{"id":"https://openalex.org/W4416517629","doi":"https://doi.org/10.1109/iccv51701.2025.01206","title":"Unified Multimodal Understanding via Byte-Pair Visual Encoding","display_name":"Unified Multimodal Understanding via Byte-Pair Visual Encoding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416517629","doi":"https://doi.org/10.1109/iccv51701.2025.01206"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.23639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101893972","display_name":"Wanpeng Zhang","orcid":"https://orcid.org/0000-0002-7548-5220"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanpeng Zhang","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100609931","display_name":"Yicheng Feng","orcid":"https://orcid.org/0000-0002-4652-7794"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Feng","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101888089","display_name":"Hao Luo","orcid":"https://orcid.org/0000-0003-3735-6337"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Luo","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005222486","display_name":"Yijiang Li","orcid":"https://orcid.org/0000-0003-0644-7199"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijiang Li","raw_affiliation_strings":["University of California,San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104436927","display_name":"Zihao Yue","orcid":"https://orcid.org/0000-0002-3470-5442"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Yue","raw_affiliation_strings":["School of Information, Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017047744","display_name":"Sipeng Zheng","orcid":"https://orcid.org/0000-0001-5331-6314"},"institutions":[{"id":"https://openalex.org/I2803021693","display_name":"Steinbeis Foundation","ror":"https://ror.org/0184gbk60","country_code":"DE","type":"other","lineage":["https://openalex.org/I2803021693"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sipeng Zheng","raw_affiliation_strings":["BeingBeyond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BeingBeyond","institution_ids":["https://openalex.org/I2803021693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089642905","display_name":"Zongqing Lu","orcid":"https://orcid.org/0000-0003-3967-2704"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongqing Lu","raw_affiliation_strings":["School of Computer Science, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":"12976","last_page":"12986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.982200026512146,"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":0.982200026512146,"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":0.00279999990016222,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.002099999925121665,"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/mirroring","display_name":"Mirroring","score":0.7796000242233276},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6542999744415283},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5227000117301941},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.46309998631477356},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4187999963760376},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3831999897956848},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3813999891281128},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.35249999165534973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101000189781189},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.7796000242233276},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5519999861717224},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.46309998631477356},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3813999891281128},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3424000144004822},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3278999924659729},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C171018156","wikidata":"https://www.wikidata.org/wiki/Q7370306","display_name":"Rotation formalisms in three dimensions","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.23639","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23639","pdf_url":"https://arxiv.org/pdf/2506.23639","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.23639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.23639","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.23639","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.23639","pdf_url":"https://arxiv.org/pdf/2506.23639","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Multimodal":[0],"large":[1],"language":[2,59],"models":[3],"(MLLMs)":[4],"have":[5],"made":[6],"significant":[7],"progress":[8],"in":[9,57],"vision-language":[10,108],"understanding,":[11],"yet":[12],"effectively":[13],"aligning":[14],"different":[15],"modalities":[16],"remains":[17],"a":[18,23,63,76],"fundamental":[19],"challenge.":[20],"We":[21,61],"present":[22],"framework":[24],"that":[25,39,67],"unifies":[26],"multimodal":[27,130],"understanding":[28],"by":[29],"applying":[30],"byte-pair":[31],"encoding":[32,65],"to":[33,91,122],"visual":[34,51,99,115],"tokens.":[35],"Unlike":[36],"conventional":[37],"approaches":[38],"rely":[40],"on":[41,81],"modality-specific":[42],"encoders,":[43],"our":[44,119],"method":[45],"directly":[46],"incorporates":[47],"structural":[48],"information":[49],"into":[50],"tokens,":[52],"mirroring":[53],"successful":[54],"tokenization":[55],"strategies":[56],"text-only":[58],"models.":[60,132],"introduce":[62],"priority-guided":[64],"scheme":[66],"considers":[68],"both":[69],"frequency":[70],"and":[71,96,116,128],"spatial":[72],"consistency,":[73],"coupled":[74],"with":[75,98],"multi-stage":[77],"training":[78],"procedure":[79],"based":[80],"curriculum-driven":[82],"data":[83],"composition.":[84],"These":[85],"enhancements":[86],"enable":[87],"the":[88,112,123],"transformer":[89],"model":[90],"better":[92],"capture":[93],"cross-modal":[94],"relationships":[95],"reason":[97],"information.":[100],"Comprehensive":[101],"experiments":[102],"demonstrate":[103],"improved":[104],"performance":[105],"across":[106],"diverse":[107],"tasks.":[109],"By":[110],"bridging":[111],"gap":[113],"between":[114],"textual":[117],"representations,":[118],"approach":[120],"contributes":[121],"advancement":[124],"of":[125],"more":[126],"capable":[127],"efficient":[129],"foundation":[131]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}