← back to paper

Review history

arxiv: 2506.19697 · 2 revisions

Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   144500 ms 219 in 11789 out 2026-08-15T18:27:44.838009+00:00
2. 2026-08-06 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   152101 ms 26215 in 15320 out 2026-08-06T23:04:44.058767+00:00