Release UniGenBench++ artifacts on Hugging Face

[NielsRogge]

Hi @CodeGoat24 🤗

Niels here from 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/2510.18701.
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 that you've already released the UniGenBench-EvalModel-qwen-72b-v1 model and the UniGenBench-Eval-Images dataset on the 🤗 Hub! To further improve their discoverability and visibility, it would be great to officially link these existing artifacts to your paper page on Hugging Face.

Additionally, I noticed that the core UniGenBench++ benchmark prompts (English and Chinese, found as test_prompts_en.csv and test_prompts_zh.csv in your GitHub repository) are currently only hosted on GitHub. Would it be awesome to make these available as a dedicated dataset on the 🤗 Hub as well? This would allow people to easily load them using datasets.load_dataset() and benefit from the dataset viewer.

Uploading the UniGenBench++ prompt dataset

Would be awesome to make these prompt datasets available on 🤗 , so that people can do:

from datasets import load_dataset

dataset = load_dataset("your-hf-org-or-username/unigenbench-prompts")

See here for a guide: https://huggingface.co/docs/datasets/loading.

Besides that, there's the dataset viewer which allows people to quickly explore the first few rows of the data in the browser.

Linking existing artifacts to your paper

We can link your existing model (UniGenBench-EvalModel-qwen-72b-v1) and dataset (UniGenBench-Eval-Images) to the paper page (read here) so people can discover your work directly from the paper page.

Let me know if you're interested/need any help regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗