← back to paper

Review history

arxiv: 2607.09757 · 2 revisions

RSRA: Training-Free Probing of Representation Sensitivity for Efficient LoRA Rank Allocation

1. 2026-08-04 REJECT MODERATE v1.3.0-alltime-deepseek novelty 6.0
   165388 ms 138 in 14983 out 2026-08-04T04:28:13.937699+00:00
2. 2026-07-14 CONDITIONAL MODERATE v1.1.0-grok45 novelty 6.0
   50862 ms 19259 in 3242 out 2026-07-14T16:22:10.850036+00:00