Hi @hengrui-h 🤗
Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and your paper "Segment Anything Across Shots: A Method and Benchmark" which got featured on our paper page: https://huggingface.co/papers/2511.13715.
The paper page lets people discuss your paper and find related artifacts (such as your models, datasets, or demos). You can also claim the paper as yours, which will show up on your public profile at HF, and add Github and project page URLs.
It's great to see that you've released the Cut-VOS dataset on the Hugging Face Hub already! We can link this dataset directly to your paper page to improve its discoverability.
Additionally, I noticed you have pre-trained SAAS model checkpoints (SAAS_b+_ytvos_tma.pt and SAAS_l_ytvos_tma.pt) available, for which hosting URLs are mentioned in your GitHub README (one on Google Drive, another mentioned but without a direct link). It would be awesome to host these model checkpoints directly on the 🤗 Hub as well, to further improve their discoverability and visibility. We can add relevant tags in their model cards so that people can easily find and use them.
Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can leverage the hf_hub_download one-liner to download a checkpoint from the Hub.
We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.
Linking dataset
Since your Cut-VOS dataset is already on the 🤗 Hub (https://huggingface.co/datasets/FudanCVL/Cut-VOS), we can easily link it to your paper page (read here) so people can discover your work.
Let me know if you're interested in hosting the models or need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @hengrui-h 🤗
Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and your paper "Segment Anything Across Shots: A Method and Benchmark" which got featured on our paper page: https://huggingface.co/papers/2511.13715.
The paper page lets people discuss your paper and find related artifacts (such as your models, datasets, or demos). You can also claim the paper as yours, which will show up on your public profile at HF, and add Github and project page URLs.
It's great to see that you've released the Cut-VOS dataset on the Hugging Face Hub already! We can link this dataset directly to your paper page to improve its discoverability.
Additionally, I noticed you have pre-trained SAAS model checkpoints (
SAAS_b+_ytvos_tma.ptandSAAS_l_ytvos_tma.pt) available, for which hosting URLs are mentioned in your GitHub README (one on Google Drive, another mentioned but without a direct link). It would be awesome to host these model checkpoints directly on the 🤗 Hub as well, to further improve their discoverability and visibility. We can add relevant tags in their model cards so that people can easily find and use them.Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, we could leverage the PyTorchModelHubMixin class which adds
from_pretrainedandpush_to_hubto any customnn.Module. Alternatively, one can leverage the hf_hub_download one-liner to download a checkpoint from the Hub.We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.
Linking dataset
Since your
Cut-VOSdataset is already on the 🤗 Hub (https://huggingface.co/datasets/FudanCVL/Cut-VOS), we can easily link it to your paper page (read here) so people can discover your work.Let me know if you're interested in hosting the models or need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗