{"id":"https://openalex.org/W4407359580","doi":"https://doi.org/10.1109/iccv51701.2025.01953","title":"EVEv2: Improved Baselines for Encoder-Free Vision-Language Models","display_name":"EVEv2: Improved Baselines for Encoder-Free Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4407359580","doi":"https://doi.org/10.1109/iccv51701.2025.01953"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01953","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/2502.06788","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015049935","display_name":"Haiwen Diao","orcid":"https://orcid.org/0000-0002-4156-5417"},"institutions":[{"id":"https://openalex.org/I38007976","display_name":"De Lin Institute of Technology","ror":"https://ror.org/00y3by878","country_code":"TW","type":"education","lineage":["https://openalex.org/I38007976"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Haiwen Diao","raw_affiliation_strings":["DLUT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DLUT","institution_ids":["https://openalex.org/I38007976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371872","display_name":"Xiaotong Li","orcid":"https://orcid.org/0000-0001-9960-5373"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaotong Li","raw_affiliation_strings":["PKU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PKU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070703617","display_name":"Yufeng Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufeng Cui","raw_affiliation_strings":["BAAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BAAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038675825","display_name":"Yueze Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yueze Wang","raw_affiliation_strings":["BAAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BAAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070145690","display_name":"Haoge Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoge Deng","raw_affiliation_strings":["BUPT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BUPT","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050986728","display_name":"Ting Pan","orcid":"https://orcid.org/0000-0003-3774-7450"},"institutions":[{"id":"https://openalex.org/I9796191","display_name":"University College of Applied Science","ror":"https://ror.org/00f72x493","country_code":"PS","type":"education","lineage":["https://openalex.org/I9796191"]}],"countries":["PS"],"is_corresponding":false,"raw_author_name":"Ting Pan","raw_affiliation_strings":["UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCAS","institution_ids":["https://openalex.org/I9796191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084395808","display_name":"Wenxuan Wang","orcid":"https://orcid.org/0000-0002-0193-816X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxuan Wang","raw_affiliation_strings":["CASIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CASIA","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[{"id":"https://openalex.org/I38007976","display_name":"De Lin Institute of Technology","ror":"https://ror.org/00y3by878","country_code":"TW","type":"education","lineage":["https://openalex.org/I38007976"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["DLUT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DLUT","institution_ids":["https://openalex.org/I38007976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101453649","display_name":"Xin-Long Wang","orcid":"https://orcid.org/0000-0002-5279-5859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinlong Wang","raw_affiliation_strings":["BAAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BAAI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01482565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21014","last_page":"21025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9681000113487244,"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":0.9681000113487244,"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/encoder","display_name":"Encoder","score":0.6787430047988892},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6106455326080322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4032039940357208},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3822461664676666},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32640647888183594}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6787430047988892},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6106455326080322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4032039940357208},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3822461664676666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32640647888183594},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01953","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:2502.06788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.06788","pdf_url":"https://arxiv.org/pdf/2502.06788","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.2502.06788","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.06788","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:2502.06788","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.06788","pdf_url":"https://arxiv.org/pdf/2502.06788","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":[{"id":"https://openalex.org/G1276140022","display_name":null,"funder_award_id":"62293542","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3913634163","display_name":null,"funder_award_id":"62441231,62293542","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4087307477","display_name":null,"funder_award_id":"2022ZD0116302","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4585823974","display_name":null,"funder_award_id":"62441231","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6444725075","display_name":null,"funder_award_id":"LD25F020001","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407359580.pdf","grobid_xml":"https://content.openalex.org/works/W4407359580.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Existing":[0],"encoder-free":[1,55,62,82,113],"vision-language":[2],"models":[3],"(VLMs)":[4],"are":[5],"rapidly":[6],"narrowing":[7],"the":[8,16,32,51],"performance":[9,33],"gap":[10,34],"with":[11,23],"their":[12],"encoder-based":[13,67],"counterparts,":[14],"highlighting":[15],"promising":[17],"potential":[18],"for":[19,61,112,124],"unified":[20,98],"multimodal":[21],"systems":[22],"structural":[24],"simplicity":[25],"and":[26,43,78,90,94,135],"efficient":[27,59],"deployment.":[28],"We":[29,57,84],"systematically":[30],"clarify":[31],"between":[35,102],"VLMs":[36,63],"using":[37],"pre-trained":[38],"vision":[39,93],"encoders,":[40],"discrete":[41],"tokenizers,":[42],"minimalist":[44],"visual":[45],"layers":[46],"from":[47],"scratch,":[48],"deeply":[49],"excavating":[50],"under-examined":[52],"characteristics":[53],"of":[54,81],"VLMs.":[56,83,114],"develop":[58],"strategies":[60],"that":[64],"rival":[65],"mainstream":[66],"ones.":[68],"After":[69],"an":[70],"in-depth":[71],"investigation,":[72],"we":[73],"launch":[74],"EVEv2.0,":[75],"a":[76,97,121,126],"new":[77],"improved":[79],"family":[80],"show":[85],"that:":[86],"(i)":[87],"Properly":[88],"decomposing":[89],"hierarchically":[91],"associating":[92],"language":[95],"within":[96],"model":[99],"reduces":[100],"interference":[101],"modalities.":[103],"(ii)":[104],"A":[105],"well-designed":[106],"training":[107],"strategy":[108],"enables":[109],"effective":[110],"optimization":[111],"Through":[115],"extensive":[116],"evaluation,":[117],"our":[118],"EVEv2.0":[119],"represents":[120],"thorough":[122],"study":[123],"developing":[125],"decoder-only":[127],"architecture":[128],"across":[129],"modalities,":[130],"demonstrating":[131],"superior":[132],"data":[133],"efficiency":[134],"strong":[136],"vision-reasoning":[137],"capability.":[138],"Code":[139],"is":[140],"publicly":[141],"available":[142],"at:":[143],"https://github.com/baaivision/EVE.":[144]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}