ReCreate: Reasoning and Creating Domain Agents Driven by Experience Paper • 2601.11100 • Published 11 days ago • 17
Spectral Alignment as Predictor of Loss Explosion in Neural Network Training Paper • 2510.04202 • Published Oct 5, 2025
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention Paper • 2510.04212 • Published Oct 5, 2025 • 24
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention Paper • 2510.04212 • Published Oct 5, 2025 • 24
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention Paper • 2510.04212 • Published Oct 5, 2025 • 24 • 2