LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published 2 days ago • 128
Precise Debugging Benchmark: Is Your Model Debugging or Regenerating? Paper • 2604.17338 • Published Apr 19 • 4
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs Paper • 2510.11696 • Published Oct 13, 2025 • 183
Running 3.89k The Ultra-Scale Playbook 🌌 3.89k The ultimate guide to training LLM on large GPU Clusters