Hi @tkpham3105 🤗
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/2606.30811.
The paper page lets people discuss about your paper and lets them find artifacts about it (your AVTok model 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.
Your paper introduces AVTok, a novel unified tokenizer for holistic audio-video generation. The abstract mentions that "source code are in our anonymous project page," and we found your GitHub repository (https://github.com/hkust-longgroup/AVTok). However, it appears the repository currently hosts the static project page files, and the actual implementation code for AVTok along with its pre-trained model checkpoints are not yet openly available for download.
Would you like to host the AVTok model (pre-trained tokenizer weights) and its associated code on https://huggingface.co/models?
Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add tags in the model card (e.g., any-to-any or audio-to-video, video-to-audio) so that people find the model easier, link it to the paper page, and allow users to easily integrate it into downstream pipelines.
If you're interested, here's a guide for uploading models: https://huggingface.co/docs/hub/models-uploading.
If it's a custom PyTorch model, you can use the PyTorchModelHubMixin class, which adds from_pretrained and push_to_hub to your model, making it simple to upload and for others to download and use. Alternatively, people can use hf_hub_download to fetch individual files.
After uploading, we can also link the model to the paper page (read here) so people can discover your model.
You could also build a demo for AVTok on Spaces to showcase its impressive capabilities; we can provide you a ZeroGPU grant, which gives you A100 GPUs for free.
Please let me know if you're interested or need any guidance!
Kind regards,
Niels
Hi @tkpham3105 🤗
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/2606.30811.
The paper page lets people discuss about your paper and lets them find artifacts about it (your AVTok model 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.
Your paper introduces AVTok, a novel unified tokenizer for holistic audio-video generation. The abstract mentions that "source code are in our anonymous project page," and we found your GitHub repository (https://github.com/hkust-longgroup/AVTok). However, it appears the repository currently hosts the static project page files, and the actual implementation code for AVTok along with its pre-trained model checkpoints are not yet openly available for download.
Would you like to host the AVTok model (pre-trained tokenizer weights) and its associated code on https://huggingface.co/models?
Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add tags in the model card (e.g.,
any-to-anyoraudio-to-video,video-to-audio) so that people find the model easier, link it to the paper page, and allow users to easily integrate it into downstream pipelines.If you're interested, here's a guide for uploading models: https://huggingface.co/docs/hub/models-uploading.
If it's a custom PyTorch model, you can use the PyTorchModelHubMixin class, which adds
from_pretrainedandpush_to_hubto your model, making it simple to upload and for others to download and use. Alternatively, people can use hf_hub_download to fetch individual files.After uploading, we can also link the model to the paper page (read here) so people can discover your model.
You could also build a demo for AVTok on Spaces to showcase its impressive capabilities; we can provide you a ZeroGPU grant, which gives you A100 GPUs for free.
Please let me know if you're interested or need any guidance!
Kind regards,
Niels