Hi @zixianma 🤗
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/2603.24575.
The paper page lets people discuss about your paper and lets them find artifacts about it. I saw that you've already released the VFIG-4B model checkpoint and a demo on the Hub, which is fantastic! It's a great contribution to the field of figure vectorization.
Would you also like to host the datasets you've introduced (VFIG-DATA and VFIG-BENCH) on https://huggingface.co/datasets? Hosting them on Hugging Face will give the work even more visibility and enable better discoverability. It also allows researchers to use the data directly via:
from datasets import load_dataset
dataset = load_dataset("your-hf-org-or-username/VFIG-DATA")If you're down, I'm leaving a guide here. Besides ease of use, there's the dataset viewer which allows people to quickly explore the images and SVG code pairs directly in the browser.
After they are uploaded, we can also link the datasets to the paper page and your model cards so people can discover the full suite of artifacts in one place.
Let me know if you're interested or need any guidance!
Kind regards,
Niels
Hi @zixianma 🤗
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/2603.24575.
The paper page lets people discuss about your paper and lets them find artifacts about it. I saw that you've already released the VFIG-4B model checkpoint and a demo on the Hub, which is fantastic! It's a great contribution to the field of figure vectorization.
Would you also like to host the datasets you've introduced (VFIG-DATA and VFIG-BENCH) on https://huggingface.co/datasets? Hosting them on Hugging Face will give the work even more visibility and enable better discoverability. It also allows researchers to use the data directly via:
If you're down, I'm leaving a guide here. Besides ease of use, there's the dataset viewer which allows people to quickly explore the images and SVG code pairs directly in the browser.
After they are uploaded, we can also link the datasets to the paper page and your model cards so people can discover the full suite of artifacts in one place.
Let me know if you're interested or need any guidance!
Kind regards,
Niels