{"id":"https://openalex.org/W7166701221","doi":"https://doi.org/10.48550/arxiv.2606.29395","title":"NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation","display_name":"NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation","publication_year":2026,"publication_date":"2026-06-28","ids":{"openalex":"https://openalex.org/W7166701221","doi":"https://doi.org/10.48550/arxiv.2606.29395"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29395","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29395","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.2606.29395","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101706154","display_name":"Cheng Wan","orcid":"https://orcid.org/0000-0002-9818-0139"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139646505","display_name":"Yongsen Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Yongsen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139663567","display_name":"Wenzheng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Wenzheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133576391","display_name":"Yuxuan Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125728484","display_name":"Chucheng Xiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Chucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139689535","display_name":"Runze Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Runze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139634632","display_name":"Xiang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139636412","display_name":"Zhongyuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhongyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080908779","display_name":"Rushi Dai","orcid":"https://orcid.org/0000-0001-5973-7363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Rushi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139688535","display_name":"Yuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuan","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":0.43959999084472656,"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":0.43959999084472656,"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":0.18729999661445618,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.08259999752044678,"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/inference","display_name":"Inference","score":0.5116999745368958},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42399999499320984},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.40720000863075256},{"id":"https://openalex.org/keywords/3d-model","display_name":"3d model","score":0.37070000171661377},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3212999999523163},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.3061999976634979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966000199317932},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022000074386597},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43549999594688416},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42399999499320984},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29395","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29395","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.2606.29395","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29395","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"have":[5],"emerged":[6],"as":[7,37],"promising":[8],"layout":[9,16,22,66,147,155,163],"agents":[10,17,164],"for":[11,68],"3D":[12,29,32,54,57,64,70,75,85,89],"scene":[13,71,86],"generation.":[14],"Existing":[15],"still":[18],"suffer":[19],"from":[20],"implausible":[21],"generation":[23,72,167],"because":[24],"most":[25],"of":[26,117],"them":[27],"convert":[28],"assets":[30,55,76,90],"and":[31,39,53,56,88,98,108,115,134,154,169],"layouts":[33],"into":[34,92],"textual":[35],"descriptions":[36],"inputs":[38],"outputs,":[40],"which":[41],"involves":[42],"severe":[43],"information":[44],"loss":[45],"due":[46],"to":[47,176],"the":[48,78,81,93,113,137],"modality":[49],"gap":[50],"between":[51],"texts":[52],"layouts.":[58],"We":[59],"propose":[60],"NaLA,":[61],"a":[62,121,141],"native":[63],"LLM":[65],"Agent":[67],"high-quality":[69],"by":[73],"placing":[74],"in":[77,130,165],"scene.":[79],"For":[80],"inputs,":[82],"NaLA":[83,119,149,160],"encodes":[84],"boundaries":[87],"directly":[91],"LLM,":[94],"preserving":[95],"fine-grained":[96],"geometry":[97],"enabling":[99],"explicit":[100],"reasoning":[101],"over":[102],"relationships":[103],"like":[104],"collisions,":[105],"surface":[106],"supporting,":[107],"containment.":[109],"To":[110],"accurately":[111],"output":[112],"positions":[114],"orientations":[116],"assets,":[118],"adopts":[120],"coarse-to-fine":[122],"prediction":[123],"mechanism":[124],"that":[125,159],"first":[126],"predicts":[127],"discrete":[128,138],"poses":[129,139],"an":[131],"autoregressive":[132],"manner":[133],"then":[135],"refines":[136],"with":[140,172],"continuous":[142],"regression.":[143],"Trained":[144],"on":[145],"diverse":[146],"datasets,":[148],"attains":[150],"strong":[151],"geometric":[152],"perception":[153],"coherence.":[156],"Experiments":[157],"demonstrate":[158],"outperforms":[161],"prior":[162],"both":[166],"quality":[168],"inference":[170],"efficiency,":[171],"comprehensive":[173],"ablation":[174],"studies":[175],"verify":[177],"each":[178],"component's":[179],"effectiveness.":[180]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}