{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:59:25Z","timestamp":1764014365034,"version":"3.45.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Ministry of Education and Science of Bulgaria"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/lra.2025.3623037","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:42:36Z","timestamp":1760722956000},"page":"12588-12595","source":"Crossref","is-referenced-by-count":0,"title":["GaussianVLM: Scene-Centric 3D Vision-Language Models Using Language-Aligned Gaussian Splats for Embodied Reasoning and Beyond"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1053-9063","authenticated-orcid":false,"given":"Anna-Maria","family":"Halacheva","sequence":"first","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”, Sofia, Bulgaria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2566-0841","authenticated-orcid":false,"given":"Jan-Nico","family":"Zaech","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”, Sofia, Bulgaria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5442-1116","authenticated-orcid":false,"given":"Xi","family":"Wang","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”, Sofia, Bulgaria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1739-1867","authenticated-orcid":false,"given":"Danda Pani","family":"Paudel","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”, Sofia, Bulgaria"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3445-5711","authenticated-orcid":false,"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University “St. Kliment Ohridski”, Sofia, Bulgaria"}]}],"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":"10.1007\/978-3-319-46454-1_24"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref4","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref7","first-page":"202","article-title":"ScanRefer: 3D object localization in RGB-D scans using natural language","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhenyu Chen","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01070"},{"article-title":"Grounded 3D-LLM with referent tokens","year":"2024","author":"Chen","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00321"},{"article-title":"Vicuna: An open-source ChatBot impressing GPT-4 with 90%  ChatGPT quality","year":"2023","author":"Chiang","key":"ref12"},{"key":"ref13","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out","author":"Chin-Yew","year":"2004"},{"article-title":"Guidance for open source 3D reconstruction toolbox for gaussian splats on AWS","year":"2024","author":"Cornwell","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01377"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00220"},{"key":"ref18","first-page":"14369","article-title":"PerLA: Perceptive 3D language assistant","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Guofeng","year":"2025"},{"key":"ref19","first-page":"20482","article-title":"3D-LLM: Injecting the 3D world into large language models","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Hong","year":"2023"},{"key":"ref20","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref21","first-page":"113991","article-title":"Chat-Scene: Bridging 3D scene and large language models with object identifiers","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Huang","year":"2024"},{"key":"ref22","first-page":"20413","article-title":"An embodied generalist agent in 3D world","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref24","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_3"},{"article-title":"Scenesplat: Gaussian splatting-based scene understanding with vision-language pretraining","year":"2025","author":"Li","key":"ref26"},{"key":"ref27","first-page":"140903","article-title":"Multi-modal situated reasoning in 3D scenes","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Linghu","year":"2024"},{"key":"ref28","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref29","first-page":"33558","article-title":"RoboMP2: A robotic multimodal perception-planning framework with mutlimodal large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lv","year":"2024"},{"article-title":"SceneSplat: A large dataset and comprehensive benchmark for language Gaussian splatting","year":"2025","author":"Ma","key":"ref30"},{"key":"ref31","article-title":"SQA3D: Situated question answering 3D scenes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01298"},{"key":"ref33","first-page":"76819","article-title":"Lexicon3D: Probing visual foundation models for complex 3D scene understanding","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Man","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802241"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"year":"2025","key":"ref37","article-title":"Transform your work with precise 3D scans and AR with PIX4Dcatch"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref39","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref40","first-page":"23","article-title":"SayPlan: Grounding large language models using 3D scene graphs for scalable task planning","volume-title":"Proc. 7th Conf. Robot Learn.","author":"Rana","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref44","first-page":"4748","article-title":"Splat-mover: Multi-stage, open-vocabulary robotic manipulation via editable Gaussian splatting","volume-title":"Proc. 8th Conf. Robot Learn.","author":"Shorinwa","year":"2024"},{"key":"ref45","first-page":"251","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Szot","year":"2021"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref46"},{"article-title":"SIGLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","year":"2025","author":"Tschannen","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"article-title":"Chat-3D: Data-efficiently tuning large language model for universal dialogue of 3D scenes","year":"2023","author":"Wang","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341577"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/172"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"article-title":"OPT: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref57"},{"key":"ref58","first-page":"73388","article-title":"Spartun3D: Situated spatial understanding of 3D world in large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2025"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00356"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_11"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11215960\/11206564.pdf?arnumber=11206564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T19:02:44Z","timestamp":1764010964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11206564\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":61,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3623037","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}