Hi @Foreshhh 🤗
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/2605.12481.
The paper page lets people discuss about your paper and lets them find artifacts about it, and 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 great to see that you've already hosted the ToolCUA-8B model on the Hub!
Would you also like to host the OSWorld-MCP benchmark and the interleaved training trajectories on https://huggingface.co/datasets?
I see you're currently using a Github repository for the benchmark, and the trajectories are on your TODO list. Hosting the data components on Hugging Face will give your work more visibility, enable better discoverability within the agent research community, and will also allow people to do:
from datasets import load_dataset
dataset = load_dataset("mPLUG/OSWorld-MCP")If you're down, leaving a guide here: https://huggingface.co/docs/datasets/loading.
Besides that, there's the dataset viewer which allows people to quickly explore the screenshots and trajectory steps in the browser.
After uploaded, we can also link the datasets to the paper page so people can discover all your work in one place.
Let me know if you're interested/need any guidance regarding this!
Kind regards,
Niels
ML Engineer @ HF 🤗
Hi @Foreshhh 🤗
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/2605.12481.
The paper page lets people discuss about your paper and lets them find artifacts about it, and 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 great to see that you've already hosted the ToolCUA-8B model on the Hub!
Would you also like to host the OSWorld-MCP benchmark and the interleaved training trajectories on https://huggingface.co/datasets?
I see you're currently using a Github repository for the benchmark, and the trajectories are on your TODO list. Hosting the data components on Hugging Face will give your work more visibility, enable better discoverability within the agent research community, and will also allow people to do:
If you're down, leaving a guide here: https://huggingface.co/docs/datasets/loading.
Besides that, there's the dataset viewer which allows people to quickly explore the screenshots and trajectory steps in the browser.
After uploaded, we can also link the datasets to the paper page so people can discover all your work in one place.
Let me know if you're interested/need any guidance regarding this!
Kind regards,
Niels
ML Engineer @ HF 🤗