Unified Generation, Reconstruction, and Representation: Generalized
Diffusion with Adaptive Latent Encoding-Decoding
Unified Generation, Reconstruction, and Representation: Generalized
Diffusion with Adaptive Latent Encoding-Decoding
The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations -- across various data types, such as discrete text/protein sequences and continuous images. Existing model families, like variational autoencoders (VAEs), generative adversarial networks (GANs), autoregressive models, and …