RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
Structured denoising diffusion models in discrete state-spaces
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
A method trains discrete diffusion policies for combinatorial RL by matching to a PMD-regularized target distribution, reporting SOTA performance and sample efficiency on DNA generation, macro-action, and multi-agent benchmarks.
citing papers explorer
-
Relative Score Policy Optimization for Diffusion Language Models
RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
-
Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
A method trains discrete diffusion policies for combinatorial RL by matching to a PMD-regularized target distribution, reporting SOTA performance and sample efficiency on DNA generation, macro-action, and multi-agent benchmarks.