---
license: apache-2.0
pipeline_tag: image-text-to-text
library_name: transformers
base_model: Qwen/Qwen2.5-VL-3B-Instruct
tags:
- 3d
- spatial-reasoning
- vlm
- qwen2.5-vl
---

# 3DThinker-Mindcube

This repository contains the stage 1 model checkpoint for **3DThinker**, as presented in the paper [Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views](https://huggingface.co/papers/2510.18632).

3DThinker is a framework that enables Vision-Language Models (VLMs) to exploit geometric information within images for 3D spatial reasoning, simulating human-like spatial imagination without requiring explicit 3D prior inputs or labeled 3D training data.

- **Paper:** [Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views](https://huggingface.co/papers/2510.18632)
- **Code:** [GitHub - zhangquanchen/3DThinker](https://github.com/zhangquanchen/3DThinker)

## Introduction
* The model was trained on **Mindcube_Train** and tested on **MindCube-Tiny**.
* This model corresponds to **stage 1** training (supervised alignment of 3D latents) of Qwen2.5-3B-VL.
* Note that Tab. 2 in the paper is trained on a different training data configuration.
  
## Bibtex
If you find 3DThinker helpful for your work, please cite:

```
@article{chen2025think,
  title={Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views},
  author={Chen, Zhangquan and Zhang, Manyuan and Yu, Xinlei and Luo, Xufang and Sun, Mingze and Pan, Zihao and Feng, Yan and Pei, Peng and Cai, Xunliang and Huang, Ruqi},
  journal={arXiv preprint arXiv:2510.18632},
  year={2025}
}
```