193],"attention,":[34],"but":[35],"conventional":[36],"patterns":[39],"often":[40],"fail":[41],"deliver":[43],"significant":[44],"speedups":[45,168],"because":[46],"tokens":[47,75],"within":[48],"a":[49,61,80,96,182],"window":[50,135],"are":[51,76,87],"not":[52],"contiguous":[53],"1D":[56,93],"sequence.":[57,94],"This":[58],"work":[59],"proposes":[60],"novel":[62],"method":[63],"for":[64,195],"constructing":[65],"windows":[66,84],"neighborhoods":[68,86],"based":[69],"on":[70,90],"Hilbert":[72,81,126,130,155,160],"curve.":[73],"Image":[74],"first":[77],"reordered":[78,92],"along":[79],"curve,":[82],"then":[88],"formed":[89],"From":[95],"block-sparse":[97,111,179],"perspective,":[98],"this":[99],"strategy":[100,150],"significantly":[101],"increases":[102],"block":[103],"sparsity":[104],"be":[107],"combined":[108],"with":[109,169,178],"existing":[110],"2D":[118,192],"attention.":[120],"Experiments":[121],"show":[122],"that":[123],"proposed":[125],"Window":[127,156],"Attention":[128,132],"Slide":[131],"accelerate":[134],"slide":[138],"about":[141],"$4\\times$":[142],"$18\\times$,":[144],"respectively.":[145],"To":[146],"assess":[147],"practicality,":[148],"is":[151],"instantiated":[152],"as":[153],"Transformer":[157],"Neighborhood":[161],"Transformer,":[162],"both":[163],"which":[165],"achieve":[166],"end-to-end":[167],"minimal":[170],"accuracy":[171],"loss.":[172],"Overall,":[173],"combining":[174],"Hilbert-guided":[175],"offers":[181],"general":[183],"practical":[185],"approach":[186],"enhancing":[188]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-11-12T00:00:00"}