# MBZUAI researchers present a 3D language model for fine-grained grounding

> MBZUAI’s Ground3D-LMM links text prompts to 3D point clouds to locate and measure objects and their parts.

- Canonical URL: https://newsverum.com/en/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026
- Publisher: Newsverum
- Section: Technology
- Country: United Arab Emirates
- Published: 2026-10-20T14:20:10+00:00
- Updated: 2026-10-20T14:20:10+00:00
- Event / data period: 2026-10-20
- Other editions: [Türkçe](https://newsverum.com/tr/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026.md), [العربية](https://newsverum.com/ar/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026.md), [Français](https://newsverum.com/fr/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026.md), [Español](https://newsverum.com/es/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026.md), [Deutsch](https://newsverum.com/de/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026.md), [Português](https://newsverum.com/pt/news/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026.md)

Ground3D-LMM, developed by MBZUAI researchers, uses text prompts with 3D point-cloud data to locate and measure particular objects and object parts in a scene. The university’s 20 October feature says the model was trained and evaluated with a dataset built from ScanNet and ScanNet++, with annotations for objects and their parts.

The dataset contains about 2.5 million question-answer pairs across roughly 2,500 indoor environments and eight tasks. MBZUAI reported that Ground3D-LMM outperformed other systems by nearly 20% on ScanRefer without using 2D images; this is a comparative result on a specified research benchmark. The findings were presented at ECCV 2026. The work does not establish real-world robot capability or reliable physical measurement.

## Data

### Ground3D-LMM dataset summary

Scope of the dataset assembled by the researchers for model training and evaluation.

Methodology: These figures describe the approximate size and scope of a research dataset; they are not Abu Dhabi or UAE measurements. The reported near-20% ScanRefer comparison is qualified in the story and should not be interpreted as general performance or a field result.

| Indicator | Value | Unit |
|---|---|---|
| Question-answer pairs | 2500000 | count |
| Indoor environments | 2500 | count |
| Tasks | 8 | count |

Sources: <https://mbzuai.ac.ae/news-events/news/building-llm-can-reason-about-the-physical-3d-world-fine-grained-level> · Download data: [JSON](https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026/data/ground3d-lmm-dataset-summary?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/mbzuai-ground3d-lmm-fine-grained-3d-grounding-2026/data/ground3d-lmm-dataset-summary?lang=en&format=csv)

## Sources

- [Mohamed bin Zayed University of Artificial Intelligence](<https://mbzuai.ac.ae/news-events/news/building-llm-can-reason-about-the-physical-3d-world-fine-grained-level>) (Source checked: 2026-10-20; Published: 2026-10-20)

---

Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)