{"id":"https://openalex.org/W4412887737","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1037","title":"Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward","display_name":"Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887737","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1037"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1037","pdf_url":"https://aclanthology.org/2025.findings-acl.1037.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1037.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072650382","display_name":"Zhiyuan Fan","orcid":"https://orcid.org/0000-0002-0976-1127"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhiyuan Fan","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100680203","display_name":"Yumeng Wang","orcid":"https://orcid.org/0000-0002-9273-6239"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yumeng Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119181201","display_name":"Sandeep Polisetty","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sandeep Polisetty","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029408111","display_name":"Yi R. Fung","orcid":"https://orcid.org/0009-0006-1869-0363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi R. Fung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20222","last_page":"20242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.16609999537467957,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.16609999537467957,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.788844108581543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5809365510940552},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4694387912750244},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3631405532360077},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09457150101661682}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.788844108581543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5809365510940552},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4694387912750244},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3631405532360077},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09457150101661682},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1037","pdf_url":"https://aclanthology.org/2025.findings-acl.1037.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-168887","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168887","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1037","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1037","pdf_url":"https://aclanthology.org/2025.findings-acl.1037.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887737.pdf","grobid_xml":"https://content.openalex.org/works/W4412887737.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"Vision":[1],"Language":[2],"Models":[3],"(LVLMs)":[4],"excel":[5,89],"in":[6,15,23,31,83,156,183],"various":[7],"vision-language":[8],"tasks.Yet,":[9],"their":[10],"robustness":[11,68],"to":[12,29,80],"visual":[13,81,108,122,146],"variations":[14],"position,":[16],"scale,":[17],"orientation,":[18],"and":[19,33,63,118,160],"context":[20],"that":[21,88,111,149,170],"objects":[22],"natural":[24],"scenes":[25],"inevitably":[26],"exhibit":[27,105],"due":[28],"changes":[30],"viewpoint":[32],"environment":[34],"remains":[35],"largely":[36],"underexplored.To":[37],"bridge":[38],"this":[39],"gap,":[40],"we":[41,75,131],"introduce":[42],"V":[43],"2":[44],"R-Bench,":[45],"a":[46,77,106,120,133,140],"comprehensive":[47],"benchmark":[48],"framework":[49,135],"for":[50,66,136,144,180],"evaluating":[51],"Visual":[52],"Variation":[53],"Robustness":[54],"of":[55,114,128],"LVLMs,":[56,74],"which":[57,84],"encompasses":[58],"automated":[59],"evaluation":[60,71],"dataset":[61],"generation":[62],"principled":[64],"metrics":[65],"thorough":[67],"assessment.Through":[69],"extensive":[70],"on":[72,96],"21":[73],"reveal":[76],"surprising":[78],"vulnerability":[79],"variations,":[82],"even":[85],"advanced":[86],"models":[87,104],"at":[90],"complex":[91],"visionlanguage":[92],"tasks":[93,98],"significantly":[94],"underperform":[95],"simple":[97],"such":[99],"as":[100],"object":[101],"recognition.Interestingly,":[102],"these":[103,129,150,171],"distinct":[107],"position":[109],"bias":[110],"contradicts":[112],"theories":[113],"effective":[115],"receptive":[116],"fields,":[117],"demonstrate":[119,169],"humanlike":[121],"acuity":[123],"threshold.To":[124],"identify":[125],"the":[126,157,178],"source":[127],"vulnerabilities,":[130],"present":[132],"systematic":[134],"component-level":[137],"analysis,":[138],"featuring":[139],"novel":[141],"visualization":[142],"approach":[143],"aligned":[145],"features.Results":[147],"show":[148],"vulnerabilities":[151],"stem":[152],"from":[153],"error":[154],"accumulation":[155],"pipeline":[158],"architecture":[159],"inadequate":[161],"multimodal":[162],"alignment.Complementary":[163],"experiments":[164],"with":[165],"synthetic":[166],"data":[167],"further":[168],"limitations":[172],"are":[173],"fundamentally":[174],"architectural":[175,181],"deficiencies,":[176],"scoring":[177],"need":[179],"innovations":[182],"future":[184],"LVLM":[185],"designs.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
