Understanding R1-Zero-Like Training: A Critical Perspective Paper • 2503.20783 • Published 8 days ago • 17
SkyLadder: Better and Faster Pretraining via Context Window Scheduling Paper • 2503.15450 • Published 15 days ago • 11
RegMix: Data Mixture as Regression for Language Model Pre-training Paper • 2407.01492 • Published Jul 1, 2024 • 37
Bootstrapping Language Models with DPO Implicit Rewards Paper • 2406.09760 • Published Jun 14, 2024 • 40