We prove quantitative convergence estimates for single layer neural networks in the NTK regime to gaussian processes at positive training time

We develop a discrete graph diffusion denoising model that dynamically grows or shrinks a chemical graph during generation.

We introduce SceneSplat-49K, a large 3DGS dataset spanning diverse indoor and outdoor environments, and provide a comprehensive benchmark SceneSplat-Bench for Language Gaussian Splatting methods.

We show the effects of vanishing gradients on GNNs.

This paper argues that privacy must be measured and integrated as a core dimension in the evaluation of human pose estimation systems.