Training Diffusion Models Towards Diverse Image Generation with Reinforcement Learning
CVPR 2024（2024）
Key words
Diffusion Model,Image Generation,Diverse Images,Training Set,Diffusion Process,Reward Function,Policy Gradient,Reference Distribution,Policy Gradient Method,Images Of Samples,Feature Space,Implementation Details,Random Selection,Random Noise,Mutual Information,Kernel Function,Reversible Process,Kullback-Leibler,Gaussian Process,Reference Image,Maximum Mean Discrepancy,Fine-tuned Model,Individual Reward,Marginal Utility,Policy Network,Diverse Models,Subset Selection,Application Of Reinforcement Learning
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined