{"id":"https://openalex.org/W4415708277","doi":"https://doi.org/10.1109/icme59968.2025.11209792","title":"Leave the Bias in Bias: Mitigating the Label Noise Effects in Continual Visual Instruction Fine-Tuning","display_name":"Leave the Bias in Bias: Mitigating the Label Noise Effects in Continual Visual Instruction Fine-Tuning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708277","doi":"https://doi.org/10.1109/icme59968.2025.11209792"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111214779","display_name":"Xiaoyu Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaoyu Tan","raw_affiliation_strings":["INFLY TECH (Shanghai) Co., Ltd.,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"INFLY TECH (Shanghai) Co., Ltd.,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090685223","display_name":"Teqi Hao","orcid":"https://orcid.org/0009-0006-9510-8154"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teqi Hao","raw_affiliation_strings":["Shanghai University of Engineering Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Engineering Science,Shanghai,China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007950680","display_name":"Xihe Qiu","orcid":"https://orcid.org/0000-0003-4024-925X"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihe Qiu","raw_affiliation_strings":["Shanghai University of Engineering Science,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University of Engineering Science,Shanghai,China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027743711","display_name":"Shaojie Shi","orcid":"https://orcid.org/0009-0004-5781-0941"},"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":"Shaojie Shi","raw_affiliation_strings":["Fudan University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088242275","display_name":"Cheng Yuan","orcid":"https://orcid.org/0000-0002-3926-6098"},"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":"Yuan Cheng","raw_affiliation_strings":["Fudan University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056008057","display_name":"Wei Chu","orcid":"https://orcid.org/0000-0002-0276-224X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chu","raw_affiliation_strings":["INFLY TECH (Shanghai) Co., Ltd.,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"INFLY TECH (Shanghai) Co., Ltd.,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101102420","display_name":"Yinghui Xu","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":"Yinghui Xu","raw_affiliation_strings":["Fudan University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676886","display_name":"Yuan Qi","orcid":"https://orcid.org/0000-0002-2685-0340"},"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":"Yuan Qi","raw_affiliation_strings":["Fudan University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5111214779"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33794959,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7565000057220459,"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":0.7565000057220459,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.12189999967813492,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.017799999564886093,"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/noise","display_name":"Noise (video)","score":0.7311000227928162},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.3666999936103821},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.36010000109672546},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35040000081062317},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.29750001430511475},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.289000004529953}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7311000227928162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7003999948501587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5389000177383423},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4742000102996826},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C35772409","wikidata":"https://www.wikidata.org/wiki/Q1323086","display_name":"Image noise","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1988720110","https://openalex.org/W2052049901","https://openalex.org/W2124219775","https://openalex.org/W2616630373","https://openalex.org/W2843010082","https://openalex.org/W2901466771","https://openalex.org/W2947312908","https://openalex.org/W2963518342","https://openalex.org/W2996060033","https://openalex.org/W3095319910","https://openalex.org/W3165058054","https://openalex.org/W3173486383","https://openalex.org/W4287947470","https://openalex.org/W4382457317","https://openalex.org/W4385572116","https://openalex.org/W4387428070","https://openalex.org/W4389523793","https://openalex.org/W4389524500"],"related_works":[],"abstract_inverted_index":{"In":[0,86],"recent":[1],"years,":[2],"multimodal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"with":[8],"vision":[9,72,110],"processing":[10],"capability":[11],"have":[12],"shown":[13],"substantial":[14],"advancements,":[15,44],"excelling":[16],"particularly":[17],"in":[18,24,29,79,126,137,147,172],"interpreting":[19],"general":[20,138],"images.":[21],"Their":[22],"application":[23],"domain-specific":[25,57],"tasks,":[26],"like":[27],"those":[28],"the":[30,54,69,97,107,114,120,152,159,167],"medical":[31,148],"fields,":[32],"is":[33,158],"further":[34],"enhanced":[35],"through":[36,119],"continuous":[37],"visual":[38,139],"instruction":[39],"fine-tuning":[40],"(CVIF).":[41],"Despite":[42],"these":[43],"a":[45,91],"significant":[46,145],"challenge":[47],"arises":[48],"from":[49],"label":[50,64,100,117,170],"noise":[51,65,118,171],"encountered":[52],"during":[53],"collection":[55],"of":[56,71,99,109,116,124,154,169],"data.":[58],"Our":[59,102],"studies":[60],"reveal":[61],"that":[62,131],"this":[63,87,157],"can":[66],"adversely":[67],"affect":[68],"learning":[70,108],"projection":[73],"embeddings":[74,111],"and":[75,112,165],"contribute":[76],"to":[77,84,95,162],"inaccuracies":[78],"LLMs\u2019":[80],"fine-tuning,":[81],"often":[82],"leading":[83],"hallucinations.":[85],"paper,":[88],"we":[89],"introduce":[90],"novel":[92],"framework":[93,133],"designed":[94],"minimize":[96],"impact":[98,168],"noise.":[101],"approach":[103],"focuses":[104],"on":[105],"stabilizing":[106],"reducing":[113],"effect":[115],"inherent":[121],"semantic":[122],"understanding":[123],"uncertainty":[125],"LLMs.":[127],"Extensive":[128],"experiments":[129],"demonstrate":[130],"our":[132,155],"maintains":[134],"robust":[135],"performance":[136],"question-answer":[140],"(VQA)":[141],"tasks":[142],"while":[143],"showing":[144],"effectiveness":[146],"VQA":[149],"tasks.":[150],"To":[151],"best":[153],"knowledge,":[156],"first":[160],"study":[161],"specifically":[163],"address":[164],"analyze":[166],"CVIF.":[173]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}