Release AnyRecon sparse attention weights on Hugging Face

Hi @yutian10 🤗

I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as AnyRecon got featured: https://huggingface.co/papers/2604.19747.

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, and add your GitHub and project page URLs.

It's great to see that you've already hosted the AnyRecon LoRA weights on Hugging Face! I noticed in your GitHub README TODO list that the sparse attention weights are still to be uploaded. Would you like to host those on https://huggingface.co/models as well?

Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add tags in the model cards so that people find the models easier, and we can link all relevant checkpoints to the paper page.

If you're down, you can simply push them to your existing repository or a new one. Let me know if you're interested or need any guidance regarding this!

Kind regards,

Niels

Start with the README TODO list referenced in the issue and identify which sparse attention weights are still missing. Check the existing AnyRecon Hugging Face repository or a new model repository, then confirm the sparse attention weights are uploaded and discoverable alongside the paper artifacts.