{"id":"https://openalex.org/W4409991262","doi":"https://doi.org/10.1109/tmm.2025.3557620","title":"3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding","display_name":"3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409991262","doi":"https://doi.org/10.1109/tmm.2025.3557620"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3557620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557620","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","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/A5101597800","display_name":"Hongyan Xiong","orcid":"https://orcid.org/0000-0002-9003-281X"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haomiao Xiong","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048521072","display_name":"Yunzhi Zhuge","orcid":"https://orcid.org/0000-0002-4288-4516"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhi Zhuge","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086570697","display_name":"Jiawen Zhu","orcid":"https://orcid.org/0000-0001-5431-1654"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawen Zhu","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087681764","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0003-4648-4437"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986293","display_name":"Huchuan Lu","orcid":"https://orcid.org/0000-0002-6668-9758"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huchuan Lu","raw_affiliation_strings":["School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China"],"affiliations":[{"raw_affiliation_string":"School of Future Technology and the School of Artificial Intelligence, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101597800"],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":8.5265,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9769655,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"27","issue":null,"first_page":"2899","last_page":"2911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9907000064849854,"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":0.9907000064849854,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9814000129699707,"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/T12290","display_name":"Human Motion and Animation","score":0.9661999940872192,"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/computer-science","display_name":"Computer science","score":0.8314024209976196},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.800276517868042},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5323052406311035},{"id":"https://openalex.org/keywords/end-of-history","display_name":"End of history","score":0.4657624065876007},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.4343975782394409},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4229298233985901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4016048312187195},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3728969693183899},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35961031913757324},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34105658531188965},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17514875531196594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314024209976196},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.800276517868042},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5323052406311035},{"id":"https://openalex.org/C2778935963","wikidata":"https://www.wikidata.org/wiki/Q13218530","display_name":"End of history","level":3,"score":0.4657624065876007},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.4343975782394409},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4229298233985901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4016048312187195},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3728969693183899},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35961031913757324},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34105658531188965},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17514875531196594},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3557620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3557620","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1358076444","display_name":null,"funder_award_id":"DUT24YG119","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3080167161","display_name":null,"funder_award_id":"62206039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4319081443","display_name":null,"funder_award_id":"DUT24RC(3)025","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"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/G6387696347","display_name":null,"funder_award_id":"62406053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2594519801","https://openalex.org/W2963125977","https://openalex.org/W2966683369","https://openalex.org/W2979912832","https://openalex.org/W2981422075","https://openalex.org/W2988715931","https://openalex.org/W3089979672","https://openalex.org/W3107521863","https://openalex.org/W3108381027","https://openalex.org/W3182910454","https://openalex.org/W3212953023","https://openalex.org/W4214624153","https://openalex.org/W4214755140","https://openalex.org/W4226376247","https://openalex.org/W4312815172","https://openalex.org/W4313014889","https://openalex.org/W4383109105","https://openalex.org/W4385245566","https://openalex.org/W4386066792","https://openalex.org/W4386076097","https://openalex.org/W4390872495","https://openalex.org/W4390874386","https://openalex.org/W4390874575","https://openalex.org/W4402671766","https://openalex.org/W4402703030","https://openalex.org/W4402716423","https://openalex.org/W4402727764","https://openalex.org/W4402727922","https://openalex.org/W4402753960","https://openalex.org/W4402961820","https://openalex.org/W4403778769","https://openalex.org/W4404719654","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6810081322","https://openalex.org/W6810334672","https://openalex.org/W6810738896","https://openalex.org/W6811013733","https://openalex.org/W6846381433","https://openalex.org/W6847076894","https://openalex.org/W6849177959","https://openalex.org/W6849622024","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6852489829","https://openalex.org/W6852874933","https://openalex.org/W6853178439","https://openalex.org/W6855425132","https://openalex.org/W6855815363","https://openalex.org/W6856398428","https://openalex.org/W6856592842","https://openalex.org/W6856659047","https://openalex.org/W6857569170","https://openalex.org/W6857872576","https://openalex.org/W6859304583","https://openalex.org/W6860041859"],"related_works":["https://openalex.org/W3016188207","https://openalex.org/W4299590256","https://openalex.org/W2151749779","https://openalex.org/W4286908490","https://openalex.org/W3179968364","https://openalex.org/W4406318200","https://openalex.org/W4393212338","https://openalex.org/W4367860523","https://openalex.org/W2417674618","https://openalex.org/W1538841260"],"abstract_inverted_index":{"Multi-modal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"exhibit":[5],"impressive":[6],"capabilities":[7],"in":[8,14,23,70,131],"2D":[9,28,89],"tasks,":[10],"yet":[11],"encounter":[12],"challenges":[13],"discerning":[15],"the":[16,35,41,46,56,76,104,114,133,136,162,179,193,220],"spatial":[17,181],"positions,":[18],"interrelations,":[19],"and":[20,54,61,74,91,98,147,183,214,219],"causal":[21],"logic":[22],"scenes":[24],"when":[25],"transitioning":[26],"from":[27,166],"to":[29,64,93,102,176,192],"3D":[30,51,66,119,126,142,149,173,180],"representations.":[31],"We":[32],"find":[33],"that":[34],"limitations":[36],"mainly":[37],"lie":[38],"in:":[39],"i)":[40],"high":[42],"annotation":[43],"cost":[44],"restricting":[45],"scale-up":[47],"of":[48,50,58,125,135,159],"volumes":[49],"scene":[52],"data,":[53,111],"ii)":[55],"lack":[57],"a":[59,84,156,172],"straightforward":[60],"effective":[62],"way":[63],"perceive":[65],"information":[67],"which":[68],"results":[69],"prolonged":[71],"training":[72,210],"durations":[73],"complicates":[75],"streamlined":[77],"framework.":[78],"To":[79],"this":[80,108],"end,":[81],"we":[82,112,170],"develop":[83],"pipeline":[85],"based":[86],"on":[87,205],"open-source":[88],"MLLMs":[90],"LLMs":[92],"generate":[94],"high-quality":[95,109],"3D-text":[96],"pairs":[97],"construct":[99],"3DS-160":[100,221],"K,":[101],"enhance":[103],"pre-training":[105,110],"process.":[106],"Leveraging":[107],"introduce":[113],"3UR-LLM":[115,139,186,198,218],"model,":[116],"an":[117],"end-to-end":[118],"MLLM":[120],"designed":[121],"for":[122,196,217],"precise":[123],"interpretation":[124],"scenes,":[127],"showcasing":[128],"exceptional":[129],"capability":[130],"navigating":[132],"complexities":[134],"physical":[137],"world.":[138],"directly":[140],"receives":[141],"point":[143],"cloud":[144],"as":[145],"input":[146],"project":[148],"features":[150],"fused":[151],"with":[152,190],"text":[153],"instructions":[154],"into":[155],"manageable":[157],"set":[158],"tokens.":[160],"Considering":[161],"computation":[163],"burden":[164],"derived":[165],"these":[167],"hybrid":[168],"tokens,":[169],"design":[171],"compressor":[174],"module":[175],"cohesively":[177],"compress":[178],"cues":[182],"textual":[184],"narrative.":[185],"achieves":[187],"promising":[188],"performance":[189],"respect":[191],"previous":[194],"SOTAs,":[195],"instance,":[197],"exceeds":[199],"its":[200],"counterparts":[201],"by":[202],"7.1%":[203],"CIDEr":[204],"ScanQA,":[206],"while":[207],"utilizing":[208],"fewer":[209],"resources.":[211],"The":[212],"code":[213],"model":[215],"weights":[216],"K":[222],"benchmark":[223],"are":[224],"available":[225],"at":[226],"3UR-LLM.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}