{"id":"https://openalex.org/W4414140741","doi":"https://doi.org/10.1109/icmew68306.2025.11152190","title":"MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis","display_name":"MVLLaVA: An Intelligent Agent for Unified and Flexible Novel View Synthesis","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4414140741","doi":"https://doi.org/10.1109/icmew68306.2025.11152190"},"language":"en","primary_location":{"id":"doi:10.1109/icmew68306.2025.11152190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"},"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/A5005793252","display_name":"Hanyu Jiang","orcid":"https://orcid.org/0009-0003-9258-521X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyu Jiang","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763213","display_name":"Jian Xue","orcid":"https://orcid.org/0000-0002-9460-802X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Xue","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056446118","display_name":"Xing Lan","orcid":"https://orcid.org/0000-0003-3624-5926"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Lan","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017022799","display_name":"Guohong Hu","orcid":"https://orcid.org/0000-0002-2980-5166"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohong Hu","raw_affiliation_strings":["University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,School of Engineering Science,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079281855","display_name":"Ke L\u00fc","orcid":"https://orcid.org/0000-0002-3456-4993"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Lu","raw_affiliation_strings":["Peng Cheng Laboratory,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory,Shenzhen,China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.24638658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9988999962806702,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6302000284194946},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.45320001244544983},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.36070001125335693},{"id":"https://openalex.org/keywords/intelligent-agent","display_name":"Intelligent agent","score":0.35120001435279846},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681000232696533},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6302000284194946},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4489000141620636},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C56397880","wikidata":"https://www.wikidata.org/wiki/Q6044094","display_name":"Intelligent decision support system","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew68306.2025.11152190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew68306.2025.11152190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2971278627","https://openalex.org/W3035524985","https://openalex.org/W3153220274","https://openalex.org/W3168867926","https://openalex.org/W3180196270","https://openalex.org/W4200150166","https://openalex.org/W4285102264","https://openalex.org/W4312933868","https://openalex.org/W4320539074","https://openalex.org/W4362707064","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4378768739","https://openalex.org/W4380353763","https://openalex.org/W4380559227","https://openalex.org/W4385318467","https://openalex.org/W4386075660","https://openalex.org/W4386395766","https://openalex.org/W4387929748","https://openalex.org/W4389469745","https://openalex.org/W4390873331","https://openalex.org/W4391462886","https://openalex.org/W4397028879","https://openalex.org/W4398886928","https://openalex.org/W4403853618","https://openalex.org/W4409129266"],"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":{"Novel":[0],"view":[1,79],"synthesis":[2,80],"creates":[3],"images":[4],"from":[5,28],"unseen":[6],"angles,":[7],"which":[8,49],"is":[9],"vital":[10],"in":[11],"computer":[12],"vision.":[13],"Recently,":[14],"multi-view":[15,137],"diffusion":[16,85],"models":[17,41,86],"have":[18],"emerged":[19],"as":[20,33,131],"a":[21,29,37,95,132],"powerful":[22,133],"tool":[23],"to":[24,57,94],"synthesize":[25],"views":[26],"efficiently":[27],"single":[30],"prompt":[31],"such":[32],"an":[34,68],"image":[35],"or":[36],"caption.":[38],"However,":[39],"these":[40,63],"lack":[42],"the":[43,122],"versatility":[44,125],"and":[45,54,100,105,124],"intuitive":[46],"user":[47],"control,":[48],"cannot":[50],"achieve":[51],"free-modal":[52],"inputs":[53,99],"are":[55],"restricted":[56],"their":[58],"predefined":[59],"modal.":[60],"To":[61],"overcome":[62],"limitations,":[64],"we":[65],"introduce":[66],"MVLLaVA,":[67,127],"intelligent":[69],"agent":[70],"capable":[71],"of":[72,98,108,126],"handling":[73],"five":[74],"input":[75],"types":[76],"for":[77,135],"novel":[78],"tasks.":[81,139],"By":[82],"integrating":[83],"multiple":[84],"with":[87],"LLaVA,":[88],"MVLLaVA":[89],"offers":[90],"exceptional":[91],"flexibility,":[92],"adapting":[93],"wide":[96],"range":[97],"instructions.":[101],"The":[102],"careful":[103],"design":[104],"efficient":[106],"fine-tuning":[107],"task-specific":[109],"instruction":[110],"templates":[111],"further":[112],"enhance":[113],"its":[114,129],"performance":[115],"across":[116],"various":[117],"scenarios.":[118],"Experimental":[119],"results":[120],"validate":[121],"robustness":[123],"highlighting":[128],"potential":[130],"solution":[134],"unified":[136],"generation":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}