Hi @eddyhkchiu 馃
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/2509.18053.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models and dataset for instance), and you can also claim the paper as yours which will show up on your public profile at HF.
It's great to see that you've already hosted the V2V-GoT-QA dataset on the Hub! I noticed that the model checkpoints for V2V-GoT and V2V-LLM are currently provided as a zip file within that dataset repository.
Would you like to host these models as standalone repositories on https://huggingface.co/models?
Hosting them directly in the Model Hub (as opposed to a zip file inside a dataset repo) will give them significantly more visibility and enable better discoverability. We can add specific metadata tags (like image-text-to-text) so that people find the models easier when filtering. It also allows people to see download statistics and use Hub-native libraries more effectively.
If you're down, leaving a guide here. We encourage researchers to push each model checkpoint to a separate model repository so that things like model cards and versioning work correctly. Since your models are based on LLaVA, they might also be compatible with the transformers library, which would make them even more accessible to the community.
After they are uploaded, we can also link the models to the paper page so people can discover your work.
Let me know if you're interested or need any guidance :)
Kind regards,
Niels
Hi @eddyhkchiu 馃
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/2509.18053.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models and dataset for instance), and you can also claim the paper as yours which will show up on your public profile at HF.
It's great to see that you've already hosted the V2V-GoT-QA dataset on the Hub! I noticed that the model checkpoints for V2V-GoT and V2V-LLM are currently provided as a zip file within that dataset repository.
Would you like to host these models as standalone repositories on https://huggingface.co/models?
Hosting them directly in the Model Hub (as opposed to a zip file inside a dataset repo) will give them significantly more visibility and enable better discoverability. We can add specific metadata tags (like
image-text-to-text) so that people find the models easier when filtering. It also allows people to see download statistics and use Hub-native libraries more effectively.If you're down, leaving a guide here. We encourage researchers to push each model checkpoint to a separate model repository so that things like model cards and versioning work correctly. Since your models are based on LLaVA, they might also be compatible with the
transformerslibrary, which would make them even more accessible to the community.After they are uploaded, we can also link the models to the paper page so people can discover your work.
Let me know if you're interested or need any guidance :)
Kind regards,
Niels