mars-fm

MarS-FM (MD-CATH) Model Checkpoint

This repository contains the PyTorch model weights for MarS-FM (Markov Space Flow Matching) trained on the MD-CATH dataset. This model was introduced in the ICLR 2026 paper: MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models.

🔗 Links and Resources

• Official GitHub Repository: valence-labs/mars-fm
• Paper: arXiv:2509.24779
• Dataset: compsciencelab/mdCATH

⚙️ Model Configuration

• Dataset: MD-CATH (--mdcath)
• Temperature: 450K (--temp 450)
• MSM States (--msm_num_states): 10
• MSM Lag Time (--msm_lagtime): 50

💻 How to Use

For full instructions on how to set up the environment, load this checkpoint, and run generation sampling, please follow the documentation in the official GitHub repository.

📝 Citation

If you use these weights, please cite the original authors:

@article{kapusniak2025mars,
  title={MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models},
  author={Kapu{\'s}niak, Kacper and Gabellini, Cristian and Bronstein, Michael and Tossou, Prudencio and Di Giovanni, Francesco},
  journal={arXiv preprint arXiv:2509.24779},
  year={2025}
}