← back to paper

Review history

arxiv: 2604.25098 · 2 revisions

Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling

1. 2026-07-01 UNVERDICTED LOW v0.9.1-grok novelty 5.0
   28780 ms 5756 in 960 out 2026-07-01T09:14:15.115836+00:00
2. 2026-05-07 UNVERDICTED LOW v0.9.0 novelty 7.0
   52224 ms 5510 in 1084 out 2026-05-07T16:45:47.003146+00:00