view article Article You could have designed state of the art positional encoding By FL33TW00D-HF • Nov 25, 2024 • 312
view article Article DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge By NormalUhr • Feb 7 • 182
view article Article Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment By NormalUhr • Feb 11 • 51
Getting it Right: Improving Spatial Consistency in Text-to-Image Models Paper • 2404.01197 • Published Apr 1, 2024 • 32