Any-to-Any
Transformers
Safetensors
chameleon
image-to-text
multimodal
reasoning
sft
rl
Omni-R1-Zero / README.md
charlesdj's picture
Update README.md
daf22e7 verified
metadata
library_name: transformers
tags:
  - multimodal
  - reasoning
  - sft
  - rl
datasets:
  - LightChen2333/M3CoT
  - ModalityDance/Omni-Bench
base_model:
  - GAIR/Anole-7b-v0.1
license: mit
pipeline_tag: any-to-any

Omni-R1-Zero

Omni-R1-Zero is trained without multimodal annotations. It bootstraps step-wise visualizations from text-only CoT seeds, then follows the SFT→RL recipe to learn interleaved multimodal reasoning.

Paper👁️ · Code🐙 · Omni-Bench🧪

Citation

@misc{cheng2026omnir1unifiedgenerativeparadigm,
      title={Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning}, 
      author={Dongjie Cheng and Yongqi Li and Zhixin Ma and Hongru Cai and Yupeng Hu and Wenjie Wang and Liqiang Nie and Wenjie Li},
      year={2026},
      eprint={2601.09536},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2601.09536}, 
}