{"id":"https://openalex.org/W7135019269","doi":"https://doi.org/10.1145/3776734.3796242","title":"Multimodal Large Language Models for Real-Time Situated Reasoning","display_name":"Multimodal Large Language Models for Real-Time Situated Reasoning","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135019269","doi":"https://doi.org/10.1145/3776734.3796242"},"language":"en","primary_location":{"id":"doi:10.1145/3776734.3796242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3796242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.01880","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013548937","display_name":"Giulio Antonio Abbo","orcid":"https://orcid.org/0000-0001-6301-0028"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Giulio Antonio Abbo","raw_affiliation_strings":["Ghent University \u2013 imec, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-6301-0028","affiliations":[{"raw_affiliation_string":"Ghent University \u2013 imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129091622","display_name":"Senne Lenaerts","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Senne Lenaerts","raw_affiliation_strings":["Ghent University \u2013 imec, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0009-0002-9357-9666","affiliations":[{"raw_affiliation_string":"Ghent University \u2013 imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129025485","display_name":"Tony Belpaeme","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tony Belpaeme","raw_affiliation_strings":["Ghent University \u2013 imec, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-5207-7745","affiliations":[{"raw_affiliation_string":"Ghent University \u2013 imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1161","last_page":"1163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3221000134944916,"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":0.3221000134944916,"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/T12031","display_name":"Speech and dialogue systems","score":0.2215999960899353,"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/T10028","display_name":"Topic Modeling","score":0.149399995803833,"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/situated","display_name":"Situated","score":0.6114000082015991},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34860000014305115},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.320499986410141},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.32019999623298645},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.311599999666214},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3061000108718872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6226000189781189},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4510999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44290000200271606},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.373199999332428},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.263700008392334}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3776734.3796242","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3776734.3796242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.01880","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.01880","pdf_url":"https://arxiv.org/pdf/2602.01880","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:archive.ugent.be:01KM2WZGH30FGFSSGTYTBMQ7C9","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01KM2WZGH30FGFSSGTYTBMQ7C9","pdf_url":"https://biblio.ugent.be/publication/01KM2WZGH30FGFSSGTYTBMQ7C9/file/01KM2X26BT7FX9FXQB4R8QAZ92","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9798400723216","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.01880","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.01880","pdf_url":"https://arxiv.org/pdf/2602.01880","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4313293993473053}],"awards":[{"id":"https://openalex.org/G5083669671","display_name":null,"funder_award_id":"101070930","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G669774598","display_name":"Value-Aware Artificial Intelligence","funder_award_id":"101070930","funder_id":"https://openalex.org/F4320338448","funder_display_name":"HORIZON EUROPE European Innovation Council"}],"funders":[{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320338448","display_name":"HORIZON EUROPE European Innovation Council","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7135019269.pdf","grobid_xml":"https://content.openalex.org/works/W7135019269.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W4280571816","https://openalex.org/W4318969863","https://openalex.org/W4408665449","https://openalex.org/W4410296745","https://openalex.org/W4414485088","https://openalex.org/W7124180503"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,20],"explore":[4],"how":[5],"multimodal":[6,120],"large":[7,121],"language":[8,24,122],"models":[9,64,123],"can":[10],"support":[11],"real-time":[12,140],"context-":[13],"and":[14,48,72,75,91,108,128,139],"value-aware":[15],"decision-making.":[16],"To":[17],"do":[18],"so,":[19],"combine":[21],"the":[22,43,60,81,84,95,117],"GPT-4o":[23],"model":[25,41],"with":[26,80],"a":[27,32,38,98],"TurtleBot":[28],"4":[29],"platform":[30],"simulating":[31],"smart":[33],"vacuum":[34],"cleaning":[35],"robot":[36],"in":[37,97,124],"home.":[39],"The":[40,57],"evaluates":[42],"environment":[44],"through":[45],"vision":[46],"input":[47],"determines":[49],"whether":[50],"it":[51],"is":[52],"appropriate":[53],"to":[54,65,105,136],"initiate":[55],"cleaning.":[56],"system":[58,96],"highlights":[59],"ability":[61,104],"of":[62,83,119],"these":[63],"reason":[66],"about":[67],"domestic":[68],"activities,":[69],"social":[70],"norms,":[71],"user":[73],"preferences":[74],"take":[76],"nuanced":[77],"decisions":[78],"aligned":[79],"values":[82,109],"people":[85],"involved,":[86],"such":[87],"as":[88],"cleanliness,":[89],"comfort,":[90],"safety.":[92],"We":[93],"demonstrate":[94],"realistic":[99],"home":[100],"environment,":[101],"showing":[102],"its":[103],"infer":[106],"context":[107],"from":[110],"limited":[111],"visual":[112],"input.":[113],"Our":[114],"results":[115],"highlight":[116],"promise":[118],"enhancing":[125],"robotic":[126],"autonomy":[127],"situational":[129],"awareness,":[130],"while":[131],"also":[132],"underscoring":[133],"challenges":[134],"related":[135],"consistency,":[137],"bias,":[138],"performance.":[141]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2026-02-06T00:00:00"}
