| # ViGaL: Visual Game Learning | |
| ## Model Overview | |
| We present **Visual Game Learning (ViGaL)**, a novel post-training paradigm where multimodal large language models (MLLMs) develop out-of-domain generalization of multimodal reasoning through playing arcade-like games. | |
| **ViGaL-7B** demonstrates that training a 7B-parameter MLLM via reinforcement learning on simple arcade-like games like Snake significantly enhances its downstream performance on multimodal math benchmarks like MathVista, and on multi-discipline questions like MMMU, **without seeing any worked solutions, equations, or diagrams during RL**, suggesting the capture of transferable reasoning skills. | |
| ## Dataset Usage | |
| ### Preparing the Training Data | |
| After unzipping the dataset, please check the `rotation` subfolder. | |
| #### Converting Image Paths | |
| If you're doing training, you'll need to process the JSON line metadata file in the `rotation` subfolder. The framework currently only supports absolute image paths, but the JSON line metadata file uses relative paths, so you'll need to add the absolute path prefix. | |
| We provide a simple utility script `add_root_prefix.py` to convert relative paths to absolute paths. Run this script to update the metadata file before training: | |
| ```bash | |
| python add_root_prefix.py --input rotation/metadata.jsonl --output rotation/metadata_absolute.jsonl --root /path/to/your/dataset | |
| ``` | |
| ### Running Training | |
| To run the training, please follow the instructions in this README. You can also refer to [https://github.com/ModalMinds/MM-EUREKA/tree/qwen](https://github.com/ModalMinds/MM-EUREKA/tree/qwen) for additional information - we're using the same codebase. | |
| ## Resources | |
| For details of our approach and performance comparison, please see our [paper](https://arxiv.org/abs/2506.08011). | |
| For details of training and evaluation, please see our [code repo](https://github.com/yunfeixie233/ViGaL). | |
| | [**🚀 Project Page**](https://yunfeixie233.github.io/ViGaL/) | [**📖 Paper**](https://arxiv.org/abs/2506.08011) | [**🔗 GitHub**](https://github.com/yunfeixie233/ViGaL) | [**🤗 Training Data**](https://huggingface.co/yunfeixie/vigal_data) | [**🤗 Model**](https://huggingface.co/yunfeixie/ViGaL-7B) | | |
| ## Citation | |
| If you find this model useful, please cite our work: | |
| ```bibtex | |
| @article{xie2025play, | |
| title = {Play to Generalize: Learning to Reason Through Game Play}, | |
| author = {Xie, Yunfei and Ma, Yinsong and Lan, Shiyi and Yuille, Alan and Xiao, Junfei and Wei, Chen}, | |
| journal = {arXiv preprint arXiv:2506.08011}, | |
| year = {2025}, | |
| } | |
| ``` |