{"id":"https://openalex.org/W7166163905","doi":"https://doi.org/10.1145/3774521.3774575","title":"Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications","display_name":"Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7166163905","doi":"https://doi.org/10.1145/3774521.3774575"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774575","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075873387","display_name":"S Dasgupta","orcid":null},"institutions":[{"id":"https://openalex.org/I56404289","display_name":"Indian Institute of Technology BHU","ror":"https://ror.org/01kh5gc44","country_code":"IN","type":"education","lineage":["https://openalex.org/I56404289","https://openalex.org/I91357014"]},{"id":"https://openalex.org/I91357014","display_name":"Banaras Hindu University","ror":"https://ror.org/04cdn2797","country_code":"IN","type":"education","lineage":["https://openalex.org/I91357014"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shayon Dasgupta","raw_affiliation_strings":["IIT (BHU) Varanasi, Varanasi, India"],"raw_orcid":"https://orcid.org/0009-0009-5622-0209","affiliations":[{"raw_affiliation_string":"IIT (BHU) Varanasi, Varanasi, India","institution_ids":["https://openalex.org/I56404289","https://openalex.org/I91357014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139443574","display_name":"Avijit Dasgupta","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avijit Dasgupta","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0001-5633-1843","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139441626","display_name":"C. V. Jawahar","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jawahar C. V.","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0001-6767-7057","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3845,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88348477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9495000243186951,"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":0.9495000243186951,"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/T13629","display_name":"Text Readability and Simplification","score":0.006300000008195639,"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/T12031","display_name":"Speech and dialogue systems","score":0.004000000189989805,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/assistive-technology","display_name":"Assistive technology","score":0.5920000076293945},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.49889999628067017},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.44929999113082886},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4228000044822693},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.4122999906539917},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.38940000534057617},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3562999963760376},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3456000089645386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293999791145325},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6894999742507935},{"id":"https://openalex.org/C3017715821","wikidata":"https://www.wikidata.org/wiki/Q688498","display_name":"Assistive technology","level":2,"score":0.5920000076293945},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40230000019073486},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.33000001311302185},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2782999873161316},{"id":"https://openalex.org/C2778121785","wikidata":"https://www.wikidata.org/wiki/Q781083","display_name":"Augmentative and alternative communication","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3774521.3774575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774575","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.25084","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.25084","pdf_url":"https://arxiv.org/pdf/2606.25084","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774575","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774575","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8811448216438293}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":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],"have":[5],"redefined":[6],"visual":[7,28],"understanding":[8],"by":[9],"combining":[10],"vision":[11],"encoders":[12],"with":[13],"large-scale":[14],"language":[15],"models.":[16],"This":[17],"unified":[18],"architecture":[19],"enables":[20],"strong":[21],"performance":[22],"on":[23],"tasks":[24],"like":[25],"image":[26],"captioning,":[27],"question":[29],"answering,":[30],"and":[31,37,43],"multimodal":[32],"dialogue,":[33],"often":[34],"in":[35],"zero-":[36],"few-shot":[38],"settings.":[39],"Their":[40],"general-purpose":[41],"capabilities":[42],"flexible":[44],"interfaces":[45],"make":[46],"MLLMs":[47],"a":[48],"promising":[49],"foundation":[50],"for":[51],"real-world":[52],"vision-language":[53],"applications.":[54]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2026-06-27T00:00:00"}
