Generating, Reconstructing, and Representing Discrete and Continuous Data: Generalized Diffusion with Learnable Encoding-Decoding

arXiv:2402.19009v1 Announce Type: new
Abstract: 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 diffusion models, generally excel in specific capabilities and data types but fall short in others. We introduce generalized diffusion with learnable encoder-decoder (DiLED), that seamlessly …

abstract applications arxiv autoencoders capabilities continuous core cs.ai cs.lg data decoding deep generative models diffusion encoding families generalized generative generative models images inputs instances protein text type types variational autoencoders vast