Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2, 2025 • 187
view article Article DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge Feb 7, 2025 • 266
Configuration error Featured 1.45k EasyControl Ghibli 🦀 1.45k New Ghibli EasyControl model is now released!!