Hi @LogosRoboticsGroup 馃
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work on TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation via the arXiv page (https://arxiv.org/abs/2609.05266) and the GitHub repository (https://github.com/LogosRoboticsGroup/TacPAC). I noticed that the code is already open-sourced and that you plan to release datasets and checkpoints soon.
It would be great to make those upcoming artifacts available on the Hugging Face Hub as well, to improve their visibility and discoverability. We can add proper metadata tags so that people find them when filtering on https://huggingface.co/models and https://huggingface.co/datasets, and we can link them to your paper鈥檚 HF page.
For the model checkpoints, you can follow the guide at https://huggingface.co/docs/hub/models-uploading, or use the PyTorchModelHubMixin to add from_pretrained and push_to_hub to your models. For the datasets, the datasets library makes it easy to upload and load them:
from datasets import load_dataset
dataset = load_dataset("your-hf-org-or-username/your-dataset")See the guide here: https://huggingface.co/docs/datasets/loading. We would be happy to help you with the upload process and to link the artifacts to the paper page afterwards.
Let me know if you are interested or have any questions. Thanks for considering it!
Kind regards,
Niels
ML Engineer @ Hugging Face 馃
Hi @LogosRoboticsGroup 馃
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work on TacPAC: Tactile Prediction and Real-Time Action Correction in World-Action Models for Contact-Rich Manipulation via the arXiv page (https://arxiv.org/abs/2609.05266) and the GitHub repository (https://github.com/LogosRoboticsGroup/TacPAC). I noticed that the code is already open-sourced and that you plan to release datasets and checkpoints soon.
It would be great to make those upcoming artifacts available on the Hugging Face Hub as well, to improve their visibility and discoverability. We can add proper metadata tags so that people find them when filtering on https://huggingface.co/models and https://huggingface.co/datasets, and we can link them to your paper鈥檚 HF page.
For the model checkpoints, you can follow the guide at https://huggingface.co/docs/hub/models-uploading, or use the PyTorchModelHubMixin to add
from_pretrainedandpush_to_hubto your models. For the datasets, thedatasetslibrary makes it easy to upload and load them:See the guide here: https://huggingface.co/docs/datasets/loading. We would be happy to help you with the upload process and to link the artifacts to the paper page afterwards.
Let me know if you are interested or have any questions. Thanks for considering it!
Kind regards,
Niels
ML Engineer @ Hugging Face 馃