MLLM-4D / README.md
flow666's picture
Add model card for MLLM-4D (#1)
16bb0c5
---
library_name: transformers
pipeline_tag: video-text-to-text
---
# MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence
[**MLLM-4D**](https://github.com/GVCLab/MLLM-4D) is a comprehensive framework designed to bridge the gaps in training data curation and model post-training for spatiotemporal understanding and reasoning. It enables multimodal large language models (MLLMs) to perceive and reason about the evolution of 3D space over time from purely visual inputs.
- **Paper:** [MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence](https://huggingface.co/papers/2603.00515)
- **Repository:** [https://github.com/GVCLab/MLLM-4D](https://github.com/GVCLab/MLLM-4D)
- **Project Page:** [https://github.com/GVCLab/MLLM-4D](https://github.com/GVCLab/MLLM-4D)
## Model Description
MLLM-4D achieves state-of-the-art spatiotemporal intelligence by focusing on the relationships between objects and the camera within 3D space. The model establishes foundational 4D understanding via Supervised Fine-Tuning (SFT) and further catalyzes 4D reasoning capabilities by employing Group Relative Policy Optimization (GRPO) with specialized Spatiotemporal Chain of Thought (ST-CoT) prompting. It achieves these capabilities using purely 2D RGB inputs without architectural modifications.
## Usage
To run the inference demo for MLLM-4D, please refer to the setup instructions in the [official repository](https://github.com/GVCLab/MLLM-4D) and use the following commands:
```bash
# for MLLM-4D-SFT
python scripts/inference.py --model_type "MLLM-4D-SFT" --model_path PATH-to-MLLM-4D-SFT
# for MLLM-4D-RFT
python scripts/inference.py --model_type "MLLM-4D-RFT" --model_path PATH-to-MLLM-4D-RFT
```
## Citation
If you find the work useful, please consider citing:
```bibtex
@article{yin2026mllm4d,
title={MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence},
author={Yin, Xingyilang and Li, Chengzhengxu and Chang, Jiahao and Pun, Chi-Man and Cun, Xiaodong},
journal={arXiv preprint arXiv:2603.00515},
year={2026}
}
```