Harmon-0.5B-RecA

A self-supervised training framework that aligns understanding and generation in modest compute, with huge zero-shot gain on generation and editing capability.

This repository hosts the model weights for Harmon-0.5B-RecA. For installation, usage instructions, and further documentation, please visit Harmon's original GitHub repository.

🧠 Method

📊 Benchmarks

Model	GenEval ↑	DPGBench ↑	WISE ↑
Harmon-0.5B	0.68	80.12	0.33
Harmon-0.5B-RecA	0.79	84.67	0.40

License

Harmon-0.5B-RecA is licensed under the Apache 2.0 license.

✍️ Citation

If you find our work inspiring or use our codebase in your research, please consider giving a star ⭐ and a citation~

@article{xie2025reconstruction,
  title={Reconstruction Alignment Improves Unified Multimodal Models},
  author={Xie, Ji and Darrell, Trevor and Zettlemoyer, Luke and Wang, XuDong},
  journal={arXiv preprint arXiv:2509.07295},
  year={2025}
}