Article Summary

• MMRPT: MultiModal Reinforcement Pre-Training via Masked Vision-Dependent Reasoning J. Chen, L. Wang, K. Gupta
  Multimodal Learning Reinforcement Learning Pre-training Vision-Language Models Masked Modeling
  Published: 2025-12-11 Link: https://arxiv.org/pdf/2512.07203.pdf
• Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation Alice Chen, Bob Davis, Carol Evans
  Reinforcement Learning Generative Models Text-to-Image Synthesis Masked Modeling Policy Optimization
  Published: 2025-10-16 Link: https://arxiv.org/pdf/2510.13418.pdf