pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

stat.ML 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Variational Proximal Policy Optimization

stat.ML · 2026-06-06 · unverdicted · novelty 5.0

VP2O maps PPO to SVGD in a MoE architecture using functional kernels and expert orthogonalization, claiming +179 ELO on Codeforces and 32% token reduction on AIME for a 33B/4B model.

citing papers explorer

Showing 1 of 1 citing paper.

  • Variational Proximal Policy Optimization stat.ML · 2026-06-06 · unverdicted · none · ref 77

    VP2O maps PPO to SVGD in a MoE architecture using functional kernels and expert orthogonalization, claiming +179 ELO on Codeforces and 32% token reduction on AIME for a 33B/4B model.