{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:19:36Z","timestamp":1777889976358,"version":"3.51.4"},"reference-count":52,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-2525840,CNS-2432534,ECCS-2514574"],"award-info":[{"award-number":["IIS-2525840,CNS-2432534,ECCS-2514574"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["1RF1MH133764-01"],"award-info":[{"award-number":["1RF1MH133764-01"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004351","name":"Cisco","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004351","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00372","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3905-3915","source":"Crossref","is-referenced-by-count":2,"title":["Robin3D Improving 3D Large Language Model via Robust Instruction Tuning"],"prefix":"10.1109","author":[{"given":"Weitai","family":"Kang","sequence":"first","affiliation":[{"name":"University of Illinois Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhang","family":"Shang","sequence":"additional","affiliation":[{"name":"University of Central Florida"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mubarak","family":"Shah","sequence":"additional","affiliation":[{"name":"University of Central Florida"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref4","article-title":"Robocat: A selfimproving foundation agent for robotic manipulation","author":"Bousmalis","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02496"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3387838"},{"key":"ref9","article-title":"Grounded 3d-1lm with referent tokens","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"issue":"3","key":"ref11","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with * chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"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":"Imagebind-llm: Multi-modality instruction tuning","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Chat-scene: Bridging 3d scene and large language models with object identifiers","author":"Huang","journal-title":"NeurIPS 2024. 2, 3, 5, 6"},{"key":"ref20","volume-title":"Chat-3d v2: Bridging 3d scene and large language models with object identifiers","author":"Huang","year":"2023"},{"key":"ref21","article-title":"An embodied generalist agent in 3d world","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01057"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.494"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_4"},{"key":"ref25","article-title":"Intent3d: 3d object detection in rgb-d scans based on human intention","author":"Kang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Actress: Active retraining for semi-supervised visual grounding","author":"Kang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755338"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref29","volume-title":"With spatial intelligence, ai will understand the real world","author":"Li","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref32","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref33","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref34","article-title":"Oryx mllm: On-demand spatial-temporal understanding at arbitrary resolution","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Vista-llama: Reliable video narrator via equal distance to visual tokens","author":"Ma","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Sqa3d: Situated question answering in 3d scenes","author":"Ma","year":"2022","journal-title":"arXiv preprint"},{"key":"ref37","volume-title":"Chatgpt"},{"key":"ref38","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref42","article-title":"D3net: Densely connected multidilated densenet for music source separation","author":"Takahashi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Chat-3d: Data-efficiently tuning large language model for universal dialogue of 3d scenes","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_8"},{"key":"ref47","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Ferretv2: An improved baseline for referring and grounding with large language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01397"},{"key":"ref50","article-title":"Uni3d: Exploring unified 3d representation at scale","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_11"}],"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\/11445613.pdf?arnumber=11445613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:23:27Z","timestamp":1777613007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00372","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}