{"id":"https://openalex.org/W7161704485","doi":"https://doi.org/10.48550/arxiv.2605.17566","title":"Rethinking Point Clouds as Sequences: A Causal Next-Token Predictive Learning Framework","display_name":"Rethinking Point Clouds as Sequences: A Causal Next-Token Predictive Learning Framework","publication_year":2026,"publication_date":"2026-05-17","ids":{"openalex":"https://openalex.org/W7161704485","doi":"https://doi.org/10.48550/arxiv.2605.17566"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.17566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17566","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.17566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136493405","display_name":"Yumeng Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Yumeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136477282","display_name":"Jingzhi Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Jingzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136502567","display_name":"Haowen Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Haowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136467873","display_name":"Tao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136504197","display_name":"Zonghan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zonghan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043863561","display_name":"Xiaoshui Huang","orcid":"https://orcid.org/0000-0002-3579-538X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xiaoshui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136475148","display_name":"Yazhou Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Yazhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":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":0.9521999955177307,"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":0.9521999955177307,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0032999999821186066,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.5788000226020813},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5159000158309937},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.47859999537467957},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.46549999713897705},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4332999885082245},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.421099990606308},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.36880001425743103},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.3156000077724457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6732000112533569},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5333999991416931},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4577000141143799},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4332999885082245},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.17566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17566","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.17566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17566","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,130,151],"rapid":[2],"progress":[3],"of":[4,172],"multimodal":[5],"foundation":[6],"models":[7],"and":[8,32,49,91,116,165,170,181,198],"predictive":[9,58,213],"pre-training,":[10],"an":[11],"important":[12],"open":[13],"question":[14],"is":[15,27,85,106,154],"how":[16],"to":[17,53,100,132],"equip":[18],"3D":[19,96,209,216],"point":[20,69,83],"clouds":[21],"with":[22,30,118],"a":[23,73,94,110,119,195,207],"pre-training":[24,71],"paradigm":[25,201],"that":[26,150],"better":[28],"aligned":[29],"next-token":[31],"next-embedding":[33],"learning.":[34],"Existing":[35],"point-cloud":[36,203],"self-supervised":[37,204],"methods":[38],"are":[39],"largely":[40],"built":[41],"on":[42,167,179,185,211],"masked":[43],"reconstruction":[44,141],"or":[45,143],"explicit":[46,144],"geometric":[47,145],"generation,":[48],"thus":[50],"remain":[51],"tied":[52],"input":[54],"recovery":[55],"rather":[56],"than":[57],"dependency":[59],"modeling.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"introduce":[65],"PointNTP,":[66],"which":[67],"reformulates":[68],"cloud":[70,84],"as":[72],"fully":[74],"causal,":[75],"decoder-free":[76,190],"latent":[77,138,192],"Next-Token":[78],"Prediction":[79],"problem.":[80],"Specifically,":[81],"each":[82],"first":[86],"partitioned":[87],"into":[88,93],"local":[89],"patches":[90],"serialized":[92],"structured":[95],"token":[97],"sequence":[98,105],"according":[99],"patch-center":[101],"geometry.":[102],"The":[103],"resulting":[104],"then":[107],"modeled":[108],"by":[109,124],"causal":[111,191],"Transformer":[112],"under":[113],"prefix-only":[114],"conditioning,":[115],"trained":[117],"shift-based":[120],"prediction":[121,193],"objective":[122],"stabilized":[123],"stop-gradient":[125],"targets.":[126],"This":[127],"design":[128],"enables":[129],"model":[131],"learn":[133],"structural":[134],"dependencies":[135],"directly":[136],"in":[137,177],"space,":[139],"without":[140],"decoders":[142],"recovery.":[146],"Extensive":[147],"experiments":[148],"demonstrate":[149],"proposed":[152],"PointNTP":[153],"highly":[155],"competitive":[156],"across":[157],"multiple":[158],"downstream":[159],"tasks:":[160],"it":[161],"achieves":[162],"93.8%(+0.5%),":[163],"92.6%(+0.3%),":[164],"89.3%(+1.1%)":[166],"OBJ_BG,":[168],"OBJ_ONLY,":[169],"PB_T50_RS":[171],"ScanObjectNN,":[173],"respectively;":[174],"obtains":[175],"85.0%(+0.1%)":[176],"Cls.mIoU":[178],"ShapeNetPart;":[180],"reaches":[182],"71.1%":[183],"mAcc":[184],"S3DIS":[186],"Area":[187],"5.":[188],"Overall,":[189],"provides":[194],"simple,":[196],"scalable,":[197],"potentially":[199],"modality-agnostic":[200],"for":[202,215],"learning,":[205],"offering":[206],"new":[208],"perspective":[210],"foundation-style":[212],"learning":[214],"data.":[217]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}