Hi @qianben 🤗
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/2510.12838.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models 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 noticed on the first page of your Arxiv paper that "Open Source: Code Models" is mentioned, with a date of October 17, 2025. Your A$^2$FM model, an "Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning," sounds like a significant contribution, especially given its SOTA performance on agentic and reasoning benchmarks, including BrowseComp, which often involves multimodal capabilities.
Would you be interested in hosting the A$^2$FM model on https://huggingface.co/models once it's officially released?
Hosting on Hugging Face will give you more visibility and enable better discoverability. We can add relevant tags in the model cards (e.g., image-text-to-text for its multimodal agentic capabilities) so that people find the models easier, link it directly to your paper page, etc.
If you're interested, here's a guide: https://huggingface.co/docs/hub/models-uploading. If it's a custom PyTorch model, you can use the PyTorchModelHubMixin
class which adds from_pretrained and push_to_hub to the model, allowing you to upload it easily and others to download and use it right away.
After uploading, we can also link the models to the paper page (read here) so people can discover your model.
You can also build a demo for your model on Spaces, and we can provide you a ZeroGPU grant, which gives you A100 GPUs for free.
Let me know if you're interested or need any guidance as you prepare for the release!
Kind regards,
Niels
Hi @qianben 🤗
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/2510.12838.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models 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 noticed on the first page of your Arxiv paper that "Open Source: Code Models" is mentioned, with a date of October 17, 2025. Your A$^2$FM model, an "Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning," sounds like a significant contribution, especially given its SOTA performance on agentic and reasoning benchmarks, including BrowseComp, which often involves multimodal capabilities.
Would you be interested in hosting the A$^2$FM model on https://huggingface.co/models once it's officially released?
Hosting on Hugging Face will give you more visibility and enable better discoverability. We can add relevant tags in the model cards (e.g.,
image-text-to-textfor its multimodal agentic capabilities) so that people find the models easier, link it directly to your paper page, etc.If you're interested, here's a guide: https://huggingface.co/docs/hub/models-uploading. If it's a custom PyTorch model, you can use the PyTorchModelHubMixin
class which adds
from_pretrainedandpush_to_hubto the model, allowing you to upload it easily and others to download and use it right away.After uploading, we can also link the models to the paper page (read here) so people can discover your model.
You can also build a demo for your model on Spaces, and we can provide you a ZeroGPU grant, which gives you A100 GPUs for free.
Let me know if you're interested or need any guidance as you prepare for the release!
Kind regards,
Niels