Hi! I'm Niels from the Hugging Face community team.
This PR adds a comprehensive model card for VisCoP. It includes:
- Correct metadata tags (`pipeline_tag: video-text-to-text`).
- A link to the paper [VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models](https://huggingface.co/papers/2510.13808).
- A link to the official GitHub repository.
- Quickstart inference and environment installation steps.
Feel free to merge if this looks good to you!