{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:46Z","timestamp":1757608726678,"version":"3.44.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128559","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"13537-13544","source":"Crossref","is-referenced-by-count":0,"title":["3D Spatial Understanding in MLLMs: Disambiguation and Evaluation"],"prefix":"10.1109","author":[{"given":"Chun-Peng","family":"Chang","sequence":"first","affiliation":[{"name":"DFKI Augmented Vision, (German Research Center for Artificial Intelligence)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alain","family":"Pagani","sequence":"additional","affiliation":[{"name":"DFKI Augmented Vision, (German Research Center for Artificial Intelligence)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Didier","family":"Stricker","sequence":"additional","affiliation":[{"name":"DFKI Augmented Vision, (German Research Center for Artificial Intelligence)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00068"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"journal-title":"J.B.A.: Flamingo: a visual language model for few-shot learning","year":"2022","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"ref5","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01597"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01340"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00321"},{"journal-title":"D3net: A speaker-listener architecture for semi-supervised dense captioning and visual grounding in rgb-d scans","year":"2021","author":"Chen","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01070"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3387838"},{"volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","year":"2023","author":"Chiang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01410"},{"article-title":"3d-llm: Injecting the 3d world into large language models","volume-title":"NeurIPS","author":"Hong","key":"ref15"},{"article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16253"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"journal-title":"Bottom up top down detection transformers for language grounding in images and point clouds","year":"2021","author":"Jain","key":"ref19"},{"journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge","year":"2024","author":"Liu","key":"ref22"},{"journal-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.02413"},{"key":"ref25","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00223"},{"key":"ref28","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00187"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref31","article-title":"Video-llama: An instruction-tuned audio-visual language model for video understanding","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00292"},{"volume-title":"Contextual modeling for 3d dense captioning on point clouds","year":"2022","author":"Zhong","key":"ref33"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128559.pdf?arnumber=11128559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:13:26Z","timestamp":1756880006000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128559","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}