{"id":"https://openalex.org/W7160280549","doi":"https://doi.org/10.1109/wacv61042.2026.00054","title":"Interleaved Vision-and-Language Generation via Generative Voken","display_name":"Interleaved Vision-and-Language Generation via Generative Voken","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160280549","doi":"https://doi.org/10.1109/wacv61042.2026.00054"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5004952111","display_name":"Kaizhi Zheng","orcid":"https://orcid.org/0000-0002-8718-1603"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaizhi Zheng","raw_affiliation_strings":["University of California,Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101181260","display_name":"Xuehai He","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuehai He","raw_affiliation_strings":["University of California,Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135342829","display_name":"Xin Eric Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Eric Wang","raw_affiliation_strings":["University of California,Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185103710"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51645629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"472","last_page":"482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5853000283241272,"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":0.5853000283241272,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.042500000447034836,"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/T12090","display_name":"Language and cultural evolution","score":0.03150000050663948,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2955000102519989},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.28200000524520874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.26899999380111694},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.26489999890327454},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.2533000111579895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5698999762535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510699987411499},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26089999079704285},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.24860000610351562}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2169203263","https://openalex.org/W2886641317","https://openalex.org/W2970641574","https://openalex.org/W3087871082","https://openalex.org/W3101065397","https://openalex.org/W3174770825","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4385565405","https://openalex.org/W4385571466","https://openalex.org/W4402727764","https://openalex.org/W4410536678","https://openalex.org/W7133185348","https://openalex.org/W7133196460","https://openalex.org/W7133209381","https://openalex.org/W7133211372","https://openalex.org/W7133220561","https://openalex.org/W7133233472"],"related_works":[],"abstract_inverted_index":{"The":[0,116],"effectiveness":[1],"of":[2,19,41,75,85],"Multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"demonstrates":[8],"a":[9,31,60],"profound":[10],"capability":[11],"in":[12],"multimodal":[13,67,96,109,133],"understanding.":[14],"However,":[15],"the":[16,39,83,105,124],"simultaneous":[17],"generation":[18,35,110],"images":[20,87],"with":[21],"coherent":[22,52],"texts":[23],"is":[24,57,121],"still":[25],"underdeveloped.":[26],"Addressing":[27],"this,":[28],"we":[29],"introduce":[30],"novel":[32],"interleaved":[33],"vision-and-language":[34],"method,":[36],"centered":[37],"around":[38],"concept":[40],"\"generative":[42],"vokens\".":[43],"These":[44],"vokens":[45],"serve":[46],"as":[47],"pivotal":[48],"elements":[49],"contributing":[50],"to":[51,81],"image-text":[53],"outputs.":[54],"Our":[55,98],"method":[56],"marked":[58],"by":[59],"unique":[61],"two-stage":[62],"training":[63],"strategy":[64],"for":[65,132],"description-free":[66],"generation,":[68,134],"which":[69],"does":[70],"not":[71],"necessitate":[72],"extensive":[73],"descriptions":[74],"images.":[76],"We":[77],"integrate":[78],"classifier-free":[79],"guidance":[80],"enhance":[82],"alignment":[84],"generated":[86],"and":[88,93,114],"texts,":[89],"ensuring":[90],"more":[91,128],"seamless":[92],"contextually":[94],"relevant":[95],"interactions.":[97],"model,":[99],"MiniGPT-5,":[100],"exhibits":[101],"substantial":[102],"improvement":[103],"over":[104],"baseline":[106,125],"models":[107],"on":[108,127],"datasets,":[111],"including":[112],"MMDialog":[113],"VIST.":[115],"human":[117],"evaluation":[118],"shows":[119],"MiniGPT-5":[120],"better":[122],"than":[123,129],"model":[126],"56%":[130],"cases":[131],"highlighting":[135],"its":[136],"efficacy":[137],"across":[138],"diverse":[139],"benchmarks.":[140],"Project":[141],"page:":[142],"https://eric-ai-lab.github.io/minigpt-5.github.io/.":[143]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}