Hi @Ironieser 🤗
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 yours got featured: https://huggingface.co/papers/2508.18264.
The paper page lets people discuss about your paper and lets them find artifacts about it (such as your code implementation or a demo), 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 on your GitHub repository and project page that the code implementation for MMTok is "Coming Soon". This is exciting! We'd be thrilled if you considered releasing your MMTok code on the Hugging Face Hub once it's ready.
Hosting your code, for example as a custom model implementation or a Python library, can significantly increase its visibility and discoverability within the AI community. You could also create a Gradio Space to demonstrate the impressive speedup and efficiency benefits of MMTok. We can even provide you with a ZeroGPU grant to host such a demo on A100 GPUs for free.
Here are some resources that might be helpful:
Let me know if you're interested or need any guidance once your code is ready for release!
Kind regards,
Niels
Hi @Ironieser 🤗
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 yours got featured: https://huggingface.co/papers/2508.18264.
The paper page lets people discuss about your paper and lets them find artifacts about it (such as your code implementation or a demo), 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 on your GitHub repository and project page that the code implementation for MMTok is "Coming Soon". This is exciting! We'd be thrilled if you considered releasing your MMTok code on the Hugging Face Hub once it's ready.
Hosting your code, for example as a custom model implementation or a Python library, can significantly increase its visibility and discoverability within the AI community. You could also create a Gradio Space to demonstrate the impressive speedup and efficiency benefits of MMTok. We can even provide you with a ZeroGPU grant to host such a demo on A100 GPUs for free.
Here are some resources that might be helpful:
Let me know if you're interested or need any guidance once your code is ready for release!
Kind regards,
Niels