← back to paper

Review history

arxiv: 2608.09233 · 2 revisions

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

1. 2026-08-14 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   162664 ms 23923 in 17413 out 2026-08-14T04:14:53.674076+00:00
2. 2026-08-11 CONDITIONAL MODERATE v1.4.0-daily-deepseek-medium novelty 6.0
   112294 ms 23806 in 12417 out 2026-08-11T20:59:47.250024+00:00