{"id":"https://openalex.org/W7133501137","doi":"https://doi.org/10.48550/arxiv.2603.03283","title":"Utonia: Toward One Encoder for All Point Clouds","display_name":"Utonia: Toward One Encoder for All Point Clouds","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133501137","doi":"https://doi.org/10.48550/arxiv.2603.03283"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.03283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.03283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.03283","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128085594","display_name":"Yujia Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Yujia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102724054","display_name":"Xiaoyang Wu","orcid":"https://orcid.org/0009-0001-6851-0395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiaoyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128054063","display_name":"Yunhan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yunhan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128126651","display_name":"Xianzhe Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Xianzhe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128097175","display_name":"Han Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128052187","display_name":"Yuechen Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuechen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017829201","display_name":"Zehao Huang","orcid":"https://orcid.org/0000-0003-1653-208X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zehao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128117753","display_name":"Naiyan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Naiyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128103950","display_name":"Hengshuang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Hengshuang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5128085594"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.3215000033378601,"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"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.3215000033378601,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.21950000524520874,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.10639999806880951,"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/encoder","display_name":"Encoder","score":0.6912000179290771},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6686000227928162},{"id":"https://openalex.org/keywords/swap","display_name":"Swap (finance)","score":0.6327999830245972},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.486299991607666},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.46709999442100525},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4560999870300293},{"id":"https://openalex.org/keywords/unification","display_name":"Unification","score":0.453000009059906},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44530001282691956}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6912000179290771},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6686000227928162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6513000130653381},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.6327999830245972},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.486299991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47929999232292175},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.453000009059906},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44530001282691956},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2874000072479248},{"id":"https://openalex.org/C88626702","wikidata":"https://www.wikidata.org/wiki/Q1128903","display_name":"Continuation","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C161677786","wikidata":"https://www.wikidata.org/wiki/Q2478475","display_name":"Neighbourhood (mathematics)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.03283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.03283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.03283","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.03283","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,131],"dream":[1],"of":[2],"a":[3,16,29,34,71,137],"future":[4],"where":[5],"point":[6,37,55],"clouds":[7,56],"from":[8,58],"all":[9],"domains":[10,93],"can":[11,104,134],"come":[12],"together":[13],"to":[14],"shape":[15],"single":[17,35],"model":[18],"that":[19,75,89,101],"benefits":[20],"them":[21,122],"all.":[22],"Toward":[23],"this":[24],"goal,":[25],"we":[26,99],"present":[27],"Utonia,":[28],"first":[30],"step":[31,138],"toward":[32,139],"training":[33],"self-supervised":[36],"transformer":[38],"encoder":[39],"across":[40,77],"diverse":[41],"domains,":[42],"spanning":[43],"remote":[44],"sensing,":[45],"outdoor":[46],"LiDAR,":[47],"indoor":[48],"RGB-D":[49],"sequences,":[50],"object-centric":[51],"CAD":[52],"models,":[53],"and":[54,67,108,120,146,153],"lifted":[57],"RGB-only":[59],"videos.":[60],"Despite":[61],"their":[62],"distinct":[63],"sensing":[64],"geometries,":[65],"densities,":[66],"priors,":[68],"Utonia":[69,102,115,133],"learns":[70],"consistent":[72],"representation":[73],"space":[74],"transfers":[76],"domains.":[78],"This":[79],"unification":[80],"improves":[81,117],"perception":[82],"capability":[83],"while":[84],"revealing":[85],"intriguing":[86],"emergent":[87],"behaviors":[88],"arise":[90],"only":[91],"when":[92],"are":[94],"trained":[95],"jointly.":[96],"Beyond":[97],"perception,":[98],"observe":[100],"representations":[103],"also":[105],"benefit":[106],"embodied":[107],"multimodal":[109],"reasoning:":[110],"conditioning":[111],"vision-language-action":[112],"policies":[113],"on":[114,128],"features":[116],"robotic":[118],"manipulation,":[119],"integrating":[121],"into":[123],"vision-language":[124],"models":[125,141],"yields":[126],"gains":[127],"spatial":[129],"reasoning.":[130],"hope":[132],"serve":[135],"as":[136],"foundation":[140],"for":[142],"sparse":[143],"3D":[144],"data,":[145],"support":[147],"downstream":[148],"applications":[149],"in":[150],"AR/VR,":[151],"robotics,":[152],"autonomous":[154],"driving.":[155]},"counts_by_year":[],"updated_date":"2026-03-05T07:36:02.291473","created_date":"2026-03-05T00:00:00"}
