Skip to content
Tagged articles

OptiMer

1 articles · Page 1 of 1
Machine Heart
Machine Heart
Nov 14, 2026 · Artificial Intelligence

OptiMer: Merging Distribution Vectors Beats Data Mixing for Continual Pre-Training

NICT researchers propose OptiMer, a method that merges distribution vectors from separately trained models to find optimal data mixing ratios for continual pre-training, achieving 15-35x speedup over traditional data mixing and outperforming it on benchmarks like C-Eval, MMLU, and GSM8K.

Bayesian optimizationEMNLP 2026OptiMer
0 likes · 12 min read
OptiMer: Merging Distribution Vectors Beats Data Mixing for Continual Pre-Training