{"id":"https://openalex.org/W7167245951","doi":"https://doi.org/10.1145/3811319","title":"Role-Aware Virtual Agents for Navigational Interaction guided by a Multimodal Large Language Model","display_name":"Role-Aware Virtual Agents for Navigational Interaction guided by a Multimodal Large Language Model","publication_year":2026,"publication_date":"2026-07-03","ids":{"openalex":"https://openalex.org/W7167245951","doi":"https://doi.org/10.1145/3811319"},"language":"en","primary_location":{"id":"doi:10.1145/3811319","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811319","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3811319","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100670947","display_name":"Minyoung Kim","orcid":"https://orcid.org/0000-0003-4273-7118"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minyoung Kim","raw_affiliation_strings":["George Mason University, Fairfax, USA"],"raw_orcid":"https://orcid.org/0000-0003-4273-7118","affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101569536","display_name":"Changyang Li","orcid":"https://orcid.org/0000-0002-0074-3889"},"institutions":[{"id":"https://openalex.org/I4210159818","display_name":"Alpha Environmental (United States)","ror":"https://ror.org/05j2afk93","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changyang Li","raw_affiliation_strings":["Goertek Alpha Labs, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0002-0074-3889","affiliations":[{"raw_affiliation_string":"Goertek Alpha Labs, Santa Clara, USA","institution_ids":["https://openalex.org/I4210159818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027672529","display_name":"Cuong Nguyen","orcid":"https://orcid.org/0000-0001-9234-9960"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cuong Nguyen","raw_affiliation_strings":["Adobe Research, San Francisco, USA"],"raw_orcid":"https://orcid.org/0000-0001-9234-9960","affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084967276","display_name":"Lap-Fai Yu","orcid":"https://orcid.org/0000-0002-2656-5654"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lap-Fai Yu","raw_affiliation_strings":["George Mason University, Fairfax, USA"],"raw_orcid":"https://orcid.org/0000-0002-2656-5654","affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88935895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"4","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4997999966144562,"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":0.4997999966144562,"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/T12290","display_name":"Human Motion and Animation","score":0.14800000190734863,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.08550000190734863,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.6840999722480774},{"id":"https://openalex.org/keywords/virtual-agent","display_name":"Virtual agent","score":0.5687999725341797},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.5270000100135803},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.5023999810218811},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.42579999566078186},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41600000858306885},{"id":"https://openalex.org/keywords/virtual-machine","display_name":"Virtual machine","score":0.40459999442100525},{"id":"https://openalex.org/keywords/virtual-actor","display_name":"Virtual actor","score":0.3903999924659729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853999733924866},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.7531999945640564},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.6840999722480774},{"id":"https://openalex.org/C2983409430","wikidata":"https://www.wikidata.org/wiki/Q7935065","display_name":"Virtual agent","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41600000858306885},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C150303390","wikidata":"https://www.wikidata.org/wiki/Q1983852","display_name":"Virtual actor","level":3,"score":0.3903999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3873000144958496},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C2780806968","wikidata":"https://www.wikidata.org/wiki/Q6045196","display_name":"Interaction model","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.29429998993873596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C13854087","wikidata":"https://www.wikidata.org/wiki/Q1061656","display_name":"Interaction design","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C2776977519","wikidata":"https://www.wikidata.org/wiki/Q4636326","display_name":"3D interaction","level":3,"score":0.25189998745918274},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3811319","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811319","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3811319","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3811319","pdf_url":null,"source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5337851169","display_name":"Advancing Multi-User Virtual Reality Classrooms to Support Collaborative Experiential Learning and Teaching of Introductory Physics","funder_award_id":"2418236","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7125309318","display_name":"EAGER: TaskDCL: Adapting Mixed Reality Training Programs to Real-World Scenes to enhance Human-AI Teaming in Emergency Responses","funder_award_id":"2430673","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2561391009","https://openalex.org/W2900225429","https://openalex.org/W2942109448","https://openalex.org/W2981618276","https://openalex.org/W3021415790","https://openalex.org/W3031955824","https://openalex.org/W3048557070","https://openalex.org/W3090160436","https://openalex.org/W3105994851","https://openalex.org/W3162419062","https://openalex.org/W3196967586","https://openalex.org/W3209948883","https://openalex.org/W4225145829","https://openalex.org/W4296973799","https://openalex.org/W4309663019","https://openalex.org/W4366547532","https://openalex.org/W4390722831","https://openalex.org/W4390874280","https://openalex.org/W4392633612","https://openalex.org/W4393147219","https://openalex.org/W4396832915","https://openalex.org/W4398794902","https://openalex.org/W4400582116","https://openalex.org/W4401415105","https://openalex.org/W4408724923","https://openalex.org/W4408954469","https://openalex.org/W7124316512","https://openalex.org/W7133213104"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,63],"role-aware":[3,91],"virtual":[4,47],"agent":[5,92],"navigational":[6],"interaction":[7,85],"that":[8],"generates":[9],"consistent,":[10],"role-aligned":[11],"movement":[12],"behaviors.":[13],"Our":[14,44,76],"approach":[15,45,77],"leverages":[16],"Multimodal":[17],"Large":[18],"Language":[19],"Models":[20],"(MLLMs)":[21],"to":[22,49,57,86],"interpret":[23],"multimodal":[24],"inputs":[25],"including":[26],"scene":[27],"information,":[28],"user":[29],"state,":[30],"and":[31,40,55,71,90],"high-level":[32],"language":[33],"role":[34,70],"instruction,":[35],"producing":[36],"discrete":[37],"navigation":[38],"decisions":[39],"stylized":[41],"planning":[42],"path.":[43],"enables":[46],"agents":[48],"behave":[50],"consistently":[51],"with":[52],"narrative":[53],"roles":[54],"respond":[56],"dynamic":[58],"actions,":[59],"such":[60,97],"as":[61,98],"playing":[62],"hide-and-seek":[64],"taking":[65],"into":[66],"account":[67],"the":[68,72],"agent's":[69],"user's":[73],"possible":[74],"intention.":[75],"demonstrates":[78],"how":[79],"MLLMs":[80],"can":[81],"go":[82],"beyond":[83],"language-based":[84],"support":[87],"embodied,":[88],"spatial,":[89],"behaviors":[93],"in":[94],"immersive":[95],"environments":[96],"augmented":[99],"reality.":[100]},"counts_by_year":[],"updated_date":"2026-07-04T06:14:54.683239","created_date":"2026-07-04T00:00:00"}
