Release SceneGen artifacts (models, dataset) on Hugging Face

[NielsRogge]

Hi @haoningwu3639 and @Mengmouxu 🤗

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/2508.15769.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo for instance), you can also claim
the paper as yours which will show up on your public profile at HF, add Github and project page URLs.

I saw from your abstract, paper page comments, and GitHub README that you are organizing your code, data, and checkpoints, and plan to gradually open-source them in the near future. That's fantastic news! Your interactive 3D model viewer on the project page is particularly impressive, demonstrating the exciting capabilities of SceneGen.

It'd be great to make these checkpoints and any new datasets available on the 🤗 hub once they are ready, to improve their discoverability and visibility.
We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.

Uploading models

See here for a guide: https://huggingface.co/docs/hub/models-uploading.

In this case, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can leverages the hf_hub_download one-liner to download a checkpoint from the hub.

We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.

You can also build a demo for your model on Spaces, perhaps similar to your interactive demo, which can bring your work to life for even more users. We can provide you a ZeroGPU grant, which gives you A100 GPUs for free.

Uploading dataset

Would be awesome to make the dataset (perhaps your generated 3D scenes as shown on the project page) available on 🤗 , so that people can do:

from datasets import load_dataset

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

See here for a guide: https://huggingface.co/docs/datasets/loading.

Besides that, there's the dataset viewer which allows people to quickly explore the first few rows of the data in the browser.

Let me know if you're interested or need any help regarding this as you prepare for the release!

Cheers,

Niels
ML Engineer @ HF 🤗