Skip to content
ModelListedExternal
Browse files

Robust U1

Robust-U1 is a unified Multimodal Large Language Model (MLLM) that can self-recover corrupted visual content and perform multimodal reasoning over it. This enables robust visual understanding even under real-world...

KindText modelVersionBgrade

Model source

Kind
Text model
File size
320 MB–27.2 GB
Version
vRevision 4388f4f
Updated
Nov 1, 2026
Downloads
42
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) that can self-recover corrupted visual content and perform multimodal reasoning over it. This enables robust visual understanding even under real-world image degradations.

🏰 Pretrained Checkpoints

CheckpointLinkNote
BAGEL-7B-MoTByteDance-Seed/BAGEL-7B-MoTUsed as initial weights for training.
Robust-U1Jiaqi-hkust/Robust-U1Final model for visual self-recovery and multimodal reasoning.
Robust-U1-RLJiaqi-hkust/Robust-U1-RLFine-tuned with reinforcement learning.
Robust-U1-SFTJiaqi-hkust/Robust-U1-SFTFine-tuned with supervised learning.

⭐️ Citation

If you find this repository useful, please cite the paper:

@inproceedings{tang2026robustu1,
      title={Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?},
      author={Tang, Jiaqi and Chen, Jianmin and Zhai, Youyang and Wei, Wei and Liu, Runtao and Zhao, Mengjie and Wu, Xiangyu and Xiao, Qingfa and Chen, Qifeng},
      booktitle={Proceedings of the 43rd International Conference on Machine Learning (ICML)},
      year={2026},
}

Requirements

Models

1
  • VAE · 320 MB · SAFETENSORS · FP32 (tensor header) · Hugging Face · Jiaqi-hkust/Robust-U1

Sources

1 source
Hugging FacePrimaryVersion 4388f4f41f97862f7530dc593d9bf0a4ee57caab
huggingface.co/Jiaqi-hkust/Robust-U1/tree/4388f4f41f97862f7530dc593d9bf0a4ee57caab

Verified Nov 1

Download files

Model artifacts

2 artifacts

ae.safetensors

safetensors · FP32 (tensor header) · 320 MB · SHA-256 afc8e28272cd…9e38 · Hugging Face

Download file

model.safetensors

safetensors · BF16 (unverified) · 27.2 GB · SHA-256 bedcdcfa1be2…90e3 · Hugging Face

Download file

Source excerpts

3 excerpts

--- license: mit library_name: transformers pipeline_tag: any-to-any --- # 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) that can self-recover corrupted visual content and perform multimodal reasoning over it. This enables robust visual understanding even under real-world image degradations. - **Paper:** [Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?](https://arxiv.org/abs/2606.08063) - **Repository:** [jqtangust/Robust-U1](https://github.com/jqtangust/Robust-U1) - **Demo:** [Hugging Face Space](https://huggingface.co/spaces/Jiaqi-hkust/Robust-U1) ### 🏰 **Pretrained Checkpoints** | 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 the paper: ```bibtex @inproceedings{tang2026robustu1, title={Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?}, author={Tang, Jiaqi and Chen, Jianmin and Zhai, Youyang and Wei, Wei and Liu, Runtao and Zhao, Mengjie and Wu, Xiangyu and Xiao, Qingfa and Chen, Qifeng}, booktitle={Proceedings of the 43rd International Conference on Machine Learning (ICML)}, year={2026}, } ```

Source context: 42 downloads · 2 likes · Pipeline any-to-any · Library transformers · Repo Jiaqi-hkust/Robust-U1

Source context: 8 downloads · 1 likes · Pipeline any-to-any · Library transformers · Repo Jiaqi-hkust/Robust-U1