{"id":"https://openalex.org/W4403488476","doi":"https://doi.org/10.3233/faia240541","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","display_name":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403488476","doi":"https://doi.org/10.3233/faia240541"},"language":"en","primary_location":{"id":"doi:10.3233/faia240541","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240541","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia240541","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113220383","display_name":"Jinjin Xu","orcid":"https://orcid.org/0000-0002-2428-0305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinjin Xu","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040844494","display_name":"Liwu Xu","orcid":"https://orcid.org/0009-0004-3489-4169"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liwu Xu","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027089869","display_name":"Yuzhe Yang","orcid":"https://orcid.org/0000-0001-9098-2105"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuzhe Yang","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111288284","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-1395-5266"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070831046","display_name":"Fanyi Wang","orcid":"https://orcid.org/0000-0002-8685-4300"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanyi Wang","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058083133","display_name":"Yanchun Xie","orcid":"https://orcid.org/0000-0002-1274-2103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanchun Xie","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101266070","display_name":"Yi-Jie Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Jie Huang","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075992428","display_name":"Yaqian Li","orcid":"https://orcid.org/0000-0003-3582-9997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaqian Li","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4292,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93549515,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9537000060081482,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9537000060081482,"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/T10028","display_name":"Topic Modeling","score":0.944599986076355,"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/modal","display_name":"Modal","score":0.7079454660415649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6019335985183716},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4084889888763428},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.14572879672050476},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05474823713302612}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7079454660415649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6019335985183716},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4084889888763428},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.14572879672050476},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05474823713302612},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240541","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240541","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240541","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240541","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":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":{"Recent":[0],"advancements":[1],"in":[2,13],"multi-modal":[3],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"have":[8],"led":[9],"to":[10,57,79,119],"substantial":[11],"improvements":[12],"visual":[14,87],"understanding,":[15],"primarily":[16],"driven":[17],"by":[18,66],"sophisticated":[19],"modality":[20,70],"alignment":[21,71],"strategies.":[22],"However,":[23],"predominant":[24],"approaches":[25],"prioritize":[26],"global":[27,55],"or":[28],"regional":[29],"comprehension,":[30],"with":[31,95],"less":[32],"focus":[33],"on":[34],"fine-grained,":[35],"pixel-level":[36],"tasks.":[37],"To":[38],"address":[39],"this":[40,107],"gap,":[41],"we":[42],"introduce":[43],"u-LLaVA,":[44],"an":[45,68],"innovative":[46],"unifying":[47],"multi-task":[48,113],"framework":[49,131],"that":[50],"integrates":[51],"pixel,":[52],"regional,":[53],"and":[54,76,98,121,135,146],"features":[56],"refine":[58],"the":[59,81,123],"perceptual":[60],"faculties":[61],"of":[62,127],"MLLMs.":[63,128],"We":[64,142],"commence":[65],"leveraging":[67],"efficient":[69],"approach,":[72],"harnessing":[73],"both":[74],"image":[75],"video":[77],"datasets":[78],"bolster":[80],"model\u2019s":[82],"foundational":[83],"understanding":[84],"across":[85,139],"diverse":[86],"contexts.":[88],"Subsequently,":[89],"a":[90,110],"joint":[91],"instruction":[92],"tuning":[93],"method":[94],"task-specific":[96],"projectors":[97],"decoders":[99],"for":[100],"end-to-end":[101],"downstream":[102],"training":[103],"is":[104,132],"presented.":[105],"Furthermore,":[106],"work":[108],"contributes":[109],"novel":[111],"mask-based":[112],"dataset":[114],"comprising":[115],"277K":[116],"samples,":[117],"crafted":[118],"challenge":[120],"assess":[122],"fine-grained":[124],"perception":[125],"capabilities":[126],"The":[129],"overall":[130],"simple,":[133],"effective,":[134],"achieves":[136],"state-of-the-art":[137],"performance":[138],"multiple":[140],"benchmarks.":[141],"make":[143],"model,":[144],"data,":[145],"code":[147],"publicly":[148],"accessible":[149],"at":[150],"https://github.com/OPPOMKLab/u-LLaVA.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}