AI RESEARCH
dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
arXiv CS.LG
•
ArXi:2605.09291v1 Announce Type: new Discrete flow models (DFMs) are a class of flexible generative models for generating discrete data, and diffusion large language models (dLLMs) can be viewed as a special case with a specific choice of mixture path and a masked source distribution. While several recent works have explored reinforcement learning into dLLMs, its application to general discrete flow models remains underexplored.