Release DeVI on Hugging Face

[NielsRogge]

Hi @HyeonWooKim 🤗

Niels here from 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/2604.20841.

The paper page lets people discuss about your paper and find artifacts about it. You can also claim the paper as yours which will show up on your public profile at HF, and add your Github and project page URLs.

I saw on your Github repository that you're planning to release the code and results for DeVI soon! It'd be great to make the checkpoints (the control policies) and potentially any synthetic datasets available on the 🤗 hub, to improve their discoverability/visibility.

We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets (using categories like robotics or reinforcement-learning).

Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading. For custom physics-based or RL models, you can easily upload the weights through the UI or the CLI. Alternatively, you can use the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module.

Uploading dataset
If you plan to release the generated synthetic interaction data or imitation targets, we'd love to host those as well so people can do:

from datasets import load_dataset
dataset = load_dataset("your-hf-org-or-username/your-dataset")

You could also build a demo for DeVI on Spaces to showcase the synthetic video imitation in action; we can even provide you a ZeroGPU grant if needed.

Let me know if you're interested or need any guidance!

Best regards,

Niels
ML Engineer @ HF 🤗