{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:59:31Z","timestamp":1784185171646,"version":"3.55.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00409","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4295-4305","source":"Crossref","is-referenced-by-count":3,"title":["LLaVA-3D: A Simple Yet Effective Pathway to Empowering LMMs with 3D Capabilities"],"prefix":"10.1109","author":[{"given":"Chenming","family":"Zhu","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"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","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref5","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1492"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01070"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02496"},{"key":"ref9","article-title":"Grounded 3d-11m with referent tokens","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref12","article-title":"3d-llava: Towards generalist 3d 1 mms with omni superpoint transformer","author":"Deng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"ref14","article-title":"Scene-llm: Extending language model for 3d visual understanding and reasoning","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"3d-llm: Injecting the 3 d world into large language models","author":"Hong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Chat-3d v 2: Bridging 3d scene and large language models with object identifiers","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3620"},{"key":"ref18","article-title":"An embodied generalist agent in 3d world","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01508"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00342"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01057"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref26","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Blip2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref32","article-title":"Coarse correspondence elicit 3d spacetime understanding in multimodal language model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00294"},{"key":"ref38","article-title":"Mmscan: A multi-modal 3d scene dataset with hierarchical grounded language annotations","author":"Lyu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Sqa3d: Situated question answering in 3d scenes","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01560"},{"key":"ref41","article-title":"Gpt4scene: Understand 3d scenes from videos with vision-language models","author":"Qi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref42","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":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref44","first-page":"785","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar","year":"2023"},{"key":"ref45","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","first-page":"69925","article-title":"Visionllm v2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref47","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref50","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00292"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00841"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_9"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444543.pdf?arnumber=11444543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:33:11Z","timestamp":1777530791000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444543\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00409","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}