Hi @dendenxu 🤗
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/2506.08015.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models 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.
It's great to see that the main projectaria/4DGT model is already available on the Hugging Face Hub! I also noticed in your GitHub repository that you provide a "first stage model" checkpoint (e.g., checkpoints/4dgt_1st_stage.pth) which is trained only using EgoExo4D data.
It would be awesome to also make this 4DGT 1st stage model checkpoint available on the 🤗 Hub, to further improve its discoverability and visibility. We can add tags so that people find it easily when filtering https://huggingface.co/models and link it to your paper page.
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.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @dendenxu 🤗
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/2506.08015.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models 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.
It's great to see that the main
projectaria/4DGTmodel is already available on the Hugging Face Hub! I also noticed in your GitHub repository that you provide a "first stage model" checkpoint (e.g.,checkpoints/4dgt_1st_stage.pth) which is trained only using EgoExo4D data.It would be awesome to also make this
4DGT 1st stage modelcheckpoint available on the 🤗 Hub, to further improve its discoverability and visibility. We can add tags so that people find it easily when filtering https://huggingface.co/models and link it to your paper page.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_pretrainedandpush_to_hubto any customnn.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.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗