{"id":"https://openalex.org/W4414360595","doi":"https://doi.org/10.24963/ijcai.2025/262","title":"G3PT: Unleash the Power of Autoregressive Modeling in 3D Generation via Cross-Scale Querying Transformer","display_name":"G3PT: Unleash the Power of Autoregressive Modeling in 3D Generation via Cross-Scale Querying Transformer","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360595","doi":"https://doi.org/10.24963/ijcai.2025/262"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/262","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5101427440","display_name":"Jinzhi Zhang","orcid":"https://orcid.org/0000-0001-6430-0502"},"institutions":[{"id":"https://openalex.org/I4210092862","display_name":"Arctic Monitoring And Assessment Programme","ror":"https://ror.org/00hgq1a05","country_code":"NO","type":"other","lineage":["https://openalex.org/I4210092862"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Jinzhi Zhang","raw_affiliation_strings":["AMAP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP","institution_ids":["https://openalex.org/I4210092862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050983870","display_name":"Feng Xiong","orcid":"https://orcid.org/0000-0002-6927-8903"},"institutions":[{"id":"https://openalex.org/I4210092862","display_name":"Arctic Monitoring And Assessment Programme","ror":"https://ror.org/00hgq1a05","country_code":"NO","type":"other","lineage":["https://openalex.org/I4210092862"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Feng Xiong","raw_affiliation_strings":["AMAP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP","institution_ids":["https://openalex.org/I4210092862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066971089","display_name":"Guangyu Wang","orcid":"https://orcid.org/0000-0002-5581-6926"},"institutions":[{"id":"https://openalex.org/I4210092862","display_name":"Arctic Monitoring And Assessment Programme","ror":"https://ror.org/00hgq1a05","country_code":"NO","type":"other","lineage":["https://openalex.org/I4210092862"]},{"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","NO"],"is_corresponding":false,"raw_author_name":"Guangyu Wang","raw_affiliation_strings":["AMAP","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP","institution_ids":["https://openalex.org/I4210092862"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100532751","display_name":"Mu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092862","display_name":"Arctic Monitoring And Assessment Programme","ror":"https://ror.org/00hgq1a05","country_code":"NO","type":"other","lineage":["https://openalex.org/I4210092862"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Mu Xu","raw_affiliation_strings":["AMAP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP","institution_ids":["https://openalex.org/I4210092862"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"2350","last_page":"2358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9452999830245972,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9452999830245972,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7289999723434448},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6279000043869019},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5582000017166138},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5422999858856201},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49540001153945923},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.4528999924659729},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.428600013256073},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.36970001459121704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398999929428101},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7289999723434448},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6279000043869019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641999840736389},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5582000017166138},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5422999858856201},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49540001153945923},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.4528999924659729},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3792000114917755},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.32330000400543213},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C163173736","wikidata":"https://www.wikidata.org/wiki/Q3308558","display_name":"Key generation","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/262","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/262","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Autoregressive":[0],"transformers":[1],"have":[2],"revolutionized":[3],"generative":[4,71],"models":[5,20],"in":[6,13,60,171],"language":[7],"processing":[8],"and":[9,15,77,158],"shown":[10],"substantial":[11],"promise":[12],"image":[14],"video":[16],"generation.":[17],"However,":[18],"these":[19],"face":[21],"significant":[22],"challenges":[23],"when":[24],"extended":[25],"to":[26,31,37,84,162],"3D":[27,49,58,69,87,134,143,172],"generation":[28,135,141,156],"tasks":[29],"due":[30],"their":[32],"reliance":[33],"on":[34,57],"next-token":[35],"prediction":[36],"learn":[38],"token":[39],"sequences,":[40],"which":[41],"is":[42,83],"incompatible":[43],"with":[44,73,92],"the":[45,140,168],"unordered":[46],"nature":[47],"of":[48,52,95,105,120,142],"data.":[50],"Instead":[51],"imposing":[53],"an":[54],"artificial":[55],"order":[56],"data,":[59],"this":[61,128],"paper,":[62],"we":[63],"introduce":[64],"G3PT,":[65],"a":[66,99,103,132],"scalable,":[67],"coarse-to-fine":[68],"native":[70],"model":[72],"cross-scale":[74,78],"vector":[75],"quantization":[76],"autoregressive":[79,109],"modeling.":[80,110],"The":[81],"key":[82],"map":[85],"point-based":[86],"data":[88],"into":[89],"discrete":[90],"tokens":[91,115],"different":[93,118],"levels":[94,119],"detail,":[96],"naturally":[97],"establishing":[98],"sequential":[100],"relationship":[101],"across":[102,117],"variety":[104],"scales":[106],"suitable":[107],"for":[108,167],"Remarkably,":[111],"our":[112],"method":[113],"connects":[114],"globally":[116],"detail":[121],"without":[122],"manually":[123],"specified":[124],"ordering.":[125],"Benefiting":[126],"from":[127],"approach,":[129],"G3PT":[130,153,176],"features":[131],"versatile":[133],"pipeline":[136],"that":[137,152],"effortlessly":[138],"supports":[139],"shapes":[144],"under":[145],"diverse":[146],"conditional":[147],"modalities.":[148],"Extensive":[149],"experiments":[150],"demonstrate":[151],"achieves":[154],"superior":[155],"quality":[157],"generalization":[159],"ability":[160],"compared":[161],"previous":[163],"baselines.":[164],"Most":[165],"importantly,":[166],"first":[169],"time":[170],"generation,":[173],"scaling":[174,180],"up":[175],"reveals":[177],"distinct":[178],"power-law":[179],"behaviors.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}