{"id":"https://openalex.org/W4402727635","doi":"https://doi.org/10.1109/cvpr52733.2024.02512","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","display_name":"ModaVerse: Efficiently Transforming Modalities with LLMs","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402727635","doi":"https://doi.org/10.1109/cvpr52733.2024.02512"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.02512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070947544","display_name":"Xinyu Wang","orcid":"https://orcid.org/0000-0003-2085-8824"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076928390","display_name":"Bohan Zhuang","orcid":"https://orcid.org/0000-0002-0074-0303"},"institutions":[{"id":"https://openalex.org/I2801239119","display_name":"Australian Regenerative Medicine Institute","ror":"https://ror.org/02qa5kg76","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2801037857","https://openalex.org/I2801239119","https://openalex.org/I56590836"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bohan Zhuang","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I2801239119","https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060958969","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-3631-256X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26596","last_page":"26606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9430999755859375,"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/T10028","display_name":"Topic Modeling","score":0.926800012588501,"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/modalities","display_name":"Modalities","score":0.7360624074935913},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4853212237358093},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.1121549904346466},{"id":"https://openalex.org/keywords/social-science","display_name":"Social science","score":0.10882106423377991}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7360624074935913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4853212237358093},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.1121549904346466},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.10882106423377991}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.02512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.02512","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2425121537","https://openalex.org/W2966715458","https://openalex.org/W2969876226","https://openalex.org/W3035365026","https://openalex.org/W3035644209","https://openalex.org/W3091588028","https://openalex.org/W3165647589","https://openalex.org/W3166396011","https://openalex.org/W3168867926","https://openalex.org/W4225323055","https://openalex.org/W4226125322","https://openalex.org/W4226174231","https://openalex.org/W4281632497","https://openalex.org/W4281633595","https://openalex.org/W4283026156","https://openalex.org/W4292779060","https://openalex.org/W4296406182","https://openalex.org/W4312933868","https://openalex.org/W4318718936","https://openalex.org/W4318718996","https://openalex.org/W4318752004","https://openalex.org/W4319049530","https://openalex.org/W4320165837","https://openalex.org/W4320458302","https://openalex.org/W4322718191","https://openalex.org/W4353113046","https://openalex.org/W4361194507","https://openalex.org/W4361866031","https://openalex.org/W4366330503","https://openalex.org/W4366456807","https://openalex.org/W4366566341","https://openalex.org/W4366850747","https://openalex.org/W4367359628","https://openalex.org/W4376167553","https://openalex.org/W4377372281","https://openalex.org/W4378711593","https://openalex.org/W4378768739","https://openalex.org/W4384112212","https://openalex.org/W4384918448","https://openalex.org/W4386065764","https://openalex.org/W4386555501","https://openalex.org/W4386556027","https://openalex.org/W4386655647","https://openalex.org/W4386794869","https://openalex.org/W4386942465","https://openalex.org/W4387156669","https://openalex.org/W4387294588","https://openalex.org/W4387723654","https://openalex.org/W4390872747","https://openalex.org/W4402727764","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6773842166","https://openalex.org/W6775970589","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6796242362","https://openalex.org/W6796581206","https://openalex.org/W6810334672","https://openalex.org/W6810940779","https://openalex.org/W6811156277","https://openalex.org/W6838461927","https://openalex.org/W6838785959","https://openalex.org/W6839015040","https://openalex.org/W6842585177","https://openalex.org/W6849109464","https://openalex.org/W6849177959","https://openalex.org/W6849307739","https://openalex.org/W6849416043","https://openalex.org/W6849732303","https://openalex.org/W6850204008","https://openalex.org/W6851513886","https://openalex.org/W6851592950","https://openalex.org/W6852410717","https://openalex.org/W6852975727","https://openalex.org/W6853040936"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2185469136","https://openalex.org/W2011264131","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4306353150","https://openalex.org/W2026860389","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Humans":[0],"possess":[1],"the":[2,102,109,113,119,128,155,158],"capability":[3],"to":[4],"comprehend":[5],"diverse":[6],"modalities":[7,34],"and":[8,29,38,52,69,126],"seamlessly":[9],"transfer":[10],"information":[11],"between":[12],"them.":[13],"In":[14],"this":[15],"work,":[16],"we":[17,90,146],"introduce":[18],"ModaVerse,":[19],"a":[20,60,92,136],"Multi-modal":[21],"Large":[22],"Language":[23],"Model":[24],"(MLLM)":[25],"capable":[26],"of":[27,50,79,104,115,132,157],"comprehending":[28],"transforming":[30],"content":[31],"across":[32],"various":[33],"in-cluding":[35],"images,":[36],"videos,":[37],"audio.":[39],"Predominant":[40],"MLLM":[41],"frameworks":[42],"have":[43],"largely":[44],"relied":[45],"on":[46,64,72,143],"aligning":[47],"latent":[48,123],"spaces":[49],"textual":[51],"non-textual":[53],"features.":[54],"This":[55],"alignment":[56,96],"process,":[57],"which":[58],"synchronizes":[59],"language":[61],"model":[62],"trained":[63,71],"tex-tual":[65],"data":[66,165],"with":[67,112,122,154],"encoders":[68],"decoders":[70],"multimodal":[73],"data,":[74],"often":[75],"necessitates":[76],"extensive":[77],"training":[78,130],"several":[80,144],"projection":[81],"layers":[82],"in":[83,164],"multiple":[84,129],"stages.":[85],"Inspired":[86],"by":[87],"LLM-as-agent":[88],"methodologies,":[89],"propose":[91],"novel":[93],"Input/Output":[94],"(I/O)":[95],"mechanism":[97],"that":[98,148],"operates":[99],"directly":[100],"at":[101,171],"level":[103],"natural":[105],"language.":[106],"It":[107],"aligns":[108],"LLM's":[110],"output":[111],"input":[114],"generative":[116],"models,":[117],"avoiding":[118],"complexities":[120],"associated":[121],"feature":[124],"alignments,":[125],"simplifying":[127],"stages":[131],"existing":[133],"MLLMs":[134],"into":[135],"single,":[137],"efficient":[138],"process.":[139],"By":[140],"conducting":[141],"experiments":[142],"benchmarks,":[145],"demonstrate":[147],"our":[149],"approach":[150],"at-tains":[151],"comparable":[152],"performance":[153],"state":[156],"art":[159],"while":[160],"achieving":[161],"considerable":[162],"efficiencies":[163],"usage.":[166],"The":[167],"code":[168],"is":[169],"available":[170],"https://github.com/xinke-wang/ModaVerse.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}