🏢 Korea Institute for Advanced Study
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
·2261 words·11 mins·
loading
·
loading
Reinforcement Learning
🏢 Korea Institute for Advanced Study
Boosting diffusion model sample quality, especially with few steps, is achieved via a novel maximum entropy inverse reinforcement learning approach, jointly training the model and an energy-based mode…