Model Card for EagleVision-4B

Model Details

• Baseline Detector: Oriented R-CNN
• LLM: microsoft/Phi-3-mini-128k-instruct
• Training Data: EVAttrs-95K

Model Sources

• Repository: https://github.com/XiangTodayEatsWhat/EagleVision
• Paper: https://arxiv.org/abs/2503.23330

Citation

@misc{jiang2025eaglevisionobjectlevelattributemultimodal,
      title={EagleVision: Object-level Attribute Multimodal LLM for Remote Sensing}, 
      author={Hongxiang Jiang and Jihao Yin and Qixiong Wang and Jiaqi Feng and Guo Chen},
      year={2025},
      eprint={2503.23330},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2503.23330}, 
}