Verify evals on Papers with Code

Hi,

Niels here from the open-source team at Hugging Face. Congratulations on your work!

I've made the [paper](https://paperswithcode.co/paper/2410.16512) and [9 paper-native evaluations](https://paperswithcode.co/paper/2410.16512#results) available on Papers with Code.

The paper has results on [Image Understanding](https://paperswithcode.co/tasks/image-understanding), [Image Classification](https://paperswithcode.co/tasks/image-classification), and [Image segmentation](https://paperswithcode.co/tasks/image-segmentation) task pages.

The TIPS-g/14 HR result currently ranks fourth on [COCO Captions Text-to-Image Retrieval](https://paperswithcode.co/benchmark/coco-captions-text-to-image?task=image-understanding&eval=7780).

Would it be possible to verify these results and let me know if any score, model name, benchmark protocol, or openness metadata should be corrected?

You can also edit the task, methods, project page, and GitHub URL directly from the paper page using your Hugging Face account.

Kind regards,

Niels

Start with the linked Papers with Code paper and its nine evaluation pages. Compare their scores, model name, benchmark protocol, and openness metadata with the project's published results, then identify and report any discrepancies. Done means the listed results and metadata have been verified or the required corrections are clearly documented.

Written by the indexing model from the issue text.