{"id":"https://openalex.org/W4414360209","doi":"https://doi.org/10.24963/ijcai.2025/167","title":"A Dual Stream Visual Tokenizer for LLM Image Generation","display_name":"A Dual Stream Visual Tokenizer for LLM Image Generation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360209","doi":"https://doi.org/10.24963/ijcai.2025/167"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/167","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5112483092","display_name":"Yongqian Li","orcid":"https://orcid.org/0009-0005-3176-8156"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Yongqian Li","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039158745","display_name":"Yong Luo","orcid":"https://orcid.org/0000-0002-2296-6370"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Yong Luo","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003753939","display_name":"Xiantao Cai","orcid":"https://orcid.org/0000-0002-0764-5085"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Xiantao Cai","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034648573","display_name":"Zheng He","orcid":"https://orcid.org/0000-0002-7700-0901"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Zheng He","raw_affiliation_strings":["School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111871536","display_name":"Z MENG","orcid":null},"institutions":[{"id":"https://openalex.org/I182937616","display_name":"Hyundai Mobis (South Korea)","ror":"https://ror.org/038b1qn73","country_code":"KR","type":"company","lineage":["https://openalex.org/I182937616","https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zhennan Meng","raw_affiliation_strings":["Mobvoi Innovation Technology Company Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobvoi Innovation Technology Company Limited","institution_ids":["https://openalex.org/I182937616"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nidong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I182937616","display_name":"Hyundai Mobis (South Korea)","ror":"https://ror.org/038b1qn73","country_code":"KR","type":"company","lineage":["https://openalex.org/I182937616","https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nidong Wang","raw_affiliation_strings":["Mobvoi Innovation Technology Company Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobvoi Innovation Technology Company Limited","institution_ids":["https://openalex.org/I182937616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102788683","display_name":"Yunlin Chen","orcid":"https://orcid.org/0000-0001-7423-983X"},"institutions":[{"id":"https://openalex.org/I182937616","display_name":"Hyundai Mobis (South Korea)","ror":"https://ror.org/038b1qn73","country_code":"KR","type":"company","lineage":["https://openalex.org/I182937616","https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunlin Chen","raw_affiliation_strings":["Mobvoi Innovation Technology Company Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobvoi Innovation Technology Company Limited","institution_ids":["https://openalex.org/I182937616"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100782895","display_name":"Zhifei Li","orcid":"https://orcid.org/0000-0002-7720-8403"},"institutions":[{"id":"https://openalex.org/I182937616","display_name":"Hyundai Mobis (South Korea)","ror":"https://ror.org/038b1qn73","country_code":"KR","type":"company","lineage":["https://openalex.org/I182937616","https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Zhifei Li","raw_affiliation_strings":["Mobvoi Innovation Technology Company Limited"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mobvoi Innovation Technology Company Limited","institution_ids":["https://openalex.org/I182937616"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"1494","last_page":"1502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.8945000171661377,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.8945000171661377,"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":0.8761000037193298,"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/T11439","display_name":"Video Analysis and Summarization","score":0.8224999904632568,"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/security-token","display_name":"Security token","score":0.6741999983787537},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6565999984741211},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6500999927520752},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4993000030517578},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4683000147342682},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4309000074863434},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.3767000138759613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410999774932861},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6741999983787537},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6565999984741211},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6500999927520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.647599995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6198999881744385},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/167","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"proposes":[1],"a":[2,59,84,89,97],"novel":[3],"visual":[4,32],"tokenizer":[5],"by":[6],"combining":[7],"high-level":[8,62],"semantic":[9,63,106],"tokens":[10,14,64,75,82,119],"and":[11,37,96,108,120,134],"low-level":[12,73],"pixel":[13,74],"to":[15,19,51,92,100],"represent":[16],"images,":[17],"aiming":[18],"address":[20],"the":[21,66,70,115],"challenges":[22],"of":[23,69,117],"image-to-sequence":[24],"conversion":[25],"for":[26,129],"Large":[27],"Language":[28],"Models":[29],"(LLMs).":[30],"Existing":[31],"tokenizers,":[33],"such":[34],"as":[35,45],"VQ-VAE":[36,90],"diffusion-based":[38],"models,":[39],"either":[40],"struggle":[41],"with":[42,104],"token":[43],"explosion":[44],"image":[46,122,132],"resolution":[47],"increases":[48],"or":[49],"fail":[50],"capture":[52,65],"detailed":[53],"structural":[54,77,109],"information.":[55],"Our":[56],"method":[57],"introduces":[58],"dual-token":[60],"system:":[61],"main":[67],"content":[68],"image,":[71],"while":[72],"preserve":[76],"details.":[78],"By":[79],"integrating":[80],"these":[81],"in":[83],"hybrid":[85],"architecture,":[86],"we":[87],"leverage":[88],"branch":[91],"generate":[93],"low-resolution":[94],"guidance":[95],"diffusion":[98],"process":[99],"reconstruct":[101],"high-resolution":[102],"images":[103],"both":[105],"coherence":[107],"accuracy.":[110],"This":[111],"approach":[112],"significantly":[113],"reduces":[114],"number":[116],"required":[118],"enhances":[121],"reconstruction":[123],"quality,":[124],"offering":[125],"an":[126],"efficient":[127],"solution":[128],"tasks":[130],"like":[131],"generation":[133],"understanding":[135],"based":[136],"on":[137],"LLMs.":[138]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
