Hi @kliyer 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2604.11737.
The paper page lets people find artifacts about your work (your models for instance), and you can also claim the paper as yours which will show up on your public profile.
It's great to see that you've already hosted the ZipMo model weights on the Hub! Would you like to also host the evaluation datasets and tracks you've released on https://huggingface.co/datasets?
I see you're currently using Google Drive for the ground-truth tracks and videos. Hosting on Hugging Face will give the data more visibility and will also allow people to do:
from datasets import load_dataset
dataset = load_dataset("CompVis/zipmo-eval-tracks")If you're down, leaving a guide here: https://huggingface.co/docs/datasets/loading. We also support Webdataset, which is very useful for video datasets.
Besides discoverability, there's the dataset viewer which allows people to quickly explore the data in the browser. After it's uploaded, we can also link the dataset directly to the paper page.
I also noticed you have a Gradio demo in your repository—you could also host it on Spaces so people can try it out immediately! We can provide you with a ZeroGPU grant, which gives you free A100 GPU access for the demo.
Let me know if you're interested or need any guidance!
Kind regards,
Niels
Hi @kliyer 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2604.11737.
The paper page lets people find artifacts about your work (your models for instance), and you can also claim the paper as yours which will show up on your public profile.
It's great to see that you've already hosted the ZipMo model weights on the Hub! Would you like to also host the evaluation datasets and tracks you've released on https://huggingface.co/datasets?
I see you're currently using Google Drive for the ground-truth tracks and videos. Hosting on Hugging Face will give the data more visibility and will also allow people to do:
If you're down, leaving a guide here: https://huggingface.co/docs/datasets/loading. We also support Webdataset, which is very useful for video datasets.
Besides discoverability, there's the dataset viewer which allows people to quickly explore the data in the browser. After it's uploaded, we can also link the dataset directly to the paper page.
I also noticed you have a Gradio demo in your repository—you could also host it on Spaces so people can try it out immediately! We can provide you with a ZeroGPU grant, which gives you free A100 GPU access for the demo.
Let me know if you're interested or need any guidance!
Kind regards,
Niels