{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:08:06Z","timestamp":1779944886129,"version":"3.53.1"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00177","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1873-1883","source":"Crossref","is-referenced-by-count":0,"title":["3D-GENERALIST: Vision-Language-Action Models for Crafting 3D Worlds"],"prefix":"10.1109","author":[{"given":"Fan-Yun","family":"Sun","sequence":"first","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengguang","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Jacobsen","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Yim","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoming","family":"Zou","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Zook","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangru","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Hsin","family":"Chou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ethem","family":"Can","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xunlei","family":"Wu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clemens","family":"Eppner","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valts","family":"Blukis","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Tremblay","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stan","family":"Birchfield","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nick","family":"Haber","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Open-universe indoor scene generation using 11 m program synthesis and uncurated object databases","author":"Aguina-Kang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Edify 3d: Scalable high-quality 3d asset generation","author":"Bala","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"I-design: Personalized 11 m interior designer","author":"\u00c7elen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1217"},{"key":"ref6","article-title":"Sceneseer: 3d scene design with natural language","author":"Chang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.124"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4293"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383316"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref13","article-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref15","article-title":"Disentangled 3D scene generation with layout learning","author":"Epstein","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Diffusion360: Seamless 360 degree panoramic image generation based on diffusion models","author":"Feng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366154"},{"key":"ref19","first-page":"10514","article-title":"Rel3D: A minimally contrastive benchmark for grounding spatial relations in 3d","volume":"33","author":"Goyal","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref22","article-title":"Scenecraft: An 11 m agent for synthesizing 3d scenes as blender code","volume-title":"Forty-first International Conference on Machine Learning","author":"Hu","year":"2024"},{"key":"ref23","article-title":"Large language models cannot self-correct reasoning yet","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Training language models to self-correct via reinforcement learning","author":"Kumar","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"InstructScene: Instructiondriven 3D indoor scene synthesis with semantic graph prior","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00419"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275035"},{"key":"ref28","article-title":"RoboCasa: Large-scale simulation of everyday tasks for generalist robots","author":"Nasiriany","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"12013","article-title":"Atiss: Autoregressive transformers for indoor scene synthesis","volume":"34","author":"Paschalidou","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14927"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00026"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref33","article-title":"Lay-a-scene: Personalized 3d object arrangement using text-to-image priors","author":"Rahamim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00593"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180660"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00114"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02744"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2775"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00105"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"ref44","article-title":"Amber: An llm -free multi-dimensional benchmark for mllms hallucination evaluation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Is a picture worth a thousand words? delving into spatial reasoning for vision language models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Robogen: Towards unleashing infinite data for automated robot learning via generative simulation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref48","article-title":"InstantMesh: Efficient 3D mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4v","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01539"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3730841"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2417575"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00652"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_19"},{"key":"ref56","article-title":"GALA3D: Towards text-to-3d complex scene generation via layout-guided generative gaussian splatting","author":"Zhou","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533166.pdf?arnumber=11533166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:01:23Z","timestamp":1779944483000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00177","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}