@article{unirlselfimprovingunifiedmultimodal, title = {UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning}, author = {Weijia Mao and Zhenheng Yang and Mike Zheng Shou}, year = {2025}, eprint = {2505.23380}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.23380v1}, }