{"id":"https://openalex.org/W7203479434","doi":"https://doi.org/10.48550/arxiv.2608.12746","title":"Dual-Stream Cross-Anchor Correction Grounding Long-Form Captions and the Domain Limits of Object-Level Anchors","display_name":"Dual-Stream Cross-Anchor Correction Grounding Long-Form Captions and the Domain Limits of Object-Level Anchors","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7203479434","doi":"https://doi.org/10.48550/arxiv.2608.12746"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.12746","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12746","pdf_url":"https://arxiv.org/pdf/2608.12746","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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/2608.12746","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147183227","display_name":"LingKai Bu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bu, Lingkai","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences) , Jinan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences) , Jinan , China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137043326","display_name":"Qian Gao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137060544","display_name":"Jun Fan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137004015","display_name":"Guohui Ding","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Guohui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138111403","display_name":"Zhenyu Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001752284","display_name":"Yuteng Xiao","orcid":"https://orcid.org/0000-0003-0773-638X","observed_orcids":["https://orcid.org/0000-0003-0773-638X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Yuteng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5147581186","display_name":"Jinyi Liang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Jinyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":1.0,"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":1.0,"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":0.0,"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":0.0,"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/object-hallucination","display_name":"object hallucination","score":0.9079999923706055},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.8579999804496765},{"id":"https://openalex.org/keywords/visual-anchors","display_name":"visual anchors","score":0.7459999918937683},{"id":"https://openalex.org/keywords/cross-attention","display_name":"cross-attention","score":0.7139999866485596},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.7749999761581421},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.7139999866485596},{"id":"https://openalex.org/keywords/cross-domain-generalisation","display_name":"cross-domain generalisation","score":0.8809999823570251},{"id":"https://openalex.org/keywords/hallucination-correction","display_name":"hallucination correction","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775000095367432},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4343000054359436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C2776545253","wikidata":"https://www.wikidata.org/wiki/Q5464292","display_name":"Folding (DSP implementation)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.2754000127315521},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.12746","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12746","pdf_url":"https://arxiv.org/pdf/2608.12746","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.12746","doi":"https://doi.org/10.48550/arxiv.2608.12746","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.12746","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.12746","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.12746","pdf_url":"https://arxiv.org/pdf/2608.12746","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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/W7203479434.pdf","grobid_xml":"https://content.openalex.org/works/W7203479434.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4382142077"],"related_works":["https://openalex.org/W7140113582","https://openalex.org/W7171964443","https://openalex.org/W7206179358","https://openalex.org/W7131687187","https://openalex.org/W7083699837","https://openalex.org/W4393969551","https://openalex.org/W7214208679","https://openalex.org/W7171926382","https://openalex.org/W7141489732","https://openalex.org/W4399197990"],"abstract_inverted_index":{"Object":[0],"hallucination":[1],"in":[2],"multimodal":[3],"large":[4],"language":[5,9,82],"models":[6],"arises":[7],"when":[8,215],"priors":[10],"and":[11,122,140,150,160,165,243,247],"corpus":[12,52,159],"co-occurrence":[13],"bias":[14],"outweigh":[15],"the":[16,26,81,157,169,173,179,187,196,206,218,234,239],"visual":[17,78],"evidence,":[18],"with":[19,153],"nothing":[20],"tying":[21],"an":[22,95],"object":[23,194],"mention":[24],"to":[25,43,98,238],"image.":[27],"Most":[28],"remedies":[29],"intervene":[30],"at":[31,94,118,190],"decoding":[32],"time,":[33],"yet":[34,212],"under":[35,198],"a":[36,50,87,103,107,123,132,163,199,204,230],"unified":[37],"protocol":[38],"their":[39],"benefit":[40],"is":[41,224],"confined":[42],"short":[44],"captions;":[45],"supervised":[46],"fine-tuning":[47],"(SFT)":[48],"on":[49,135,156,217,245],"detail-rich":[51],"lengthens":[53],"captions,":[54],"but":[55],"over":[56],"forty":[57],"percent":[58],"still":[59],"name":[60],"absent":[61],"objects.":[62],"This":[63],"paper":[64],"proposes":[65],"Dual-Stream":[66],"Cross-Anchor":[67],"Correction":[68],"(DSCC).":[69],"Unlike":[70],"work":[71],"that":[72],"post-processes":[73],"decoding,":[74],"DSCC":[75,176],"injects":[76],"object-level":[77,91],"anchors":[79,101,115],"into":[80],"model":[83],"itself":[84],"during":[85],"fine-tuning:":[86],"perception":[88,207],"stream":[89,109,208],"aligns":[90],"hidden":[92],"states":[93],"intermediate":[96],"layer":[97],"frozen":[99],"text":[100],"by":[102,116],"bidirectional":[104],"contrastive":[105],"objective;":[106],"cognition":[108,219],"lets":[110],"deeper":[111],"layers":[112],"query":[113],"those":[114],"cross-attention":[117],"every":[119],"generation":[120],"step;":[121],"two-stage":[124],"curriculum":[125],"gate":[126],"couples":[127],"them,":[128],"making":[129],"evidence":[130],"retrieval":[131],"structural":[133],"constraint":[134],"generation.":[136],"Under":[137],"one":[138,141],"backbone":[139],"scoring":[142],"protocol,":[143],"experiments":[144],"span":[145],"long-caption":[146],"hallucination,":[147],"object-existence":[148],"discrimination":[149],"cross-domain":[151],"generalisation,":[152],"vanilla":[154],"SFT":[155],"same":[158],"schedule":[161],"as":[162],"length-":[164],"density-matched":[166],"control":[167],"separating":[168],"data":[170],"effect":[171],"from":[172],"architectural":[174],"gain.":[175],"alone":[177,209],"reaches":[178],"long-caption,":[180],"low-hallucination":[181],"region:":[182],"captions":[183],"roughly":[184],"1.9":[185],"times":[186],"baseline":[188],"length":[189],"88.19%":[191],"precision":[192,211],"per":[193],"mention,":[195],"highest":[197],"density-independent":[200],"criterion.":[201],"Ablations":[202],"expose":[203],"synergy:":[205],"degrades":[210],"reverses":[213],"sign":[214],"stacked":[216],"stream.":[220],"No":[221],"universal":[222],"superiority":[223],"claimed:":[225],"three":[226],"out-of-domain":[227],"benchmarks":[228],"yield":[229],"predictable,":[231],"falsifiable":[232],"domain-conditionality,":[233],"synergy":[235],"being":[236],"bound":[237],"anchors'":[240],"semantic":[241],"domain":[242],"breaking":[244],"charts":[246],"illusions.":[248]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-15T00:00:00"}