Hi! I'm Niels, part of the community science team at Hugging Face. I've noticed this model repository is based on the paper "Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction" but doesn't have much information in its README.
This PR improves the model card by:
- Adding the `zero-shot-image-classification` pipeline tag to improve discoverability.
- Linking the repository to the associated paper on arXiv.
- Linking to the official GitHub repository.
- Adding a citation section for researchers.
