Release AnyTrack on Hugging Face

[NielsRogge]

Hi @IdolLab 🤗

Niels here from the open-source team at Hugging Face. I discovered your work through Hugging Face Daily Papers: https://huggingface.co/papers/2608.06773 Congratulations on the ACMMM 2026 Oral!

The paper page lets people discuss your paper and find related artifacts, and you can also claim the paper as yours so it shows up on your public Hugging Face profile. It would be great to make the AnyTrack checkpoints and the extended multi-modal tracking benchmark available on the Hugging Face Hub once they are released, to improve their discoverability and visibility.

I noticed your GitHub repository is still under construction. Once the code, checkpoints, and any extended benchmark datasets are ready, hosting them on Hugging Face would be very valuable for the community.

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 use the hf_hub_download helper to download a checkpoint from the hub.

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

Uploading dataset

If you also release the extended multi-modal tracking benchmark, it would be awesome to make it available on Hugging Face so 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 is the dataset viewer which allows people to quickly explore the data directly in the browser.

Let me know if you're interested or need any help regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗