{"id":"https://openalex.org/W7160284406","doi":"https://doi.org/10.1109/wacv61042.2026.00570","title":"Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation","display_name":"Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160284406","doi":"https://doi.org/10.1109/wacv61042.2026.00570"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5035078042","display_name":"H Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu He","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100515056","display_name":"Xiao Zeng","orcid":"https://orcid.org/0000-0003-4800-5858"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xiao Zeng","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135382040","display_name":"Yizhi Song","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhi Song","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070952449","display_name":"Albert Y. C. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Albert Y. C. Chen","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135418115","display_name":"Lu Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lu Xia","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135291408","display_name":"Shashwat Verma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shashwat Verma","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126195209","display_name":"Sankalp Dayal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sankalp Dayal","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135291918","display_name":"Min Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Min Sun","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135382675","display_name":"Cheng-Hao Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cheng-Hao Kuo","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125748224","display_name":"Daniel Aliaga","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Aliaga","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5886","last_page":"5897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6080999970436096,"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":0.6080999970436096,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.05290000140666962,"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/T12290","display_name":"Human Motion and Animation","score":0.028200000524520874,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/visualization","display_name":"Visualization","score":0.3327000141143799},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.28769999742507935},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2759999930858612},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.23499999940395355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5422999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34700000286102295},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2498999983072281},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.24570000171661377},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.23499999940395355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1991264156","https://openalex.org/W2117539524","https://openalex.org/W2185175083","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2507296351","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2907143950","https://openalex.org/W2947312908","https://openalex.org/W2948672349","https://openalex.org/W2963518342","https://openalex.org/W2963622213","https://openalex.org/W2979382951","https://openalex.org/W3004268082","https://openalex.org/W3032768507","https://openalex.org/W4312339971","https://openalex.org/W4312933868","https://openalex.org/W4319069109","https://openalex.org/W4381802186","https://openalex.org/W4385991013","https://openalex.org/W4386071604","https://openalex.org/W4386075528","https://openalex.org/W4386075660","https://openalex.org/W4390873054","https://openalex.org/W4390873887","https://openalex.org/W4402713111","https://openalex.org/W4402716288","https://openalex.org/W4402727764","https://openalex.org/W4402727885","https://openalex.org/W4402753807","https://openalex.org/W4402754023","https://openalex.org/W4402754148","https://openalex.org/W4403771683","https://openalex.org/W4403923795","https://openalex.org/W4413146565","https://openalex.org/W4415800665","https://openalex.org/W4416036344","https://openalex.org/W7133200339","https://openalex.org/W7133205559","https://openalex.org/W7133220561","https://openalex.org/W7133223072","https://openalex.org/W7133250524","https://openalex.org/W7138833045"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"struggle":[5],"with":[6,32,108],"accurately":[7],"capturing":[8],"camera-object":[9,35,78,110,136],"relations,":[10],"especially":[11],"for":[12,91],"object":[13],"orientation,":[14],"camera":[15,18],"viewpoint,":[16],"and":[17,37,64,67,96,112,143],"shots.":[19],"This":[20],"stems":[21],"from":[22],"the":[23],"fact":[24],"that":[25],"existing":[26],"MLLMs":[27,115],"are":[28,85],"trained":[29],"on":[30,117,135],"images":[31,75],"limited":[33],"diverse":[34],"relations":[36],"corresponding":[38,113],"textual":[39],"descriptions.":[40],"To":[41],"address":[42],"this,":[43],"we":[44],"propose":[45],"a":[46,103,125],"synthetic":[47],"generation":[48,70],"pipeline":[49],"to":[50,72,87,147],"create":[51,73,101],"large-scale":[52],"3D":[53,60],"visual":[54,93],"instruction":[55,94],"datasets.":[56],"Our":[57,140],"framework":[58],"takes":[59],"assets":[61],"as":[62],"input":[63],"uses":[65],"rendering":[66],"diffusion-based":[68],"image":[69,98],"models":[71,83,123],"photorealistic":[74],"preserving":[76],"precise":[77,109],"relations.":[79],"Additionally,":[80],"large":[81,126],"language":[82],"(LLMs)":[84],"used":[86],"generate":[88],"text":[89],"prompts":[90],"guiding":[92],"tuning":[95],"controlling":[97],"generation.":[99],"We":[100],"Ultimate3D,":[102],"dataset":[104,120],"of":[105,133],"240K":[106],"VQAs":[107],"annotations,":[111],"benchmark.":[114],"fine-tuned":[116],"our":[118],"proposed":[119],"outperform":[121],"commercial":[122],"by":[124],"margin,":[127],"achieving":[128],"an":[129],"average":[130],"accuracy":[131],"improvement":[132],"33.4%":[134],"relation":[137],"recognition":[138],"tasks.":[139],"code,":[141],"dataset,":[142],"benchmark":[144],"will":[145],"contribute":[146],"broad":[148],"MLLM":[149],"applications.":[150]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}