{"id":"https://openalex.org/W7160031978","doi":"https://doi.org/10.1109/iccv51701.2025.00592","title":"Mamba-3VL: Taming State Space Model for 3D Vision Language Learning","display_name":"Mamba-3VL: Taming State Space Model for 3D Vision Language Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160031978","doi":"https://doi.org/10.1109/iccv51701.2025.00592"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.00592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","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/A5135229031","display_name":"Yuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135159911","display_name":"Yuxin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Chen","raw_affiliation_strings":["Tencent PCG,ARC Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101500719","display_name":"Zhongang Qi","orcid":"https://orcid.org/0000-0001-8298-4063"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongang Qi","raw_affiliation_strings":["Tencent PCG,ARC Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135176765","display_name":"Lijun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I9796191","display_name":"University College of Applied Science","ror":"https://ror.org/00f72x493","country_code":"PS","type":"education","lineage":["https://openalex.org/I9796191"]}],"countries":["PS"],"is_corresponding":false,"raw_author_name":"Lijun Liu","raw_affiliation_strings":["UCAS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCAS","institution_ids":["https://openalex.org/I9796191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006378664","display_name":"Jile Jiao","orcid":"https://orcid.org/0000-0003-2644-717X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jile Jiao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055185546","display_name":"Xuetao Feng","orcid":"https://orcid.org/0000-0002-1309-8954"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuetao Feng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009139809","display_name":"Yujia Liang","orcid":"https://orcid.org/0000-0002-0585-5169"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujia Liang","raw_affiliation_strings":["HUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HUST","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135123737","display_name":"Ying Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["Tencent PCG,ARC Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100410124","display_name":"Zhipeng Zhang","orcid":"https://orcid.org/0000-0001-9054-5263"},"institutions":[{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhipeng Zhang","raw_affiliation_strings":["School of Artificial Intelligence, SJTU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, SJTU","institution_ids":["https://openalex.org/I4210164862"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":"6273","last_page":"6283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7028999924659729,"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":0.7028999924659729,"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":0.03370000049471855,"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/T12031","display_name":"Speech and dialogue systems","score":0.03009999915957451,"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/state","display_name":"State (computer science)","score":0.38920000195503235},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.37869998812675476},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.35179999470710754},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.30300000309944153},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.29589998722076416},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2904999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5896999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5526999831199646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4034999907016754},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51701.2025.00592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00592","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4890269637107849,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2979750740","https://openalex.org/W3090449556","https://openalex.org/W3095974555","https://openalex.org/W3168640669","https://openalex.org/W3182910454","https://openalex.org/W3203949114","https://openalex.org/W4221167937","https://openalex.org/W4226376247","https://openalex.org/W4312385518","https://openalex.org/W4312649925","https://openalex.org/W4312650216","https://openalex.org/W4312707839","https://openalex.org/W4312852845","https://openalex.org/W4312912313","https://openalex.org/W4313162371","https://openalex.org/W4383109105","https://openalex.org/W4386065742","https://openalex.org/W4386066126","https://openalex.org/W4386066792","https://openalex.org/W4386075583","https://openalex.org/W4386075997","https://openalex.org/W4386076628","https://openalex.org/W4386076635","https://openalex.org/W4390872240","https://openalex.org/W4390872495","https://openalex.org/W4390874124","https://openalex.org/W4390874439","https://openalex.org/W4393154152","https://openalex.org/W4398238196","https://openalex.org/W4402703032","https://openalex.org/W4402704512","https://openalex.org/W4402778219","https://openalex.org/W4402951640","https://openalex.org/W4402952251","https://openalex.org/W4402961736","https://openalex.org/W4403600470","https://openalex.org/W4403842425","https://openalex.org/W4403906550","https://openalex.org/W4409365601","https://openalex.org/W4409366606","https://openalex.org/W4413145436","https://openalex.org/W4415796939","https://openalex.org/W4415800492","https://openalex.org/W4416559250","https://openalex.org/W7133188016","https://openalex.org/W7133193691","https://openalex.org/W7133250029"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-05T00:00:00"}
