Hello,
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/2512.18181.
The paper page lets people find artifacts about your work (models, datasets, or demos), and you can also claim the paper as yours to show it on your public profile.
It's fantastic to see that you've already made the MA-Data dataset and the Appearance Expert weights available on the 🤗 hub!
I noticed a couple of things that could help improve the visibility and discoverability of your work:
- Motion Expert Weights: While the code is available, I couldn't find the pre-trained weights for the Motion Expert. Would you like to host those on Hugging Face as well?
- Model Repositories: Currently, the model weights seem to be hosted within a dataset repository. We generally recommend pushing each model checkpoint to a separate model repository at https://huggingface.co/models. This enables better tracking (like download stats) and allows people to use them more easily with specialized tools.
- Linking to Paper Page: I noticed the artifacts aren't appearing on the Hugging Face paper page yet. You can link them by adding
arxiv: 2512.18181 to the metadata (YAML header) of your model/dataset READMEs. See the guide here.
Uploading models
If you're interested in hosting the Motion Expert or moving the Appearance Expert to a dedicated repo, you can find a guide here: https://huggingface.co/docs/hub/models-uploading. For custom PyTorch models, the PyTorchModelHubMixin is a great way to add from_pretrained support.
Let me know if you're interested or need any guidance!
Best regards,
Niels
ML Engineer @ HF 🤗
Hello,
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/2512.18181.
The paper page lets people find artifacts about your work (models, datasets, or demos), and you can also claim the paper as yours to show it on your public profile.
It's fantastic to see that you've already made the MA-Data dataset and the Appearance Expert weights available on the 🤗 hub!
I noticed a couple of things that could help improve the visibility and discoverability of your work:
arxiv: 2512.18181to the metadata (YAML header) of your model/dataset READMEs. See the guide here.Uploading models
If you're interested in hosting the Motion Expert or moving the Appearance Expert to a dedicated repo, you can find a guide here: https://huggingface.co/docs/hub/models-uploading. For custom PyTorch models, the PyTorchModelHubMixin is a great way to add
from_pretrainedsupport.Let me know if you're interested or need any guidance!
Best regards,
Niels
ML Engineer @ HF 🤗