Configuration Parsing Warning:Config file config.json cannot be fetched (too big)

Configuration Parsing Warning:Config file chat_template.json cannot be fetched (too big)

Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)

G2VLM-2B-MoT

Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

👁 G2VLM

👁 G2VLM Website
👁 G2VLM Paper on arXiv
👁 Github

We present G²VLM, a geometry grounded vision-language model proficient in both spatial 3D reconstruction and spatial understanding tasks. For spatial reasoning questions, G²VLM can natively predict 3D geometry and employ interleaved reasoning for an answer.

This repository hosts the model weights for G²VLM. For installation, usage instructions, and further documentation, please visit our GitHub repository.

👁 Image

🧠 Method

G²VLM 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.

👁 Image

License

G2VLM is licensed under the Apache 2.0 license.

✍️ Citation

@article{hu2025g2vlmgeometrygroundedvision,
 title={G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning}, 
 author={Wenbo Hu and Jingli Lin and Yilin Long and Yunlong Ran and Lihan Jiang and Yifan Wang and Chenming Zhu and Runsen Xu and Tai Wang and Jiangmiao Pang},
 year={2025},
 eprint={2511.21688},
 archivePrefix={arXiv},
 primaryClass={cs.CV},
 url={https://arxiv.org/abs/2511.21688}, 
}

Base model