NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
control
4 papers
From Kolmogorov to Cauchy: Shallow XNet Surpasses KANs
Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting
Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs