Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
| Date | Stars |
|---|---|
| 2026-07-31 | 347 |
| 2026-08-06 | 347 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<!-- <h1 align="center"><img src="assets/icon.png" align="center" width="6.5%"><strong>G<sup>2</sup>VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning</strong></h1>
</div> -->
<h1 align="center"><strong>G<sup>2</sup>VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning</strong></h1>
</div>
<p align="center">
<a href="https://gordonhu608.github.io">Wenbo Hu</a><sup>1,2*</sup>,
<a href="https://openreview.net/profile?id=~Jingli_Lin1">Jingli Lin</a><sup>1,3*</sup>,
<a href="https://openreview.net/profile?id=~Yilin_Long2">Yilin Long</a><sup>1,4*</sup>,
<a href="https://openreview.net/profile?id=~Yunlong_Ran1">Yunlong Ran</a><sup>1,5</sup>,
<a href="https://jianglh-whu.github.io/">Lihan Jiang</a><sup>1,6</sup>,
<a href="https://github.com/yyfz">Yifan Wang</a><sup>1,3</sup>,
<a href="https://zcmax.github.io/">Chenming Zhu</a><sup>1,7</sup>,
<a href="https://runsenxu.com/">Runsen Xu</a><sup>1,8</sup>,
<a href="https://tai-wang.github.io/">Tai Wang</a><sup>1†</sup>,
<a href="https://oceanpang.github.io/">Jiangmiao Pang</a><sup>1†</sup>
</p>
<p align="center">
<sup>1</sup>Shanghai AI Lab,
<sup>2</sup>UCLA,
<sup>3</sup>SJTU,
<sup>4</sup>FDU,
<sup>5</sup>ZJU,
<sup>6</sup>USTC,
<sup>7</sup>HKU,
<sup>8</sup>CUHK
</p>
<p align="center">
<sup>*</sup>Equal Contribution
<sup>†</sup>Corresponding Author
</p>
<p align="center">
<a href="https://arxiv.org/pdf/2511.21688">📑 Paper</a> |
<a href="https://arxiv.org/abs/2511.21688">📖 arXiv</a> |
<a href="https://gordonhu608.github.io/g2vlm.github.io/">🌐 Homepage</a> |
<a href="https://huggingface.co/InternRobotics/G2VLM-2B-MoT">🤗 Model</a>
</p>
## 🏠 About
<div style="text-align: center;">
<img src="assets/teaser.png" alt="Dialogue_Teaser" width=100% >
</div>
We present <b>G<sup>2</sup>VLM</b>, a geometry grounded vision-language model proficient in both spatial 3D reconstruction and spatial
understanding tasks. For spatial reasoning questions, G<sup>2</sup>VLM can natively predict 3D geometry and employ interleaved reasoning for an answer.
## 📢 News
- [2026-04-18] 📝 We release our training code in the [train folder](./train). Please refer to our training instructions below.
- [2026-02-20] 🔥 Our work is accepted by CVPR 2026!
- [2026-01-14] We release the evaluation code for 3D reconstruction. Please refer to the eval readme [here](./eval_code/recons/README.md).
- [Coming!] 📝 We will release the checkpoint of G<sup>2</sup>VLM-SR, a strong spatial reasoning model. Stay tuned!
- [2025-11-27] 🔥 We release the example training data preprocessing code in the [data folder](./data).
- [2025-11-27] 🔥 We release the inference code and the checkpoint of G<sup>2</sup>VLM.
- [2025-11-27] 🔥 We release the [paper](https://arxiv.org/abs/2511.21688) of G<sup>2</sup>VLM.
<!-- contents with emoji -->
<!-- ## 📋 Contents
- [🤖 Online Demo](#-online-demo)
- [💬 Dialogue Examples](#-dialogue-examples)
- [🔍 Overview](#-overview)
- [📦 Training and Evaluation](#-training-and-evaluation)
- [📝 TODO List](#-todo-list)
- [🔗 Citation](#-citation)
- [📄 License](#-license)
- [👏 Acknowledgements](#-acknowledgements) -->
### Model
<p align="center">
<img src="assets/method.png" align="center" width="100%">
</p>
G<sup>2</sup>VLM is a unified model that integrates both a geometric perception expert for 3D reconstruction and a semantic perception expert for multimodal understanding and spatial reasoning tasks. All tokens can do shared multi-modal self attention in each transformer block.
## 🚀 Quick Start
1️⃣ Set up environment
```bash
git clone https://github.com/InternRobotics/G2VLM
cd G2VLM
conda create -n g2vlm python=3.10 -y
conda activate g2vlm
pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu121
pip install -rExcerpt of 7,362 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c699053737f7f431, topic:3d-reconstruction, desc:3d reconstruction
matched fp:c699053737f7f431, desc:vision-language, desc:vision language model