{"id":"https://openalex.org/W7137846755","doi":"https://doi.org/10.1609/aaai.v40i11.37883","title":"SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse","display_name":"SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137846755","doi":"https://doi.org/10.1609/aaai.v40i11.37883"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i11.37883","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37883","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37883/41845","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37883/41845","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129732117","display_name":"Yiming Sun","orcid":null},"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":"Yiming Sun","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129662148","display_name":"Mi Zhang","orcid":null},"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":"Mi Zhang","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129659000","display_name":"Feifei Li","orcid":null},"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":"Feifei Li","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691329","display_name":"Geng Hong","orcid":null},"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":"Geng Hong","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129735458","display_name":"Min Hee Yang","orcid":null},"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":"Min Yang","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"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":"40","issue":"11","first_page":"9251","last_page":"9259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.33169999718666077,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.33169999718666077,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.05130000039935112,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.035100001841783524,"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/hallucinating","display_name":"Hallucinating","score":0.8314999938011169},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.462799996137619},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.39820000529289246},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.33640000224113464},{"id":"https://openalex.org/keywords/visual-hallucination","display_name":"Visual Hallucination","score":0.32679998874664307},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.32089999318122864},{"id":"https://openalex.org/keywords/backward-masking","display_name":"Backward masking","score":0.29120001196861267}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.8314999938011169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029000282287598},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45410001277923584},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.33640000224113464},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3221000134944916},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C2776817677","wikidata":"https://www.wikidata.org/wiki/Q4839818","display_name":"Backward masking","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2597000002861023},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i11.37883","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37883","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37883/41845","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37883","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37883","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37883","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37883/41845","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137846755.pdf","grobid_xml":"https://content.openalex.org/works/W7137846755.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"Video":[1],"Large":[2],"Language":[3],"Models":[4],"(Video-LLMs)":[5],"having":[6],"rapidly":[7],"advanced":[8],"in":[9,58,144,178],"recent":[10],"years,":[11],"perceptual":[12],"hallucinations":[13,153],"pose":[14],"a":[15,51,59,141],"substantial":[16,142],"safety":[17],"risk,":[18],"which":[19,100],"severely":[20],"restricts":[21],"their":[22],"real-world":[23],"applicability.":[24],"While":[25],"several":[26],"methods":[27],"for":[28,40,154],"hallucination":[29,90,131],"mitigation":[30],"have":[31],"been":[32],"proposed,":[33],"they":[34],"often":[35,81],"compromise":[36],"the":[37,64,89,95,103,111,116,123,180],"model\u2019s":[38,65],"capacity":[39],"video":[41,113,163],"understanding":[42,164],"and":[43,133,165],"reasoning.":[44],"In":[45],"this":[46,56],"work,":[47],"we":[48],"propose":[49],"SmartSight,":[50],"pioneering":[52],"step":[53],"to":[54,75,140],"address":[55],"issue":[57],"training-free":[60],"manner":[61],"by":[62,83,156,171],"leveraging":[63],"own":[66],"introspective":[67],"capabilities.":[68],"Specifically,":[69],"SmartSight":[70,121,150],"generates":[71],"multiple":[72],"candidate":[73],"responses":[74],"uncover":[76],"low-hallucinated":[77],"outputs":[78],"that":[79,149],"are":[80],"obscured":[82],"standard":[84],"greedy":[85],"decoding.":[86],"It":[87],"assesses":[88],"of":[91,110,136,182],"each":[92],"response":[93],"using":[94],"Temporal":[96],"Attention":[97,125],"Collapse":[98],"score,":[99],"measures":[101],"whether":[102],"model":[104],"over-focuses":[105],"on":[106,158,169],"trivial":[107],"temporal":[108],"regions":[109],"input":[112],"when":[114],"generating":[115],"response.":[117],"To":[118],"improve":[119],"efficiency,":[120],"identifies":[122],"Visual":[124],"Vanishing":[126],"point,":[127],"enabling":[128],"more":[129],"accurate":[130],"estimation":[132],"early":[134],"termination":[135],"hallucinated":[137],"responses,":[138],"leading":[139],"reduction":[143],"decoding":[145],"cost.":[146],"Experiments":[147],"show":[148],"substantially":[151],"lowers":[152],"QwenVL-2.5-7B":[155],"10.59%":[157],"VRIPT-HAL,":[159],"while":[160],"simultaneously":[161],"enhancing":[162],"reasoning,":[166],"boosting":[167],"performance":[168],"VideoMMMU":[170],"8.86%.":[172],"These":[173],"results":[174],"highlight":[175],"SmartSight\u2019s":[176],"effectiveness":[177],"improving":[179],"reliability":[181],"open-source":[183],"Video-LLMs.":[184]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}