Show-o-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 Show-o-RecA. For installation, usage instructions, and further documentation, please visit Show-o's original GitHub repository.

🧠 Method

📊 Benchmarks

Model	GenEval ↑	DPGBench ↑	WISE ↑
Show-o	0.57	70.65	0.33
Show-o-RecA	0.62	75.70	0.34

License

Show-o-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~

@misc{xie2025reconstructionalignmentimprovesunified, title={Reconstruction Alignment Improves Unified Multimodal Models}, author={Ji Xie and Trevor Darrell and Luke Zettlemoyer and XuDong Wang}, year={2025}, eprint={2509.07295}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2509.07295}, }