{"id":"https://openalex.org/W4414414062","doi":"https://doi.org/10.1109/iccv51701.2025.02057","title":"Advancing Visual Large Language Model for Multi-Granular Versatile Perception","display_name":"Advancing Visual Large Language Model for Multi-Granular Versatile Perception","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414414062","doi":"https://doi.org/10.1109/iccv51701.2025.02057"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02057","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.16213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057441439","display_name":"Wentao Xiang","orcid":"https://orcid.org/0000-0002-6891-6088"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wentao Xiang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071239924","display_name":"Haoxian Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoxian Tan","raw_affiliation_strings":["Meituan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390457","display_name":"Cong Wei","orcid":"https://orcid.org/0000-0002-1492-7240"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujie Zhong","raw_affiliation_strings":["Meituan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028886830","display_name":"Yujie Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Wei","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084583022","display_name":"Dengjie Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dengjie Li","raw_affiliation_strings":["Meituan Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020953714","display_name":"Yujiu Yang","orcid":"https://orcid.org/0000-0002-6427-1024"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujiu Yang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5057441439"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2289268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22153","last_page":"22164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9696999788284302,"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":0.9696999788284302,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9401999711990356,"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/perception","display_name":"Perception","score":0.5976999998092651},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5450000166893005},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5135999917984009},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5076000094413757},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5073999762535095},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.3952000141143799},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.37770000100135803},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3125999867916107}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770000100135803},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5976999998092651},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48899999260902405},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4611999988555908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32190001010894775},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3100999891757965},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30300000309944153},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25290000438690186}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02057","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:2507.16213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.16213","pdf_url":"https://arxiv.org/pdf/2507.16213","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2507.16213","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.16213","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:2507.16213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.16213","pdf_url":"https://arxiv.org/pdf/2507.16213","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/G5436302066","display_name":null,"funder_award_id":"2024YFB2808903","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Perception":[0,70],"is":[1,79],"a":[2,12,42,66,95,107,117,138,157],"fundamental":[3],"task":[4],"in":[5,104,151,161],"the":[6,145,169],"field":[7],"of":[8,15,45,120,159,171],"computer":[9],"vision,":[10],"encompassing":[11],"diverse":[13],"set":[14],"subtasks":[16],"that":[17],"can":[18],"be":[19,177],"systematically":[20],"categorized":[21],"into":[22],"four":[23],"distinct":[24],"groups":[25],"based":[26],"on":[27,41],"two":[28],"dimensions:":[29],"prediction":[30],"type":[31],"and":[32,53,68,85,91,131,147,164],"instruction":[33],"type.":[34],"Notably,":[35],"existing":[36],"researches":[37],"often":[38],"focus":[39],"solely":[40],"limited":[43,125],"subset":[44],"these":[46],"potential":[47],"combinations,":[48],"which":[49],"constrains":[50],"their":[51],"applicability":[52],"versatility":[54],"across":[55,116,156],"various":[56],"contexts.":[57],"In":[58],"response":[59],"to":[60,81,126],"this":[61],"challenge,":[62],"we":[63,136],"present":[64],"MVP-LM,":[65],"Multi-granular":[67],"Versatile":[69],"framework":[71,78],"incorporating":[72],"Visual":[73],"Large":[74],"Language":[75],"Model.":[76],"Our":[77],"designed":[80],"integrate":[82],"both":[83,162],"word-based":[84,163],"sentence-based":[86,165],"perception":[87,166],"tasks":[88,167],"alongside":[89],"box":[90],"mask":[92],"predictions":[93],"within":[94],"single":[96],"architecture.":[97],"MVP-LM":[98],"features":[99],"an":[100],"innovative":[101],"multi-granularity":[102],"decoder":[103],"conjunction":[105],"with":[106],"CoT-inspired":[108],"dataset":[109],"unification":[110],"strategy,":[111],"enabling":[112],"seamless":[113],"supervised":[114],"fine-tuning":[115],"wide":[118],"spectrum":[119],"tasks,":[121],"including":[122],"but":[123],"not":[124],"panoptic":[127],"segmentation,":[128],"detection,":[129],"grounding,":[130],"referring":[132],"expression":[133],"segmentation.":[134],"Furthermore,":[135],"introduce":[137],"query":[139],"enhancement":[140],"strategy":[141],"aimed":[142],"at":[143,179],"harnessing":[144],"decoding":[146],"generative":[148],"capabilities":[149],"inherent":[150],"VLLMs.":[152],"Extensive":[153],"experiments":[154],"conducted":[155],"range":[158],"benchmarks":[160],"substantiate":[168],"efficacy":[170],"our":[172],"framework.":[173],"The":[174],"code":[175],"will":[176],"available":[178],"https://github.com/xiangwentao666/MVP-LM.":[180]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}