Omni-R1
Collection
Checkpoints and data for the paper Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning.
•
3 items
•
Updated
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🧪
@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},
}
Base model
GAIR/Anole-7b-v0.1Totally Free + Zero Barriers + No Login Required