{"id":"https://openalex.org/W7134232106","doi":"https://doi.org/10.1145/3742414.3794710","title":"AIoT Smart Home Automation Architecture: Autonomous Decision-Making Powered by Multimodal Large Language Models (MLLMs)","display_name":"AIoT Smart Home Automation Architecture: Autonomous Decision-Making Powered by Multimodal Large Language Models (MLLMs)","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134232106","doi":"https://doi.org/10.1145/3742414.3794710"},"language":null,"primary_location":{"id":"doi:10.1145/3742414.3794710","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742414.3794710","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":"Companion Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3742414.3794710","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128530355","display_name":"He Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Zhang","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, University Park, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0000-0002-8169-1653","affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, University Park, Pennsylvania, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuewen Zhang","orcid":"https://orcid.org/0009-0007-6308-6242"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewen Zhang","raw_affiliation_strings":["The Future Laboratory, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-6308-6242","affiliations":[{"raw_affiliation_string":"The Future Laboratory, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bochen Li","orcid":"https://orcid.org/0009-0003-6160-0165"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bochen Li","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-6160-0165","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wen Chen","orcid":"https://orcid.org/0009-0002-4204-8777"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Chen","raw_affiliation_strings":["The Future Laboratory, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-4204-8777","affiliations":[{"raw_affiliation_string":"The Future Laboratory, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122156861","display_name":"Yueyan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueyan Liu","raw_affiliation_strings":["Future Laboratory, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-8591-1374","affiliations":[{"raw_affiliation_string":"Future Laboratory, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qianyao Xu","orcid":"https://orcid.org/0009-0006-6707-5236"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianyao Xu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-6707-5236","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008892243","display_name":"Xinyi Fu","orcid":"https://orcid.org/0000-0001-6927-0111"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Fu","raw_affiliation_strings":["The Future Laboratory, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6927-0111","affiliations":[{"raw_affiliation_string":"The Future Laboratory, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"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":0.29830333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5029000043869019,"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":0.5029000043869019,"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/T12222","display_name":"IoT-based Smart Home Systems","score":0.10100000351667404,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.05950000137090683,"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/home-automation","display_name":"Home automation","score":0.8978000283241272},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6085000038146973},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.5031999945640564},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46939998865127563},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.45500001311302185},{"id":"https://openalex.org/keywords/building-automation","display_name":"Building automation","score":0.4302999973297119}],"concepts":[{"id":"https://openalex.org/C507571656","wikidata":"https://www.wikidata.org/wiki/Q848436","display_name":"Home automation","level":2,"score":0.8978000283241272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6514000296592712},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6085000038146973},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.45500001311302185},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4359000027179718},{"id":"https://openalex.org/C83931994","wikidata":"https://www.wikidata.org/wiki/Q1149653","display_name":"Building automation","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C152223200","wikidata":"https://www.wikidata.org/wiki/Q3055471","display_name":"Smart environment","level":3,"score":0.38029998540878296},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C2780202397","wikidata":"https://www.wikidata.org/wiki/Q2294986","display_name":"Smart objects","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C176563091","wikidata":"https://www.wikidata.org/wiki/Q669238","display_name":"Intelligent sensor","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.271699994802475}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3742414.3794710","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742414.3794710","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":"Companion Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3742414.3794710","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742414.3794710","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":"Companion Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44952166080474854}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1989244791","https://openalex.org/W1992775733","https://openalex.org/W2002775580","https://openalex.org/W2077356545","https://openalex.org/W2156385131","https://openalex.org/W3185349529","https://openalex.org/W4307472847","https://openalex.org/W4391094120","https://openalex.org/W4392210642","https://openalex.org/W4392210648","https://openalex.org/W4396833646","https://openalex.org/W4400909679","https://openalex.org/W4401985001","https://openalex.org/W4402531536","https://openalex.org/W4403674743","https://openalex.org/W4408735049"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"smart":[1,26,97,113],"home":[2,27,47,98,114],"systems":[3],"often":[4],"rely":[5],"on":[6],"heterogeneous":[7],"sensors":[8],"and":[9,17,52,66,77,88,95,105],"rigid":[10],"rule-based":[11],"pipelines,":[12],"which":[13],"limit":[14],"scalability,":[15],"flexibility,":[16],"ease":[18],"of":[19,107],"deployment.":[20],"We":[21],"propose":[22],"a":[23,37],"highly":[24],"extensible":[25],"framework":[28],"driven":[29],"by":[30],"multimodal":[31],"large":[32],"language":[33],"models":[34],"(MLLMs),":[35],"utilizing":[36],"single":[38],"camera":[39],"as":[40,62],"the":[41,103],"minimal":[42],"sensing":[43],"unit":[44],"for":[45,112],"unified":[46],"environment":[48],"perception,":[49],"structured":[50],"labeling,":[51],"autonomous":[53],"decision-making.":[54],"Our":[55],"system":[56],"automatically":[57],"generates":[58],"standardized":[59],"tags,":[60],"such":[61],"cleanliness,":[63],"object":[64,78],"locations,":[65],"human":[67],"activities,":[68],"to":[69,86],"enable":[70],"functions":[71],"like":[72],"cleaning":[73],"scheduling,":[74],"health":[75],"reporting,":[76],"tracking.":[79],"These":[80],"tags":[81],"can":[82],"also":[83],"be":[84],"extended":[85],"organize":[87],"integrate":[89],"additional":[90],"data":[91],"sources,":[92],"supporting":[93],"comprehensive":[94],"scalable":[96],"management.":[99],"Preliminary":[100],"results":[101],"demonstrate":[102],"feasibility":[104],"promise":[106],"this":[108],"single-camera,":[109],"MLLM-powered":[110],"approach":[111],"automation.":[115]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-10T00:00:00"}
