Author

Yuxian Wei

h-index 0 View on Semantic Scholar

We have 1 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models

This work proposes DreOPD, a Degraded-reference extrapolative OPD method for flow-matching models that bridges these two paradigms, and converts implicit reward extrapolation into closed-form velocity regression, enabling extrapolative post-training with the stability of OPD.

Ming-Hung Lin, Chengfei Cai, Lin Xu et al. · 0 citations