{"id":"https://openalex.org/W4404990078","doi":"https://doi.org/10.1109/iccv51701.2025.02237","title":"MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding","display_name":"MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404990078","doi":"https://doi.org/10.1109/iccv51701.2025.02237"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02237","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.17762","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114988477","display_name":"Rongchang Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongchang Xie","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114988478","display_name":"Chen Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Du","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083640604","display_name":"Ping Song","orcid":"https://orcid.org/0000-0001-7939-1902"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Song","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102921312","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0003-0846-956X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang Liu","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00070687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24135","last_page":"24146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.775600016117096,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.775600016117096,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.7402999997138977,"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/T10320","display_name":"Neural Networks and Applications","score":0.7257000207901001,"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/encoding","display_name":"Encoding (memory)","score":0.6825871467590332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5918075442314148},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3360399305820465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24205145239830017}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6825871467590332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5918075442314148},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3360399305820465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24205145239830017}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02237","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:2411.17762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.17762","pdf_url":"https://arxiv.org/pdf/2411.17762","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.2411.17762","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.17762","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.17762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.17762","pdf_url":"https://arxiv.org/pdf/2411.17762","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0],"introduce":[1],"MUSE-VL,":[2],"a":[3,57],"Unified":[4],"Vision-Language":[5],"Model":[6],"through":[7],"Semantic":[8,80],"discrete":[9],"Encoding":[10,82],"for":[11,25],"multimodal":[12],"understanding":[13,75,128,142],"and":[14,28,55,92,111,138],"generation.":[15],"Recently,":[16],"the":[17,87,100,106,113,116,120,127,134,140,152],"research":[18],"community":[19],"has":[20],"begun":[21],"exploring":[22],"unified":[23,117,154],"models":[24,155],"visual":[26,90,101,157],"generation":[27,158],"understanding.":[29],"However,":[30],"existing":[31,153],"vision":[32],"tokenizers":[33],"(e.g.,":[34],"VQGAN)":[35],"only":[36],"consider":[37],"low-level":[38],"information,":[39],"which":[40,84],"makes":[41],"it":[42],"difficult":[43],"to":[44,63,99,133],"align":[45],"with":[46],"language":[47,93],"tokens.":[48],"This":[49,77,103],"results":[50],"in":[51],"high":[52],"training":[53,61,109],"complexity":[54],"necessitates":[56],"large":[58],"amount":[59,107],"of":[60,89,108,115],"data":[62,110],"achieve":[64],"optimal":[65],"performance.":[66],"Additionally,":[67],"their":[68],"performance":[69,114,129],"is":[70],"still":[71],"far":[72],"from":[73],"dedicated":[74,141],"models.":[76],"paper":[78],"proposes":[79],"Discrete":[81],"(SDE),":[83],"effectively":[85],"aligns":[86],"information":[88],"tokens":[91,94],"by":[95,130,146],"adding":[96],"semantic":[97],"constraints":[98],"tokenizer.":[102],"greatly":[104],"reduces":[105],"improves":[112],"model.":[118],"With":[119],"same":[121],"LLM":[122],"size,":[123],"our":[124],"method":[125],"improved":[126],"4.8%":[131],"compared":[132],"previous":[135],"SOTA":[136],"Emu3":[137],"surpassed":[139],"model":[143,149],"LLaVA-NeXT":[144],"34B":[145],"3.7%.":[147],"Our":[148],"also":[150],"surpasses":[151],"on":[156],"benchmarks.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}