{"id":"https://openalex.org/W7133207314","doi":"https://doi.org/10.48550/arxiv.2602.23739","title":"U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation","display_name":"U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation","publication_year":2026,"publication_date":"2026-02-27","ids":{"openalex":"https://openalex.org/W7133207314","doi":"https://doi.org/10.48550/arxiv.2602.23739"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.23739","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.23739","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.23739","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127870308","display_name":"Xiang Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Deng, Xiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127828557","display_name":"Feng Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Feng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127779054","display_name":"Yong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127810984","display_name":"Youxin Pang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pang, Youxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127870158","display_name":"Xu Xiaoming","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoming, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127845104","display_name":"Zhuoliang Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Zhuoliang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127845895","display_name":"Xiaoming Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Xiaoming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127789437","display_name":"Yebin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yebin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5127870308"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9599000215530396,"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":0.9599000215530396,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.008100000210106373,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.007600000128149986,"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/rendering","display_name":"Rendering (computer graphics)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4991999864578247},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.49000000953674316},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.47530001401901245},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.40869998931884766},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.382099986076355},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.35499998927116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922999858856201},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5771999955177307},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4991999864578247},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4293999969959259},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.23739","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.23739","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.23739","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.23739","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.42758017778396606,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Full-stack":[0],"multimodal":[1,55,160],"interaction":[2,161],"in":[3,9],"real-time":[4,59,133],"is":[5],"a":[6,71,80,95,110,132,157],"central":[7],"goal":[8],"building":[10],"intelligent":[11],"embodied":[12],"agents":[13],"capable":[14],"of":[15,159],"natural,":[16],"dynamic":[17],"communication.":[18],"However,":[19],"existing":[20],"systems":[21],"are":[22],"either":[23],"limited":[24],"to":[25],"unimodal":[26],"generation":[27,60,123],"or":[28],"suffer":[29],"from":[30],"degraded":[31],"reasoning":[32,101],"and":[33,39,61,67,83,99,140,144,168],"poor":[34],"cross-modal":[35,92],"alignment,":[36],"preventing":[37],"coherent":[38],"perceptually":[40],"grounded":[41],"interactions.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,130],"introduce":[47],"U-Mind,":[48],"the":[49,128,172],"first":[50],"unified":[51],"system":[52],"for":[53],"high-intelligence":[54],"dialogue":[56],"that":[57,86,114,151],"supports":[58],"jointly":[62],"models":[63],"language,":[64],"speech,":[65,141],"motion,":[66],"video":[68,134],"synthesis":[69],"within":[70],"single":[72],"interactive":[73],"loop.":[74],"At":[75],"its":[76],"core,":[77],"U-Mind":[78,108,152],"implements":[79],"Unified":[81],"Alignment":[82],"Reasoning":[84],"Framework":[85],"addresses":[87],"two":[88],"key":[89],"challenges:":[90],"enhancing":[91],"synchronization":[93],"via":[94],"segment-wise":[96],"alignment":[97],"strategy,":[98],"preserving":[100],"abilities":[102],"through":[103],"Rehearsal-Driven":[104],"Learning.":[105],"During":[106],"inference,":[107],"adopts":[109],"text-first":[111],"decoding":[112],"pipeline":[113],"performs":[115],"internal":[116],"chain-of-thought":[117],"planning":[118],"followed":[119],"by":[120],"temporally":[121],"synchronized":[122,145],"across":[124],"modalities.":[125],"To":[126],"close":[127],"loop,":[129],"implement":[131],"rendering":[135],"framework":[136],"conditioned":[137],"on":[138,156],"pose":[139],"enabling":[142],"expressive":[143],"visual":[146],"feedback.":[147],"Extensive":[148],"experiments":[149],"demonstrate":[150],"achieves":[153],"state-of-the-art":[154],"performance":[155],"range":[158],"tasks,":[162],"including":[163],"question":[164],"answering,":[165],"instruction":[166],"following,":[167],"motion":[169],"generation,":[170],"paving":[171],"way":[173],"toward":[174],"intelligent,":[175],"immersive":[176],"conversational":[177],"agents.":[178]},"counts_by_year":[],"updated_date":"2026-03-03T06:18:10.843953","created_date":"2026-03-03T00:00:00"}