← back to paper

Review history

arxiv: 2605.11739 · 3 revisions

Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation

1. 2026-05-22 UNVERDICTED LOW v0.9.0 novelty 5.0
   52960 ms 5805 in 1400 out 2026-05-22T10:06:51.092603+00:00
2. 2026-05-14 UNVERDICTED LOW v0.9.0 novelty 6.0
   41896 ms 5574 in 1023 out 2026-05-14T21:04:08.675163+00:00
3. 2026-05-13 UNVERDICTED LOW v0.9.0 novelty 6.0
   97465 ms 5574 in 1361 out 2026-05-13T06:54:53.142835+00:00