Ir para o conteúdo
ModelListadosExterno
Browse files

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...

TipoText modelVersãoBnota

Fonte do modelo

Tipo
Text model
Tamanho do arquivo
320 MB–27,2 GB
Versão
vRevision 921e52e
Atualizado
1 de nov. de 2026
Downloads
19
Fonte
Hugging Face

Descrição da fonte

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.

🏰 Pretrained checkpoints (reference)

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 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}
}

Requisitos

Modelos

1
  • ae.safetensors

    Encontrado

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

Fontes

1 fonte
Hugging FacePrimárioVersão 921e52e335552a6a5da3608fa902f7fca346cd24
huggingface.co/Jiaqi-hkust/Robust-U1-RL/tree/921e52e335552a6a5da3608fa902f7fca346cd24

Verificado 1 de nov.

Download files

Artefatos de modelo

2 artefatos

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 92b569c135a3…2dd9 · Hugging Face

Download file

Trechos de fonte

3 trechos

--- 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