← back to paper

Review history

arxiv: 2509.02528 · 2 revisions

Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 7.0
   92205 ms 47106 in 10877 out 2026-08-15T16:36:41.699572+00:00
2. 2026-08-05 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   201772 ms 48453 in 20046 out 2026-08-05T11:33:34.115456+00:00