Release artifacts (code, models) for Rethinking Chain-of-Thought Reasoning for Videos on Hugging Face

[NielsRogge]

Hi @YiwuZhong 🤗

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/2512.09616.
The paper page lets people discuss about your paper and lets them find artifacts about it (your code, 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.

I saw in the abstract that "Our code will be released at this https URL.", and the GitHub repository (https://github.com/LaVi-Lab/Rethink_CoT_Video) mentions "Stay tuned!". We'd be very interested in having your code and any associated models (e.g., the enhanced MLLMs resulting from your framework) and/or datasets (if any were introduced and will be released) available on the 🤗 hub once they are ready. This would greatly improve their discoverability and visibility within the AI community.

We can add tags so that people find them easily when filtering https://huggingface.co/models and https://huggingface.co/datasets.

Uploading code / models

You can directly push your code repository to the Hugging Face Hub, similar to how you use GitHub. This can be particularly useful for others to find and use your framework. See here for a guide: https://huggingface.co/docs/hub/repositories-the-basics#create-a-repository.

If you decide to release model checkpoints trained with your framework, here's 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. Your models, being video MLLMs, would likely fit the video-text-to-text pipeline tag.

Uploading dataset

If you are introducing any new datasets as part of your work, it would be awesome to make them available on 🤗 , so that people can 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.

Let me know if you're interested/need any help regarding this, or if you have an estimated timeline for the code release!

Cheers,

Niels
ML Engineer @ HF 🤗

[YiwuZhong]

@NielsRogge, thank you for your interests in our work! We will consider releasing a counterpart on HuggingFace.