ReFPO adds explicit Reflow regularization to FPO, stabilizing PPO-style training and supporting high-fidelity one-step inference across GridWorld, MuJoCo, and Humanoid tasks.
Analyzing and mitigating model collapse in rectified flow models.arXiv preprint arXiv:2412.08175, 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Early DC component convergence in text-to-image Transformer features causes output homogeneity; selective early attenuation via DAVE improves diversity without retraining or extra cost.
citing papers explorer
-
ReFPO: Reflow Regularization for Flow Matching Policy Gradients
ReFPO adds explicit Reflow regularization to FPO, stabilizing PPO-style training and supporting high-fidelity one-step inference across GridWorld, MuJoCo, and Humanoid tasks.
-
Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation
Early DC component convergence in text-to-image Transformer features causes output homogeneity; selective early attenuation via DAVE improves diversity without retraining or extra cost.