Richard Baraniuk

Neon: Negative Extrapolation From Self-Training Improves Image Generation

Leakage and Second-Order Dynamics Improve Hippocampal RNN Replay

The Centroid Affinity Hypothesis: How Deep Network Represent Features

What Deep Networks Want to Learn and How to Get There

WaLRUS: Wavelets for Long range Representation Using State Space Methods

ScaLES: Scalable Latent Exploration Score for Pre-Trained Generative Networks

MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES

Mutual-Inform SMoE: Improving Routing Stability via Probabilistic Graphical Model

Improving Fairness and Mitigating MADness in Generative Models

MazeNet: An Accurate, Fast, & Scalable Deep Learning Solution for Steiner Minimum Trees