Running 31 Weight-Space Geometry of Offline Reasoning Training 🧭 31 Interactive weight-space geometry of six reasoning losses
Running 19 Defeating the trainer-generator precision mismatch in TRL 🎯 19 Download research PDF (Pro access required)
Running 199 The ultimate guide to RL environments: building and scaling them in the LLM era 📝 199 Building and scaling RL environments for LLM training