{"id":"https://openalex.org/W4415540287","doi":"https://doi.org/10.1145/3746027.3754752","title":"NEXUS-O: An Omni-Perceptive and -Interactive Model for Language, Audio, and Vision","display_name":"NEXUS-O: An Omni-Perceptive and -Interactive Model for Language, Audio, and Vision","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540287","doi":"https://doi.org/10.1145/3746027.3754752"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754752","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":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3754752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103477299","display_name":"Che Liu","orcid":"https://orcid.org/0009-0004-3738-7998"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Che Liu","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0004-3738-7998","affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002797727","display_name":"Yingji Zhang","orcid":"https://orcid.org/0000-0003-1499-3309"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yingji Zhang","raw_affiliation_strings":["University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1499-3309","affiliations":[{"raw_affiliation_string":"University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dong Zhang","orcid":"https://orcid.org/0009-0001-8811-8454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["HiThink Research, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-8811-8454","affiliations":[{"raw_affiliation_string":"HiThink Research, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weijie Zhang","orcid":"https://orcid.org/0009-0002-3352-652X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weijie Zhang","raw_affiliation_strings":["HiThink Research, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-3352-652X","affiliations":[{"raw_affiliation_string":"HiThink Research, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087133043","display_name":"Chenggong Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenggong Gong","raw_affiliation_strings":["HiThink Research, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-6755-5405","affiliations":[{"raw_affiliation_string":"HiThink Research, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Lu","orcid":"https://orcid.org/0009-0003-9695-6241"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Lu","raw_affiliation_strings":["HiThink Research, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-9695-6241","affiliations":[{"raw_affiliation_string":"HiThink Research, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049266156","display_name":"Shilin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin Zhou","raw_affiliation_strings":["Soochow University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-4500-3963","affiliations":[{"raw_affiliation_string":"Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047019585","display_name":"Ziliang Gan","orcid":"https://orcid.org/0009-0000-7450-9887"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziliang Gan","raw_affiliation_strings":["HiThink Research, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-7450-9887","affiliations":[{"raw_affiliation_string":"HiThink Research, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108033372","display_name":"Ziao Wang","orcid":"https://orcid.org/0000-0002-8019-2334"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ziao Wang","raw_affiliation_strings":["Hong Kong Baptist University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8019-2334","affiliations":[{"raw_affiliation_string":"Hong Kong Baptist University, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071627107","display_name":"Haipang Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haipang Wu","raw_affiliation_strings":["HiThink Research, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-0386-8479","affiliations":[{"raw_affiliation_string":"HiThink Research, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396329","display_name":"Ji Liu","orcid":"https://orcid.org/0000-0002-9421-4100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji Liu","raw_affiliation_strings":["HiThink Research, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9421-4100","affiliations":[{"raw_affiliation_string":"HiThink Research, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andre Freitas","orcid":"https://orcid.org/0000-0002-4430-4837"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andre Freitas","raw_affiliation_strings":["University of Manchester, Manchester, United Kingdom and Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-4430-4837","affiliations":[{"raw_affiliation_string":"University of Manchester, Manchester, United Kingdom and Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774659","display_name":"Qifan Wang","orcid":"https://orcid.org/0000-0002-7570-5756"},"institutions":[{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qifan Wang","raw_affiliation_strings":["Meta AI, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0000-0002-7570-5756","affiliations":[{"raw_affiliation_string":"Meta AI, Menlo Park, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051227924","display_name":"Zenglin Xu","orcid":"https://orcid.org/0000-0001-5550-6461"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zenglin Xu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5550-6461","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034543604","display_name":"Rongjunchen Zhang","orcid":"https://orcid.org/0000-0003-1823-2726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongjunchen Zhang","raw_affiliation_strings":["HiThink Research, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1823-2726","affiliations":[{"raw_affiliation_string":"HiThink Research, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046017342","display_name":"Yong Dai","orcid":"https://orcid.org/0000-0002-3041-5851"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Dai","raw_affiliation_strings":["X-Humanoid, Beijing, China and Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3041-5851","affiliations":[{"raw_affiliation_string":"X-Humanoid, Beijing, China and Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":8,"corresponding_author_ids":[],"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":"10787","last_page":"10796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9965999722480774,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.996399998664856,"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/pipeline","display_name":"Pipeline (software)","score":0.704200029373169},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6930000185966492},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4666000008583069},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4487000107765198},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4228000044822693},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.39500001072883606},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.3596999943256378},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35019999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029999732971191},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.704200029373169},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6930000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557000041007996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.54339998960495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47290000319480896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4487000107765198},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3596999943256378},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3366999924182892},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754752","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":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1838824","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1838824","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.1145/3746027.3754752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3754752","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":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2108598243","https://openalex.org/W3156892778","https://openalex.org/W3196509775","https://openalex.org/W3198587774","https://openalex.org/W4401043116","https://openalex.org/W4402684170","https://openalex.org/W4402726948","https://openalex.org/W4405595839"],"related_works":[],"abstract_inverted_index":{"Human":[0],"beings":[1],"perceive":[2],"the":[3,80,87,130,136,142,158,166,171,177,183,205,215,246],"real":[4,201],"world":[5],"through":[6],"a":[7,59,71],"spectrum":[8],"of":[9,54,66,90,132,160,240],"sensory":[10],"modalities,":[11],"encompassing":[12],"auditory,":[13,31],"visual,":[14,32],"and":[15,33,47,114,254],"linguistic":[16,34],"faculties.":[17],"This":[18],"work":[19],"proposes":[20],"an":[21,94,122],"industry-level":[22,123],"omni-modal":[23,124],"large":[24],"language":[25],"model":[26,83,154,172,210],"(LLM)":[27],"pipeline":[28,52,97],"that":[29,75,98,244],"integrates":[30],"modalities":[35],"to":[36,229],"overcome":[37],"challenges":[38],"such":[39,109],"as":[40,110],"limited":[41],"tri-modal":[42,241],"datasets,":[43],"high":[44],"computational":[45],"costs,":[46],"complex":[48],"feature":[49],"alignments.":[50],"Our":[51],"consists":[53],"three":[55],"main":[56],"components:":[57],"First,":[58],"modular,":[60],"end-to-end":[61],"framework":[62],"enabling":[63],"flexible":[64],"configuration":[65],"various":[67],"encoder-LLM-decoder":[68],"architectures.":[69],"Second,":[70],"lightweight":[72],"training":[73,162],"strategy":[74],"pre-trains":[76],"audio-language":[77],"alignment":[78,242,251],"on":[79,219,233],"state-of-the-art":[81],"vision-language":[82],"Qwen2.5-VL,":[84],"thus":[85],"avoiding":[86],"costly":[88],"pre-training":[89],"vision-specific":[91],"modalities.":[92],"Third,":[93],"audio":[95,247],"synthesis":[96],"generates":[99],"high-quality":[100],"audio-text":[101],"data":[102],"from":[103],"diverse":[104],"real-world":[105],"scenarios,":[106],"supporting":[107],"applications":[108],"Automatic":[111],"Speech":[112],"Recognition":[113],"Speech-to-Speech":[115],"chat.":[116],"To":[117],"this":[118],"end,":[119],"we":[120],"introduce":[121],"LLM,":[125],"NEXUS-O.":[126],"Extensive":[127],"experiments":[128],"validate":[129],"efficacy":[131],"our":[133,161,189,209],"pipeline,":[134],"yielding":[135],"following":[137],"key":[138],"findings:":[139],"(1)":[140],"In":[141,188,204,214],"visual":[143],"understanding":[144],"task,":[145,170,208,217],"NEXUSO":[146],"exhibits":[147],"superior":[148],"performance":[149],"compared":[150],"with":[151],"its":[152,198,230],"backbone":[153,231],"-":[155],"Qwen2.5-VL-7B,":[156],"validating":[157],"efficiency":[159],"strategy.":[163],"(2)":[164],"Within":[165],"English":[167],"Spoken":[168],"Question-Answering":[169],"achieves":[173,194],"better":[174],"accuracy":[175],"than":[176],"same-period":[178],"competitor":[179],"(i.e,":[180],"MiniCPM-o2.6-7B)":[181],"in":[182,200],"LLaMA":[184],"Q.":[185],"benchmark.":[186,235],"(3)":[187],"realworld":[190],"ASR":[191],"testset,":[192],"NEXUS-O":[193,226],"outstanding":[195],"performance,":[196],"indicating":[197],"robustness":[199],"scenarios.":[202],"(4)":[203],"Speech-to-Text":[206],"Translation":[207],"outperforms":[211],"Qwen2-Audio-Instruct-7B.":[212],"(5)":[213],"Text-to-Speech":[216],"based":[218],"pretrained":[220],"vocoder":[221,232],"(e.g.,":[222],"Fishspeech1.4":[223],"or":[224],"CosyVoice2.0),":[225],"is":[227],"comparable":[228],"Seed-TTS":[234],"(6)":[236],"An":[237],"in-depth":[238],"analysis":[239],"reveals":[243],"incorporating":[245],"modality":[248],"enhances":[249],"representational":[250],"between":[252],"vision":[253],"language.":[255]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}