Running 31 Weight-Space Geometry of Offline Reasoning Training 🧠31 Interactive weight-space geometry of six reasoning losses
Disty0/RaiFlow-v0_01-256px-rough-pre-train Text-to-Image • 0.7B • Updated 27 days ago • 14 • 7
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation Paper • 2601.22813 • Published Jan 30 • 63