🚗 AutoDriveRL Repository

Welcome to the AutoDriveRL repository! 🎉

📄 Read the paper: DriveRX: A Vision-Language Reasoning Model for Cross-Task Autonomous Driving

Here you'll find:

• 📂 Datasets for autonomous driving multi-task learning
• 🧑‍💻 Codebase for the AutoDriveRL framework
• 🏁 DriveRX Checkpoints — the model weights from our latest experiments

🔓 We're planning to open-source everything soon — stay tuned! 🌟

---

📚 About AutoDriveRL

AutoDriveRL is a multi-task vision-language model (VLM) framework designed for autonomous driving.
It focuses on:

• 🚘 Robust perception and reasoning
• 🔍 Improved generalization under diverse driving scenarios
• 🤖 Enhanced real-world applicability

---

📚 Citation

🙏 If you find this useful for your research, please consider citing our paper!

@misc{diao2025driverxvisionlanguagereasoningmodel,
      title={DriveRX: A Vision-Language Reasoning Model for Cross-Task Autonomous Driving}, 
      author={Muxi Diao and Lele Yang and Hongbo Yin and Zhexu Wang and Yejie Wang and Daxin Tian and Kongming Liang and Zhanyu Ma},
      year={2025},
      eprint={2505.20665},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2505.20665}, 
}