{"id":"https://openalex.org/W4387446815","doi":"https://doi.org/10.1145/3610661.3617514","title":"Design of Generative Multimodal AI Agents to Enable Persons with Learning Disability","display_name":"Design of Generative Multimodal AI Agents to Enable Persons with Learning Disability","publication_year":2023,"publication_date":"2023-10-09","ids":{"openalex":"https://openalex.org/W4387446815","doi":"https://doi.org/10.1145/3610661.3617514"},"language":"en","primary_location":{"id":"doi:10.1145/3610661.3617514","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610661.3617514","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610661.3617514","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610661.3617514","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022914325","display_name":"A. Rajagopal","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajagopal A","raw_affiliation_strings":["Indian Institute of Technology, Madras, India"],"raw_orcid":"https://orcid.org/0000-0002-5602-6416","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108001625","display_name":"V. Nirmala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nirmala V","raw_affiliation_strings":["Queen Mary's College, India"],"raw_orcid":"https://orcid.org/0000-0001-7370-2490","affiliations":[{"raw_affiliation_string":"Queen Mary's College, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081746752","display_name":"Immanuel Johnraja Jebadurai","orcid":"https://orcid.org/0000-0002-8548-3333"},"institutions":[{"id":"https://openalex.org/I119668213","display_name":"Karunya University","ror":"https://ror.org/03k23nv15","country_code":"IN","type":"education","lineage":["https://openalex.org/I119668213"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Immanuel Johnraja Jebadurai","raw_affiliation_strings":["Karunya Institute of Technology &amp; Sciences, India"],"raw_orcid":"https://orcid.org/0000-0002-8548-3333","affiliations":[{"raw_affiliation_string":"Karunya Institute of Technology &amp; Sciences, India","institution_ids":["https://openalex.org/I119668213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Arun Muthuraj Vedamanickam","orcid":"https://orcid.org/0000-0001-5361-9438"},"institutions":[{"id":"https://openalex.org/I91277730","display_name":"Maulana Azad National Institute of Technology","ror":"https://ror.org/026vtd268","country_code":"IN","type":"education","lineage":["https://openalex.org/I91277730"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arun Muthuraj Vedamanickam","raw_affiliation_strings":["National Institute of Technology, India"],"raw_orcid":"https://orcid.org/0000-0001-5361-9438","affiliations":[{"raw_affiliation_string":"National Institute of Technology, India","institution_ids":["https://openalex.org/I91277730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020709905","display_name":"P. Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I5816614","display_name":"National Institute of Design","ror":"https://ror.org/05g2swp31","country_code":"IN","type":"education","lineage":["https://openalex.org/I5816614"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prajakta Uthaya Kumar","raw_affiliation_strings":["National Institute of Design, India"],"raw_orcid":"https://orcid.org/0009-0006-3821-1403","affiliations":[{"raw_affiliation_string":"National Institute of Design, India","institution_ids":["https://openalex.org/I5816614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.9797,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.97483557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"259","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12481","display_name":"Digital Accessibility for Disabilities","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3307","display_name":"Human Factors and Ergonomics"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12207","display_name":"Assistive Technology in Communication and Mobility","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/3609","display_name":"Occupational Therapy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7434900403022766},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5760517716407776},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5630961656570435},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5588513612747192},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.47976693511009216},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.45673203468322754},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.44636744260787964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.416978657245636},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10610014200210571}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7434900403022766},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5760517716407776},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5630961656570435},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5588513612747192},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.47976693511009216},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.45673203468322754},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.44636744260787964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.416978657245636},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10610014200210571},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610661.3617514","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610661.3617514","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610661.3617514","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3610661.3617514","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610661.3617514","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610661.3617514","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Cconference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8799999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387446815.pdf","grobid_xml":"https://content.openalex.org/works/W4387446815.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W253975593","https://openalex.org/W1988306926","https://openalex.org/W2519981993","https://openalex.org/W3020737195","https://openalex.org/W4225156133","https://openalex.org/W4285159263","https://openalex.org/W4361865337","https://openalex.org/W4366594418","https://openalex.org/W4367678106","https://openalex.org/W4375869762","https://openalex.org/W4376311951","https://openalex.org/W4376480780","https://openalex.org/W4376652806","https://openalex.org/W4376864533","https://openalex.org/W4377372281","https://openalex.org/W4379540039","https://openalex.org/W4380137118","https://openalex.org/W4382490555","https://openalex.org/W4385571343"],"related_works":["https://openalex.org/W4389505417","https://openalex.org/W2962931510","https://openalex.org/W2035104213","https://openalex.org/W2922283411","https://openalex.org/W4384789578","https://openalex.org/W4380551887","https://openalex.org/W127837312","https://openalex.org/W4287761641","https://openalex.org/W3034009428","https://openalex.org/W4233495470"],"abstract_inverted_index":{"The":[0],"recent":[1,43,92],"advances":[2,44,93],"in":[3,28,45,94,134,165,173,229,255],"Multimodal":[4,96,139,248,316,319],"AI":[5,8,40,104,140,178,189,325,352,385],"&":[6,36,65],"Generative":[7,95],"open":[9],"doors":[10],"to":[11,50,63,128,169,193,206,213,252,263,291,298,323,345,350,380,388],"the":[12,46,52,76,91,103,108,124,136,138,163,166,175,177,188,194,199,208,211,265,308,331,335,347,373,409],"possibilities":[13],"of":[14,54,78,131,198,247,277,280,296,310,384,401],"solving":[15],"key":[16],"challenges":[17],"for":[18,115,153,354],"Persons":[19],"with":[20,57,90,118,156,204,239,261,357,390],"Learning":[21,242],"Disability.":[22],"To":[23,201,258,306,328,368],"assist":[24],"individuals":[25],"facing":[26],"difficulty":[27,254],"visual":[29,81,144,185,256,271,274,363],"or":[30,59,365],"auditory":[31,147,300,366],"perception,":[32],"this":[33,69,402],"paper":[34],"designs":[35],"develops":[37],"a":[38,72,116,154,224,278,339,382,406],"multimodal":[39,237],"agent":[41,105,141,190],"using":[42,282],"field.":[47],"We":[48,67,234,396],"aim":[49],"solve":[51],"challenge":[53],"enabling":[55],"persons":[56,260],"Visual":[58,119,225],"Auditory":[60,158],"Processing":[61,120,159],"Disorders":[62],"learn":[64],"communicate.":[66],"do":[68],"by":[70],"exploring":[71],"design":[73,86,209,220,266,333,341,403],"that":[74],"allows":[75,210],"transformation":[77],"information":[79,132,145,171],"across":[80,326],"and":[82,196,243,285,303,387,404],"language":[83],"modalities.":[84],"This":[85,219,273],"can":[87],"be":[88],"realized":[89,222],"AI.":[97],"Based":[98],"on":[99,372,408],"each":[100,311],"individual's":[101,167],"needs,":[102],"dynamically":[106,179,192],"adapts":[107,191],"Human":[109],"Computer":[110],"interaction":[111],"model.":[112],"For":[113],"instance,":[114,152],"child":[117],"Disorder":[121,160],"(VPD),":[122],"given":[123,162],"child's":[125],"hindered":[126],"ability":[127,168],"make":[129],"sense":[130],"taken":[133,172],"through":[135,174],"eyes,":[137],"transforms":[142],"any":[143,181],"into":[146,184,270,334],"user":[148],"interaction.":[149],"In":[150],"another":[151],"person":[155],"Central":[157],"(CAPD),":[161],"hindrance":[164],"analyze":[170],"ears,":[176],"translates":[180,267],"speech":[182,283],"modality":[183],"cues.":[186,272],"Thus":[187],"strengths":[195,309],"abilities":[197],"individual.":[200],"enable":[202,259,369],"students":[203],"VPD":[205],"learn,":[207,264],"student":[212],"ask":[214],"questions":[215],"about":[216],"an":[217,378],"image.":[218],"is":[221],"as":[223,362],"Question":[226],"Answering":[227],"task":[228],"Vision":[230],"Language":[231,250,287],"Transformer":[232],"models.":[233],"explore":[235,315,338,377],"interactive":[236],"conversations":[238],"Few":[240],"shot":[241],"In-Context":[244],"Instruction":[245],"Tuning":[246],"Large":[249,286],"Models":[251,288],"address":[253,299],"reasoning.":[257],"CAPD":[262],"audio":[268],"lectures":[269],"cue":[275],"consists":[276],"combination":[279],"words":[281],"recognition":[284],"based":[289,318,342],"re-phrasing":[290],"simpler":[292],"words,":[293],"cross-modal":[294],"retrieval":[295],"images":[297],"memory":[301],"challenges,":[302],"AI-generated":[304],"images.":[305],"identify":[307],"child,":[312],"we":[313,337,376],"also":[314],"embedding":[317],"latent":[320],"space":[321],"arithmetic":[322],"link":[324],"senses.":[327],"effectively":[329],"integrate":[330],"proposed":[332,374],"mainstream,":[336],"universal":[340],"inclusive":[343],"approach":[344],"extend":[346],"use":[348],"case":[349],"create":[351],"assistants":[353],"assisting":[355],"children":[356],"different":[358],"learning":[359],"styles":[360],"such":[361],"learners":[364],"learners.":[367],"future":[370],"research":[371],"design,":[375],"architecture":[379],"compose":[381],"pipeline":[383],"models,":[386],"connect":[389],"external":[391],"systems":[392],"via":[393],"plugin":[394],"connectors.":[395],"implement":[397],"lab":[398],"scale":[399],"prototypes":[400],"present":[405],"demo":[407],"project":[410],"webpage":[411],"at":[412],"https://sites.google.com/view/multimodallearningdisability.":[413]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
