← back to paper

Review history

arxiv: 2605.12288 · 2 revisions

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

1. 2026-05-15 UNVERDICTED LOW v0.9.0 novelty 7.0
   45448 ms 5505 in 1237 out 2026-05-15T05:37:51.027432+00:00
2. 2026-05-13 UNVERDICTED LOW v0.9.0 novelty 6.0
   46518 ms 5505 in 1214 out 2026-05-13T04:51:44.653866+00:00