Thank you for your impactful contributions to the MLLM community!
We’re excited to share MindOmni, a new framework for unified multimodal understanding and generation, strengthened by our RGPO reinforcement learning algorithm. We’d be honored if you would consider adding it to your repo!
Arxiv: https://arxiv.org/pdf/2505.13031
Code: https://github.com/TencentARC/MindOmni
Thank you for your impactful contributions to the MLLM community!
We’re excited to share MindOmni, a new framework for unified multimodal understanding and generation, strengthened by our RGPO reinforcement learning algorithm. We’d be honored if you would consider adding it to your repo!
Arxiv: https://arxiv.org/pdf/2505.13031
Code: https://github.com/TencentARC/MindOmni