pith. machine review for the scientific record. sign in

In: International conference on machine learning

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

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models

cs.CV · 2026-04-05 · unverdicted · novelty 8.0

OP-GRPO is the first off-policy GRPO method for flow-matching models that reuses trajectories via replay buffer and importance sampling corrections, matching on-policy performance with 34.2% of the training steps.

citing papers explorer

Showing 1 of 1 citing paper.

  • OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models cs.CV · 2026-04-05 · unverdicted · none · ref 32

    OP-GRPO is the first off-policy GRPO method for flow-matching models that reuses trajectories via replay buffer and importance sampling corrections, matching on-policy performance with 34.2% of the training steps.