BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts Paper • 2408.08274 • Published 9 days ago • 11
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain Paper • 2407.19584 • Published 27 days ago • 60
Theia: Distilling Diverse Vision Foundation Models for Robot Learning Paper • 2407.20179 • Published 26 days ago • 45
WARP: On the Benefits of Weight Averaged Rewarded Policies Paper • 2406.16768 • Published Jun 24 • 22