Langevin dynamics, the samples contain small Gaussian noise that

We thank all the reviewers for providing valuable feedback in this time of stress. We will include these new results in the revision. NCSN (CIFAR-10) NCSNv2 (CIFAR-10) NCSN (CelebA) NCSNv2 (CelebA) FID 27.44 10.31 17.57 9.69 [R1] Is the model memorizing data (like the Eiffel towers in Figure 1)? NCSNv2 uses the new architecture and the others use the old one. We will incorporate your suggestions in the revision.