Story
arxiv_cs_lg · Apr 20, 2026 · paper
Source brief
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
arxiv.orgApr 20, 2026
original source linked
In brief
Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains largely unexplored. We observe that na...
Continue reading