Termsslug: multilingual-pretraining

Multilingual Pretraining

多语言预训练

Training base models on corpora from multiple languages to acquire cross-lingual capabilities

Curated Intelligence

1 items · Page 1/1
Google ResearchT1·Models
78 pts
ATLAS: Adaptive Scaling Laws for Multilingual Models

The ICLR 2026 paper 'ATLAS' presents the largest public multilingual pre-training study to date, covering 774 runs across 400+ languages. It introduces adaptive transfer scaling laws that quantify synergies between 1,400 language pairs, providing data-driven guidance on efficiency and cost for building multilingual models.