metadata
license: apache-2.0
pipeline_tag: image-text-to-text
HermesFlow
Official Repository of the paper: HermesFlow.



News🔥🔥🔥
- Feb.18, 2025. Our checkpoints are publicly available on HuggingFace Repo.
Introduction
HermesFlow is a general alignment framework for multimodal LLMs, which cruate homologous preference data itself and utilize self-play iterative optimization with Pair-DPO to seamlessly close the gap between multimodal understanding and generation.
Citation
@article{yang2025hermesflow,
title={HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation},
author={Yang, Ling and Zhang, Xinchen and Tian, Ye and Shang, Chenming and Xu, Minghao and Zhang, Wentao and Cui, Bin},
journal={arXiv preprint arXiv:2502.12148},
year={2025}
}