Hi @chengzhag 🤗
Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and your impressive paper, "PanFlow: Decoupled Motion Control for Panoramic Video Generation", which was featured on our daily papers page: https://huggingface.co/papers/2512.00832.
The paper page allows people to discuss your paper and easily 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'd be great to make the models and datasets you've released more discoverable and accessible on the 🤗 Hub! I noticed that your "PanFlow Main Checkpoints", "PanFlow Finetuned LoRA Weights", and "PanoFlow(RAFT)-wo-CFE" models, as well as the "PanFlow Toy Dataset", are currently hosted on OneDrive and Weiyun.
I also saw that you've already made the "PanFlow Full Dataset" available on the 🤗 Hub at https://huggingface.co/datasets/chengzhag/PanFlow! That's fantastic. However, the Hugging Face REST API shows it's not yet linked to your paper page. We can easily link this dataset for better discoverability.
Uploading models
We'd love for you to host the "PanFlow Main Checkpoints", "PanFlow Finetuned LoRA Weights", and "PanoFlow(RAFT)-wo-CFE" on https://huggingface.co/models. This would centralize access and improve visibility. We can add tags so that people find them when filtering https://huggingface.co/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 leverages 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.
Uploading and linking datasets
We'd be thrilled if you could host the "PanFlow Toy Dataset" on https://huggingface.co/datasets. For the "PanFlow Full Dataset" which is already on HF, linking it to the paper page would be awesome so people can easily discover it. This would allow users to do:
from datasets import load_dataset
dataset = load_dataset("your-hf-org-or-username/your-dataset")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.
After uploaded, we can also link the datasets and models to the paper page (read here) so people can discover your work.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @chengzhag 🤗
Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and your impressive paper, "PanFlow: Decoupled Motion Control for Panoramic Video Generation", which was featured on our daily papers page: https://huggingface.co/papers/2512.00832.
The paper page allows people to discuss your paper and easily 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'd be great to make the models and datasets you've released more discoverable and accessible on the 🤗 Hub! I noticed that your "PanFlow Main Checkpoints", "PanFlow Finetuned LoRA Weights", and "PanoFlow(RAFT)-wo-CFE" models, as well as the "PanFlow Toy Dataset", are currently hosted on OneDrive and Weiyun.
I also saw that you've already made the "PanFlow Full Dataset" available on the 🤗 Hub at https://huggingface.co/datasets/chengzhag/PanFlow! That's fantastic. However, the Hugging Face REST API shows it's not yet linked to your paper page. We can easily link this dataset for better discoverability.
Uploading models
We'd love for you to host the "PanFlow Main Checkpoints", "PanFlow Finetuned LoRA Weights", and "PanoFlow(RAFT)-wo-CFE" on https://huggingface.co/models. This would centralize access and improve visibility. We can add tags so that people find them when filtering https://huggingface.co/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 leverages 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.
Uploading and linking datasets
We'd be thrilled if you could host the "PanFlow Toy Dataset" on https://huggingface.co/datasets. For the "PanFlow Full Dataset" which is already on HF, linking it to the paper page would be awesome so people can easily discover it. This would allow users to do:
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.
After uploaded, we can also link the datasets and models to the paper page (read here) so people can discover your work.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗