linhuixiao

/

Awesome-Visual-Grounding

like 1

Hi! I'm Niels from the community science team at Hugging Face.

This PR updates the model card to correctly reflect the paper ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling. The previous content appeared to be placeholder information for an unrelated survey paper.

Changes include:

1. Adding the image-to-text pipeline tag to the metadata.
2. Replacing the placeholder survey text with a summary of the ViGoR framework and dataset.
3. Adding links to the official paper and GitHub repository.
4. Providing the correct BibTeX citation.