{"id":"https://openalex.org/W7214927893","doi":"https://doi.org/10.48550/arxiv.2609.37123","title":"EviViT: Evidence-Adaptive Vision Transformers for Fine-Grained Perception","display_name":"EviViT: Evidence-Adaptive Vision Transformers for Fine-Grained Perception","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214927893","doi":"https://doi.org/10.48550/arxiv.2609.37123"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37123","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37123","pdf_url":"https://arxiv.org/pdf/2609.37123","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37123","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153626833","display_name":"Yaoxin Niu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Yaoxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153660049","display_name":"Zhangquan Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhangquan","raw_affiliation_strings":["Equal contribution","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153605284","display_name":"Yang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhang, Yang","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153583368","display_name":"Xiang An","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An, Xiang","raw_affiliation_strings":["LMMs-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMMs-Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079400975","display_name":"Zhumei Wang","orcid":"https://orcid.org/0000-0001-6314-865X","observed_orcids":["https://orcid.org/0000-0001-6314-865X"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhumei","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053113105","display_name":"Chih-Ting Liao","orcid":"https://orcid.org/0009-0008-2223-9131","observed_orcids":["https://orcid.org/0009-0008-2223-9131"]},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liao, Chih-Ting","raw_affiliation_strings":["University of New South Wales"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153641201","display_name":"Hongkun Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cao, Hongkun","raw_affiliation_strings":["Peng Cheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086379651","display_name":"Ruqi Huang","orcid":"https://orcid.org/0000-0001-5942-3671","observed_orcids":["https://orcid.org/0000-0001-5942-3671"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Ruqi","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0007999999797903001,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0006000000284984708,"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/vision-transformer","display_name":"vision transformer","score":0.7979999780654907},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.6019999980926514},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.4429999887943268},{"id":"https://openalex.org/keywords/high-resolution-imagery","display_name":"high-resolution imagery","score":0.4779999852180481},{"id":"https://openalex.org/keywords/token-efficiency","display_name":"token efficiency","score":0.3070000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988000273704529},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6299999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050999760627747},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5651999711990356},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5564000010490417},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.5410000085830688},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.5171999931335449},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.3855000138282776},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2605000138282776}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37123","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37123","pdf_url":"https://arxiv.org/pdf/2609.37123","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.37123","doi":"https://doi.org/10.48550/arxiv.2609.37123","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37123","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37123","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37123","pdf_url":"https://arxiv.org/pdf/2609.37123","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214927893.pdf","grobid_xml":"https://content.openalex.org/works/W7214927893.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2950628590","https://openalex.org/W3094502228","https://openalex.org/W3168867926","https://openalex.org/W4306886919","https://openalex.org/W4403853618","https://openalex.org/W4415193793","https://openalex.org/W4416780398","https://openalex.org/W4417066038","https://openalex.org/W7127939476","https://openalex.org/W7128783650","https://openalex.org/W7151585725","https://openalex.org/W7160652239","https://openalex.org/W7161676639","https://openalex.org/W7162645559","https://openalex.org/W7162751813","https://openalex.org/W7167094583","https://openalex.org/W7171653369","https://openalex.org/W7196926645"],"related_works":["https://openalex.org/W7168167538","https://openalex.org/W7211908714","https://openalex.org/W7153009701","https://openalex.org/W7106694053","https://openalex.org/W7204872038","https://openalex.org/W7196977374","https://openalex.org/W4303633479","https://openalex.org/W7204169938","https://openalex.org/W7213590180","https://openalex.org/W4417328209"],"abstract_inverted_index":{"Fine-grained":[0],"visual":[1,15,28,82,153],"perception":[2],"enables":[3],"vision-language":[4],"models":[5],"to":[6,41,93,100],"distinguish":[7],"subtle":[8],"attributes":[9],"and":[10,78,119],"ground":[11],"their":[12],"answers":[13],"in":[14,104,132],"evidence.":[16,45],"In":[17],"high-resolution":[18],"scenes,":[19],"processing":[20,144],"the":[21,38,43,75,79,90,94,98,108,112,116],"whole":[22],"image":[23],"at":[24,145],"greater":[25],"resolution":[26],"spends":[27],"tokens":[29],"on":[30],"irrelevant":[31],"content,":[32],"while":[33,150],"isolated":[34],"crops":[35],"can":[36],"lose":[37],"context":[39],"needed":[40],"interpret":[42,101],"selected":[44],"We":[46],"introduce":[47],"EviViT,":[48],"a":[49,55,66],"lightweight":[50],"attachment":[51,113],"that":[52,140],"learns":[53],"where":[54],"pretrained":[56],"vision":[57],"transformer":[58],"should":[59],"acquire":[60],"detail.":[61],"Human":[62],"visual-search":[63],"traces":[64],"supervise":[65],"question-conditioned":[67],"evidence":[68,103],"density,":[69],"which":[70],"guides":[71],"regional":[72,91],"re-reading":[73],"from":[74],"original":[76],"pixels":[77],"allocation":[80],"of":[81],"tokens.":[83,154],"A":[84],"sparse,":[85],"coordinate-aware":[86],"bridge":[87],"then":[88],"connects":[89],"features":[92],"global":[95],"scene,":[96],"allowing":[97],"host":[99,109],"precise":[102],"context.":[105],"Learned":[106],"with":[107],"backbone":[110],"frozen,":[111],"serves":[114],"both":[115],"base":[117],"model":[118],"compatible":[120],"post-trained":[121],"descendants":[122],"without":[123],"refitting.":[124],"Experiments":[125],"across":[126],"nine":[127],"hosts":[128],"show":[129,139],"consistent":[130],"gains":[131],"average":[133],"fine-grained":[134],"accuracy.":[135],"Matched-budget":[136],"comparisons":[137],"further":[138],"EviViT":[141],"outperforms":[142],"global-only":[143],"every":[146],"tested":[147],"token":[148],"ceiling":[149],"using":[151],"fewer":[152]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}