{"id":"https://openalex.org/W7130597485","doi":"https://doi.org/10.1109/ictc66702.2025.11388011","title":"Trends in Multi-modal Large Language Models for 3D Point Cloud Understanding","display_name":"Trends in Multi-modal Large Language Models for 3D Point Cloud Understanding","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7130597485","doi":"https://doi.org/10.1109/ictc66702.2025.11388011"},"language":null,"primary_location":{"id":"doi:10.1109/ictc66702.2025.11388011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","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/A5125747701","display_name":"Seok Bin Son","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seok Bin Son","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093460594","display_name":"Soohyun Park","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soohyun Park","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049202871","display_name":"Joongheon Kim","orcid":"https://orcid.org/0000-0003-2126-768X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joongheon Kim","raw_affiliation_strings":["Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Electrical and Computer Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"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":"133","last_page":"135"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.49000000953674316,"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":0.49000000953674316,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.20170000195503235,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.09189999848604202,"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/point-cloud","display_name":"Point cloud","score":0.784600019454956},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5472000241279602},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5081999897956848},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42730000615119934},{"id":"https://openalex.org/keywords/3d-city-models","display_name":"3D city models","score":0.3698999881744385},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.3310000002384186},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.3212999999523163}],"concepts":[{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.784600019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210000157356262},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5537999868392944},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4982999861240387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C2778597888","wikidata":"https://www.wikidata.org/wiki/Q172169","display_name":"3D city models","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.3310000002384186},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc66702.2025.11388011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc66702.2025.11388011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4117128849029541}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W4391136507","https://openalex.org/W4402716423","https://openalex.org/W4402838140","https://openalex.org/W4405908117","https://openalex.org/W4409991262","https://openalex.org/W4410356996","https://openalex.org/W4416018107"],"related_works":[],"abstract_inverted_index":{"Recent":[0,64],"advances":[1],"in":[2,13,143],"multi-modal":[3,84,117,144],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"have":[8,37],"demonstrated":[9],"strong":[10],"reasoning":[11],"capabilities":[12,22],"2D":[14],"vision-language":[15],"tasks,":[16],"motivating":[17],"the":[18,48,126],"extension":[19],"of":[20,34,53,129],"these":[21,67],"to":[23,110],"3D":[24,35,99,145],"domains.":[25],"Point":[26],"clouds,":[27],"as":[28],"a":[29,39,122],"compact":[30],"and":[31,50,61,89,95,116,136],"precise":[32],"representation":[33],"geometry,":[36],"become":[38],"key":[40],"modality":[41],"for":[42,58,93],"enabling":[43],"high-level":[44],"spatial":[45],"understanding.":[46,147],"However,":[47],"irregular":[49],"unordered":[51],"structure":[52],"point":[54,78,82,87,130],"clouds":[55],"introduces":[56],"challenges":[57,68],"efficient":[59],"processing":[60],"cross-modal":[62],"integration.":[63],"research":[65],"addressing":[66],"can":[69],"be":[70],"categorized":[71],"into":[72,139],"four":[73],"main":[74],"paradigms:":[75],"(i)":[76],"direct":[77],"cloud":[79,88],"encoding,":[80],"(ii)":[81],"cloud\u2013based":[83],"alignment,":[85],"(iii)":[86],"semantic":[90],"information":[91],"fusion":[92],"upsampling,":[94],"(iv)":[96],"multi-view":[97],"image\u2013based":[98],"processing.":[100],"Representative":[101],"methods":[102],"within":[103],"each":[104],"paradigm":[105],"employ":[106],"distinct":[107],"architectural":[108],"choices":[109],"balance":[111],"geometric":[112],"fidelity,":[113],"computational":[114],"efficiency,":[115],"capability.":[118],"This":[119],"taxonomy":[120],"provides":[121],"structured":[123],"perspective":[124],"on":[125],"evolving":[127],"landscape":[128],"cloud\u2013LLM":[131],"integration,":[132],"highlighting":[133],"design":[134],"trade-offs":[135],"offering":[137],"insights":[138],"potential":[140],"future":[141],"directions":[142],"scene":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}
