{"id":"https://openalex.org/W4414359469","doi":"https://doi.org/10.24963/ijcai.2025/1164","title":"Words Over Pixels? Rethinking Vision in Multimodal Large Language Models","display_name":"Words Over Pixels? Rethinking Vision in Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359469","doi":"https://doi.org/10.24963/ijcai.2025/1164"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1164","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081598659","display_name":"Anubhooti Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anubhooti Jain","raw_affiliation_strings":["IIT Jodhpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050521702","display_name":"Mayank Vatsa","orcid":"https://orcid.org/0000-0001-5952-2274"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mayank Vatsa","raw_affiliation_strings":["IIT Jodhpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011779957","display_name":"Richa Singh","orcid":"https://orcid.org/0000-0003-4060-4573"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Richa Singh","raw_affiliation_strings":["IIT Jodhpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154549908"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10481","last_page":"10489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9409000277519226,"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":0.9409000277519226,"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/component","display_name":"Component (thermodynamics)","score":0.5734999775886536},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5228999853134155},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.48809999227523804},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4194999933242798},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.3930000066757202},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3441999852657318},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.34380000829696655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6963000297546387},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508899986743927},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46209999918937683},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32120001316070557},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C200220432","wikidata":"https://www.wikidata.org/wiki/Q7936208","display_name":"Vision science","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1164","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"promise":[5],"seamless":[6],"integration":[7],"of":[8,42,70],"vision":[9,44,81,122],"and":[10,51,67,72,85,107,111,135],"language":[11],"understanding.":[12],"However,":[13],"despite":[14],"their":[15,86],"strong":[16],"performance,":[17],"recent":[18,93],"studies":[19],"reveal":[20],"that":[21],"MLLMs":[22],"often":[23],"fail":[24],"to":[25,100,120,123],"effectively":[26],"utilize":[27],"visual":[28,65,71,102],"information,":[29],"frequently":[30],"relying":[31],"on":[32],"textual":[33,73],"cues":[34],"instead.":[35],"This":[36],"survey":[37],"provides":[38],"a":[39],"comprehensive":[40],"analysis":[41],"the":[43,117,130],"component":[45],"in":[46,79],"MLLMs,":[47],"covering":[48],"both":[49],"application-level":[50],"architectural":[52],"aspects.":[53],"We":[54],"investigate":[55],"critical":[56],"challenges":[57],"such":[58],"as":[59],"weak":[60],"spatial":[61],"reasoning,":[62],"poor":[63],"fine-grained":[64],"perception,":[66],"suboptimal":[68],"fusion":[69],"modalities.":[74],"Additionally,":[75],"we":[76,95],"explore":[77],"limitations":[78],"current":[80],"encoders,":[82],"benchmark":[83],"inconsistencies,":[84],"implications":[87],"for":[88,132],"downstream":[89],"tasks.":[90],"By":[91],"synthesizing":[92],"advancements,":[94],"highlight":[96],"key":[97],"research":[98],"opportunities":[99],"enhance":[101],"understanding,":[103],"improve":[104],"cross-modal":[105],"alignment,":[106],"develop":[108],"more":[109,133],"robust":[110],"efficient":[112],"MLLMs.":[113],"Our":[114],"observations":[115],"emphasize":[116],"urgent":[118],"need":[119],"elevate":[121],"an":[124],"equal":[125],"footing":[126],"with":[127],"language,":[128],"paving":[129],"path":[131],"reliable":[134],"perceptually":[136],"aware":[137],"multimodal":[138],"models.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}