pith. sign in

Kevin Zhou

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning

cs.LG · 2026-04-30 · unverdicted · novelty 6.0

Latent-GRPO stabilizes reinforcement learning in latent space, delivering 7.86 Pass@1 gains on low-difficulty tasks over latent baselines and 4.27 points over explicit GRPO on high-difficulty tasks with 3-4x shorter reasoning chains.

citing papers explorer

Showing 1 of 1 citing paper.

  • Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning cs.LG · 2026-04-30 · unverdicted · none · ref 29

    Latent-GRPO stabilizes reinforcement learning in latent space, delivering 7.86 Pass@1 gains on low-difficulty tasks over latent baselines and 4.27 points over explicit GRPO on high-difficulty tasks with 3-4x shorter reasoning chains.