Robust U1 RL
Robust-U1 is a unified Multimodal Large Language Model (MLLM) designed to self-recover corrupted visual content and perform reasoning over it. This framework addresses the performance degradation of MLLMs under...
Model source
- Kind
- Text model
- File size
- 320 MB–27.2 GB
- Version
- vRevision 921e52e
- Updated
- Nov 1, 2026
- Downloads
- 19
- Source
- Hugging Face
Source description
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
Robust-U1 is a unified Multimodal Large Language Model (MLLM) designed to self-recover corrupted visual content and perform reasoning over it. This framework addresses the performance degradation of MLLMs under real-world visual corruptions by equipping them with explicit visual self-recovery capabilities.
- Paper: Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
- Repository: GitHub - jqtangust/Robust-U1
- Demo: Hugging Face Space
🏰 Pretrained checkpoints (reference)
| Checkpoint | Link | Note |
|---|---|---|
| BAGEL-7B-MoT | ByteDance-Seed/BAGEL-7B-MoT | Used as initial weights for training. |
| Robust-U1 | Jiaqi-hkust/Robust-U1 | Final model for visual self-recovery and multimodal reasoning. |
| Robust-U1-RL | Jiaqi-hkust/Robust-U1-RL | Fine-tuned with reinforcement learning. |
| Robust-U1-SFT | Jiaqi-hkust/Robust-U1-SFT | Fine-tuned with supervised learning. |
⭐️ Citation
If you find this repository useful, please cite our paper:
@inproceedings{
2026robustu,
title={Robust-U1: Can {MLLM}s Self-Recover Corrupted Visual Content for Robust Understanding?},
author={Jiaqi Tang, Jianmin Chen, Youyang Zhai, Wei Wei, Runtao Liu, Mengjie Zhao, Xiangyu Wu, Qingfa Xiao, Qifeng Chen},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=I6W6cxVVts}
}
Requirements
Models
1- Found
VAE · 320 MB · SAFETENSORS · FP32 (tensor header) · Hugging Face · Jiaqi-hkust/Robust-U1-RL
Sources
1 source
Sources
1 sourceVerified Nov 1
Download files
Repository files
File inventory only; completeness is unverified.
Model artifacts
2 artifacts
Model artifacts
2 artifactsae.safetensors
safetensors · FP32 (tensor header) · 320 MB · SHA-256 afc8e28272cd…9e38 · Hugging Face
Download filemodel.safetensors
safetensors · BF16 (unverified) · 27.2 GB · SHA-256 92b569c135a3…2dd9 · Hugging Face
Download fileSource excerpts
3 excerpts
Source excerpts
3 excerpts--- license: mit pipeline_tag: any-to-any library_name: transformers --- # Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? [Robust-U1](https://arxiv.org/abs/2606.08063) is a unified Multimodal Large Language Model (MLLM) designed to **self-recover corrupted visual content** and perform reasoning over it. This framework addresses the performance degradation of MLLMs under real-world visual corruptions by equipping them with explicit visual self-recovery capabilities. - **Paper:** [Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?](https://arxiv.org/abs/2606.08063) - **Repository:** [GitHub - jqtangust/Robust-U1](https://github.com/jqtangust/Robust-U1) - **Demo:** [Hugging Face Space](https://huggingface.co/spaces/Jiaqi-hkust/Robust-U1) ### 🏰 **Pretrained checkpoints (reference)** | Checkpoint | Link | Note | |:----------:|:----:|:----:| | BAGEL-7B-MoT | [ByteDance-Seed/BAGEL-7B-MoT](https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT) | Used as initial weights for training. | | **Robust-U1** | [Jiaqi-hkust/Robust-U1](https://huggingface.co/Jiaqi-hkust/Robust-U1) | Final model for visual self-recovery and multimodal reasoning. | | **Robust-U1-RL** | [Jiaqi-hkust/Robust-U1-RL](https://huggingface.co/Jiaqi-hkust/Robust-U1-RL) | Fine-tuned with reinforcement learning. | | **Robust-U1-SFT** | [Jiaqi-hkust/Robust-U1-SFT](https://huggingface.co/Jiaqi-hkust/Robust-U1-SFT) | Fine-tuned with supervised learning. | ## ⭐️ **Citation** If you find this repository useful, please cite our paper: ```bibtex @inproceedings{ 2026robustu, title={Robust-U1: Can {MLLM}s Self-Recover Corrupted Visual Content for Robust Understanding?}, author={Jiaqi Tang, Jianmin Chen, Youyang Zhai, Wei Wei, Runtao Liu, Mengjie Zhao, Xiangyu Wu, Qingfa Xiao, Qifeng Chen}, booktitle={Forty-third International Conference on Machine Learning}, year={2026}, url={https://openreview.net/forum?id=I6W6cxVVts} } ```
Source context: 19 downloads · 1 likes · Pipeline any-to-any · Library transformers · Repo Jiaqi-hkust/Robust-U1-RL
Source context: 7 downloads · 1 likes · Pipeline any-to-any · Library transformers · Repo Jiaqi-hkust/Robust-U1-RL
