{"id":"https://openalex.org/W7162012597","doi":"https://doi.org/10.48550/arxiv.2605.20713","title":"SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction","display_name":"SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162012597","doi":"https://doi.org/10.48550/arxiv.2605.20713"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20713","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.20713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027369574","display_name":"Miaobo Hu","orcid":"https://orcid.org/0000-0002-6417-3280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Miaobo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136726214","display_name":"Shuhao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Shuhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136644531","display_name":"Bokun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bokun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136647074","display_name":"Rui Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136658709","display_name":"Wang, Xin, 1966-","orcid":"https://orcid.org/0009-0006-0413-0330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136643921","display_name":"Xiaobo Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Xiaobo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051666209","display_name":"Daren Zha","orcid":"https://orcid.org/0009-0002-6042-3454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zha, Daren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136645618","display_name":"Jun Jun Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Jun","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6324999928474426,"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":0.6324999928474426,"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":0.15070000290870667,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02630000002682209,"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/submodular-set-function","display_name":"Submodular set function","score":0.7017999887466431},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5006999969482422},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4717000126838684},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.46239998936653137},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3837999999523163},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.34880000352859497},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.33079999685287476},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.329800009727478}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.7017999887466431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5152999758720398},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30820000171661377},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20713","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20713","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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"IE":[1],"in":[2,101,106],"social":[3],"media":[4],"is":[5,44,144],"difficult":[6],"because":[7],"a":[8,76,91,119,123,132,137,148,193],"post":[9],"may":[10],"attach":[11],"multiple":[12],"images":[13,69],"that":[14,174],"are":[15],"weakly":[16],"related,":[17],"redundant,":[18],"or":[19,51,169],"even":[20],"misleading":[21],"with":[22,126],"respect":[23],"to":[24,45,96],"the":[25,109,115],"text.":[26],"In":[27],"this":[28],"setting,":[29],"always-on":[30,183],"multimodal":[31,81,86,184],"fusion":[32],"wastes":[33],"computation":[34],"and":[35,85,113,163,182,197,200],"can":[36],"amplify":[37],"spurious":[38],"visual":[39,99,159],"cues.":[40],"The":[41],"core":[42],"challenge":[43],"decide,":[46],"for":[47,80,166],"each":[48],"candidate":[49],"span":[50],"marked":[52,111],"entity":[53,83,167],"pair,":[54],"whether":[55],"vision":[56],"should":[57],"be":[58],"consulted":[59],"at":[60,192],"all":[61],"and,":[62],"if":[63],"so,":[64],"which":[65,143],"small":[66],"subset":[67,140],"of":[68],"provides":[70],"trustworthy":[71],"evidence.":[72],"We":[73],"propose":[74],"SAVER,":[75],"selective":[77],"vision-as-needed":[78],"framework":[79],"named":[82],"recognition":[84],"relation":[87,170],"extraction.":[88],"SAVER":[89,175],"uses":[90],"Conformal":[92],"Groundability":[93],"Gate":[94],"(CGG)":[95],"estimate":[97],"span-level":[98],"groundability":[100],"MNER,":[102],"derive":[103],"pair-level":[104],"activation":[105,116,190],"MRE":[107],"from":[108],"two":[110],"entities,":[112],"calibrate":[114],"threshold":[117],"on":[118],"held-out":[120],"split":[121],"via":[122],"conformal-style":[124],"procedure":[125],"Clopper--Pearson":[127],"upper":[128],"bounds.":[129],"When":[130],"activated,":[131],"submodular":[133],"relevance--diversity":[134],"selector":[135],"chooses":[136],"compact":[138],"evidence":[139],"across":[141],"images,":[142],"then":[145],"aggregated":[146],"by":[147],"Set":[149],"Transformer.":[150],"An":[151],"energy-inspired":[152],"joint":[153],"scoring":[154],"head":[155],"combines":[156],"text,":[157],"optional":[158],"evidence,":[160],"text--image":[161],"consistency,":[162],"sparse":[164],"routing":[165],"typing":[168],"classification.":[171],"Experiments":[172],"show":[173],"consistently":[176],"improves":[177],"F1":[178],"over":[179],"strong":[180],"text-only":[181],"baselines,":[185],"while":[186],"reducing":[187],"AURC,":[188],"increasing":[189],"coverage":[191],"fixed":[194],"risk":[195],"level,":[196],"lowering":[198],"FLOPs":[199],"P90":[201],"latency.":[202]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-22T00:00:00"}