← back to paper

Review history

arxiv: 2605.11726 · 2 revisions

Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models

1. 2026-05-14 UNVERDICTED LOW v0.9.0 novelty 7.0
   34281 ms 5586 in 1052 out 2026-05-14T21:01:43.374936+00:00
2. 2026-05-13 UNVERDICTED LOW v0.9.0 novelty 7.0
   76518 ms 5589 in 1404 out 2026-05-13T06:57:23.417873+00:00