3 papers
cs.LG2026
The Diffusion Encoder
Akhil Premkumar, Sarah Lucioni
We construct a new kind of encoder, leveraging the expressive power of diffusion models. In a traditional variational autoencoder, the encoder and decoder jointly negotiate a laten…
cs.LG2026
On the Separability of Information in Diffusion Models
Akhil Premkumar
Diffusion models transform noise into data by injecting information that was captured in their neural network during the training phase. In this paper, we ask: \textit{what} is thi…
cs.LG2025
Neural Entropy
Akhil Premkumar
We explore the connection between deep learning and information theory through the paradigm of diffusion models. A diffusion model converts noise into structured data by reinstatin…