Pith. sign in

← back to paper

Review history

arxiv: 2604.18518 · 2 revisions

UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models

  1. 2026-07-05 UNVERDICTED LOW v1.1.0-glm novelty 6.0
    98211 ms 4681 in 1820 out 2026-07-05T11:27:51.910357+00:00
  2. 2026-05-10 UNVERDICTED LOW v0.9.0 novelty 7.0
    29853 ms 5543 in 1155 out 2026-05-10T05:28:11.602824+00:00