Continued pre-training study scales embodied agents across virtual worlds
One hundred twenty runs span 0.8B–27B models, 50–1,600 hours of data, and five world mixtures.
2 stories, newest first · one card per story
One hundred twenty runs span 0.8B–27B models, 50–1,600 hours of data, and five world mixtures.
Climate-ModernBERT domain-adapted encoders reach 76.3 average F1 across nine climate benchmarks, 2.8 points above vanilla ModernBERT-Base.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views