Harmon-1.5B-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-1.5B-RecA, a model from the paper Reconstruction Alignment Improves Unified Multimodal Models. For installation, usage instructions, and further documentation, please visit Harmon's original GitHub repository.

🧠 Method

👁 Paper
👁 ArXiv
👁 Github
👁 Hugging Face Collection
👁 HF Demo
👁 Project Page

📊 Benchmarks

Model	GenEval ↑	DPGBench ↑	WISE ↑
Harmon-1.5B	0.73	80.93	0.41
Harmon-1.5B-RecA	0.86	87.21	0.50

✍️ 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}
}