view article Article How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day 20 days ago • 46
Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training Paper • 2503.18929 • Published Mar 24 • 4
Transformers Can Do Arithmetic with the Right Embeddings Paper • 2405.17399 • Published May 27, 2024 • 54