Xu Minghui

test noise schedule and train noise schedule are different?

2

how is the performance when setting different?

If the dimension k=3 for three dimensional data, then the following -1 should be -3/2? `line 259: kl_loss = 0.5 * torch.sum(z_mu.pow(2) + z_sigma.pow(2) - torch.log(z_sigma.pow(2)) - 1, dim=[1, 2,...

Joint training of VAE and Transformer

5

Thanks for your excellent work. Could you clarify whether the VAE and the transformer that operates on the latent features can be jointly optimized—that is, trained end-to-end? Thanks for your...