{"id":"https://openalex.org/W7169673837","doi":"https://doi.org/10.1007/978-981-92-3429-5_11","title":"Semantic-Guided Visual Byte-Pair Encoding for Unified Autoregressive Multimodal Modeling","display_name":"Semantic-Guided Visual Byte-Pair Encoding for Unified Autoregressive Multimodal Modeling","publication_year":2026,"publication_date":"2026-07-18","ids":{"openalex":"https://openalex.org/W7169673837","doi":"https://doi.org/10.1007/978-981-92-3429-5_11"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-3429-5_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-3429-5_11","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5077210450","display_name":"Kangwei Liu","orcid":"https://orcid.org/0009-0006-2807-6199"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kangwei Liu","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212003, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141124778","display_name":"WenLong Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"WenLong Dong","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212003, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112123045","display_name":"Gao L","orcid":null},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijian Gao","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212003, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]},{"id":"https://openalex.org/I4210102840","display_name":"Ubiquitous Energy (United States)","ror":"https://ror.org/01b06j989","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102840"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Qirong Mao","raw_affiliation_strings":["Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications, Zhenjiang, 212003, China","School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications, Zhenjiang, 212003, China","institution_ids":["https://openalex.org/I4210102840"]},{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212003, China","institution_ids":["https://openalex.org/I115592961"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077210450"],"corresponding_institution_ids":["https://openalex.org/I115592961"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"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":"127","last_page":"138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7562999725341797},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6664000153541565},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5975000262260437},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5709999799728394},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.4512999951839447},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.32199999690055847},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.31779998540878296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9020000100135803},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7562999725341797},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6664000153541565},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916000008583069},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5709999799728394},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.32199999690055847},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-3429-5_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-3429-5_11","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2251512949","https://openalex.org/W2560730294","https://openalex.org/W2619383789","https://openalex.org/W2886641317","https://openalex.org/W2963622213","https://openalex.org/W4312846625","https://openalex.org/W4389523832","https://openalex.org/W4402672034","https://openalex.org/W4402727764","https://openalex.org/W4403081466","https://openalex.org/W4404356490","https://openalex.org/W4404784276","https://openalex.org/W4406800520","https://openalex.org/W4411113010","https://openalex.org/W4416036998","https://openalex.org/W7160200801"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-19T06:00:50.952336","created_date":"2026-07-19T00:00:00"}
