Hi @HarryHsing 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Papers with Code as yours got featured: https://paperswithcode.co/paper/2606.19341.
The paper page lets people discuss about your paper and lets them find artifacts about it (I see you've already linked your excellent RL and SFT models!), you can also claim the paper as yours which will show up on your public profile at HF, and add project page URLs.
Would you like to host the 58K synthetic trajectory dataset you've introduced for Agentic SFT on https://huggingface.co/datasets?
I see you've shared example formats in the GitHub repo. Hosting the full dataset on Hugging Face will give it more visibility and enable better discoverability within the multimodal agent community. It will also allow people to do:
from datasets import load_dataset
dataset = load_dataset("harryhsing/OmniAgent-SFT-Trajectories")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 trajectories in the browser.
After uploaded, we can also link the dataset to the paper page (read here) so people can discover your work more easily.
Let me know if you're interested or need any guidance!
Kind regards,
Niels
Hi @HarryHsing 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Papers with Code as yours got featured: https://paperswithcode.co/paper/2606.19341.
The paper page lets people discuss about your paper and lets them find artifacts about it (I see you've already linked your excellent RL and SFT models!), you can also claim the paper as yours which will show up on your public profile at HF, and add project page URLs.
Would you like to host the 58K synthetic trajectory dataset you've introduced for Agentic SFT on https://huggingface.co/datasets?
I see you've shared example formats in the GitHub repo. Hosting the full dataset on Hugging Face will give it more visibility and enable better discoverability within the multimodal agent community. It 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 trajectories in the browser.
After uploaded, we can also link the dataset to the paper page (read here) so people can discover your work more easily.
Let me know if you're interested or need any guidance!
Kind regards,
Niels