{"id":"https://openalex.org/W7204872038","doi":"https://doi.org/10.18653/2026.emnlp-main.868","title":"State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models","display_name":"State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204872038","doi":"https://doi.org/10.18653/2026.emnlp-main.868"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.868","doi":"https://doi.org/10.18653/2026.emnlp-main.868","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.868","pdf_url":"https://aclanthology.org/2026.emnlp-main.868.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.868.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109693861","display_name":"Mingxu Chai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxu Chai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121670954","display_name":"Chenyu Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Liu","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133140190","display_name":"Ziyu Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Shen","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144446186","display_name":"Jiazheng Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazheng Zhang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148885756","display_name":"Kaidi Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaidi Zhang","raw_affiliation_strings":["ByteDance , LarkAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance , LarkAI","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026984917","display_name":"Jihua Kang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Kang","raw_affiliation_strings":["ByteDance , LarkAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance , LarkAI","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160074088","display_name":"Tao Gui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Gui","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University","Shanghai Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160141028","display_name":"Qi Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70526203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20078","last_page":"20095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5615000128746033,"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":0.5615000128746033,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.43160000443458557,"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/T10028","display_name":"Topic Modeling","score":0.0024999999441206455,"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/document-parsing","display_name":"document parsing","score":0.8500000238418579},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9049999713897705},{"id":"https://openalex.org/keywords/autoregressive-decoding","display_name":"autoregressive decoding","score":0.9390000104904175},{"id":"https://openalex.org/keywords/robustness-efficiency-trade-off","display_name":"efficiency-robustness trade-off","score":0.7239999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547000050544739},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.557699978351593},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.426800012588501},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4178999960422516},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.40230000019073486},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3546999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.868","doi":"https://doi.org/10.18653/2026.emnlp-main.868","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.868","pdf_url":"https://aclanthology.org/2026.emnlp-main.868.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.28698","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28698","pdf_url":"https://arxiv.org/pdf/2608.28698","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.2608.28698","doi":"https://doi.org/10.48550/arxiv.2608.28698","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28698","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":"doi:10.18653/2026.emnlp-main.868","doi":"https://doi.org/10.18653/2026.emnlp-main.868","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.868","pdf_url":"https://aclanthology.org/2026.emnlp-main.868.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204872038.pdf","grobid_xml":"https://content.openalex.org/works/W7204872038.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7129045588","https://openalex.org/W4404340624","https://openalex.org/W7140893054","https://openalex.org/W7153003918","https://openalex.org/W7214927893","https://openalex.org/W7083843687","https://openalex.org/W4416331536","https://openalex.org/W7220390935","https://openalex.org/W7197019678","https://openalex.org/W7133625066"],"abstract_inverted_index":{"Compared":[0],"with":[1],"typical":[2],"vision-language":[3,14],"tasks,":[4],"document":[5,161],"parsing":[6,17,162],"places":[7],"stronger":[8],"demands":[9],"on":[10,20,53,91,109,160],"fine-grained":[11,26,120,130,188],"visual":[12,23,43,82,121,184],"perception.Existing":[13],"model":[15,89],"(VLM)-based":[16],"approaches":[18],"rely":[19],"globally":[21,124],"compressed":[22],"tokens,":[24],"where":[25],"details":[27],"are":[28],"entangled":[29],"within":[30],"a":[31,92,101,150,175],"single":[32],"representation":[33,95],"and":[34,51,99,143,173],"repeatedly":[35],"accessed":[36,63],"during":[37,86],"decoding.However,":[38],"we":[39,77,148],"observe":[40],"that":[41,134,165],"the":[42,54,110,157,180],"evidence":[44,83,185],"for":[45,96,187],"each":[46],"prediction":[47],"is":[48,141],"typically":[49],"localized":[50],"conditioned":[52,108],"current":[55,111],"decoding":[56,68],"state,":[57],"whereas":[58],"such":[59,136],"representations":[60,126],"must":[61],"be":[62],"in":[64,71,139],"full":[65],"at":[66],"every":[67],"step,":[69],"resulting":[70],"inefficient":[72],"computation.To":[73],"address":[74],"this":[75,146],"mismatch,":[76],"formulate":[78],"perception":[79],"as":[80],"state-conditioned":[81,137],"retrieval":[84,138,158,186],"(SCVER)":[85],"autoregressive":[87],"decoding.The":[88],"operates":[90],"compact":[93],"global":[94],"coarse":[97],"structure":[98],"retrieves":[100],"small":[102],"set":[103],"of":[104,182],"relevant":[105],"high-resolution":[106],"regions":[107],"token":[112],"state.This":[113],"coarse-to-fine":[114],"design":[115],"enables":[116],"on-demand":[117,183],"access":[118],"to":[119,155],"cues,":[122],"relieving":[123],"shared":[125],"from":[127],"encoding":[128],"all":[129],"details.We":[131],"further":[132],"find":[133],"learning":[135],"VLMs":[140],"challenging":[142],"unstable.To":[144],"stabilize":[145],"process,":[147],"introduce":[149],"Spatially-Guided":[151],"Learning":[152],"Objective":[153],"(SGLO)":[154],"guide":[156],"process.Experiments":[159],"benchmarks":[163],"show":[164],"SCVER":[166],"improves":[167],"robustness":[168],"under":[169],"reduced":[170],"input":[171],"resolution":[172],"achieves":[174],"better":[176],"accuracy-efficiency":[177],"trade-off,":[178],"demonstrating":[179],"effectiveness":[181],"perception.":[189]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-09-02T00:00:00"}