← back to paper

Review history

arxiv: 2606.25086 · 2 revisions

Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models

1. 2026-07-01 UNVERDICTED LOW v0.9.1-grok novelty 7.0
   28414 ms 5770 in 1247 out 2026-07-01T06:34:20.119452+00:00
2. 2026-06-26 UNVERDICTED LOW v0.9.1-grok novelty 7.0
   20533 ms 5770 in 1252 out 2026-06-26T00:07:35.883058+00:00