Hello,
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/2509.21990.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo 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.
It's fantastic to see that you've already hosted the WAVE-7B checkpoint on the Hub at tsinghua-ee/WAVE-7B! This will definitely help with its visibility and ease of use.
I noticed in your paper that you introduced a new benchmark for versatile audio-visual learning. Would you be interested in hosting this dataset on Hugging Face as well? Having it on the Hub would enable better discoverability and allow researchers to easily explore it via the dataset viewer or load it via the datasets library:
from datasets import load_dataset
dataset = load_dataset("tsinghua-ee/WAVE-benchmark")Additionally, I saw that the BEATs backbone checkpoint is currently hosted on OneDrive. Would you like to host that on Hugging Face too? We recommend hosting all model components in repositories on the Hub to improve reliability and persistence compared to personal cloud storage links.
If you're down, leaving guides here for uploading models and datasets.
Let me know if you're interested or need any guidance!
Best regards,
Niels
ML Engineer @ HF 🤗
Hello,
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/2509.21990.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo 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.
It's fantastic to see that you've already hosted the
WAVE-7Bcheckpoint on the Hub attsinghua-ee/WAVE-7B! This will definitely help with its visibility and ease of use.I noticed in your paper that you introduced a new benchmark for versatile audio-visual learning. Would you be interested in hosting this dataset on Hugging Face as well? Having it on the Hub would enable better discoverability and allow researchers to easily explore it via the dataset viewer or load it via the
datasetslibrary:Additionally, I saw that the
BEATsbackbone checkpoint is currently hosted on OneDrive. Would you like to host that on Hugging Face too? We recommend hosting all model components in repositories on the Hub to improve reliability and persistence compared to personal cloud storage links.If you're down, leaving guides here for uploading models and datasets.
Let me know if you're interested or need any guidance!
Best regards,
Niels
ML Engineer @ HF 🤗