Poster
Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback
TaeHo Yoon · Kibeom Myoung · Keon Lee · Jaewoong Cho · Albert No · Ernest Ryu
Great Hall & Hall B1+B2 (level 1) #622
Abstract:
Diffusion models have recently shown remarkable success in high-quality image generation. Sometimes, however, a pre-trained diffusion model exhibits partial misalignment in the sense that the model can generate good images, but it sometimes outputs undesirable images. If so, we simply need to prevent the generation of the bad images, and we call this task censoring. In this work, we present censored generation with a pre-trained diffusion model using a reward model trained on minimal human feedback. We show that censoring can be accomplished with extreme human feedback efficiency and that labels generated with a mere few minutes of human feedback are sufficient.
Chat is not available.